{"schema_version": 1, "published_at": "2026-09-25T20:02:52.890588+00:00", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs", "aq05_url": "https://huggingface.co/spaces/jzshared/mlebench-aq05-12h-20260921", "experiments": [{"id": "mlebench-baselines-20260906", "title": "MLEBench · 基线五方法", "family": "MLEBench", "note": "历史归档；验证曲线与官方最终评分分开。跨批次配置与评估协议可能不同。", "records": 110, "run_count": 110, "datasets": ["aerial-cactus-identification", "aptos2019-blindness-detection", "denoising-dirty-documents", "detecting-insults-in-social-commentary", "dog-breed-identification", "dogs-vs-cats-redux-kernels-edition", "histopathologic-cancer-detection", "jigsaw-toxic-comment-classification-challenge", "leaf-classification", "mlsp-2013-birds", "new-york-city-taxi-fare-prediction", "nomad2018-predict-transparent-conductors", "plant-pathology-2020-fgvc7", "random-acts-of-pizza", "ranzcr-clip-catheter-line-classification", "siim-isic-melanoma-classification", "spooky-author-identification", "tabular-playground-series-dec-2021", "tabular-playground-series-may-2022", "text-normalization-challenge-english-language", "text-normalization-challenge-russian-language", "the-icml-2013-whale-challenge-right-whale-redux"], "methods": ["base", "bnvs", "bnvs_root", "bnvs_root_only", "bo"]}, {"id": "mlebench-gp6-20260908", "title": "MLEBench · GP6 / GP6-draft", "family": "MLEBench", "note": "历史归档；验证曲线与官方最终评分分开。跨批次配置与评估协议可能不同。", "records": 44, "run_count": 44, "datasets": ["aerial-cactus-identification", "aptos2019-blindness-detection", "denoising-dirty-documents", "detecting-insults-in-social-commentary", "dog-breed-identification", "dogs-vs-cats-redux-kernels-edition", "histopathologic-cancer-detection", "jigsaw-toxic-comment-classification-challenge", "leaf-classification", "mlsp-2013-birds", "new-york-city-taxi-fare-prediction", "nomad2018-predict-transparent-conductors", "plant-pathology-2020-fgvc7", "random-acts-of-pizza", "ranzcr-clip-catheter-line-classification", "siim-isic-melanoma-classification", "spooky-author-identification", "tabular-playground-series-dec-2021", "tabular-playground-series-may-2022", "text-normalization-challenge-english-language", "text-normalization-challenge-russian-language", "the-icml-2013-whale-challenge-right-whale-redux"], "methods": ["gp6", "gp6_draft"]}, {"id": "mlebench-gp7-recovery-20260913", "title": "MLEBench · GP7 recovery", "family": "MLEBench", "note": "历史归档；验证曲线与官方最终评分分开。跨批次配置与评估协议可能不同。", "records": 44, "run_count": 44, "datasets": ["aerial-cactus-identification", "aptos2019-blindness-detection", "denoising-dirty-documents", "detecting-insults-in-social-commentary", "dog-breed-identification", "dogs-vs-cats-redux-kernels-edition", "histopathologic-cancer-detection", "jigsaw-toxic-comment-classification-challenge", "leaf-classification", "mlsp-2013-birds", "new-york-city-taxi-fare-prediction", "nomad2018-predict-transparent-conductors", "plant-pathology-2020-fgvc7", "random-acts-of-pizza", "ranzcr-clip-catheter-line-classification", "siim-isic-melanoma-classification", "spooky-author-identification", "tabular-playground-series-dec-2021", "tabular-playground-series-may-2022", "text-normalization-challenge-english-language", "text-normalization-challenge-russian-language", "the-icml-2013-whale-challenge-right-whale-redux"], "methods": ["gp7_ancestry_logei", "laplacian_anchor_logei"]}, {"id": "mlebench-gp7-three-20260916", "title": "MLEBench · GP7 三方法", "family": "MLEBench", "note": "历史归档；验证曲线与官方最终评分分开。跨批次配置与评估协议可能不同。", "records": 66, "run_count": 66, "datasets": ["aerial-cactus-identification", "aptos2019-blindness-detection", "denoising-dirty-documents", "detecting-insults-in-social-commentary", "dog-breed-identification", "dogs-vs-cats-redux-kernels-edition", "histopathologic-cancer-detection", "jigsaw-toxic-comment-classification-challenge", "leaf-classification", "mlsp-2013-birds", "new-york-city-taxi-fare-prediction", "nomad2018-predict-transparent-conductors", "plant-pathology-2020-fgvc7", "random-acts-of-pizza", "ranzcr-clip-catheter-line-classification", "siim-isic-melanoma-classification", "spooky-author-identification", "tabular-playground-series-dec-2021", "tabular-playground-series-may-2022", "text-normalization-challenge-english-language", "text-normalization-challenge-russian-language", "the-icml-2013-whale-challenge-right-whale-redux"], "methods": ["gp7_ancestry_logei", "gp7_long_horizon_logei", "gp7_long_horizon_pibo"]}, {"id": "mlebench-gp7-hard14-20260917", "title": "MLEBench · GP7 hard14", "family": "MLEBench", "note": "历史归档；验证曲线与官方最终评分分开。实际 hard14 配置为 child-UCB，目录中的 logei 为历史名称。", "records": 42, "run_count": 42, "datasets": ["aerial-cactus-identification", "aptos2019-blindness-detection", "dog-breed-identification", "jigsaw-toxic-comment-classification-challenge", "leaf-classification", "mlsp-2013-birds", "new-york-city-taxi-fare-prediction", "nomad2018-predict-transparent-conductors", "random-acts-of-pizza", "ranzcr-clip-catheter-line-classification", "siim-isic-melanoma-classification", "tabular-playground-series-may-2022", "text-normalization-challenge-english-language", "text-normalization-challenge-russian-language"], "methods": ["gp7_ancestry_logei", "gp7_no_ancestry_logei", "gp7_short_ucb_pibo"]}, {"id": "nanogpt-development-r1-v1-20260917", "title": "nanoGPT · development_r1_v1", "family": "nanoGPT", "note": "开发轮次；仅报告原始登记的预算内成绩，未启动条目不计入运行数。原始候选曲线可能含预算后结果。", "records": 7, "run_count": 7, "datasets": ["nanoGPT"], "methods": ["bo_study_gp7_logei", "bo_study_gp7_long_ucb", "bo_study_gp7_mean", "bo_study_gp7_no_ancestry_ucb", "bo_study_gp7_ucb", "bo_study_mcgs", "bo_study_parent_greedy"]}, {"id": "nanogpt-development-r2-v1-20260917", "title": "nanoGPT · development_r2_v1", "family": "nanoGPT", "note": "开发轮次；仅报告原始登记的预算内成绩，未启动条目不计入运行数。原始候选曲线可能含预算后结果。", "records": 7, "run_count": 1, "datasets": ["nanoGPT"], "methods": ["bo_study_absolute_mean", "bo_study_absolute_ucb", "bo_study_gp7_long_ucb", "bo_study_gp7_ucb", "bo_study_mcgs", "bo_study_parent_coefficient_mean", "bo_study_parent_coefficient_ucb"]}, {"id": "nanogpt-development-r2-v2-20260917", "title": "nanoGPT · development_r2_v2", "family": "nanoGPT", "note": "开发轮次；仅报告原始登记的预算内成绩，未启动条目不计入运行数。原始候选曲线可能含预算后结果。", "records": 7, "run_count": 7, "datasets": ["nanoGPT"], "methods": ["bo_study_absolute_mean", "bo_study_absolute_ucb", "bo_study_gp7_long_ucb", "bo_study_gp7_ucb", "bo_study_mcgs", "bo_study_parent_coefficient_mean", "bo_study_parent_coefficient_ucb"]}, {"id": "nanogpt-development-r3-v1-20260917", "title": "nanoGPT · development_r3_v1", "family": "nanoGPT", "note": "开发轮次；仅报告原始登记的预算内成绩，未启动条目不计入运行数。原始候选曲线可能含预算后结果。", "records": 3, "run_count": 3, "datasets": ["nanoGPT"], "methods": ["bo_study_joint_ts", "bo_study_linear_ucb", "bo_study_residual_scale_ucb"]}, {"id": "nanogpt-development-r4-ancestor-v1-20260917", "title": "nanoGPT · development_r4_ancestor_v1", "family": "nanoGPT", "note": "开发轮次；仅报告原始登记的预算内成绩，未启动条目不计入运行数。原始候选曲线可能含预算后结果。", "records": 1, "run_count": 1, "datasets": ["nanoGPT"], "methods": ["bo_study_ancestor_summary_ucb"]}, {"id": "nanogpt-development-r5-bounded-v1-20260917", "title": "nanoGPT · development_r5_bounded_v1", "family": "nanoGPT", "note": "开发轮次；仅报告原始登记的预算内成绩，未启动条目不计入运行数。原始候选曲线可能含预算后结果。", "records": 1, "run_count": 1, "datasets": ["nanoGPT"], "methods": ["bo_study_bounded_parent_mean"]}, {"id": "nanogpt-development-r6-shared-lineage-v1-20260917", "title": "nanoGPT · development_r6_shared_lineage_v1", "family": "nanoGPT", "note": "开发轮次；仅报告原始登记的预算内成绩，未启动条目不计入运行数。原始候选曲线可能含预算后结果。", "records": 2, "run_count": 2, "datasets": ["nanoGPT"], "methods": ["bo_study_lineage_shared_ucb", "bo_study_stable_birth_shared_ucb"]}, {"id": "nanogpt-development-r7-birth-matern-v1-20260917", "title": "nanoGPT · development_r7_birth_matern_v1", "family": "nanoGPT", "note": "开发轮次；仅报告原始登记的预算内成绩，未启动条目不计入运行数。原始候选曲线可能含预算后结果。", "records": 1, "run_count": 1, "datasets": ["nanoGPT"], "methods": ["bo_study_stable_birth_matern_ucb"]}, {"id": "nanogpt-development-r7-context-v1-20260917", "title": "nanoGPT · development_r7_context_v1", "family": "nanoGPT", "note": "开发轮次；仅报告原始登记的预算内成绩，未启动条目不计入运行数。原始候选曲线可能含预算后结果。", "records": 1, "run_count": 1, "datasets": ["nanoGPT"], "methods": ["bo_study_stable_context_shared_ucb"]}, {"id": "nanogpt-development-r7-frozen-scale-v1-20260917", "title": "nanoGPT · development_r7_frozen_scale_v1", "family": "nanoGPT", "note": "开发轮次；仅报告原始登记的预算内成绩，未启动条目不计入运行数。原始候选曲线可能含预算后结果。", "records": 1, "run_count": 1, "datasets": ["nanoGPT"], "methods": ["bo_study_frozen_scale_ucb"]}, {"id": "nanogpt-development-r7-parent-covariance-v1-20260917", "title": "nanoGPT · development_r7_parent_covariance_v1", "family": "nanoGPT", "note": "开发轮次；仅报告原始登记的预算内成绩，未启动条目不计入运行数。原始候选曲线可能含预算后结果。", "records": 1, "run_count": 0, "datasets": ["nanoGPT"], "methods": ["bo_study_stable_parent_covariance_ucb"]}, {"id": "nanogpt-development-r7-student-t-v1-20260917", "title": "nanoGPT · development_r7_student_t_v1", "family": "nanoGPT", "note": "开发轮次；仅报告原始登记的预算内成绩，未启动条目不计入运行数。原始候选曲线可能含预算后结果。", "records": 1, "run_count": 1, "datasets": ["nanoGPT"], "methods": ["bo_study_stable_birth_student_t_ucb"]}, {"id": "nanogpt-study7-20260918", "title": "nanoGPT · Study7 七组正式实验", "family": "nanoGPT", "note": "七组均完成 6h active 预算。离线 β 重评分属于分析报告，不是在线实验结果。", "records": 7, "run_count": 7, "datasets": ["nanoGPT"], "methods": ["seven_e01_gp6_original", "seven_e02_state4_ucb", "seven_e03_state4_ancestorB_ucb", "seven_e04_state4_ratingmean_ucb", "seven_e05_state4_ancestorB_ratingmean_ucb", "seven_e06_mcgs_original", "seven_e07_parent_greedy_managed"]}, {"id": "nanogpt-autoresearch-full-workflow-8h-20260916-043851", "title": "nanoGPT · autoresearch_full_workflow_8h_20260916_043851", "family": "nanoGPT", "note": "历史原始日志；终态与预算未统一核验，保留为 archived，不推断完成。", "records": 4, "run_count": 4, "datasets": ["nanoGPT"], "methods": ["gp7_ancestry_logei", "gp7_long_horizon_logei", "gp7_long_horizon_pibo", "mlevolve_original"]}, {"id": "nanogpt-autoresearch-paired-drafts5-8h-20260916-061810", "title": "nanoGPT · autoresearch_paired_drafts5_8h_20260916_061810", "family": "nanoGPT", "note": "历史原始日志；终态与预算未统一核验，保留为 archived，不推断完成。", "records": 4, "run_count": 4, "datasets": ["nanoGPT"], "methods": ["gp7_ancestry_logei", "gp7_long_horizon_logei", "gp7_long_horizon_pibo", "mlevolve_original"]}, {"id": "nanogpt-autoresearch-paired-drafts5-serial-8h-20260916-145852", "title": "nanoGPT · autoresearch_paired_drafts5_serial_8h_20260916_145852", "family": "nanoGPT", "note": "历史原始日志；终态与预算未统一核验，保留为 archived，不推断完成。", "records": 4, "run_count": 4, "datasets": ["nanoGPT"], "methods": ["gp7_ancestry_logei", "gp7_long_horizon_logei", "gp7_long_horizon_pibo", "mlevolve_original"]}, {"id": "nanogpt-autoresearch-paired-serial-segmented8h-20260916-160835", "title": "nanoGPT · autoresearch_paired_serial_segmented8h_20260916_160835", "family": "nanoGPT", "note": "历史原始日志；终态与预算未统一核验，保留为 archived，不推断完成。", "records": 4, "run_count": 4, "datasets": ["nanoGPT"], "methods": ["gp7_ancestry_logei", "gp7_long_horizon_logei", "gp7_long_horizon_pibo", "mlevolve_original"]}, {"id": "nanogpt-autoresearch-paired-seed43-three-segmented8h-20260916-210252", "title": "nanoGPT · autoresearch_paired_seed43_three_segmented8h_20260916_210252", "family": "nanoGPT", "note": "历史原始日志；终态与预算未统一核验，保留为 archived，不推断完成。", "records": 3, "run_count": 3, "datasets": ["nanoGPT"], "methods": ["gp7_ancestry_logei", "gp7_long_horizon_logei", "gp7_long_horizon_pibo"]}, {"id": "nanogpt-study7-smoke-20260918", "title": "nanoGPT · Study7 预检 / 恢复烟测", "family": "nanoGPT", "note": "预检与恢复烟测，不计为七组正式实验。", "records": 2, "run_count": 2, "datasets": ["nanoGPT"], "methods": ["study7-bounded-smoke", "study7-review-recovery-smoke"]}, {"id": "mlebench-aq04-12h-20260921", "title": "MLEBench · AQ04 / 12h", "family": "MLEBench", "note": "原 14 题快照保留；未完成的 7 题在 Mila 使用 A100 80GB 续跑，仅补累计 12h 剩余预算。运行状态来自 Slurm 与原生心跳；详情保留原始协议限制。", "records": 14, "run_count": 14, "datasets": ["aerial-cactus-identification", "aptos2019-blindness-detection", "dog-breed-identification", "jigsaw-toxic-comment-classification-challenge", "leaf-classification", "mlsp-2013-birds", "new-york-city-taxi-fare-prediction", "nomad2018-predict-transparent-conductors", "random-acts-of-pizza", "ranzcr-clip-catheter-line-classification", "siim-isic-melanoma-classification", "tabular-playground-series-may-2022", "text-normalization-challenge-english-language", "text-normalization-challenge-russian-language"], "methods": ["AQ04"]}, {"id": "mlebench-aq04-12h-rerun-20260925", "title": "MLEBench · AQ04 / 12h · Jigsaw + Pizza 重跑 09-25", "family": "MLEBench", "records": 2, "run_count": 2, "datasets": ["jigsaw-toxic-comment-classification-challenge", "random-acts-of-pizza"], "methods": ["AQ04"], "note": "Jigsaw 与 Pizza 独立从零重跑；每题 1×A100 80GB、12h、seed 42，沿用 AQ04 与原模型。Jigsaw main 8核/48GB；Pizza unkillable 4核/24GB。先前成绩保留在原批次。"}, {"id": "mlebench-aq04-12h-pizza-main-rerun2-20260925", "title": "MLEBench · AQ04 / 12h · Pizza main 第二轮重跑 09-25", "family": "MLEBench", "records": 1, "run_count": 1, "datasets": ["random-acts-of-pizza"], "methods": ["AQ04"], "note": "Pizza 第二次独立从零重跑；main，1×A100 80GB，4核/24GB，12h，seed 42；沿用相同 AQ04、模型和 OpenCode 凭据。之前的任务与成绩保留在各自批次。"}], "runs": [{"id": "xixian.base.aerial-cactus-identification", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "base", "dataset": "aerial-cactus-identification", "status": "archived", "official_score": 0.99999, "medal": "none", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 1.0, "silver": 1.0, "bronze": 1.0}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:1", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-four-methods-muse13/runs/base/01_aerial-cactus-identification/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-four-methods-muse13/runs/base/01_aerial-cactus-identification/logs/journal.json", "metrics": [{"event_id": "e652f40cba96448ba5fda16b10ef5264", "step": 4, "value": 0.9999752516086453, "stage": "debug", "created_at": 1788671331.2823634}, {"event_id": "338d965c9ed448d19b44f33b2c3b85b6", "step": 6, "value": 0.9999764301034718, "stage": "debug", "created_at": 1788671324.6262724}, {"event_id": "44f6032e44904544909aad3920c7e3b8", "step": 7, "value": 0.9999905720413887, "stage": "improve", "created_at": 1788671542.9390836}, {"event_id": "76c133ed80474fa8a92000711d674549", "step": 8, "value": 0.9999905720413886, "stage": "improve", "created_at": 1788672129.2966895}, {"event_id": "78733807a64b4209a15f5f187ba287b1", "step": 9, "value": 0.9999964645155208, "stage": "debug", "created_at": 1788671527.603218}, {"event_id": "bd9f44fb2c4d4d05b6ce4a2f3c042909", "step": 10, "value": 0.9999552171965964, "stage": "improve", "created_at": 1788672046.584122}, {"event_id": "11d958340dea4950947210a7ae9250c2", "step": 11, "value": 0.9999893935465624, "stage": "improve", "created_at": 1788673001.3203266}, {"event_id": "af62129745b34afba7d3643ff5d2e5ad", "step": 12, "value": 0.9999752516086455, "stage": "improve", "created_at": 1788673099.5761652}, {"event_id": "d1a310ebb9c24d8b98398391ac556efd", "step": 17, "value": 0.9999150156791298, "stage": "draft", "created_at": 1788681946.5002089}, {"event_id": "01300f326a2e42bd93dbdbd3c5266aa5", "step": 18, "value": 0.9999175053621514, "stage": "debug", "created_at": 1788682059.7418578}, {"event_id": "0667812f949b46e3893e89fa9c4ec134", "step": 19, "value": 0.9999866316798631, "stage": "improve", "created_at": 1788682262.0613873}, {"event_id": "28247343625942c682f3269faccdb19e", "step": 20, "value": 1.0, "stage": "improve", "created_at": 1788682322.0438936}, {"event_id": "0bb2ec11c07c41cdb864d2188d039572", "step": 21, "value": 0.9999516817121173, "stage": "improve", "created_at": 1788682665.6802673}, {"event_id": "de7332fff7e041baa939f55223f4f501", "step": 22, "value": 0.9999322035193059, "stage": "improve", "created_at": 1788682639.0902457}, {"event_id": "1e8d6fe56e3b4388905fde3793a1a058", "step": 23, "value": 0.9999882150517359, "stage": "improve", "created_at": 1788682960.1788824}, {"event_id": "950cee11a5fd4e05a98cb817983a2d1a", "step": 26, "value": 0.9999593607175603, "stage": "improve", "created_at": 1788683426.7977517}, {"event_id": "44a9f6098080455c80530dd05b6e86c8", "step": 27, "value": 0.9999929290310415, "stage": "improve", "created_at": 1788681939.894923}, {"event_id": "46929fd700f04c35b10f06ac07c67c6f", "step": 28, "value": 0.9998862752492516, "stage": "improve", "created_at": 1788684586.6000714}, {"event_id": "700cf995091b45f6b4f1dd98532953e9", "step": 30, "value": 0.9998890112547468, "stage": "evolution", "created_at": 1788685717.3957188}, {"event_id": "ef65d50303d045d38eddb43c85c3c590", "step": 32, "value": 0.9999293056868788, "stage": "fusion", "created_at": 1788686120.573607}, {"event_id": "6ff7c7e6d2734012b32b2ad8663e10c0", "step": 33, "value": 0.9999296240102398, "stage": "evolution", "created_at": 1788686588.4853382}, {"event_id": "bdccf0caf94f4eb8be33ee1cf048c60c", "step": 35, "value": 0.9999296240102398, "stage": "evolution", "created_at": 1788687289.676754}, {"event_id": "12640593198c49959a8d7764f717b6e9", "step": 36, "value": 0.9999799475197946, "stage": "improve", "created_at": 1788687987.8845568}, {"event_id": "e8b2c7b045f4463eb096f374ccd191b9", "step": 37, "value": 0.999969921279692, "stage": "improve", "created_at": 1788688695.0879533}, {"event_id": "a6794e2b9f7847839311ce50bb71cbea", "step": 38, "value": 0.999982812159824, "stage": "evolution", "created_at": 1788689420.3618815}, {"event_id": "c8f5c6fb480d422cb2fa8dfca559323f", "step": 39, "value": 0.9999729955681961, "stage": "improve", "created_at": 1788687566.125276}, {"event_id": "f0435edecef24156bf12ca4ee48a31a6", "step": 40, "value": 0.999982812159824, "stage": "fusion", "created_at": 1788690453.4655557}, {"event_id": "cce9b61fadd14330ae3c312ae6fc3c69", "step": 41, "value": 0.9999785794904896, "stage": "debug", "created_at": 1788686541.9861853}, {"event_id": "8829874c8a63494fb072971d63df453d", "step": 44, "value": 0.9999999999999999, "stage": "improve", "created_at": 1788693755.4336329}, {"event_id": "74ef59588fe5465db4342f2d66cb8404", "step": 45, "value": 0.9999773857778853, "stage": "fusion", "created_at": 1788696994.3342066}, {"event_id": "deaa7afbae20491c9ac52ddd78174a46", "step": 46, "value": 0.999971390687917, "stage": "debug", "created_at": 1788692897.976951}, {"event_id": "737b6112efc746b693149dd362a928fe", "step": 47, "value": 0.9999795875144665, "stage": "evolution", "created_at": 1788697837.2603562}, {"event_id": "ebc17dff0ad34cad90659c5b6ead6e52", "step": 48, "value": 0.9999685920950334, "stage": "evolution", "created_at": 1788692284.9520345}, {"event_id": "d2122a8a8cf14b3789a20d87871520be", "step": 49, "value": 1.0, "stage": "evolution", "created_at": 1788698781.9593372}], "maximize": true, "elapsed_seconds": 28705.824967622757, "node_count": 51, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.base.aerial-cactus-identification.yaml", "note": ""}, {"id": "xixian.base.aptos2019-blindness-detection", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "base", "dataset": "aptos2019-blindness-detection", "status": "archived", "official_score": 0.9185, "medal": "bronze", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.930508, "silver": 0.919654, "bronze": 0.914492}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:2", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-four-methods-muse13/runs/base/02_aptos2019-blindness-detection/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-four-methods-muse13/runs/base/02_aptos2019-blindness-detection/logs/journal.json", "metrics": [{"event_id": "243931d035bb47e5946a051b7ccd287d", "step": 5, "value": 0.9197455687563862, "stage": "debug", "created_at": 1788672228.005214}, {"event_id": "8d92e0e1acd84d2284843fa7cdb6bd26", "step": 12, "value": 0.8978162652570076, "stage": "debug", "created_at": 1788683104.017085}, {"event_id": "3b8f5471c1d94ad0b9b9e37e8a4f81cf", "step": 13, "value": 0.9093665737126839, "stage": "draft", "created_at": 1788682030.6653612}, {"event_id": "957689d219d94628a0440fd46f9cd31d", "step": 15, "value": 0.922467692365372, "stage": "improve", "created_at": 1788683722.7121878}, {"event_id": "e18af402efe44bd3abedbc37aeddc196", "step": 16, "value": 0.8881979685522403, "stage": "debug", "created_at": 1788681806.605806}, {"event_id": "bd52621736544b4ba0f0c9580435a305", "step": 19, "value": 0.8979514121875283, "stage": "improve", "created_at": 1788687370.2495136}, {"event_id": "9471263370c04db8ade51b490e8e9d69", "step": 20, "value": 0.9068638767419237, "stage": "improve", "created_at": 1788688681.6743338}, {"event_id": "023275cf1f614b958fa9b1288516143b", "step": 21, "value": 0.9172421292642288, "stage": "improve", "created_at": 1788686459.4551702}, {"event_id": "c236c5f464cf40bb9619070b70332ec3", "step": 23, "value": 0.9269403407233477, "stage": "debug", "created_at": 1788686510.540295}, {"event_id": "230a05dc98214b6cb873bfd1406af9ac", "step": 24, "value": 0.9136026010992324, "stage": "improve", "created_at": 1788691352.670223}], "maximize": true, "elapsed_seconds": 28768.793993473053, "node_count": 25, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.base.aptos2019-blindness-detection.yaml", "note": ""}, {"id": "xixian.base.denoising-dirty-documents", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "base", "dataset": "denoising-dirty-documents", "status": "archived", "official_score": 0.00982, "medal": "gold", "valid_submission": true, "score_maximize": false, "thresholds": {"gold": 0.01794, "silver": 0.02609, "bronze": 0.04517}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:3", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-four-methods-muse13/runs/base/03_denoising-dirty-documents/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-four-methods-muse13/runs/base/03_denoising-dirty-documents/logs/journal.json", "metrics": [{"event_id": "5691407ab2634eaa920076c4360b900a", "step": 9, "value": 0.2933830720455639, "stage": "debug", "created_at": 1788671541.4470468}, {"event_id": "de11f05189444378ae4f7470fc3df1d5", "step": 11, "value": 0.011523335346592835, "stage": "draft", "created_at": 1788671878.5693126}, {"event_id": "3749a1be486b4a5793666a0e98992fe8", "step": 12, "value": 0.018469264390411633, "stage": "debug", "created_at": 1788671775.9702268}, {"event_id": "1072358e62ac4c939fc467cbc6a23c6e", "step": 14, "value": 0.024763582065147522, "stage": "debug", "created_at": 1788672133.5868835}, {"event_id": "e2040090b9084690bedbfb0387647c72", "step": 15, "value": 0.01293043328877166, "stage": "improve", "created_at": 1788672216.488648}, {"event_id": "38113adba3ab4a4fa061e969979d77ae", "step": 17, "value": 0.02386661396642549, "stage": "improve", "created_at": 1788672615.8454225}, {"event_id": "22e5ef08cb0a43d79bee9a4ec667e633", "step": 18, "value": 0.02164546285981073, "stage": "debug", "created_at": 1788672762.886262}, {"event_id": "8337808ebcaa47bbb5900534d5db50f3", "step": 19, "value": 0.02105905176299083, "stage": "improve", "created_at": 1788673048.0906563}, {"event_id": "f7d2f63ca8bc48b89522b3c8823c2b5b", "step": 20, "value": 0.11643119933989926, "stage": "improve", "created_at": 1788673110.9392235}, {"event_id": "31a5f612e7da410db80fb88bab7f2bfc", "step": 21, "value": 0.013069042647344181, "stage": "debug", "created_at": 1788672507.0790524}, {"event_id": "c5506cf7481f4c54ae7ce3f4433f4234", "step": 22, "value": 0.01426850299499623, "stage": "evolution", "created_at": 1788673502.762285}, {"event_id": "7c1aa8323a234d208d99d1db1e8540d3", "step": 24, "value": 0.021151222248286597, "stage": "improve", "created_at": 1788673536.7647555}, {"event_id": "ce54c0177e924f72940dfd87d54082d5", "step": 25, "value": 0.018637365912343475, "stage": "debug", "created_at": 1788673981.301184}, {"event_id": "31dda14c75534ac79d338e4b684bc2fd", "step": 26, "value": 0.02159919882244501, "stage": "improve", "created_at": 1788674103.3678923}, {"event_id": "59485c09b8404ab4ab6b89f252586c0b", "step": 27, "value": 0.016999983575208457, "stage": "improve", "created_at": 1788673763.6368816}, {"event_id": "05ea020a2e924c379fd633178a8f3dff", "step": 28, "value": 0.014186252877921784, "stage": "improve", "created_at": 1788674455.120841}, {"event_id": "eecf0ab46e5a4f0f9bc898b0fb619b41", "step": 29, "value": 0.029218873431969706, "stage": "improve", "created_at": 1788674691.3040907}, {"event_id": "2991f71541cd483295f8d1837cbcca3b", "step": 33, "value": 0.10525503349419475, "stage": "evolution", "created_at": 1788681824.2903736}, {"event_id": "1fbc281e3a6441c5bbc34185f99bdddc", "step": 35, "value": 0.31196781248767474, "stage": "improve", "created_at": 1788681813.9130175}, {"event_id": "541c3e9e740a4d859160e58d01c00e66", "step": 36, "value": 0.010521267551668404, "stage": "debug", "created_at": 1788682301.3446484}, {"event_id": "3d14d05879db45f1ab0173743bf09019", "step": 37, "value": 0.015687935593784178, "stage": "improve", "created_at": 1788681814.783082}, {"event_id": "6f9f681268b4475ab096340876cd8bd6", "step": 40, "value": 0.0100923665029982, "stage": "improve", "created_at": 1788682688.374411}, {"event_id": "b3d3d529fffe4a4f88c09dcb081a056c", "step": 41, "value": 0.0165696430734713, "stage": "debug", "created_at": 1788682994.7396843}, {"event_id": "46164e8b492f4d4681147aaf52893f2b", "step": 42, "value": 0.010302776856992008, "stage": "improve", "created_at": 1788683191.926232}, {"event_id": "e229657cce974b8497a4a36e24b168ad", "step": 44, "value": 0.010713118237560684, "stage": "improve", "created_at": 1788683917.0035896}, {"event_id": "89068c5ecb494297875c45b9f1f52b6e", "step": 45, "value": 0.023289938857762142, "stage": "improve", "created_at": 1788684752.9899893}, {"event_id": "df8d4db97e7c4ad183caedf5216ece67", "step": 46, "value": 0.023519756100212882, "stage": "improve", "created_at": 1788685220.81484}, {"event_id": "db18731a9e6b44e5bdb0089afc161320", "step": 47, "value": 0.010862977171092579, "stage": "improve", "created_at": 1788682755.5046408}, {"event_id": "70eedf8daa124b6585917baf46451e23", "step": 48, "value": 0.012150602389352535, "stage": "improve", "created_at": 1788684857.3874717}, {"event_id": "00a82c60a5324587a18f1af708425e3d", "step": 52, "value": 0.009925332560468576, "stage": "fusion", "created_at": 1788686316.4487505}, {"event_id": "483d071759634424a7a1ea01363022f3", "step": 54, "value": 0.017423861560871907, "stage": "debug", "created_at": 1788686013.3022509}, {"event_id": "25b6afbec39a48a7a64827a2ecf50b4f", "step": 55, "value": 0.00933886851227541, "stage": "debug", "created_at": 1788686956.6978524}, {"event_id": "28109e94f6e7428f887e87e86704f339", "step": 56, "value": 0.014805550203502367, "stage": "improve", "created_at": 1788687876.9691486}, {"event_id": "a45e4ef5a6974a63998d66cd535bdc7d", "step": 57, "value": 0.011871504756565432, "stage": "debug", "created_at": 1788686500.752353}, {"event_id": "cb240bd00ef144d9a36aaa0c5f85cabd", "step": 58, "value": 0.01916719424965483, "stage": "improve", "created_at": 1788689228.1746628}, {"event_id": "4870d136a5fd4598a32f7358cf63ce8c", "step": 59, "value": 0.011202885813343867, "stage": "improve", "created_at": 1788689307.7987578}, {"event_id": "1210c71bbbe342cd8c0e5d9f6216ec11", "step": 60, "value": 0.017616805502834374, "stage": "improve", "created_at": 1788691071.997021}, {"event_id": "4fe2b059126349c5a0d38448c3d38f1c", "step": 61, "value": 0.010763362246406762, "stage": "improve", "created_at": 1788692942.2889905}, {"event_id": "a71e9b2a0b564829b6505c71e57126d4", "step": 68, "value": 0.05216, "stage": "debug", "created_at": 1788694433.7428563}, {"event_id": "e6f9d2cf07364028a381249827bfab73", "step": 69, "value": 0.009712802976599271, "stage": "improve", "created_at": 1788694373.8949087}, {"event_id": "edb266baf9cc48bdb2eac15db121eefb", "step": 70, "value": 0.014128235106794625, "stage": "evolution", "created_at": 1788692109.4640448}, {"event_id": "02a01a7b6e9d495aa1ad1d7a40d2f524", "step": 71, "value": 0.014252211740356893, "stage": "evolution", "created_at": 1788695555.0237408}, {"event_id": "c68c7b634e9c44ce8306b703d724f7f2", "step": 72, "value": 0.01194, "stage": "improve", "created_at": 1788695449.7890618}, {"event_id": "41cd897b43774db2a0266321a578f11e", "step": 74, "value": 0.019256323828245478, "stage": "evolution", "created_at": 1788697181.6845572}, {"event_id": "cd99f34a892c4e66a565c7d09f30b764", "step": 77, "value": 0.014281900044919268, "stage": "evolution", "created_at": 1788697720.9582367}, {"event_id": "40a622bc98eb4b21bee914a08bf1c929", "step": 78, "value": 0.009113807690404842, "stage": "debug", "created_at": 1788698221.6622047}], "maximize": false, "elapsed_seconds": 28769.809775829315, "node_count": 80, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.base.denoising-dirty-documents.yaml", "note": ""}, {"id": "xixian.base.detecting-insults-in-social-commentary", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "base", "dataset": "detecting-insults-in-social-commentary", "status": "archived", "official_score": 0.95914, "medal": "gold", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.83321, "silver": 0.82307, "bronze": 0.79111}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:4", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-four-methods-muse13/runs/base/04_detecting-insults-in-social-commentary/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-four-methods-muse13/runs/base/04_detecting-insults-in-social-commentary/logs/journal.json", "metrics": [{"event_id": "30a73b6c216b49c69ce8468326cdb89f", "step": 4, "value": 0.9506256365488142, "stage": "draft", "created_at": 1788670699.5084345}, {"event_id": "c81b8ecdd86e4a78822d24a03747331e", "step": 5, "value": 0.9496580823512295, "stage": "debug", "created_at": 1788671169.4021575}, {"event_id": "e1e75f562dbd4d079ac8df7653a3531b", "step": 6, "value": 0.9177869925796596, "stage": "debug", "created_at": 1788671256.3720422}, {"event_id": "471ea5b47d9a4a2dbe937ce2bd993c68", "step": 8, "value": 0.953179106649207, "stage": "improve", "created_at": 1788671435.3247674}, {"event_id": "146de20817c0486aae8f86d4f7093008", "step": 10, "value": 0.9339153208206024, "stage": "improve", "created_at": 1788671409.292194}, {"event_id": "9cf126f4e9354a558e8e453c8fc85b7f", "step": 11, "value": 0.9135675832969592, "stage": "debug", "created_at": 1788671686.6735306}, {"event_id": "91a9d717cebd4b9990624a1eecaed70a", "step": 12, "value": 0.8596391677578932, "stage": "improve", "created_at": 1788671870.524894}, {"event_id": "bead699a5dd540ec9ce9ff7bb66f9655", "step": 13, "value": 0.9204932343954606, "stage": "improve", "created_at": 1788671899.93772}, {"event_id": "49b70468217e4d60b981a888da7305a8", "step": 14, "value": 0.9401134875600174, "stage": "improve", "created_at": 1788671744.573022}, {"event_id": "f25952c51eb143ecbf35655cc03c9900", "step": 15, "value": 0.9421067947039139, "stage": "improve", "created_at": 1788672249.3429992}, {"event_id": "5ac6bc62b22c402997b5fb1ec1dc6439", "step": 16, "value": 0.9366225745904114, "stage": "improve", "created_at": 1788672096.3325639}, {"event_id": "26cb05f531294d779ed7bb4d0e228072", "step": 17, "value": 0.9481303651971482, "stage": "improve", "created_at": 1788672324.0173044}, {"event_id": "991f5d022c1f451f902938fd33615315", "step": 18, "value": 0.9389422377418886, "stage": "improve", "created_at": 1788672705.3803794}, {"event_id": "0b6389bc5fab4a5fa1471bf00d5e548e", "step": 19, "value": 0.9387189547901613, "stage": "evolution", "created_at": 1788672702.337538}, {"event_id": "a62b2e6613974812a9a7d0c4c006475e", "step": 22, "value": 0.9426233085988651, "stage": "improve", "created_at": 1788673155.0482752}, {"event_id": "050f39beb3de413fbfa8c34abf12d1b1", "step": 23, "value": 0.958426219827268, "stage": "debug", "created_at": 1788674018.2803752}, {"event_id": "a2d32c1d8a3d49abb3178621c2abb75e", "step": 27, "value": 0.9231049032445802, "stage": "improve", "created_at": 1788681877.6457615}, {"event_id": "7508c68508094f2eb17aa509c340c1c0", "step": 30, "value": 0.9423832387603667, "stage": "improve", "created_at": 1788682147.6047246}, {"event_id": "3cfd69e860d34c7fae14aacf5baad765", "step": 31, "value": 0.9425634436235143, "stage": "debug", "created_at": 1788682222.266474}, {"event_id": "e67c4aa6a373440dbf95d624aaf3fb8c", "step": 32, "value": 0.9489904940852013, "stage": "improve", "created_at": 1788681794.9108336}, {"event_id": "d7567579f1c04fd1bfc1cb443e540400", "step": 33, "value": 0.9564286861548346, "stage": "improve", "created_at": 1788682517.5186424}, {"event_id": "660168f5f151462f9d2bb64bb54eafa6", "step": 34, "value": 0.9525859299710889, "stage": "improve", "created_at": 1788682785.700776}, {"event_id": "592d207d443e4c9a9304ed24a9634342", "step": 35, "value": 0.9536806225785378, "stage": "evolution", "created_at": 1788682564.9477484}, {"event_id": "2276b66c03e245fab6c974ca9737f010", "step": 36, "value": 0.9558516737817937, "stage": "improve", "created_at": 1788682507.7486355}, {"event_id": "e568de5a605c4a33a3c0597cfc90040e", "step": 37, "value": 0.9547100867330549, "stage": "improve", "created_at": 1788683189.779762}, {"event_id": "88922fc04cb54f40869c9b3dd63a2eff", "step": 38, "value": 0.9592234443050122, "stage": "improve", "created_at": 1788683788.512075}, {"event_id": "97197044b6634604bd830e0b34f0e7eb", "step": 39, "value": 0.9547052929570441, "stage": "improve", "created_at": 1788683791.1910393}, {"event_id": "101b1f7b6dee4935a43dd52aafa1fb41", "step": 40, "value": 0.967402376910017, "stage": "improve", "created_at": 1788684425.520917}, {"event_id": "012e71b6f0864104bee39571d1ed9917", "step": 41, "value": 0.9475523371366203, "stage": "improve", "created_at": 1788683795.3182206}, {"event_id": "b2b60e28d32043e68051c3a90fc36830", "step": 42, "value": 0.9262330859886513, "stage": "improve", "created_at": 1788685213.55654}, {"event_id": "a4ac3218017d4e43af394cf991594c9c", "step": 43, "value": 0.9418506961508577, "stage": "improve", "created_at": 1788685100.8051348}, {"event_id": "ca9e7bdd9c924f63879901ab4e464c9f", "step": 44, "value": 0.9633424374400237, "stage": "improve", "created_at": 1788685149.0569239}, {"event_id": "39db9bc16d4e4141bb39bbbc99385642", "step": 46, "value": 0.9431252728066346, "stage": "debug", "created_at": 1788685869.7654636}, {"event_id": "69a355fdc1dd4b70b364f618ab99b2e4", "step": 47, "value": 0.9384357312922821, "stage": "fusion", "created_at": 1788685750.131273}, {"event_id": "fa14a22929ee452694ca415e9fc28715", "step": 49, "value": 0.9602568834428287, "stage": "improve", "created_at": 1788686432.104704}, {"event_id": "4984c5625d6e4ecc9a63feeb0f333b10", "step": 50, "value": 0.942994325621999, "stage": "improve", "created_at": 1788686682.303207}, {"event_id": "200ff9a1b8fc4116bbd5117dc0f18732", "step": 51, "value": 0.9622056543884254, "stage": "improve", "created_at": 1788687539.274718}, {"event_id": "e0c609a166bc40a5b7e8b1b6784630da", "step": 52, "value": 0.9261385130219701, "stage": "improve", "created_at": 1788687570.8388526}, {"event_id": "cd722f979da040088fbce3f0dfea2f64", "step": 53, "value": 0.9642134789990404, "stage": "improve", "created_at": 1788685939.6800272}, {"event_id": "aa279c6c7c3e4b6aa7f115cfbd3cd0a1", "step": 54, "value": 0.951573430245993, "stage": "improve", "created_at": 1788689113.0608525}, {"event_id": "acbf314872d94b15925acf51012092c1", "step": 55, "value": 0.9459276671528505, "stage": "evolution", "created_at": 1788688204.903246}, {"event_id": "de6299773145465994afff7e45f9ce14", "step": 56, "value": 0.9638591570089319, "stage": "improve", "created_at": 1788690533.5234568}, {"event_id": "9c2a87414a69461e9155e272d4594c77", "step": 57, "value": 0.9658522182032923, "stage": "evolution", "created_at": 1788689083.7403502}, {"event_id": "96bdc05be5b549dd9c66888e77ec1f93", "step": 58, "value": 0.9643024697563755, "stage": "evolution", "created_at": 1788691097.343018}, {"event_id": "37ddbaee73514096960a108edeb30fef", "step": 59, "value": 0.9652026278880933, "stage": "fusion", "created_at": 1788692040.290078}, {"event_id": "eaef00990ea44b58813a89bad53250b3", "step": 60, "value": 0.956648054836806, "stage": "fusion", "created_at": 1788691609.9906683}, {"event_id": "af1ce8c99e8b42f89e9fd6230e07ef9a", "step": 61, "value": 0.9587103314232097, "stage": "evolution", "created_at": 1788692625.110854}, {"event_id": "a52cdac73c38456d87f60212ab8f11a3", "step": 62, "value": 0.9465944430299716, "stage": "improve", "created_at": 1788694621.3866754}, {"event_id": "072be4fe49fd449abd078fe7f94f7ae8", "step": 64, "value": 0.9652026278880933, "stage": "fusion", "created_at": 1788694060.834287}, {"event_id": "115f590861514d47a77cb8fca3f32540", "step": 65, "value": 0.9551120940987232, "stage": "evolution", "created_at": 1788695165.159998}, {"event_id": "7b3191d8c1ee4e3ab47cf586e88803cc", "step": 66, "value": 0.9521602955348538, "stage": "improve", "created_at": 1788696009.366597}, {"event_id": "124cbba9480a4ae8a146978313ca36d7", "step": 67, "value": 0.9619900417603597, "stage": "improve", "created_at": 1788696326.477473}, {"event_id": "1efb13fe446444ef881ca426ccd2fb28", "step": 68, "value": 0.9609513756241412, "stage": "evolution", "created_at": 1788696253.9867628}, {"event_id": "e35ea06354a44c99b5067648ceb35104", "step": 69, "value": 0.9654536059644201, "stage": "evolution", "created_at": 1788697398.4824507}, {"event_id": "7327c891a3784be98cc69d9e067b298b", "step": 70, "value": 0.9561973790174977, "stage": "fusion_draft", "created_at": 1788697822.9456654}, {"event_id": "fd0a7aa873d04dafa208be30fcfe99fe", "step": 71, "value": 0.9688049014541964, "stage": "fusion", "created_at": 1788696458.127867}], "maximize": true, "elapsed_seconds": 28767.72573876381, "node_count": 72, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.base.detecting-insults-in-social-commentary.yaml", "note": ""}, {"id": "xixian.base.dog-breed-identification", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "base", "dataset": "dog-breed-identification", "status": "archived", "official_score": 0.34292, "medal": "none", "valid_submission": true, "score_maximize": false, "thresholds": {"gold": 0.0005, "silver": 0.00539, "bronze": 0.04598}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:5", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-four-methods-muse13/runs/base/05_dog-breed-identification/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-four-methods-muse13/runs/base/05_dog-breed-identification/logs/journal.json", "metrics": [{"event_id": "c807d5318da84311b4920346c9f913ea", "step": 13, "value": 0.4994795130956193, "stage": "draft", "created_at": 1788682013.988213}, {"event_id": "fd7004d5bba640ad896bb35567d02787", "step": 14, "value": 3.2799018137365237, "stage": "debug", "created_at": 1788681794.7672167}, {"event_id": "5ef625545ed34185980d8310a692e741", "step": 16, "value": 0.5223571354088373, "stage": "improve", "created_at": 1788682622.6995766}, {"event_id": "cb91f263093a483d9c05ff272f4362ba", "step": 18, "value": 0.5886461019839626, "stage": "debug", "created_at": 1788683270.0271096}, {"event_id": "605403d076d24edc8543b6d123a2420a", "step": 19, "value": 1.7480147246372546, "stage": "debug", "created_at": 1788683483.4407446}, {"event_id": "94f16c77d0c44f4aaddb8d53f244acb7", "step": 22, "value": 0.4320931833882228, "stage": "debug", "created_at": 1788685835.7266831}, {"event_id": "5fb856cf07d14021a712f878f9db4994", "step": 23, "value": 1.3220228504761138, "stage": "improve", "created_at": 1788685312.7094424}, {"event_id": "5ed5772776c541d1b442c7da5b72b91d", "step": 24, "value": 0.5780750558426976, "stage": "improve", "created_at": 1788687018.8264923}, {"event_id": "c4d83df2bdac47978d71412250bbf203", "step": 25, "value": 0.616248195931908, "stage": "debug", "created_at": 1788685879.2091668}, {"event_id": "31663e5828a3440b904e487b68584a37", "step": 26, "value": 0.436096969283807, "stage": "improve", "created_at": 1788686980.2830799}, {"event_id": "cfe3837b2df347a5a01ac7da6f4633c9", "step": 27, "value": 0.5482579608034734, "stage": "improve", "created_at": 1788688553.2289307}, {"event_id": "766e607e11b8469eba48323c57bda85c", "step": 31, "value": 0.428464629894174, "stage": "improve", "created_at": 1788693514.2560256}, {"event_id": "2a704eb490e04301845bb2ede2ede116", "step": 35, "value": 0.5816117240159921, "stage": "improve", "created_at": 1788690365.5490627}, {"event_id": "fb8c9fa12c254e1faf405c07e287b5ae", "step": 37, "value": 0.3221815249483094, "stage": "fusion_draft", "created_at": 1788696310.6194723}, {"event_id": "dfe8cf5a607745d890e88ef4e37eec1c", "step": 38, "value": 0.39883221372401484, "stage": "debug", "created_at": 1788697182.8102498}], "maximize": false, "elapsed_seconds": 28774.943049907684, "node_count": 39, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.base.dog-breed-identification.yaml", "note": ""}, {"id": "xixian.base.dogs-vs-cats-redux-kernels-edition", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "base", "dataset": "dogs-vs-cats-redux-kernels-edition", "status": "archived", "official_score": 0.00243, "medal": "gold", "valid_submission": true, "score_maximize": false, "thresholds": {"gold": 0.03882, "silver": 0.05038, "bronze": 0.06127}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:6", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-four-methods-muse13/runs/base/06_dogs-vs-cats-redux-kernels-edition/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-four-methods-muse13/runs/base/06_dogs-vs-cats-redux-kernels-edition/logs/journal.json", "metrics": [{"event_id": "d56a3ab8ac8040fa992f95c0f359dc58", "step": 2, "value": 0.011281987967126778, "stage": "draft", "created_at": 1788670753.7527056}, {"event_id": "ec58eae519184c3fbc9cfe7e61929831", "step": 3, "value": 0.01891371430500111, "stage": "draft", "created_at": 1788671048.46024}, {"event_id": "2a54fb2a51584ede89f2aeec75ab0138", "step": 5, "value": 0.028044227950528057, "stage": "debug", "created_at": 1788671178.2803998}, {"event_id": "0bc135e36c5c49dead3eec4c10e33083", "step": 7, "value": 0.03142525252032817, "stage": "improve", "created_at": 1788672130.1272907}, {"event_id": "bec6de0456424988a1d217fe061f149f", "step": 8, "value": 0.01550630138557969, "stage": "debug", "created_at": 1788672594.362127}, {"event_id": "f2edffe392c94b3ba8b2b263159fd77e", "step": 15, "value": 0.0011454036369868991, "stage": "debug", "created_at": 1788682053.0949926}, {"event_id": "ae63df04298b4a7485ac505078b8018e", "step": 16, "value": 0.0016327989287674427, "stage": "debug", "created_at": 1788682183.8109248}, {"event_id": "10067ef9c6f2454897350fdc3f083176", "step": 17, "value": 0.0033879728252408634, "stage": "draft", "created_at": 1788681946.1333134}, {"event_id": "8ad2a64c2e034aa3a5be88b2b879c72f", "step": 18, "value": 0.000704591085655538, "stage": "improve", "created_at": 1788683805.598118}, {"event_id": "f7286e8c5a3545809d5fdb14ae169634", "step": 20, "value": 0.019084690142831068, "stage": "improve", "created_at": 1788683866.6587381}, {"event_id": "c6d9584784ad4e32b16d46f70b12b774", "step": 21, "value": 0.005468321179227427, "stage": "debug", "created_at": 1788686260.1456563}, {"event_id": "bda1705523354d2ebdd5120f88f96b41", "step": 22, "value": 0.004252202648328672, "stage": "improve", "created_at": 1788685166.7920039}, {"event_id": "41498f0d446c442b96a68a0ecae11a28", "step": 25, "value": 0.01210441134540479, "stage": "improve", "created_at": 1788686717.973362}, {"event_id": "7f92fbbf7fb249939c28836d9c34f8db", "step": 27, "value": 0.003631597408553731, "stage": "improve", "created_at": 1788690330.5983636}, {"event_id": "80c1baa3e9fc4beb8237807f6afecfee", "step": 29, "value": 0.007245335302193959, "stage": "debug", "created_at": 1788695739.040284}, {"event_id": "c139e5eba4e042e5be75bbc3fef81c41", "step": 30, "value": 0.010888935915944847, "stage": "evolution", "created_at": 1788696164.6573763}, {"event_id": "0fec0a195f3f47d5a5f552986049c9f5", "step": 32, "value": 0.010665823198277458, "stage": "improve", "created_at": 1788694709.384019}, {"event_id": "756dbdbd64b3441eaa932ac1c5d8920d", "step": 33, "value": 0.005774053454940173, "stage": "fusion_draft", "created_at": 1788697553.7950242}, {"event_id": "e9de425508ce41368ae8fc3b5b7d030f", "step": 34, "value": 0.012091503801051994, "stage": "debug", "created_at": 1788695269.941945}, {"event_id": "14867563069c4679bbe1bbe4edb75b3d", "step": 35, "value": 0.004963804191296637, "stage": "improve", "created_at": 1788698303.8100436}, {"event_id": "25a330b9a0dd4049906f78042dcaf2c0", "step": 37, "value": 0.007314120622628426, "stage": "improve", "created_at": 1788697192.7182415}, {"event_id": "0eae5dace7444b96b64e90e2e003de7a", "step": 38, "value": 0.004798813781411361, "stage": "improve", "created_at": 1788699086.752241}], "maximize": false, "elapsed_seconds": 28772.931602716446, "node_count": 39, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.base.dogs-vs-cats-redux-kernels-edition.yaml", "note": ""}, {"id": "xixian.base.histopathologic-cancer-detection", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "base", "dataset": "histopathologic-cancer-detection", "status": "archived", "official_score": 0.99072, "medal": "gold", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.9835, "silver": 0.9798, "bronze": 0.9738}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:7", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-four-methods-muse13/runs/base/07_histopathologic-cancer-detection/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-four-methods-muse13/runs/base/07_histopathologic-cancer-detection/logs/journal.json", "metrics": [{"event_id": "92edcc622ab54f9eadf659e99e0463a5", "step": 6, "value": 0.9907148871124388, "stage": "debug", "created_at": 1788681835.2610927}, {"event_id": "75518ce25da94189b9609006111745b4", "step": 8, "value": 0.9904176762906373, "stage": "improve", "created_at": 1788682711.3314695}, {"event_id": "afded6889a524a00b115934b8244e30d", "step": 9, "value": 0.9835095680858111, "stage": "debug", "created_at": 1788684192.0694337}, {"event_id": "8cb8770e49374e9cbe71af00eeca5851", "step": 11, "value": 0.9249797475141199, "stage": "draft", "created_at": 1788681963.825707}, {"event_id": "8b894335a7a9460393e468fc4ecd3e17", "step": 12, "value": 0.9605143926542967, "stage": "debug", "created_at": 1788682774.789922}, {"event_id": "c7eb9b7ef5d04b9d97df8b02d6722c12", "step": 13, "value": 0.9845700429917852, "stage": "debug", "created_at": 1788685948.5589223}, {"event_id": "79f385be9d3946549fdbe7f2bb039b8d", "step": 14, "value": 0.9248859222499473, "stage": "improve", "created_at": 1788686278.2626786}, {"event_id": "957ecc4fd878410793e3c7c785c80a0c", "step": 15, "value": 0.9874256083455685, "stage": "improve", "created_at": 1788692383.6433938}, {"event_id": "29abcb9e7f1c4e59b8d05bda010a5229", "step": 16, "value": 0.929563211225142, "stage": "improve", "created_at": 1788692959.1217017}], "maximize": true, "elapsed_seconds": 28768.377613544464, "node_count": 17, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.base.histopathologic-cancer-detection.yaml", "note": ""}, {"id": "xixian.base.jigsaw-toxic-comment-classification-challenge", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "base", "dataset": "jigsaw-toxic-comment-classification-challenge", "status": "archived", "official_score": 0.98686, "medal": "silver", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.9874, "silver": 0.98668, "bronze": 0.98639}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:8", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-four-methods-muse13/runs/base/08_jigsaw-toxic-comment-classification-challenge/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-four-methods-muse13/runs/base/08_jigsaw-toxic-comment-classification-challenge/logs/journal.json", "metrics": [{"event_id": "fa81b27e9bec4f7a84858425b14562fa", "step": 8, "value": 0.9760980445196376, "stage": "draft", "created_at": 1788681982.6659925}, {"event_id": "26e82391feec427aa11a820e6ab4be1c", "step": 9, "value": 0.9897562326118893, "stage": "improve", "created_at": 1788682907.981471}, {"event_id": "b993321239244750b8d0d45449c5f845", "step": 10, "value": 0.9686813283183912, "stage": "draft", "created_at": 1788681973.6160843}, {"event_id": "a33510c4c3274af291aec7e69081cdaa", "step": 11, "value": 0.9930594698289478, "stage": "debug", "created_at": 1788681845.3478816}, {"event_id": "6041705d4c2946b795ebf1a9674cf625", "step": 12, "value": 0.9854191876290548, "stage": "improve", "created_at": 1788685948.8883405}, {"event_id": "0a956323308a4501baf760fa8620d798", "step": 13, "value": 0.9880586635783182, "stage": "improve", "created_at": 1788691003.634926}], "maximize": true, "elapsed_seconds": 28775.666578531265, "node_count": 17, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.base.jigsaw-toxic-comment-classification-challenge.yaml", "note": ""}, {"id": "xixian.base.leaf-classification", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "base", "dataset": "leaf-classification", "status": "archived", "official_score": 0.00187, "medal": "silver", "valid_submission": true, "score_maximize": false, "thresholds": {"gold": 0.0, "silver": 0.00791, "bronze": 0.01526}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:9", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-four-methods-muse13/runs/base/09_leaf-classification/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-four-methods-muse13/runs/base/09_leaf-classification/logs/journal.json", "metrics": [{"event_id": "b3f7e1a903bc4982ab00e95a2221c0dd", "step": 2, "value": 0.059742845594882965, "stage": "draft", "created_at": 1788670920.6575205}, {"event_id": "bcf627b243c74661a134c244e8a59efe", "step": 3, "value": 0.8711161193746938, "stage": "draft", "created_at": 1788671096.7996414}, {"event_id": "1106251b1f7b471dbeb3cd70d9e44790", "step": 5, "value": 0.043722182512283325, "stage": "improve", "created_at": 1788671276.3010569}, {"event_id": "e75a092d49164c1a9d1b0f658c7b37ec", "step": 7, "value": 0.03444988653063774, "stage": "improve", "created_at": 1788671498.4864507}, {"event_id": "39c88f311d6149848e22d87b9e99068e", "step": 8, "value": 0.11900939590146246, "stage": "debug", "created_at": 1788671631.369484}, {"event_id": "e6265c0f5948434390b052c24c62cb0a", "step": 9, "value": 0.0010849840398704385, "stage": "improve", "created_at": 1788672074.3631196}, {"event_id": "5f6f2e85cc154e43812ac828b9bf0d09", "step": 10, "value": 0.0005844198620592052, "stage": "improve", "created_at": 1788673451.5078743}, {"event_id": "e885c2d2c7d24f84b3e12ef2228accb1", "step": 17, "value": 0.05907689407467842, "stage": "debug", "created_at": 1788682117.2792068}, {"event_id": "f663fe75fb964683956826e5603931d1", "step": 18, "value": 0.0014059141835599763, "stage": "debug", "created_at": 1788682182.2222376}, {"event_id": "0a11113bd7cd4c02a1c80689ae8ff13e", "step": 19, "value": 1.760832425279125e-05, "stage": "improve", "created_at": 1788682378.8396173}, {"event_id": "d2df4c5e760545e5aa6045bf9a44c1eb", "step": 20, "value": 0.010208278894424438, "stage": "improve", "created_at": 1788682324.1972804}, {"event_id": "86b15df2549d49218be55d68eec0bb1e", "step": 22, "value": 0.03823190927505493, "stage": "debug", "created_at": 1788682808.226559}, {"event_id": "ebf5d4177aa3418f893c9a0bcb7e59f3", "step": 23, "value": 1.0428065721540798e-05, "stage": "improve", "created_at": 1788682686.5135515}, {"event_id": "8d657896b93949d5aa1c6e0ea057821c", "step": 24, "value": 0.2827384182602182, "stage": "improve", "created_at": 1788683092.634271}, {"event_id": "64efe25d8a0440329b113d5af6101047", "step": 25, "value": 0.013466686167734295, "stage": "improve", "created_at": 1788683399.999995}, {"event_id": "3de51712e8244af5b8d12843ccc47d3d", "step": 26, "value": 0.04525429755449295, "stage": "improve", "created_at": 1788684113.8734546}, {"event_id": "8ca052c9446f428087bb5bbb1ffcf12d", "step": 27, "value": 0.0012186436305464652, "stage": "improve", "created_at": 1788683591.249202}, {"event_id": "0d9c3cf2833841f8b37ef24175a075c1", "step": 28, "value": 0.0604709957235343, "stage": "improve", "created_at": 1788684309.7257645}, {"event_id": "705993a21b5f48c3a1b90c400f59e520", "step": 29, "value": 0.0433111939419708, "stage": "fusion", "created_at": 1788686410.931718}, {"event_id": "e1c3cc783c9d4370b57334236bf5b5e5", "step": 32, "value": 6.853949327350947e-05, "stage": "debug", "created_at": 1788688532.3853326}, {"event_id": "d82638be5eb54d28b1f464f4c5dac4dd", "step": 33, "value": 0.06715762115082233, "stage": "debug", "created_at": 1788688613.7164972}, {"event_id": "b5f9ab5d262d420cb1a6270daf34cecb", "step": 34, "value": 0.028400830997528322, "stage": "improve", "created_at": 1788688842.14495}, {"event_id": "7edcd2a6938744a080a2a19a759ad5df", "step": 35, "value": 0.16099655963267842, "stage": "evolution", "created_at": 1788691608.1936743}, {"event_id": "91e21b5c7f3344c99b3a4d094bee2db6", "step": 36, "value": 0.008971441483152922, "stage": "improve", "created_at": 1788694603.8846092}, {"event_id": "aad32c7712304bf7b4f3d0d4e2d2df33", "step": 37, "value": 0.11407521578120516, "stage": "evolution", "created_at": 1788690490.713516}], "maximize": false, "elapsed_seconds": 28777.489744901657, "node_count": 38, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.base.leaf-classification.yaml", "note": ""}, {"id": "xixian.base.mlsp-2013-birds", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "base", "dataset": "mlsp-2013-birds", "status": "archived", "official_score": 0.89789, "medal": "bronze", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.93527, "silver": 0.90038, "bronze": 0.87372}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:10", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-four-methods-muse13/runs/base/10_mlsp-2013-birds/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-four-methods-muse13/runs/base/10_mlsp-2013-birds/logs/journal.json", "metrics": [{"event_id": "4b5a335f9ffe4baf93f012f26a987b50", "step": 5, "value": 0.7868866779461527, "stage": "debug", "created_at": 1788671366.602122}, {"event_id": "08ee7659acbf435095f54ff509ad2a05", "step": 7, "value": 0.8647220144602343, "stage": "debug", "created_at": 1788671456.4571025}, {"event_id": "17e6c4a5b21049e49ca953dd1aa564ac", "step": 8, "value": 0.7726478593497133, "stage": "improve", "created_at": 1788671591.612889}, {"event_id": "aebc262e2ac94cf5ac9de28402ddf5eb", "step": 9, "value": 0.8300837265241928, "stage": "debug", "created_at": 1788671647.2221544}, {"event_id": "55fcdf0201a646289bca630259204649", "step": 10, "value": 0.7765742239223188, "stage": "improve", "created_at": 1788671808.6924028}, {"event_id": "bfddd73b77984f278c09dffea2997319", "step": 11, "value": 0.8604338070306657, "stage": "improve", "created_at": 1788671772.060728}, {"event_id": "249dbc3db4664037b10cb42b7bb6210d", "step": 14, "value": 0.8669280229438432, "stage": "debug", "created_at": 1788672079.3790388}, {"event_id": "08e7647e5cf24adf9123181e1346ad96", "step": 15, "value": 0.8865120917476939, "stage": "improve", "created_at": 1788672123.0970755}, {"event_id": "b309a21bdad340fcb125fa9ed796d5a1", "step": 16, "value": 0.7616503604531412, "stage": "debug", "created_at": 1788672174.3033166}, {"event_id": "ca707ccdf0284d13bebf079e68e7efb8", "step": 17, "value": 0.8643954112313812, "stage": "improve", "created_at": 1788672385.349798}, {"event_id": "39187ea9856a4aa596f815c3fbcc7610", "step": 18, "value": 0.881164298180005, "stage": "improve", "created_at": 1788672416.9857936}, {"event_id": "055637fb1d334b2da27bd8f70705bcc7", "step": 19, "value": 0.787268280123584, "stage": "evolution", "created_at": 1788672452.2462225}, {"event_id": "782761a1ac3c4ff1804b7d9e5e26c213", "step": 20, "value": 0.8681750186985788, "stage": "improve", "created_at": 1788672707.181534}, {"event_id": "241596b1f81f425a8e73197c8f6a5f89", "step": 21, "value": 0.8621403460079563, "stage": "improve", "created_at": 1788672733.0139449}, {"event_id": "1b285a87fec148bab08be644b80dcbdb", "step": 22, "value": 0.8903812056737588, "stage": "improve", "created_at": 1788673007.2662818}, {"event_id": "da8adb9487094367a6750d3972c21939", "step": 23, "value": 0.7937509195233192, "stage": "improve", "created_at": 1788672791.9368343}, {"event_id": "b824dd0cfd8b40748fb225984e0bb86b", "step": 24, "value": 0.8763761680081413, "stage": "improve", "created_at": 1788673040.416296}, {"event_id": "8b0677a5e668404ba52539477a5d26ad", "step": 25, "value": 0.8809209917661208, "stage": "improve", "created_at": 1788673396.4763322}, {"event_id": "3f8b7474be9849e599ba411ba6506688", "step": 26, "value": 0.9064111175078359, "stage": "improve", "created_at": 1788673332.3835108}, {"event_id": "7faab4ccdb9c40c4885815ab26ae5024", "step": 27, "value": 0.8809209917661208, "stage": "improve", "created_at": 1788673731.2816956}, {"event_id": "a5a7dae505fa420f876bf28d9924a4b0", "step": 28, "value": 0.8793250994541586, "stage": "improve", "created_at": 1788674064.3706362}, {"event_id": "28e300337530488ab0dfb9aa84b0b938", "step": 29, "value": 0.9117164012025843, "stage": "improve", "created_at": 1788674041.3907053}, {"event_id": "3df019ead93d44bcbe11d8bb8047f608", "step": 30, "value": 0.7937509195233192, "stage": "improve", "created_at": 1788673375.2182548}, {"event_id": "cda46e475be8400c86b633fb32af6466", "step": 31, "value": 0.8253076140253492, "stage": "improve", "created_at": 1788674467.4931867}, {"event_id": "38e87b96f92a44f1bad39a311cfc5af0", "step": 38, "value": 0.8090480155426034, "stage": "improve", "created_at": 1788681886.3555129}, {"event_id": "f558921ba9b941c792401a4b3c7f2152", "step": 41, "value": 0.6109601493071337, "stage": "debug", "created_at": 1788682152.8729386}, {"event_id": "9467844ef0f648a18e197c9d99f831e8", "step": 42, "value": 0.7471724657937326, "stage": "improve", "created_at": 1788682211.3338485}, {"event_id": "cd6f7091e0a149819250bb66173f296c", "step": 43, "value": 0.6228544352148224, "stage": "improve", "created_at": 1788682362.355321}, {"event_id": "d48330e39d254430badeb4c1178a728b", "step": 45, "value": 0.6286661960526443, "stage": "improve", "created_at": 1788682577.156294}, {"event_id": "04e2ce5173ca43ce91fe5b347d26e895", "step": 46, "value": 0.8743455497382199, "stage": "improve", "created_at": 1788682348.920044}, {"event_id": "26b9d4923e554e05a2417135f7ac6a1a", "step": 48, "value": 0.8839554148276082, "stage": "evolution", "created_at": 1788682650.2737665}, {"event_id": "437ac440dc0f4db7b346d2ffdda0f70c", "step": 50, "value": 0.6330177640676524, "stage": "debug", "created_at": 1788683100.1885068}, {"event_id": "ef420b5742944a738900f52501c6a4b3", "step": 51, "value": 0.6334432507180088, "stage": "improve", "created_at": 1788683328.2749832}, {"event_id": "678ad8eb59b144afba6da7883eb09787", "step": 52, "value": 0.8868237347294939, "stage": "improve", "created_at": 1788682967.3076823}, {"event_id": "3e19baf14793425e8be40eeb00cd39cf", "step": 53, "value": 0.8920008955414828, "stage": "improve", "created_at": 1788683124.2277966}, {"event_id": "ae0058d28038477faad597f1bada66b7", "step": 54, "value": 0.6005453965245476, "stage": "improve", "created_at": 1788683553.4024389}, {"event_id": "0ecb4a697e554b228c76a6638f99b466", "step": 55, "value": 0.6180096894914469, "stage": "improve", "created_at": 1788683718.5442917}, {"event_id": "abe8a92deccf4b5a9973a54219e9c9ed", "step": 56, "value": 0.8794938917975568, "stage": "improve", "created_at": 1788683647.6719532}, {"event_id": "4604b3e9e6df462b9c23f96bcd9eb601", "step": 57, "value": 0.6133970273955383, "stage": "improve", "created_at": 1788683900.6265895}, {"event_id": "f0fcac677f5249fe918268f92cf8d14a", "step": 59, "value": 0.889971534574298, "stage": "improve", "created_at": 1788683666.8195524}, {"event_id": "ed9a9742a70e4d628c97c64ddec0379e", "step": 63, "value": 0.8526551982049364, "stage": "debug", "created_at": 1788684133.5551817}, {"event_id": "c52d41b74052472395056c17a19349d9", "step": 64, "value": 0.8699245005484668, "stage": "evolution", "created_at": 1788684361.6781244}, {"event_id": "658a9c07eb4c44658d97a07e338a5cb8", "step": 65, "value": 0.8888297191837777, "stage": "improve", "created_at": 1788684223.162729}, {"event_id": "a6f8e63961fc4c89bc4f707117b02898", "step": 66, "value": 0.8715721550566111, "stage": "evolution", "created_at": 1788684429.1016312}, {"event_id": "17c0ed91a8a243f8884c08dfed260c6f", "step": 67, "value": 0.7797045955848072, "stage": "improve", "created_at": 1788684776.997108}, {"event_id": "d1b46b1453504da68edd22a19986a2c1", "step": 68, "value": 0.8578279539808173, "stage": "improve", "created_at": 1788685019.6378803}, {"event_id": "8f7b96a7a1944bf7bcfefa3a82ae0a8f", "step": 69, "value": 0.8594055843408175, "stage": "evolution", "created_at": 1788684961.833417}, {"event_id": "d604e339b5b04022a05ccc147be71129", "step": 70, "value": 0.876312927780976, "stage": "evolution", "created_at": 1788685561.0053985}, {"event_id": "f381688835ec426ab7d073f87d23150f", "step": 71, "value": 0.8680367651762297, "stage": "improve", "created_at": 1788685481.6611593}, {"event_id": "b9f47dc6141b4b3384fd91d6cb0aff89", "step": 72, "value": 0.8583317341521141, "stage": "evolution", "created_at": 1788686270.836179}, {"event_id": "3abe8837b7604bb5bded8615112ac5ef", "step": 73, "value": 0.8919209364805221, "stage": "evolution", "created_at": 1788686309.2256248}, {"event_id": "cd574466de59463a9ee4d647a975f0be", "step": 74, "value": 0.8673447195036141, "stage": "evolution", "created_at": 1788686981.855221}, {"event_id": "8a05577743474931ac6784bbd1a752fd", "step": 75, "value": 0.8883431682978316, "stage": "improve", "created_at": 1788687122.9212968}, {"event_id": "499f5d8e9650416999f6a922beb3c6c3", "step": 77, "value": 0.7500073771535777, "stage": "debug", "created_at": 1788688069.0028226}, {"event_id": "12808b27f70d48529b679433b2328097", "step": 78, "value": 0.8706214418217872, "stage": "evolution", "created_at": 1788687692.7115686}, {"event_id": "80300ed737c84f73bf72ccb96439e5b9", "step": 79, "value": 0.7318465434345849, "stage": "improve", "created_at": 1788688382.956979}, {"event_id": "c29918d533654239a152c64b4384447f", "step": 80, "value": 0.8167870050534125, "stage": "evolution", "created_at": 1788688622.132366}, {"event_id": "f750accdeeb74ca89e0eef5b8d8ddd04", "step": 81, "value": 0.8468378199146244, "stage": "evolution", "created_at": 1788688534.6499016}, {"event_id": "6da0d2d699ca4fe7aa80cf93347f1728", "step": 82, "value": 0.8192201592784494, "stage": "evolution", "created_at": 1788689185.872666}, {"event_id": "56f055f6800948c6900c2259408e563d", "step": 83, "value": 0.8621275998983268, "stage": "evolution", "created_at": 1788689302.4040835}, {"event_id": "435f486ac95b4243891bb3882bdf3aae", "step": 84, "value": 0.8617244129685953, "stage": "evolution", "created_at": 1788689976.775165}, {"event_id": "6ef9683c92684b838eff4b4c2914a5bd", "step": 85, "value": 0.8954787234042553, "stage": "evolution", "created_at": 1788690779.8546808}, {"event_id": "2af9a141f908459ba5ee394e4d7a8e88", "step": 86, "value": 0.8325273459988486, "stage": "evolution", "created_at": 1788689873.8739529}, {"event_id": "1ebb50f7769f4fe5890b5037abccf364", "step": 87, "value": 0.8776314526962194, "stage": "fusion", "created_at": 1788691099.4080234}, {"event_id": "46a458830dbd4d73a4f9ac8d51aa80e4", "step": 88, "value": 0.8666003006460692, "stage": "fusion", "created_at": 1788691254.4339862}, {"event_id": "8d902b29b78d440383c10d46270d6934", "step": 90, "value": 0.8458833077464339, "stage": "fusion", "created_at": 1788692001.4307973}, {"event_id": "aeba3785a31b415f995ede1ea4ca61c5", "step": 91, "value": 0.9115740740740741, "stage": "debug", "created_at": 1788692217.869614}, {"event_id": "7fe45621e9084933b8d96081f5951b68", "step": 92, "value": 0.9029129085908015, "stage": "evolution", "created_at": 1788692875.7068188}, {"event_id": "7dd3762465f643d9b0eb70931ddb861d", "step": 93, "value": 0.9259243267447066, "stage": "evolution", "created_at": 1788693055.584384}, {"event_id": "b7230f14fe1745ea8ce0c399d363fa6f", "step": 94, "value": 0.9032327448346447, "stage": "improve", "created_at": 1788684864.2282283}, {"event_id": "aa96078d2b044d8baea78f82636d54c3", "step": 95, "value": 0.9030272500479755, "stage": "fusion", "created_at": 1788693656.5286427}, {"event_id": "7ceb4877f9e443a9a2e72a4859e969f9", "step": 96, "value": 0.9253126399283567, "stage": "improve", "created_at": 1788693951.529143}, {"event_id": "f8c4d02dee6b4b8588ca42f2704536e4", "step": 97, "value": 0.905110183586004, "stage": "improve", "created_at": 1788694461.3140507}, {"event_id": "fc10ce99997948bcb0447a7575890cfb", "step": 99, "value": 0.8366380413228427, "stage": "debug", "created_at": 1788695665.5370328}, {"event_id": "bfdddb4c49ff4802ae57a4d641c15684", "step": 100, "value": 0.8666, "stage": "fusion_draft", "created_at": 1788696128.6551626}, {"event_id": "ffd8e93e0305442d837f968d2398a263", "step": 101, "value": 0.9252222861894709, "stage": "improve", "created_at": 1788695290.7808042}, {"event_id": "41abde5b9d024e54830be741b3953397", "step": 102, "value": 0.809781791722638, "stage": "evolution", "created_at": 1788697187.3722155}, {"event_id": "99219f3fe13d4e199675bcf086305e84", "step": 103, "value": 0.831095279217041, "stage": "evolution", "created_at": 1788697809.4778466}, {"event_id": "b304872b98ff4521a7b38ca351ee5eb4", "step": 104, "value": 0.9262833429284206, "stage": "improve", "created_at": 1788696691.7647252}], "maximize": true, "elapsed_seconds": 28769.956775665283, "node_count": 105, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.base.mlsp-2013-birds.yaml", "note": ""}, {"id": "xixian.base.new-york-city-taxi-fare-prediction", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "base", "dataset": "new-york-city-taxi-fare-prediction", "status": "archived", "official_score": 20.90064, "medal": "none", "valid_submission": true, "score_maximize": false, "thresholds": {"gold": 2.83377, "silver": 2.88191, "bronze": 2.92371}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:11", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-four-methods-muse13/runs/base/11_new-york-city-taxi-fare-prediction/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-four-methods-muse13/runs/base/11_new-york-city-taxi-fare-prediction/logs/journal.json", "metrics": [{"event_id": "861f8f8ce9e14481b097603251781328", "step": 1, "value": 3.5897300243377686, "stage": "draft", "created_at": 1788671522.7395563}, {"event_id": "de884d5912af43daaf37e75abfaa139e", "step": 2, "value": 4.230713037859993, "stage": "draft", "created_at": 1788671173.7986965}, {"event_id": "460919fedf1d4dc4add5c7b428dd7081", "step": 3, "value": 3.7395443374218287, "stage": "improve", "created_at": 1788672005.4028127}, {"event_id": "3e9840eb767a4b469df84ee63be19a3b", "step": 4, "value": 3.33560848236084, "stage": "improve", "created_at": 1788671951.551824}, {"event_id": "2cfa44355e1d487d9d3c80b700dea77f", "step": 5, "value": 2.6550675530544736, "stage": "improve", "created_at": 1788672634.9137154}, {"event_id": "10e046e54c314ed79a9a91623dfdc652", "step": 6, "value": 3.1928121232380375, "stage": "improve", "created_at": 1788673169.4026608}, {"event_id": "93aa8f7af8314764893f7d26e32c3edb", "step": 12, "value": 4.48350160715221, "stage": "draft", "created_at": 1788681989.8729608}, {"event_id": "e5ad387074d3432e9a11ddef30ffd282", "step": 13, "value": 3.5644711907985194, "stage": "improve", "created_at": 1788682416.003004}, {"event_id": "e70dadd2600c41d082d02a7629d77cab", "step": 14, "value": 3.163952112197876, "stage": "debug", "created_at": 1788682175.3031108}, {"event_id": "136b77c3c001467581cc2c59e9c7497b", "step": 15, "value": 2.5365460330296083, "stage": "improve", "created_at": 1788683026.6152468}, {"event_id": "7ba005d72e934e2d98b335046df5d9b3", "step": 16, "value": 2.9349354743186886, "stage": "improve", "created_at": 1788683287.4259222}, {"event_id": "bff2d3fb32864a9884d1c1edcc240996", "step": 17, "value": 2.5189880305794894, "stage": "improve", "created_at": 1788683623.3080227}, {"event_id": "3c14d84f314246d79004da403b91a850", "step": 18, "value": 2.528146886812139, "stage": "improve", "created_at": 1788685136.5096033}, {"event_id": "cfa99d555a5c4581b05c78f8e78f71ba", "step": 19, "value": 2.5522119202973266, "stage": "improve", "created_at": 1788686656.997128}, {"event_id": "fde9d4781d584ec7bdc8b89ae8d5a92f", "step": 20, "value": 2.9845034866629567, "stage": "improve", "created_at": 1788684970.1534853}, {"event_id": "304687578670477b8e0a749a7e337820", "step": 21, "value": 2.536546033029605, "stage": "improve", "created_at": 1788688032.2378619}, {"event_id": "ae5d3746715b4e6ea5b9db176db835ff", "step": 22, "value": 2.5257058446842855, "stage": "fusion", "created_at": 1788688928.1658852}, {"event_id": "eb08bdb3726c46a4b44840e62f3e58eb", "step": 23, "value": 3.008686806787898, "stage": "improve", "created_at": 1788688677.908348}, {"event_id": "3e6be3d5f501461fa6792504cb7b89e2", "step": 24, "value": 2.500001749198347, "stage": "evolution", "created_at": 1788690112.3909101}, {"event_id": "29d893473e624be19529e27396b63b00", "step": 25, "value": 2.5179113566193254, "stage": "improve", "created_at": 1788692341.6119754}, {"event_id": "28a3e38e620c461798121c9f3751aa61", "step": 26, "value": 2.5189880305794894, "stage": "improve", "created_at": 1788691705.908466}, {"event_id": "e8f2ebc0c589420b82308a46ad4f8af0", "step": 27, "value": 2.492368416907404, "stage": "improve", "created_at": 1788694105.937849}, {"event_id": "103a3f28d8a0402aa08ef7d8de459268", "step": 28, "value": 2.5235891145820815, "stage": "improve", "created_at": 1788694581.5580652}, {"event_id": "49de9659022749d088713520cb126902", "step": 29, "value": 2.499779289402913, "stage": "improve", "created_at": 1788695916.102893}], "maximize": false, "elapsed_seconds": 28770.0467338562, "node_count": 33, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.base.new-york-city-taxi-fare-prediction.yaml", "note": ""}, {"id": "xixian.base.nomad2018-predict-transparent-conductors", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "base", "dataset": "nomad2018-predict-transparent-conductors", "status": "archived", "official_score": 0.06057, "medal": "silver", "valid_submission": true, "score_maximize": false, "thresholds": {"gold": 0.05589, "silver": 0.06229, "bronze": 0.06582}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:12", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-four-methods-muse13/runs/base/12_nomad2018-predict-transparent-conductors/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-four-methods-muse13/runs/base/12_nomad2018-predict-transparent-conductors/logs/journal.json", "metrics": [{"event_id": "f38c5557abe247db94141b84793aa605", "step": 2, "value": 0.06632702725488887, "stage": "draft", "created_at": 1788670814.763836}, {"event_id": "19758ae2c76f4a05bec4773e9110c816", "step": 3, "value": 0.0533547385715387, "stage": "debug", "created_at": 1788671280.1983001}, {"event_id": "dd8b874ee31d43a6bf2422f56d56e4a3", "step": 4, "value": 0.15745728033587425, "stage": "improve", "created_at": 1788671434.56811}, {"event_id": "053c05b748c64460be571b51f9cc57d9", "step": 5, "value": 0.062229336614933864, "stage": "improve", "created_at": 1788671416.1601794}, {"event_id": "4160a037c878476cbe7c191393baa604", "step": 6, "value": 0.0609202685129694, "stage": "improve", "created_at": 1788671616.4014359}, {"event_id": "bdb00fa008b74877a3a35664b603d26f", "step": 7, "value": 0.06105515213735211, "stage": "improve", "created_at": 1788671831.5540667}, {"event_id": "1130d62b5bca49ab88fb29891490fb07", "step": 9, "value": 0.06068489166441471, "stage": "debug", "created_at": 1788672171.3864706}, {"event_id": "ac81f143d7264b21844da3b338d5d009", "step": 10, "value": 0.060885000394928515, "stage": "improve", "created_at": 1788672395.5425265}, {"event_id": "32bf90a9ad4b4363be603690766a08d3", "step": 11, "value": 0.060877709382959735, "stage": "improve", "created_at": 1788672646.3047516}, {"event_id": "7e776edf26514eb9a87e831b048194a5", "step": 12, "value": 0.15745728033587425, "stage": "improve", "created_at": 1788671604.7434664}, {"event_id": "56bbe31ca13e4de781e45833d760cb09", "step": 13, "value": 0.06090309731536063, "stage": "improve", "created_at": 1788672881.7132773}, {"event_id": "c06d8975c3954910b146df93d931354a", "step": 14, "value": 0.05336447161171251, "stage": "improve", "created_at": 1788672945.6995087}, {"event_id": "e80d69f7e6054548a8a85936d2c8ac62", "step": 15, "value": 0.06011396309016798, "stage": "evolution", "created_at": 1788673362.746859}, {"event_id": "18a319da2e2e412d9d07653de9d6e948", "step": 16, "value": 1.4086037899425874, "stage": "draft", "created_at": 1788671205.678853}, {"event_id": "bd2829817d964eb784bb21a7c39471fa", "step": 20, "value": 0.2888012096866256, "stage": "draft", "created_at": 1788681998.420905}, {"event_id": "9e7057ed3e5949eeaf80d9da7721cf80", "step": 22, "value": 0.21971435269137915, "stage": "improve", "created_at": 1788682145.9941006}, {"event_id": "b62c1e70e69d498b9527f1668a3fe3bb", "step": 23, "value": 0.06622484603340903, "stage": "debug", "created_at": 1788682186.5936944}, {"event_id": "98753b32c3a247a3a15aac4066671646", "step": 26, "value": 0.06752733490835341, "stage": "improve", "created_at": 1788682454.487519}, {"event_id": "c69799f2780e43998d032c0f8a6a2fe8", "step": 27, "value": 0.06343597427558524, "stage": "improve", "created_at": 1788682756.4020574}, {"event_id": "22f0f3166dae4704ae2981b4e22af77f", "step": 28, "value": 0.05998092294446825, "stage": "improve", "created_at": 1788682988.1830518}, {"event_id": "5ab04057018d420a81efdfe4a965904a", "step": 29, "value": 0.059962776732944034, "stage": "improve", "created_at": 1788683337.243592}, {"event_id": "09c9f399d856425b880f7f3083b8e8fb", "step": 30, "value": 0.059962776732944034, "stage": "improve", "created_at": 1788683633.006843}, {"event_id": "360847ad3fd04dd49818d1496e49ace5", "step": 31, "value": 0.11723169694307964, "stage": "improve", "created_at": 1788681882.5331163}, {"event_id": "d2493f2739ea4bf5b6c3e75b929fa8df", "step": 32, "value": 0.06001353940856356, "stage": "improve", "created_at": 1788683928.3498755}, {"event_id": "6e829507d2484593b3c91f6f00a85f4b", "step": 34, "value": 0.05858682933271828, "stage": "evolution", "created_at": 1788682610.8544426}, {"event_id": "1e5a99b3658f46a9b08a169e59de4797", "step": 35, "value": 0.05408690199691839, "stage": "evolution", "created_at": 1788686830.201184}, {"event_id": "612335ab61324c77b0dd84a556cafd0a", "step": 36, "value": 0.06007500152487544, "stage": "improve", "created_at": 1788684258.2847307}, {"event_id": "9b2019c5ae8a4c62976c488a80c447ad", "step": 37, "value": 0.0536324620532529, "stage": "evolution", "created_at": 1788687589.081448}, {"event_id": "86fb82310aa34a088bea9f60e2ce6b57", "step": 38, "value": 0.13626121488540283, "stage": "debug", "created_at": 1788686174.7204962}, {"event_id": "a203f0dc269f40eb9871694c80d17acf", "step": 39, "value": 0.11909936120638621, "stage": "improve", "created_at": 1788688329.6400433}, {"event_id": "82f472e590c94f2ca2fc07ce37214ae7", "step": 40, "value": 0.05404200875239901, "stage": "evolution", "created_at": 1788688109.1239486}, {"event_id": "a85c86ab6c134850b528928ad27a6ad9", "step": 41, "value": 0.11967534646826607, "stage": "debug", "created_at": 1788690474.8402057}, {"event_id": "b993eadd83e542e8a37eb28ea0abe5bd", "step": 42, "value": 0.05334644853554092, "stage": "improve", "created_at": 1788687642.645771}, {"event_id": "b6542f0b7fe2461482dd8b93b0c556ba", "step": 44, "value": 0.11121343962055665, "stage": "fusion", "created_at": 1788692536.2211425}, {"event_id": "85d2765cc2944ff68d57677cc8b08ff6", "step": 46, "value": 0.05336447161171251, "stage": "fusion", "created_at": 1788692419.431106}, {"event_id": "598540ddc9f84b21a2226f22f2e19f40", "step": 47, "value": 0.052585746203782764, "stage": "debug", "created_at": 1788694667.5304472}, {"event_id": "2367690d103a4a74a657464e8dce5e20", "step": 49, "value": 0.052982519833592256, "stage": "debug", "created_at": 1788695139.6104007}, {"event_id": "5ffdd8883a9b433aa1cfd196ea2ff554", "step": 51, "value": 0.05224742484055282, "stage": "improve", "created_at": 1788695585.6181533}, {"event_id": "b5a4d9200b8e4beebebae1a91e609c89", "step": 52, "value": 0.053145308941900844, "stage": "improve", "created_at": 1788696115.4719546}, {"event_id": "e810b57fad88488c86d9ac46632381ba", "step": 53, "value": 0.05328878266398672, "stage": "improve", "created_at": 1788696645.0582793}, {"event_id": "fe3f150381ac4917a8a01e756a37daa3", "step": 54, "value": 0.05336447161171251, "stage": "improve", "created_at": 1788694972.2795804}, {"event_id": "3f55a41ac79447d5acf7953c20751e27", "step": 55, "value": 0.05334644853554092, "stage": "improve", "created_at": 1788694713.8600547}], "maximize": false, "elapsed_seconds": 28759.22550678253, "node_count": 56, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.base.nomad2018-predict-transparent-conductors.yaml", "note": ""}, {"id": "xixian.base.plant-pathology-2020-fgvc7", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "base", "dataset": "plant-pathology-2020-fgvc7", "status": "archived", "official_score": 0.99819, "medal": "gold", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.97836, "silver": 0.97465, "bronze": 0.97361}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:13", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-four-methods-muse13/runs/base/13_plant-pathology-2020-fgvc7/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-four-methods-muse13/runs/base/13_plant-pathology-2020-fgvc7/logs/journal.json", "metrics": [{"event_id": "943c43b8984543b9ab4662d0d0039c1e", "step": 1, "value": 0.9814039842916722, "stage": "draft", "created_at": 1788670861.7987576}, {"event_id": "f8daba4863754343819ce0df489c4502", "step": 2, "value": 0.9739432376463192, "stage": "draft", "created_at": 1788671065.454955}, {"event_id": "b294a26c64ed483bab36ff52fcfaa803", "step": 4, "value": 0.9814039842916722, "stage": "improve", "created_at": 1788672223.743631}, {"event_id": "b9b154094ff043f29c338e452e509dcb", "step": 5, "value": 0.9782154952687482, "stage": "improve", "created_at": 1788672300.7941136}, {"event_id": "aa8fc48c554247efa0db58e783ff4ffd", "step": 8, "value": 0.9812939835435425, "stage": "improve", "created_at": 1788673250.00955}, {"event_id": "580e3866397c496da61095905a16519e", "step": 13, "value": 0.9266519416486939, "stage": "draft", "created_at": 1788682041.9313111}, {"event_id": "9c3cc055dddd4dee8e2762d76c5431e0", "step": 14, "value": 0.9781496885201129, "stage": "debug", "created_at": 1788682245.4274864}, {"event_id": "9e4b4f0c1a8a4d7aab7a4b4ac3d21082", "step": 16, "value": 0.9749010849837878, "stage": "improve", "created_at": 1788682391.5695035}, {"event_id": "0449cae7c6ae4ca4bdc6cae9a7d5b368", "step": 17, "value": 0.9715192244184386, "stage": "debug", "created_at": 1788681821.292024}, {"event_id": "a3b52768adea490cadf83667c57749eb", "step": 18, "value": 0.970302374726667, "stage": "improve", "created_at": 1788683027.9823186}, {"event_id": "37df1fbe21c546f49b3e6a7c5b5cb785", "step": 19, "value": 0.9697248752289582, "stage": "improve", "created_at": 1788683427.281481}, {"event_id": "1b26f625b2824b5895a5e629c4b11278", "step": 22, "value": 0.9773602442845243, "stage": "improve", "created_at": 1788684178.4121964}, {"event_id": "0e0be9a1009b4ef7abeb2699549f2307", "step": 23, "value": 0.9350051535243491, "stage": "improve", "created_at": 1788684731.9924228}, {"event_id": "c7449f1de52f4d2ba87feb8c45896014", "step": 25, "value": 0.9907708229279508, "stage": "improve", "created_at": 1788683553.5335884}, {"event_id": "a447f4298c4644dda79925a0b54fd927", "step": 26, "value": 0.974839697315371, "stage": "debug", "created_at": 1788685656.431058}, {"event_id": "bbccae2d0d6c409199b5fd0c6134888d", "step": 28, "value": 0.9751307529381801, "stage": "improve", "created_at": 1788685126.6254048}, {"event_id": "7e4d8707957746c1aee294f336c7d22f", "step": 30, "value": 0.9745679135563914, "stage": "fusion", "created_at": 1788686710.3030486}, {"event_id": "e0ad32d2f54f48d99c723d800cfddfbc", "step": 32, "value": 0.9869978757097528, "stage": "improve", "created_at": 1788687226.3807676}, {"event_id": "6bb8d99923bc47fa8d41f8a50e0a358a", "step": 33, "value": 0.9840941913000149, "stage": "debug", "created_at": 1788686658.3064346}, {"event_id": "5ff5e332e0744d2983cb2687c5c8bcd7", "step": 34, "value": 0.9715446833627528, "stage": "fusion", "created_at": 1788689666.554903}, {"event_id": "774ec18d873d4d13ba525c131492be97", "step": 35, "value": 0.9708138239887174, "stage": "evolution", "created_at": 1788690629.2995038}, {"event_id": "e695cd5bd814401092b91040b314b921", "step": 36, "value": 0.9912911359666634, "stage": "improve", "created_at": 1788689984.854054}, {"event_id": "6c79e13b6bf4453da723d3ca37983fb3", "step": 37, "value": 0.9794248366931415, "stage": "fusion", "created_at": 1788691679.4140246}, {"event_id": "a44ca17051de420593989952fb118422", "step": 39, "value": 0.9817686057944351, "stage": "improve", "created_at": 1788690103.7155504}, {"event_id": "cf8d9b73b09b46baa156e3f5e6fcbc0d", "step": 41, "value": 0.9893151926095307, "stage": "improve", "created_at": 1788692720.3579674}, {"event_id": "cb6a38b33e7f43ccbe6543e71dc53697", "step": 42, "value": 0.9907324392477823, "stage": "improve", "created_at": 1788693185.5673277}, {"event_id": "615c3259c05446edb6be9da63fc8904a", "step": 44, "value": 0.9819375985222025, "stage": "improve", "created_at": 1788694619.7740152}, {"event_id": "f553ac739f8c424595baf9d8e1cb45af", "step": 45, "value": 0.972680585141527, "stage": "debug", "created_at": 1788695512.9990218}, {"event_id": "da51ccc34c32409ba567d4dd19599729", "step": 46, "value": 0.938, "stage": "fusion_draft", "created_at": 1788696712.1712167}, {"event_id": "7bca73f4b8484e0a8f7eadd8f164350b", "step": 48, "value": 0.9793079021479656, "stage": "improve", "created_at": 1788695186.9081862}, {"event_id": "4a14ce8f6a1c4017b3507358c042d290", "step": 49, "value": 0.9930660708056442, "stage": "debug", "created_at": 1788698368.2819676}], "maximize": true, "elapsed_seconds": 28772.36222910881, "node_count": 50, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.base.plant-pathology-2020-fgvc7.yaml", "note": ""}, {"id": "xixian.base.random-acts-of-pizza", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "base", "dataset": "random-acts-of-pizza", "status": "archived", "official_score": 0.69415, "medal": "bronze", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.97908, "silver": 0.76482, "bronze": 0.6921}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:14", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-four-methods-muse13/runs/base/14_random-acts-of-pizza/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-four-methods-muse13/runs/base/14_random-acts-of-pizza/logs/journal.json", "metrics": [{"event_id": "bfe5938e9ea34e7b83b8b19f4f422a26", "step": 4, "value": 0.6698634076204169, "stage": "draft", "created_at": 1788671070.5447307}, {"event_id": "ed7a04f4c0e24da89f0d01bfc6f468a8", "step": 5, "value": 0.6565001539408868, "stage": "debug", "created_at": 1788671450.3837068}, {"event_id": "c2a5fe97a4694753803bb482d8de29f2", "step": 6, "value": 0.6971818835370239, "stage": "debug", "created_at": 1788671352.9722655}, {"event_id": "fc83ed3be4424dfcafb2ef22f02747d3", "step": 7, "value": 0.6387680880541872, "stage": "improve", "created_at": 1788671826.3925593}, {"event_id": "4d42d5729f0f4b6e9fef4d848eefa65f", "step": 9, "value": 0.6877498202731848, "stage": "improve", "created_at": 1788671943.5600228}, {"event_id": "7c92523d30a9490c95055a2c20754377", "step": 10, "value": 0.6188423645320197, "stage": "debug", "created_at": 1788672461.345821}, {"event_id": "44f0a90f3369405cb660dcbebd6dec35", "step": 11, "value": 0.635643421998562, "stage": "improve", "created_at": 1788672683.1131918}, {"event_id": "db4da283884d49da9ba467fae73d8e59", "step": 12, "value": 0.7015672178289001, "stage": "improve", "created_at": 1788671633.434258}, {"event_id": "8854ff2a208f4a83b42b95ed6c27b4f0", "step": 14, "value": 0.6644648653886529, "stage": "improve", "created_at": 1788673038.878716}, {"event_id": "91378d5f937248389f47bf9211f083ca", "step": 19, "value": 0.6452911574406901, "stage": "debug", "created_at": 1788682308.4020567}, {"event_id": "4032315bb7034003beabfe48d5e8fb96", "step": 20, "value": 0.6882540092701754, "stage": "draft", "created_at": 1788682077.8529139}, {"event_id": "9ad3e08a86f644bb96ebc276d5497695", "step": 21, "value": 0.6464422309082504, "stage": "evolution", "created_at": 1788682485.7538695}, {"event_id": "66fa91a2fb734a11a8e7c500896c60d9", "step": 22, "value": 0.6418116462976275, "stage": "evolution", "created_at": 1788684963.8321729}, {"event_id": "94ed2b163715450caeb11435fd959d1f", "step": 23, "value": 0.6660244428468727, "stage": "evolution", "created_at": 1788685440.2147942}, {"event_id": "9feb853639a945aa84af09d0a989a903", "step": 25, "value": 0.7052480230050323, "stage": "debug", "created_at": 1788686271.8069985}, {"event_id": "02c971390a3540669c0c6315cc00d072", "step": 26, "value": 0.6828114149130315, "stage": "improve", "created_at": 1788682794.5027611}, {"event_id": "59c792f093474ab6b650f4fd00b6d203", "step": 27, "value": 0.720862688713156, "stage": "improve", "created_at": 1788686773.6989336}, {"event_id": "bf95ab2ccd4544fd898032ca242d244c", "step": 28, "value": 0.7250611071171817, "stage": "improve", "created_at": 1788689210.6845267}, {"event_id": "a61f45ce5f4e470882369ba267fb14ac", "step": 31, "value": 0.7151401869158878, "stage": "debug", "created_at": 1788691014.48058}, {"event_id": "93ff9e2298b14cf39812e7d215bf2354", "step": 32, "value": 0.6557760945751708, "stage": "improve", "created_at": 1788688681.3655603}, {"event_id": "9e8daff3510a44b1aa7100115c715d4f", "step": 33, "value": 0.716175413371675, "stage": "improve", "created_at": 1788692584.8017497}, {"event_id": "b244e2fe4d2f452db7bb306b0acd8232", "step": 35, "value": 0.7154277498202731, "stage": "improve", "created_at": 1788693264.8865452}, {"event_id": "4216b74ac844494db6f8e887404f5b0e", "step": 36, "value": 0.6975109033361462, "stage": "improve", "created_at": 1788694077.3279412}], "maximize": true, "elapsed_seconds": 28776.834789276123, "node_count": 37, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.base.random-acts-of-pizza.yaml", "note": ""}, {"id": "xixian.base.ranzcr-clip-catheter-line-classification", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "base", "dataset": "ranzcr-clip-catheter-line-classification", "status": "archived", "official_score": 0.9295, "medal": "none", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.97357, "silver": 0.97152, "bronze": 0.9709}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:15", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-four-methods-muse13/runs/base/15_ranzcr-clip-catheter-line-classification/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-four-methods-muse13/runs/base/15_ranzcr-clip-catheter-line-classification/logs/journal.json", "metrics": [{"event_id": "6b9d860b93b5492cad2306c2420652f3", "step": 5, "value": 0.9043533695930199, "stage": "debug", "created_at": 1788681865.82842}, {"event_id": "3b20e3f578804f4ea4db6db1c4859407", "step": 6, "value": 0.8359575708747814, "stage": "draft", "created_at": 1788682056.6105225}, {"event_id": "4cb01fac06484497bf0688f28a663ee4", "step": 8, "value": 0.9060655543167412, "stage": "improve", "created_at": 1788686267.9188552}], "maximize": true, "elapsed_seconds": 28761.889982700348, "node_count": 10, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.base.ranzcr-clip-catheter-line-classification.yaml", "note": ""}, {"id": "xixian.base.siim-isic-melanoma-classification", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "base", "dataset": "siim-isic-melanoma-classification", "status": "archived", "official_score": 0.85429, "medal": "none", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.9455, "silver": 0.9401, "bronze": 0.937}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:16", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-four-methods-muse13/runs/base/16_siim-isic-melanoma-classification/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-four-methods-muse13/runs/base/16_siim-isic-melanoma-classification/logs/journal.json", "metrics": [{"event_id": "1e87dead65f14d558fa18df37b30ca28", "step": 5, "value": 0.8830801945171955, "stage": "debug", "created_at": 1788671392.4212415}, {"event_id": "63acc2668ec24e86973122150fd7316e", "step": 6, "value": 0.8518706883815022, "stage": "draft", "created_at": 1788671273.900505}, {"event_id": "474c21c9e4034bd39384bbe500dc4fcc", "step": 7, "value": 0.9998098444465225, "stage": "draft", "created_at": 1788682027.5099597}, {"event_id": "b42206fc079e4de5a701f5835d9f706d", "step": 8, "value": 0.9318557311636896, "stage": "improve", "created_at": 1788693899.901447}, {"event_id": "fb2c555d0bf042a1876852fb110b5a7b", "step": 9, "value": 0.9398391471055831, "stage": "improve", "created_at": 1788694507.130979}, {"event_id": "f337bc6d5dce4ea7b84d2ddd4deae8a0", "step": 10, "value": 0.9401851678668287, "stage": "improve", "created_at": 1788695007.7674944}, {"event_id": "f8f7a58abdf6473dac7bf221097470ef", "step": 11, "value": 0.915158223651261, "stage": "evolution", "created_at": 1788695458.8883495}], "maximize": true, "elapsed_seconds": 28763.95477461815, "node_count": 12, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.base.siim-isic-melanoma-classification.yaml", "note": ""}, {"id": "xixian.base.spooky-author-identification", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "base", "dataset": "spooky-author-identification", "status": "archived", "official_score": 0.21933, "medal": "silver", "valid_submission": true, "score_maximize": false, "thresholds": {"gold": 0.16506, "silver": 0.26996, "bronze": 0.29381}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:17", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-four-methods-muse13/runs/base/17_spooky-author-identification/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-four-methods-muse13/runs/base/17_spooky-author-identification/logs/journal.json", "metrics": [{"event_id": "28ffd32938904e8a9c9b68686094b20a", "step": 9, "value": 0.2468134453956117, "stage": "debug", "created_at": 1788671602.514659}, {"event_id": "f4030a27e347448ba9388ee2f66b1494", "step": 17, "value": 0.5734624735965005, "stage": "debug", "created_at": 1788673425.216785}, {"event_id": "f4716743d5c84ac29c6c1a5ea2f8bb5d", "step": 18, "value": 0.2327061283849385, "stage": "improve", "created_at": 1788672136.2812445}, {"event_id": "0cc13574869b49118bcf8c0b2e42129e", "step": 19, "value": 0.327086267048274, "stage": "improve", "created_at": 1788673852.2215636}, {"event_id": "d146dacbe95843ff924c44a90a31afb2", "step": 21, "value": 0.22943037317154255, "stage": "improve", "created_at": 1788681907.4710984}], "maximize": false, "elapsed_seconds": 28768.989357948303, "node_count": 24, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.base.spooky-author-identification.yaml", "note": ""}, {"id": "xixian.base.tabular-playground-series-dec-2021", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "base", "dataset": "tabular-playground-series-dec-2021", "status": "archived", "official_score": 0.96028, "medal": "gold", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.9566, "silver": 0.95658, "bronze": 0.95658}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:18", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-four-methods-muse13/runs/base/18_tabular-playground-series-dec-2021/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-four-methods-muse13/runs/base/18_tabular-playground-series-dec-2021/logs/journal.json", "metrics": [{"event_id": "d96986a67316472ca5a75cee12c8bd43", "step": 4, "value": 0.9579888888888889, "stage": "debug", "created_at": 1788671248.5879097}, {"event_id": "00ed1c711b844dab8e81ad20784344d6", "step": 5, "value": 0.9546027777777778, "stage": "debug", "created_at": 1788671265.39062}, {"event_id": "a21859e7c05f4801b213328782071e7a", "step": 7, "value": 0.9597583333333334, "stage": "improve", "created_at": 1788671859.0936146}], "maximize": true, "elapsed_seconds": 28773.94114947319, "node_count": 12, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.base.tabular-playground-series-dec-2021.yaml", "note": ""}, {"id": "xixian.base.tabular-playground-series-may-2022", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "base", "dataset": "tabular-playground-series-may-2022", "status": "archived", "official_score": 0.9916, "medal": "none", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.99823, "silver": 0.99822, "bronze": 0.99818}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:19", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-four-methods-muse13/runs/base/19_tabular-playground-series-may-2022/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-four-methods-muse13/runs/base/19_tabular-playground-series-may-2022/logs/journal.json", "metrics": [{"event_id": "6c12dcd82d224a5aa1f5a1249d8c7e3c", "step": 1, "value": 0.8157392743748038, "stage": "draft", "created_at": 1788670836.7045395}, {"event_id": "ff273e1f1af842de8adb35019ab37434", "step": 2, "value": 0.9852047550683551, "stage": "draft", "created_at": 1788671015.8312993}, {"event_id": "cd3aac85d6434581aeb7de5c6fd9347c", "step": 3, "value": 0.8354476647674454, "stage": "improve", "created_at": 1788671380.9396148}, {"event_id": "73e6dde6d1114670861c59d67514bcaa", "step": 4, "value": 0.9914038794028772, "stage": "improve", "created_at": 1788671674.7992222}, {"event_id": "c0b9d0e9768a4ce18e364d5874cc9ddf", "step": 6, "value": 0.48461471542551393, "stage": "draft", "created_at": 1788681933.6678252}, {"event_id": "e585a90e7c9a4c039a9e63b7d997fd73", "step": 7, "value": 0.9860087921745802, "stage": "improve", "created_at": 1788682202.619678}, {"event_id": "9ec66e06f9e34790b8453e08a26bbf13", "step": 10, "value": 0.9821279506287796, "stage": "debug", "created_at": 1788685080.9561048}, {"event_id": "f334375518eb4393a35931c02fa13925", "step": 12, "value": 0.9909716287048019, "stage": "improve", "created_at": 1788686689.042994}], "maximize": true, "elapsed_seconds": 28765.05438041687, "node_count": 13, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.base.tabular-playground-series-may-2022.yaml", "note": ""}, {"id": "xixian.base.text-normalization-challenge-english-language", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "base", "dataset": "text-normalization-challenge-english-language", "status": "archived", "official_score": 0.99116, "medal": "bronze", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.99724, "silver": 0.99135, "bronze": 0.99038}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:20", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-four-methods-muse13/runs/base/20_text-normalization-challenge-english-language/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-four-methods-muse13/runs/base/20_text-normalization-challenge-english-language/logs/journal.json", "metrics": [{"event_id": "f3fe63ff00dc4e9497c0d77b32902494", "step": 4, "value": 0.966677803764339, "stage": "draft", "created_at": 1788671077.0828385}, {"event_id": "4b50ec035622406f9d8f36daf24240f9", "step": 6, "value": 0.9271716383996947, "stage": "debug", "created_at": 1788671466.2527974}, {"event_id": "7bf8ad4ac8524a5c96db603d8337aee5", "step": 11, "value": 0.9299977725804656, "stage": "debug", "created_at": 1788673259.7462666}, {"event_id": "b53e1a467b31474982fb61928b48ec69", "step": 12, "value": 0.937825334382376, "stage": "debug", "created_at": 1788671908.694792}, {"event_id": "4675534b7c6344d1a2e3dd0cfb18b857", "step": 13, "value": 0.9908101951851707, "stage": "debug", "created_at": 1788682134.7583563}, {"event_id": "47125a742502429589ea6718dbfa72f6", "step": 14, "value": 0.20956119835170955, "stage": "improve", "created_at": 1788687706.1652198}], "maximize": true, "elapsed_seconds": 28774.66847872734, "node_count": 17, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.base.text-normalization-challenge-english-language.yaml", "note": ""}, {"id": "xixian.base.text-normalization-challenge-russian-language", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "base", "dataset": "text-normalization-challenge-russian-language", "status": "archived", "official_score": 0.981, "medal": "bronze", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.99012, "silver": 0.98232, "bronze": 0.97592}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:21", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-four-methods-muse13/runs/base/21_text-normalization-challenge-russian-language/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-four-methods-muse13/runs/base/21_text-normalization-challenge-russian-language/logs/journal.json", "metrics": [{"event_id": "b672291770364b8cb4bd846485460c1f", "step": 12, "value": 0.94151770367824, "stage": "draft", "created_at": 1788682004.34703}, {"event_id": "9a51e87c423b4c48b862a451391a3e7c", "step": 13, "value": 0.9595, "stage": "debug", "created_at": 1788681823.940207}, {"event_id": "9d41efcc129446b2811e497e0e226d8d", "step": 14, "value": 0.9504125128910278, "stage": "improve", "created_at": 1788684758.8017294}, {"event_id": "c79d385dcda54f8b82a9739f62edc58f", "step": 15, "value": 0.5313096352219672, "stage": "debug", "created_at": 1788682112.2460485}, {"event_id": "45a71123da9245428facb73429e7c0f5", "step": 17, "value": 0.9408784578625691, "stage": "improve", "created_at": 1788687895.9708827}], "maximize": true, "elapsed_seconds": 28762.02874660492, "node_count": 18, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.base.text-normalization-challenge-russian-language.yaml", "note": ""}, {"id": "xixian.base.the-icml-2013-whale-challenge-right-whale-redux", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "base", "dataset": "the-icml-2013-whale-challenge-right-whale-redux", "status": "archived", "official_score": 0.98898, "medal": "silver", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.98961, "silver": 0.95017, "bronze": 0.90521}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:22", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-four-methods-muse13/runs/base/22_the-icml-2013-whale-challenge-right-whale-redux/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-four-methods-muse13/runs/base/22_the-icml-2013-whale-challenge-right-whale-redux/logs/journal.json", "metrics": [{"event_id": "d7810f774e9a41b4b6891071e91b4868", "step": 1, "value": 0.8805241768838683, "stage": "draft", "created_at": 1788672104.6414733}, {"event_id": "486cd57fe8dc4154833fb9235e04b29e", "step": 4, "value": 0.8853957156633144, "stage": "debug", "created_at": 1788674228.9081762}, {"event_id": "bc981f0b2d274090a4bdb88750d4cea5", "step": 9, "value": 0.8718866777344297, "stage": "draft", "created_at": 1788681960.7263722}, {"event_id": "bc500cbfd0fb4fac8a2ae9eaf3507d2d", "step": 11, "value": 0.6579068784921106, "stage": "debug", "created_at": 1788681786.855282}, {"event_id": "a4c8796d290348adb29eb3011ea80b53", "step": 12, "value": 0.948907008227605, "stage": "debug", "created_at": 1788683677.9099994}, {"event_id": "321fff947e2d4e30982c8fc3a77a9bf2", "step": 13, "value": 0.9580064402810304, "stage": "improve", "created_at": 1788684453.882769}, {"event_id": "fc85ee30c5784f9dba15a57dbcbb4db0", "step": 15, "value": 0.8737134165867566, "stage": "improve", "created_at": 1788684645.6032217}, {"event_id": "b9065620b38f4454ac408b46cadf7451", "step": 17, "value": 0.961560218349635, "stage": "improve", "created_at": 1788685406.6325521}, {"event_id": "d58a9cc722b14c9088be4ca374aa2e2f", "step": 18, "value": 0.9697707156633145, "stage": "improve", "created_at": 1788686174.4678497}, {"event_id": "aa5ab96762774ce8b2d8ed38f7149f36", "step": 19, "value": 0.9112931071484662, "stage": "debug", "created_at": 1788685669.1871588}, {"event_id": "69cf15fc01434b3abe60ef6f56d052bf", "step": 21, "value": 0.9738299008127842, "stage": "debug", "created_at": 1788686957.223854}, {"event_id": "e48cbf75d854449cb325a148b02d353e", "step": 22, "value": 0.9699889791982366, "stage": "improve", "created_at": 1788687593.677994}, {"event_id": "d8834caef83d4215be0baa2982dd069b", "step": 23, "value": 0.9792481746797079, "stage": "improve", "created_at": 1788688279.7597003}, {"event_id": "6e05a0ce77fd4f40950571a14a69783a", "step": 24, "value": 0.8508910371527687, "stage": "debug", "created_at": 1788685365.8717682}, {"event_id": "22926716ff444d06940646150d42045b", "step": 25, "value": 0.9618482228957157, "stage": "improve", "created_at": 1788688832.8414705}, {"event_id": "06b5d9b499694f56814fcc7dfc4280de", "step": 26, "value": 0.9835609451970277, "stage": "improve", "created_at": 1788689330.3355622}, {"event_id": "9600b5dce5c24c43939b791c9a4b911e", "step": 27, "value": 0.9840968461790344, "stage": "improve", "created_at": 1788689371.764189}, {"event_id": "7d635cac5a134720bd29135a12f3008a", "step": 28, "value": 0.8878278167305795, "stage": "improve", "created_at": 1788690197.780261}, {"event_id": "7d02b1f9a4ee42d49b1baf6df8fe2ae4", "step": 29, "value": 0.9558936866325412, "stage": "debug", "created_at": 1788686856.66149}, {"event_id": "77bda5274de4487e8286c47781fdb99a", "step": 30, "value": 0.9226189897339647, "stage": "improve", "created_at": 1788691279.3177707}, {"event_id": "8696f801ece74154986c50def4dcfc16", "step": 31, "value": 0.9804915666990368, "stage": "improve", "created_at": 1788691180.509982}, {"event_id": "a8fa6ed4f7bf405aad5f13e1ed102a64", "step": 34, "value": 0.9830705811752478, "stage": "improve", "created_at": 1788693431.5330172}, {"event_id": "f28b07c8ee0644e0808df763c936a788", "step": 35, "value": 0.9807, "stage": "debug", "created_at": 1788694783.9987752}, {"event_id": "2b1fe95aec2f472eb079bce93f1e3209", "step": 37, "value": 0.974395140782878, "stage": "improve", "created_at": 1788695553.9050584}, {"event_id": "a7f84eeec79f47ea904a4d4a87725fd3", "step": 38, "value": 0.9816102317931406, "stage": "improve", "created_at": 1788692584.1952865}], "maximize": true, "elapsed_seconds": 28050.09983778, "node_count": 40, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.base.the-icml-2013-whale-challenge-right-whale-redux.yaml", "note": ""}, {"id": "xixian.bo.aerial-cactus-identification", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "bo", "dataset": "aerial-cactus-identification", "status": "archived", "official_score": 0.99999, "medal": "none", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 1.0, "silver": 1.0, "bronze": 1.0}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:23", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-four-methods-muse13/runs/bo/01_aerial-cactus-identification/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-four-methods-muse13/runs/bo/01_aerial-cactus-identification/logs/journal.json", "metrics": [{"event_id": "83a34e926dac4a73b629a2f1bc86e975", "step": 2, "value": 0.9998680085794425, "stage": "draft", "created_at": 1788670964.3248167}, {"event_id": "6642ddcde177433c947a163b53798f63", "step": 3, "value": 0.999840903198435, "stage": "debug", "created_at": 1788671351.480069}, {"event_id": "75c98a8856f842cfbe88be86bd970a4d", "step": 4, "value": 0.9999455993164089, "stage": "draft", "created_at": 1788671183.2572064}, {"event_id": "0cc2f723c77c466ca241e7e434a47473", "step": 5, "value": 0.9999781070419694, "stage": "improve", "created_at": 1788671812.5062945}, {"event_id": "6088c68912134630bb7c2274205e21fc", "step": 6, "value": 0.9999917505362151, "stage": "improve", "created_at": 1788671774.5785334}, {"event_id": "52773d6a74d6401da256096dd1a65312", "step": 7, "value": 0.9999575741862493, "stage": "improve", "created_at": 1788671620.3840654}, {"event_id": "9fcc3e22aaef4bb2ba370d9f920450dd", "step": 8, "value": 0.9999976430103471, "stage": "improve", "created_at": 1788672857.2753158}, {"event_id": "d547158aa05d4466b0eff8509860d40a", "step": 9, "value": 0.9999893935465624, "stage": "improve", "created_at": 1788673847.6935616}, {"event_id": "7dffd572b40d44b0955e6f3abd9c3b64", "step": 10, "value": 0.9999031402462891, "stage": "improve", "created_at": 1788672797.7790356}, {"event_id": "4421f71553144a4ba834265f7f56dd5b", "step": 14, "value": 0.9996476300469042, "stage": "debug", "created_at": 1788682089.5279872}, {"event_id": "43186d6c57fd4b2683089726d1796405", "step": 15, "value": 0.9999870365569096, "stage": "draft", "created_at": 1788681965.5043283}, {"event_id": "4e56e408f17c4e73b2e686a0af3e1a01", "step": 16, "value": 0.9999976430103472, "stage": "improve", "created_at": 1788682686.1293964}, {"event_id": "98dfbbd424364f74aff91bfe34e37e90", "step": 17, "value": 0.9999988215051736, "stage": "improve", "created_at": 1788681860.0769992}, {"event_id": "794a55bacb5941e9af1e109cfc13fd59", "step": 19, "value": 0.999968180639687, "stage": "improve", "created_at": 1788682947.024426}, {"event_id": "63ee3c818f3e4751987eba501d8876e4", "step": 20, "value": 0.999991750536215, "stage": "improve", "created_at": 1788684302.913857}, {"event_id": "ee4b1ffb58ef4aa28383a5e1f6101aca", "step": 21, "value": 0.999970145966322, "stage": "debug", "created_at": 1788684587.129308}, {"event_id": "f16a090b526b441b95fa51811d6ab9a0", "step": 22, "value": 0.9997978881372711, "stage": "improve", "created_at": 1788685476.416799}, {"event_id": "f3b85b1a0a2a4c00a4b746220ee7d6f7", "step": 23, "value": 0.9996894666132415, "stage": "improve", "created_at": 1788685282.5008235}, {"event_id": "5e75ae8aad8a42f19b018f5382afd77d", "step": 24, "value": 0.9999269333207628, "stage": "improve", "created_at": 1788685826.1886187}, {"event_id": "fa4da36f00394003ad0c48bcd4d22a92", "step": 26, "value": 0.9999867315405877, "stage": "improve", "created_at": 1788686412.1642842}, {"event_id": "9dde99dc61d4479ea3b592675203de7e", "step": 27, "value": 0.9999693613764897, "stage": "improve", "created_at": 1788686076.8509133}, {"event_id": "5ed2da4b68ab44c98134dd4dc0feef7b", "step": 29, "value": 0.9999784733827024, "stage": "improve", "created_at": 1788686002.830164}, {"event_id": "6774be9bcb4741969ccdaa8dcba2613f", "step": 31, "value": 0.9999988215051736, "stage": "improve", "created_at": 1788690685.7980034}, {"event_id": "ad036b64fc5f4b7292b08c326e44dfba", "step": 32, "value": 0.9999203263153996, "stage": "debug", "created_at": 1788693501.0843108}, {"event_id": "2681d2118cd944c99a9a813945a9dbd2", "step": 33, "value": 0.9999988215051736, "stage": "improve", "created_at": 1788693725.5832028}, {"event_id": "df4ebb02c4054f86b1d03d5c81392654", "step": 34, "value": 0.9999988215051736, "stage": "fusion_draft", "created_at": 1788695641.4389057}, {"event_id": "d6b4df3ac4ad4dbabda61c459faf3264", "step": 35, "value": 0.9999798527839341, "stage": "improve", "created_at": 1788692544.1966274}, {"event_id": "1d512ef6879e4223932378c441a5d036", "step": 36, "value": 0.9999527024539229, "stage": "improve", "created_at": 1788697203.092935}, {"event_id": "7c818af409c74ad790085af1c55ab79f", "step": 37, "value": 0.9999952860206944, "stage": "improve", "created_at": 1788697249.6093137}, {"event_id": "9b38e4249b054c198fff6a1d4f770f80", "step": 38, "value": 0.9999952860206943, "stage": "fusion_draft", "created_at": 1788697515.391786}], "maximize": true, "elapsed_seconds": 28694.16555929184, "node_count": 41, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.bo.aerial-cactus-identification.yaml", "note": ""}, {"id": "xixian.bo.aptos2019-blindness-detection", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "bo", "dataset": "aptos2019-blindness-detection", "status": "archived", "official_score": 0.91741, "medal": "bronze", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.930508, "silver": 0.919654, "bronze": 0.914492}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:24", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-four-methods-muse13/runs/bo/02_aptos2019-blindness-detection/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-four-methods-muse13/runs/bo/02_aptos2019-blindness-detection/logs/journal.json", "metrics": [{"event_id": "6906b8753465450b96e8de167aa5b864", "step": 7, "value": 0.9207169690439442, "stage": "debug", "created_at": 1788671971.460402}, {"event_id": "03fd283d07724499b8f662fc5f71e356", "step": 8, "value": 0.9054378733440607, "stage": "debug", "created_at": 1788671910.8293543}, {"event_id": "fd35d510c36547e0b5e1905d454a57ac", "step": 9, "value": 0.9063826338127801, "stage": "debug", "created_at": 1788672473.634567}, {"event_id": "66899a344ce744078f2468db7b351435", "step": 11, "value": 0.9149482418154335, "stage": "improve", "created_at": 1788673047.2355275}, {"event_id": "b69b247eeafc42a881b64307fc62ad70", "step": 13, "value": 0.9128416025470947, "stage": "debug", "created_at": 1788673513.6116033}, {"event_id": "01170992145d48c3877d3ea11562f1a9", "step": 14, "value": 0.9201201387827452, "stage": "improve", "created_at": 1788672668.746436}, {"event_id": "033cfb61232d4c7aaef163a14e53c206", "step": 15, "value": 0.9160364426340118, "stage": "debug", "created_at": 1788674037.0426717}, {"event_id": "bc4cc2fe942f457297118ca773ad1e0e", "step": 20, "value": 0.8748697757078073, "stage": "debug", "created_at": 1788682202.2484357}, {"event_id": "afc3e74342294eeea8598ae3e8f09e0e", "step": 21, "value": 0.9067839311071412, "stage": "improve", "created_at": 1788681867.3426764}, {"event_id": "9d4451f0c51f4c6ca8ce46a34f63a4e7", "step": 24, "value": 0.9200392061126557, "stage": "improve", "created_at": 1788682842.259595}, {"event_id": "1ace26be76034db49cc6adc18dc1335c", "step": 25, "value": 0.9008412286181305, "stage": "improve", "created_at": 1788683174.6065426}, {"event_id": "cd936fc87c084cff8c92e5b1b74e59cd", "step": 26, "value": 0.8814910720772979, "stage": "draft", "created_at": 1788681969.5627966}, {"event_id": "967b0fa8851c482c9c79e1660e090195", "step": 29, "value": 0.9102189569196094, "stage": "debug", "created_at": 1788683953.7547328}, {"event_id": "ab0d9f68404d479d839610d7aac2b43e", "step": 30, "value": 0.9166779923916066, "stage": "debug", "created_at": 1788684045.4168582}, {"event_id": "d0e3d48a70714beb9d8ff2a35973c2ff", "step": 35, "value": 0.9203599160437879, "stage": "improve", "created_at": 1788683797.1627588}, {"event_id": "71f1e7c83a48424f8c1aa45c09cd0c8c", "step": 37, "value": 0.9144433207685942, "stage": "improve", "created_at": 1788686408.3141885}, {"event_id": "610a7bb7553045a5bd178a6a9a6d5af6", "step": 38, "value": 0.9164067534041579, "stage": "improve", "created_at": 1788684840.2551339}, {"event_id": "877423824a704e7297e98f384ad769f8", "step": 40, "value": 0.9247347451414755, "stage": "improve", "created_at": 1788687427.1320412}, {"event_id": "14e1285a53cd4df88d1b32361f6d0dc5", "step": 41, "value": 0.9190738407625009, "stage": "debug", "created_at": 1788687016.9567032}, {"event_id": "66b25ce1d4634c64afe03bc3bca74897", "step": 45, "value": 0.9120859512468604, "stage": "debug", "created_at": 1788689390.3876565}, {"event_id": "69e1b1471d02410ea234f242f8c3c3ce", "step": 46, "value": 0.9219809096275319, "stage": "improve", "created_at": 1788690387.3117387}, {"event_id": "66c48a86addd49e29a87cadb08aab628", "step": 47, "value": 0.9109790232362964, "stage": "improve", "created_at": 1788690002.4517443}, {"event_id": "6a7eb89c264c4908858c3f4ad57de646", "step": 49, "value": 0.9214910733057354, "stage": "debug", "created_at": 1788687411.529004}, {"event_id": "116a146f4cb548c897b5169d56be6ca0", "step": 52, "value": 0.9056516778947179, "stage": "debug", "created_at": 1788693906.8047347}, {"event_id": "cd8dd5324c0e4f82b3a5f8cf2ae14a4d", "step": 53, "value": 0.9237967470296787, "stage": "debug", "created_at": 1788692354.2250214}, {"event_id": "59ba2da3cfb74b5aa44491c0f3ce8e30", "step": 54, "value": 0.9001474846007005, "stage": "improve", "created_at": 1788694236.6711125}, {"event_id": "648d21c892764762a3633b68646b770d", "step": 58, "value": 0.9082884098337525, "stage": "improve", "created_at": 1788695647.0895588}, {"event_id": "dd605a83b3a444abb234754a4a4625a7", "step": 59, "value": 0.8688, "stage": "debug", "created_at": 1788695621.3892477}, {"event_id": "c1d8b9a416284f98b764676bccb3048c", "step": 60, "value": 0.9067933426737678, "stage": "improve", "created_at": 1788696187.6482217}, {"event_id": "1652baa97f064688840514331ea86d61", "step": 62, "value": 0.9028, "stage": "improve", "created_at": 1788696726.3019378}, {"event_id": "f375a6d70d354efbb884fa28ad33fd4e", "step": 64, "value": 0.9151238786312468, "stage": "debug", "created_at": 1788698031.227734}], "maximize": true, "elapsed_seconds": 28738.645226716995, "node_count": 65, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.bo.aptos2019-blindness-detection.yaml", "note": ""}, {"id": "xixian.bo.denoising-dirty-documents", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "bo", "dataset": "denoising-dirty-documents", "status": "archived", "official_score": 0.01393, "medal": "gold", "valid_submission": true, "score_maximize": false, "thresholds": {"gold": 0.01794, "silver": 0.02609, "bronze": 0.04517}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:25", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-four-methods-muse13/runs/bo/03_denoising-dirty-documents/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-four-methods-muse13/runs/bo/03_denoising-dirty-documents/logs/journal.json", "metrics": [{"event_id": "f2c77a032773465182e40a9cf53652df", "step": 6, "value": 0.025245418947582362, "stage": "draft", "created_at": 1788670736.7262664}, {"event_id": "7f49dcc22c854b90a2d76a1eec7572da", "step": 13, "value": 0.10876268334802383, "stage": "debug", "created_at": 1788671716.035225}, {"event_id": "5617a064b98840c4899248401ff201b1", "step": 16, "value": 0.15532414565737712, "stage": "improve", "created_at": 1788672073.7230444}, {"event_id": "3a5a208d3d5d4b77b35499e2307c5f23", "step": 18, "value": 0.016335054357046817, "stage": "debug", "created_at": 1788671906.8209376}, {"event_id": "16cb310d352d43ad8494b26a1247b3cd", "step": 23, "value": 0.03421669245648458, "stage": "improve", "created_at": 1788672462.302237}, {"event_id": "4f4764e4e1fc4db788f6a4cb6cd0ae2f", "step": 27, "value": 0.03882680934751788, "stage": "improve", "created_at": 1788672864.712994}, {"event_id": "e1cebec793d94b86a727dee9a85e2c5f", "step": 30, "value": 0.01820925008242991, "stage": "improve", "created_at": 1788672767.8724806}, {"event_id": "f829c1ed093647c39348d432082ecfc6", "step": 33, "value": 0.023515164260429433, "stage": "improve", "created_at": 1788673291.8174717}, {"event_id": "3ef91ddb1eab4bbd90b334eedce841fa", "step": 34, "value": 0.42309044859467565, "stage": "debug", "created_at": 1788674051.7552416}, {"event_id": "1bff0d2aadb441dd889afe264186e830", "step": 35, "value": 0.02405253317702651, "stage": "debug", "created_at": 1788674055.3093934}, {"event_id": "a48eba32a51347fd8f05dad4c2c2ff3e", "step": 44, "value": 0.3796077144758451, "stage": "improve", "created_at": 1788674232.4333637}, {"event_id": "093526dde7e64233bc1a509992bd0297", "step": 48, "value": 0.0326299533501585, "stage": "evolution", "created_at": 1788681875.3460643}, {"event_id": "919a0c27084c4c668b912b37fd740cad", "step": 49, "value": 0.01847300325689615, "stage": "debug", "created_at": 1788681960.8468585}, {"event_id": "1c6db83074b142e5b000c435b601dd0f", "step": 50, "value": 0.01745194648068188, "stage": "improve", "created_at": 1788681894.2066395}, {"event_id": "dfabb3d2b47e4f0891ccb7bd5fa13f48", "step": 53, "value": 0.02688599435513432, "stage": "evolution", "created_at": 1788682690.711817}, {"event_id": "6af10b1ead6a4138b6851198f7c32fb8", "step": 54, "value": 0.014019568669140505, "stage": "improve", "created_at": 1788683130.7039514}, {"event_id": "0738cb3ce00a4dfca01d3796318c9213", "step": 55, "value": 0.029729634249093556, "stage": "evolution", "created_at": 1788682912.3233402}, {"event_id": "1c06948fdb644b159374c4d74deefa98", "step": 56, "value": 0.12693902795136253, "stage": "evolution", "created_at": 1788684424.0296452}, {"event_id": "4dea6d73200043e49c205e53b27bfe14", "step": 57, "value": 0.020674064615088694, "stage": "evolution", "created_at": 1788685260.7205257}, {"event_id": "5c4ca86f074442d0b20abe115906f2d9", "step": 58, "value": 0.02119567514264685, "stage": "improve", "created_at": 1788685894.1492548}, {"event_id": "e70939c4829e4bd89c22c2d94f39d500", "step": 60, "value": 0.017139045298096706, "stage": "improve", "created_at": 1788684261.0600784}, {"event_id": "28ea0b3f98cd493eaf05f3ba3da19f74", "step": 61, "value": 0.01375315789377458, "stage": "improve", "created_at": 1788686459.446273}, {"event_id": "36d8a291ce8c42a49ded2aebc5bbd478", "step": 62, "value": 0.013647912443747516, "stage": "improve", "created_at": 1788686518.8560028}, {"event_id": "0c53e75d23cd4f9cb0b9f6bc37d37b92", "step": 64, "value": 0.016693418833132606, "stage": "improve", "created_at": 1788687300.4325228}, {"event_id": "5e8e67a29a5b4aa4b84f41c84c2e5304", "step": 66, "value": 0.016577295557155917, "stage": "debug", "created_at": 1788689852.819007}, {"event_id": "fdb4362aa6254cc4a1f2d2d3f682f783", "step": 68, "value": 0.01688335930672919, "stage": "improve", "created_at": 1788688675.4677825}, {"event_id": "031ae560d19d486b816a11258d75fe13", "step": 69, "value": 0.024650469474173202, "stage": "evolution", "created_at": 1788693001.7531846}, {"event_id": "cf9eb6c6fcfa4c088983b6459d04c4f8", "step": 70, "value": 0.019998521031548644, "stage": "evolution", "created_at": 1788694502.1012762}, {"event_id": "1723677a30b44eaa8e71b5e0d76055c0", "step": 71, "value": 0.02349620909110114, "stage": "improve", "created_at": 1788689680.1622887}, {"event_id": "d2d70c9cbf3546ebb1695355c970ae6c", "step": 73, "value": 0.01951785164756975, "stage": "fusion", "created_at": 1788695226.6393116}, {"event_id": "e614170e1b8f44f3a19e03cc75cd963c", "step": 74, "value": 0.07417050391630167, "stage": "debug", "created_at": 1788695670.3183513}, {"event_id": "9c57f75967224936800c8c5763b17e31", "step": 75, "value": 0.013881465962971021, "stage": "evolution", "created_at": 1788695964.4504962}, {"event_id": "c16937903ab647e09ba0253c912c0da5", "step": 76, "value": 0.09493025484032738, "stage": "debug", "created_at": 1788692409.9612434}, {"event_id": "5ad99c6078da4531b76ec9b72f566137", "step": 77, "value": 0.014348833207919002, "stage": "evolution", "created_at": 1788696694.0198371}, {"event_id": "2942d314944c40a495201d99c27d8a59", "step": 78, "value": 0.019175031477183378, "stage": "fusion", "created_at": 1788697236.928033}], "maximize": false, "elapsed_seconds": 28766.85277724266, "node_count": 79, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.bo.denoising-dirty-documents.yaml", "note": ""}, {"id": "xixian.bo.detecting-insults-in-social-commentary", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "bo", "dataset": "detecting-insults-in-social-commentary", "status": "archived", "official_score": 0.95505, "medal": "gold", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.83321, "silver": 0.82307, "bronze": 0.79111}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:26", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-four-methods-muse13/runs/bo/04_detecting-insults-in-social-commentary/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-four-methods-muse13/runs/bo/04_detecting-insults-in-social-commentary/logs/journal.json", "metrics": [{"event_id": "df4ba5b72c5a417483da9b21b2fa8cda", "step": 5, "value": 0.9563436636112324, "stage": "debug", "created_at": 1788671192.2378278}, {"event_id": "a9c58454e59c42a5ada75384f4dc4702", "step": 7, "value": 0.9570784228139095, "stage": "debug", "created_at": 1788671342.6213467}, {"event_id": "7c5eeea8c12e4027908eb7a44103af9e", "step": 8, "value": 0.938394787588383, "stage": "debug", "created_at": 1788671242.7209961}, {"event_id": "1d6810bfbdbd4c32a2c301ccccfa103a", "step": 9, "value": 0.95328822930307, "stage": "debug", "created_at": 1788671544.8767974}, {"event_id": "1d19ab041afb4687976a357433a0c192", "step": 10, "value": 0.9614142295940638, "stage": "improve", "created_at": 1788671667.3372695}, {"event_id": "cabe31baba28401f801723cc710666d3", "step": 11, "value": 0.9633493379892332, "stage": "improve", "created_at": 1788671857.1191556}, {"event_id": "24de884037014332b39b95f91b799e8e", "step": 12, "value": 0.9344723309764507, "stage": "improve", "created_at": 1788671809.4250045}, {"event_id": "a23334d6b8434d3798d059852d1dd72a", "step": 13, "value": 0.9574276153062709, "stage": "improve", "created_at": 1788672030.6965852}, {"event_id": "63f3f3c5c46d4daba83aa1c4aa78c45b", "step": 15, "value": 0.9596173432271206, "stage": "improve", "created_at": 1788672534.120549}, {"event_id": "31a2e1ce383842218b5f1300daa2d69c", "step": 16, "value": 0.9651025752946312, "stage": "improve", "created_at": 1788672598.6139655}, {"event_id": "09a5b17aa2ed46f88de07c282414bef9", "step": 17, "value": 0.9587007129346719, "stage": "improve", "created_at": 1788672770.2957063}, {"event_id": "62468d62bb3a4f8bb47b5654f1fc43c5", "step": 18, "value": 0.9576604103011785, "stage": "improve", "created_at": 1788673719.1327906}, {"event_id": "7552a4ce637f4238ad0266acbb0ea8ff", "step": 25, "value": 0.8791502982685874, "stage": "debug", "created_at": 1788682209.8797176}, {"event_id": "2da950d94b054c5bb570d8d03b6ee356", "step": 26, "value": 0.9393790568802233, "stage": "debug", "created_at": 1788682102.8828676}, {"event_id": "2d80185f38f8404c8a99ec8a1400433a", "step": 27, "value": 0.9603438858895448, "stage": "improve", "created_at": 1788681938.2362635}, {"event_id": "3297969f0382492581de1fe34172259e", "step": 28, "value": 0.961559726465881, "stage": "improve", "created_at": 1788682385.7094696}, {"event_id": "6b19db6fbe114a1e8005d3e89edb1a93", "step": 29, "value": 0.9603812018041613, "stage": "improve", "created_at": 1788682856.6334908}, {"event_id": "15466032d8614c47b43752990ef2e7d2", "step": 30, "value": 0.961089637207739, "stage": "evolution", "created_at": 1788682556.4437807}, {"event_id": "935ef49684544c21b0f653ec739f088b", "step": 31, "value": 0.9492652407973229, "stage": "improve", "created_at": 1788682398.5713906}, {"event_id": "6ca07f0d5cd341e0ade22578f3a8e9ee", "step": 34, "value": 0.959871962752801, "stage": "improve", "created_at": 1788683410.6588867}, {"event_id": "fa146c336c3e49fd9cdc2f2eaf2a4869", "step": 35, "value": 0.9508802560744943, "stage": "improve", "created_at": 1788683360.489847}, {"event_id": "0cc9c00813214b1ebd62466b76f34730", "step": 36, "value": 0.9600445350082978, "stage": "evolution", "created_at": 1788684122.7675157}, {"event_id": "9c7fb15bfd044cb2a9f488672518ebd8", "step": 37, "value": 0.6159351210953151, "stage": "debug", "created_at": 1788684054.7313285}, {"event_id": "4d92343d2ea9418487b9687d40240777", "step": 38, "value": 0.9922756629765375, "stage": "evolution", "created_at": 1788684869.523066}, {"event_id": "8b71766df29447b387043375ba129708", "step": 39, "value": 0.9571220718754547, "stage": "evolution", "created_at": 1788686268.117277}, {"event_id": "827c78947c714eefb24636eb7cd15cee", "step": 40, "value": 0.9646006110868616, "stage": "fusion", "created_at": 1788686845.4244018}, {"event_id": "fdfa9ff968ef480eb18fc56572267e30", "step": 42, "value": 0.9711325847811942, "stage": "improve", "created_at": 1788686428.0802424}, {"event_id": "bcdf2f56fa4e4e00b16b83e2a84cbd20", "step": 43, "value": 0.9924996759870552, "stage": "improve", "created_at": 1788687580.4519105}, {"event_id": "0a12ceea177c4fedb8458c947da0ddc1", "step": 45, "value": 0.9514840680925362, "stage": "evolution", "created_at": 1788690530.6072998}, {"event_id": "cdb4869ee79e4fc0856b6cffb1453174", "step": 46, "value": 0.9495990463164169, "stage": "debug", "created_at": 1788690762.0192256}, {"event_id": "23a72b75a32047a8bdf6bada769807db", "step": 48, "value": 0.9916384923430972, "stage": "improve", "created_at": 1788691629.5914633}, {"event_id": "5cd60e0978634cd3940580aaad06de27", "step": 49, "value": 0.9437569448967468, "stage": "debug", "created_at": 1788692198.2790473}], "maximize": true, "elapsed_seconds": 28759.18512058258, "node_count": 51, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.bo.detecting-insults-in-social-commentary.yaml", "note": ""}, {"id": "xixian.bo.dog-breed-identification", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "bo", "dataset": "dog-breed-identification", "status": "archived", "official_score": 0.35417, "medal": "none", "valid_submission": true, "score_maximize": false, "thresholds": {"gold": 0.0005, "silver": 0.00539, "bronze": 0.04598}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:27", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-four-methods-muse13/runs/bo/05_dog-breed-identification/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-four-methods-muse13/runs/bo/05_dog-breed-identification/logs/journal.json", "metrics": [{"event_id": "ded121f0e2894b5796828af0cfc2075d", "step": 1, "value": 0.698691077744017, "stage": "draft", "created_at": 1788671123.5104654}, {"event_id": "c2543f4c4c8e4b0dbe368bda8bf902b5", "step": 2, "value": 0.5741991635052075, "stage": "draft", "created_at": 1788670926.9784083}, {"event_id": "d09e20ef318f40e698d0f713b726abee", "step": 3, "value": 4.7501858439478, "stage": "draft", "created_at": 1788670728.6606917}, {"event_id": "301ed95d7dad44f6bdcc2fb73cd4b639", "step": 4, "value": 0.412860660659826, "stage": "improve", "created_at": 1788672244.7536523}, {"event_id": "3bcab44c1a154d5fa62cf085aae4a532", "step": 8, "value": 0.5016518411974876, "stage": "improve", "created_at": 1788672104.4015884}, {"event_id": "af467fb98bf44fb592f691fb217cce17", "step": 10, "value": 0.38360933745095976, "stage": "draft", "created_at": 1788682066.5930705}, {"event_id": "c18e451600b2475b988057e1b40da4fd", "step": 11, "value": 0.40068328380584717, "stage": "debug", "created_at": 1788682170.0472953}, {"event_id": "cac2a22c113b456aad1c3d9e8f101af1", "step": 16, "value": 0.4652373611108423, "stage": "debug", "created_at": 1788685848.5667992}, {"event_id": "9efbdbd50e73430787462bceacb49e1d", "step": 18, "value": 0.3921170234680176, "stage": "improve", "created_at": 1788688019.4553244}, {"event_id": "05abc10955d24522b42a4e8c0c46fa81", "step": 19, "value": 0.3239540290941595, "stage": "improve", "created_at": 1788688304.1971285}], "maximize": false, "elapsed_seconds": 28777.76538181305, "node_count": 21, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.bo.dog-breed-identification.yaml", "note": ""}, {"id": "xixian.bo.dogs-vs-cats-redux-kernels-edition", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "bo", "dataset": "dogs-vs-cats-redux-kernels-edition", "status": "archived", "official_score": 0.00958, "medal": "gold", "valid_submission": true, "score_maximize": false, "thresholds": {"gold": 0.03882, "silver": 0.05038, "bronze": 0.06127}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:28", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-four-methods-muse13/runs/bo/06_dogs-vs-cats-redux-kernels-edition/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-four-methods-muse13/runs/bo/06_dogs-vs-cats-redux-kernels-edition/logs/journal.json", "metrics": [{"event_id": "9fcea67074db4d36b9fb0caf5a6efed4", "step": 3, "value": 0.005033768005661166, "stage": "draft", "created_at": 1788671088.660954}, {"event_id": "ef5536c798bc42f78030df27adcd3666", "step": 4, "value": 0.0014650010032577726, "stage": "debug", "created_at": 1788671710.0359905}, {"event_id": "8b5aefd1564940a7b5971ce8ea010d88", "step": 5, "value": 0.015089426302089495, "stage": "draft", "created_at": 1788670896.2950616}, {"event_id": "f2a924705a924e4cafbdcd41c024a317", "step": 7, "value": 0.0034301503134823294, "stage": "improve", "created_at": 1788672207.853292}, {"event_id": "153f1e9809b84b8c823db8a7c25a75ba", "step": 8, "value": 0.0026287390160029817, "stage": "improve", "created_at": 1788673372.4317002}, {"event_id": "d9548d78df4f4b528569ef03200ece26", "step": 9, "value": 0.01669165825348132, "stage": "debug", "created_at": 1788672604.9418783}, {"event_id": "3e537dec261048948dfbac6193a9c9fc", "step": 13, "value": 0.0027890405745286356, "stage": "draft", "created_at": 1788681957.6653774}, {"event_id": "d27ea4b323ab462baad402f6d21c455e", "step": 15, "value": 0.0008911356164624627, "stage": "debug", "created_at": 1788682846.1975372}, {"event_id": "d5bcd15cc89c4acd87672afafde88388", "step": 16, "value": 0.003975942108399765, "stage": "improve", "created_at": 1788682873.3300245}, {"event_id": "6cf62edf34754ef8a146023f94968733", "step": 19, "value": 0.016205233571646573, "stage": "debug", "created_at": 1788684554.3841145}, {"event_id": "e51ed976d6ea40f594e3fd7a0af36e9a", "step": 20, "value": 0.0018534633904317755, "stage": "debug", "created_at": 1788684995.5825286}, {"event_id": "deb2de5f847e4b58a10923f503a69c77", "step": 21, "value": 0.006722064221827463, "stage": "improve", "created_at": 1788671877.6716487}, {"event_id": "ef93268befe9432fb0bd4a89a49e67e6", "step": 22, "value": 0.008826763480057953, "stage": "improve", "created_at": 1788685738.4645348}, {"event_id": "f3809245b8ae4ba6a236b271c8fa3a9c", "step": 23, "value": 0.06683472547728725, "stage": "improve", "created_at": 1788686316.9519815}, {"event_id": "0acf4462ef814b7082bc0341df4cc36a", "step": 24, "value": 0.0031717231504932012, "stage": "improve", "created_at": 1788685909.8115914}, {"event_id": "1c1a31cd525a438a819a390eaa617eee", "step": 25, "value": 0.0022922528462142925, "stage": "improve", "created_at": 1788687182.36909}, {"event_id": "7eb2938b9dd5456bb37cdbdca35f9ec9", "step": 26, "value": 0.0002443576205542393, "stage": "evolution", "created_at": 1788686862.5359988}, {"event_id": "00df2590c0bf4e408fc81d124da37eea", "step": 27, "value": 0.009099502875653486, "stage": "evolution", "created_at": 1788687397.6679652}, {"event_id": "777f40f642cf4677a367667addb91b41", "step": 29, "value": 0.015640227870965438, "stage": "improve", "created_at": 1788689235.540802}, {"event_id": "41f87c5f4b4e47a4a78dc705852a8459", "step": 32, "value": 0.0015995786332910285, "stage": "debug", "created_at": 1788689588.7792175}, {"event_id": "cb4836620eff494688904253b8f43d04", "step": 33, "value": 0.0026858192698859203, "stage": "debug", "created_at": 1788690717.7883894}, {"event_id": "1cc4a8413f3b4846870da2664f768270", "step": 34, "value": 0.006075520911518732, "stage": "improve", "created_at": 1788691619.8270938}, {"event_id": "ac6430b986784727b670c5f8f227a05c", "step": 37, "value": 0.006436689889491594, "stage": "improve", "created_at": 1788693094.4956777}, {"event_id": "a613db10294e46a486c1d87b9b338093", "step": 38, "value": 0.02152, "stage": "debug", "created_at": 1788693223.7628744}, {"event_id": "b7d65db9c798460c947bf20d416ce8b9", "step": 39, "value": 0.0038548054823279504, "stage": "fusion_draft", "created_at": 1788695263.9518843}, {"event_id": "78b1ac2a8575408fa39c00d79cfa0480", "step": 40, "value": 0.009472105303174041, "stage": "fusion", "created_at": 1788694879.3203855}, {"event_id": "ebeb6225e5504a7580bace43710379de", "step": 41, "value": 0.004626922117653611, "stage": "improve", "created_at": 1788690707.7150416}, {"event_id": "2f6a75c5721242a0833443e1058e95f7", "step": 42, "value": 0.001884312058527856, "stage": "evolution", "created_at": 1788695912.1891215}, {"event_id": "7de6781e02b648e1b138458ff1ade710", "step": 43, "value": 0.010923286067061706, "stage": "improve", "created_at": 1788697429.6878667}], "maximize": false, "elapsed_seconds": 28767.951114177704, "node_count": 44, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.bo.dogs-vs-cats-redux-kernels-edition.yaml", "note": ""}, {"id": "xixian.bo.histopathologic-cancer-detection", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "bo", "dataset": "histopathologic-cancer-detection", "status": "archived", "official_score": 0.99678, "medal": "gold", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.9835, "silver": 0.9798, "bronze": 0.9738}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:29", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-four-methods-muse13/runs/bo/07_histopathologic-cancer-detection/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-four-methods-muse13/runs/bo/07_histopathologic-cancer-detection/logs/journal.json", "metrics": [{"event_id": "a147cec482d64ebcb4962565547380fa", "step": 6, "value": 0.9692773553241641, "stage": "draft", "created_at": 1788682001.2370706}, {"event_id": "69e20a0c12c640e9bf4ada6b990d1e34", "step": 7, "value": 0.994610470621876, "stage": "debug", "created_at": 1788682065.1629696}, {"event_id": "9ee622b4624647148d1baf7108b1cc2b", "step": 8, "value": 0.9929144211519136, "stage": "debug", "created_at": 1788681783.988533}, {"event_id": "4e308008d26b46e7b482a5a4c31c0e6c", "step": 9, "value": 0.9975460900585794, "stage": "improve", "created_at": 1788686232.2241821}, {"event_id": "fd8927b4353443929cbbf7bdadeb624d", "step": 10, "value": 0.9801596676335103, "stage": "improve", "created_at": 1788685772.7386863}, {"event_id": "9f65557c5a324b8aa44b2c22e3962fa2", "step": 11, "value": 0.9976165673517199, "stage": "improve", "created_at": 1788690345.0947368}], "maximize": true, "elapsed_seconds": 28771.12775373459, "node_count": 12, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.bo.histopathologic-cancer-detection.yaml", "note": ""}, {"id": "xixian.bo.jigsaw-toxic-comment-classification-challenge", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "bo", "dataset": "jigsaw-toxic-comment-classification-challenge", "status": "archived", "official_score": 0.98692, "medal": "silver", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.9874, "silver": 0.98668, "bronze": 0.98639}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:30", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-four-methods-muse13/runs/bo/08_jigsaw-toxic-comment-classification-challenge/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-four-methods-muse13/runs/bo/08_jigsaw-toxic-comment-classification-challenge/logs/journal.json", "metrics": [{"event_id": "69aa4c5bd06a4e4f9a5e1a8b60c1d3b8", "step": 3, "value": 0.9931432506610642, "stage": "debug", "created_at": 1788671253.1280158}, {"event_id": "0e08fc0b7281455a8b999e9ac28b4d24", "step": 4, "value": 0.9917043852581848, "stage": "draft", "created_at": 1788670906.568936}, {"event_id": "579e0fa8e6d249c98aaf5ae4b66e5170", "step": 8, "value": 0.9927259175800928, "stage": "debug", "created_at": 1788682069.812177}, {"event_id": "6fb8af2cf55c496381330aff5d609107", "step": 9, "value": 0.9833592800469751, "stage": "debug", "created_at": 1788671276.6944532}, {"event_id": "145abb5779a14faaafe2f9fea520aa85", "step": 10, "value": 0.9922241022216363, "stage": "improve", "created_at": 1788685205.948379}], "maximize": true, "elapsed_seconds": 28774.45219564438, "node_count": 11, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.bo.jigsaw-toxic-comment-classification-challenge.yaml", "note": ""}, {"id": "xixian.bo.leaf-classification", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "bo", "dataset": "leaf-classification", "status": "archived", "official_score": 0.002, "medal": "silver", "valid_submission": true, "score_maximize": false, "thresholds": {"gold": 0.0, "silver": 0.00791, "bronze": 0.01526}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:31", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-four-methods-muse13/runs/bo/09_leaf-classification/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-four-methods-muse13/runs/bo/09_leaf-classification/logs/journal.json", "metrics": [{"event_id": "0f17e297246f46339ec8f3a20e4a9c1b", "step": 4, "value": 0.0012763006797766334, "stage": "draft", "created_at": 1788670761.523688}, {"event_id": "852d84ba3ce14918bc624a5b3afb00d5", "step": 5, "value": 4.256665406769874, "stage": "debug", "created_at": 1788671351.8476677}, {"event_id": "ae10f6dbebf64cbc9b5dc4acfb3ae322", "step": 6, "value": 0.0015014740963486526, "stage": "debug", "created_at": 1788671287.0952013}, {"event_id": "2b1fed520c504c94b34ce0f9414c54cf", "step": 7, "value": 0.0006841354496989975, "stage": "improve", "created_at": 1788671653.292951}, {"event_id": "7ed60fb4b03f405391fae1ed178426b1", "step": 8, "value": 0.011096230144427633, "stage": "improve", "created_at": 1788672049.65522}, {"event_id": "458a99f5e81f4f3a95f60f0e293b7dd4", "step": 9, "value": 0.0342776241100508, "stage": "improve", "created_at": 1788671913.485392}, {"event_id": "5f2f765f3b7e4b1c8a11e65d44079d43", "step": 10, "value": 0.011096230144427609, "stage": "improve", "created_at": 1788672354.4771113}, {"event_id": "b3e57aa9079f4f7db3836a12d97e0235", "step": 11, "value": 0.011096230144427609, "stage": "improve", "created_at": 1788672318.9764278}, {"event_id": "1a3326b0df094b0789b77153054a84b3", "step": 13, "value": 0.06782153747349472, "stage": "evolution", "created_at": 1788673087.1939318}, {"event_id": "d35007861f8a4a4586367b6c3bc75bbd", "step": 14, "value": 0.00070926591312358, "stage": "improve", "created_at": 1788672230.671849}, {"event_id": "fa17e819b3534c71a3f692edfd21381a", "step": 16, "value": 0.0002348104331710562, "stage": "debug", "created_at": 1788673643.8566275}, {"event_id": "98391b80a53d47bbab26a60170261289", "step": 18, "value": 0.010388764991472737, "stage": "debug", "created_at": 1788674885.1693327}, {"event_id": "1dd6901e2ec34b96a20ba56cb6950042", "step": 19, "value": 4.567395716373982, "stage": "debug", "created_at": 1788674724.3752155}, {"event_id": "1573689603184063a587b9d7d0b9e4d7", "step": 25, "value": 0.006711307777603158, "stage": "draft", "created_at": 1788682028.635537}, {"event_id": "0535dd4cc57048858f972edb494e054e", "step": 26, "value": 0.07282596119532504, "stage": "improve", "created_at": 1788681918.470811}, {"event_id": "36d4e4adb0174112ae941217cdda0e83", "step": 27, "value": 0.018244041184600567, "stage": "improve", "created_at": 1788683082.1341054}, {"event_id": "a3a1b7f481f04ff5a1f8abed5f74f126", "step": 28, "value": 0.03441096761646093, "stage": "improve", "created_at": 1788683011.2735665}, {"event_id": "5b3ca6d189324769bdabeef9fb6d780d", "step": 30, "value": 0.0029395692630976174, "stage": "evolution", "created_at": 1788684414.1756642}, {"event_id": "7e3372b0d1d94b0fb98d8b79c78b7d5b", "step": 31, "value": 6.313584946988613e-05, "stage": "debug", "created_at": 1788686847.1918108}, {"event_id": "5a708be878c14c5095d089017c4e258c", "step": 33, "value": 0.018244041184600563, "stage": "evolution", "created_at": 1788684836.5843058}, {"event_id": "9a5cf741e1c8491c9a4444e26f20e712", "step": 34, "value": 0.0024365772155682387, "stage": "fusion", "created_at": 1788687664.2174017}, {"event_id": "f4e852b05aa54d27973a5194ea89b11e", "step": 35, "value": 0.02136768287823, "stage": "debug", "created_at": 1788689376.5552135}, {"event_id": "17bd8969ddb349e1bbe5127fa938df95", "step": 36, "value": 0.013577244941897772, "stage": "improve", "created_at": 1788691096.3937428}, {"event_id": "17b8054db09245648f0a3014f58593bc", "step": 37, "value": 0.14647046671094782, "stage": "evolution", "created_at": 1788691667.584887}, {"event_id": "d6497fb02fc74db5a7afaa3acb066a5b", "step": 38, "value": 0.0012273252228228206, "stage": "evolution", "created_at": 1788689661.8444805}, {"event_id": "f82b103eafea420fa3c33da30de291aa", "step": 39, "value": 0.2103903257988227, "stage": "evolution", "created_at": 1788693897.164281}, {"event_id": "cbd0b29909bb480a805668ec5fd77b31", "step": 40, "value": 0.036814948314152086, "stage": "evolution", "created_at": 1788694435.5328026}, {"event_id": "dfbb159f634d4afabb4ed719777f7088", "step": 41, "value": 0.014168698320102431, "stage": "evolution", "created_at": 1788691572.1214266}, {"event_id": "ccb7a1dbf1564298945d7b1365157d6b", "step": 42, "value": 0.006675509759045325, "stage": "improve", "created_at": 1788694663.6865718}, {"event_id": "b1b920f772b14ceab21eeb06bc902066", "step": 43, "value": 0.0003992570109481444, "stage": "evolution", "created_at": 1788694220.0079076}, {"event_id": "c2a3c4c5389348dd8d981967cad4bf0b", "step": 45, "value": 0.06032987047954476, "stage": "debug", "created_at": 1788698462.9338953}, {"event_id": "ed7eee1994fa4fad988638df8c507aaa", "step": 46, "value": 0.31285594549400914, "stage": "fusion_draft", "created_at": 1788698896.9693673}], "maximize": false, "elapsed_seconds": 28775.555537462234, "node_count": 47, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.bo.leaf-classification.yaml", "note": ""}, {"id": "xixian.bo.mlsp-2013-birds", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "bo", "dataset": "mlsp-2013-birds", "status": "archived", "official_score": 0.78305, "medal": "none", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.93527, "silver": 0.90038, "bronze": 0.87372}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:32", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-four-methods-muse13/runs/bo/10_mlsp-2013-birds/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-four-methods-muse13/runs/bo/10_mlsp-2013-birds/logs/journal.json", "metrics": [{"event_id": "d0a3972d5f8945f7a2bd54f898e1df9d", "step": 4, "value": 0.7183026584867075, "stage": "debug", "created_at": 1788671207.4299533}, {"event_id": "9a510f8c4842497685f6e97542bc9a6d", "step": 9, "value": 0.77348055237824, "stage": "debug", "created_at": 1788671248.3749971}, {"event_id": "f44f3afe554a4993ac146a0b8050ca29", "step": 10, "value": 0.6600204498977505, "stage": "debug", "created_at": 1788671492.2747164}, {"event_id": "bb9789217a7f4a29a2c00d5fa7de8c7c", "step": 12, "value": 0.9754601226993865, "stage": "improve", "created_at": 1788671714.2821107}, {"event_id": "90867986ca1a43ab9c33a3f0aa6af163", "step": 13, "value": 0.8051906563075035, "stage": "debug", "created_at": 1788671784.9295907}, {"event_id": "078d4884baa343198baa0026c6be93d1", "step": 14, "value": 0.9802147239263804, "stage": "improve", "created_at": 1788671900.19599}, {"event_id": "a29deae573134deaa6fbdb1aa4275a7c", "step": 15, "value": 0.9326903209717874, "stage": "improve", "created_at": 1788671682.2087276}, {"event_id": "06e8af731ead4134bde0effa31fbf59e", "step": 16, "value": 0.8303261091801267, "stage": "improve", "created_at": 1788672087.519402}, {"event_id": "2f6cd03a3eb54266941de21ce2c961be", "step": 17, "value": 0.9775051124744376, "stage": "improve", "created_at": 1788672111.2478366}, {"event_id": "4ca567bcd75c49e3bd70c8fffa277aac", "step": 18, "value": 0.7023517382413088, "stage": "improve", "created_at": 1788672129.374102}, {"event_id": "ccb7bbaaa2af4c80a06008085203697f", "step": 19, "value": 0.9770961145194274, "stage": "improve", "created_at": 1788672270.5486634}, {"event_id": "ff40bb6aef514c8aa732ecce1c087b11", "step": 20, "value": 0.9778118609406954, "stage": "improve", "created_at": 1788672352.5395699}, {"event_id": "9542ace167154d7f92330e00fa4d5b51", "step": 22, "value": 0.7239809217680547, "stage": "evolution", "created_at": 1788672446.1664546}, {"event_id": "e065c03c057c418887fd89097ecd6433", "step": 24, "value": 0.9930470347648261, "stage": "evolution", "created_at": 1788672725.4333181}, {"event_id": "9a8ef78be5ef475faedb028cbd1114e2", "step": 25, "value": 0.6655128574170026, "stage": "debug", "created_at": 1788672641.6567214}, {"event_id": "63f2c57369c144de876628553f8156f7", "step": 26, "value": 0.9729550102249489, "stage": "debug", "created_at": 1788672698.6305153}, {"event_id": "7427a84813c44878b6fdb513a925fb8b", "step": 27, "value": 0.9799079754601226, "stage": "improve", "created_at": 1788672925.6910746}, {"event_id": "9cc85b938b2e457a93985687768f50a7", "step": 28, "value": 0.9783742331288344, "stage": "improve", "created_at": 1788673016.5372548}, {"event_id": "7e937e1d1f674c0082726b73d0e4bd2f", "step": 29, "value": 0.7659270982932286, "stage": "improve", "created_at": 1788673043.1828537}, {"event_id": "4adebaebe0d1473594cbd9c0c2e4c930", "step": 31, "value": 0.9576687116564417, "stage": "evolution", "created_at": 1788673182.4812157}, {"event_id": "eb9e4dbe3f544455b078d8d7e3704dff", "step": 32, "value": 0.874543436585612, "stage": "debug", "created_at": 1788673269.567654}, {"event_id": "7fe0168dcd3f4440a9203005265f005a", "step": 33, "value": 0.8628238341968912, "stage": "evolution", "created_at": 1788673255.421682}, {"event_id": "b0c66f4d4e0f4dc69fc6a1a7906ca42c", "step": 34, "value": 0.975, "stage": "evolution", "created_at": 1788673446.819285}, {"event_id": "36af4fd9259e43cba7d5e9b38fa3dfa8", "step": 35, "value": 0.9788343558282209, "stage": "evolution", "created_at": 1788673442.4726698}, {"event_id": "07678da514a642dbb54d9ca9c0e47665", "step": 36, "value": 0.9767893660531697, "stage": "evolution", "created_at": 1788673642.9739258}, {"event_id": "170d497458f744fabd612dac6846ec9c", "step": 37, "value": 0.9799079754601226, "stage": "evolution", "created_at": 1788673597.067182}, {"event_id": "799775d58d0a4f47a77a0c1da0dcb73e", "step": 38, "value": 0.9766871165644172, "stage": "evolution", "created_at": 1788673658.5654056}, {"event_id": "ddb8fd34da5a44bc96368ac45105a29a", "step": 41, "value": 0.7267567005693085, "stage": "evolution", "created_at": 1788673868.2626803}, {"event_id": "18782ee874f94373bcf236c6ae53fe93", "step": 42, "value": 0.9711656441717791, "stage": "debug", "created_at": 1788673983.1009479}, {"event_id": "fbc20e939af443a3a313b8a016d0a269", "step": 43, "value": 0.9315305924672782, "stage": "improve", "created_at": 1788674129.5906765}, {"event_id": "20aa804017a9416cb6e21888ad2a2f86", "step": 44, "value": 0.718200408997955, "stage": "evolution", "created_at": 1788674347.455758}, {"event_id": "1e00e378702d4082bea5930d146628e7", "step": 45, "value": 0.946968647087568, "stage": "improve", "created_at": 1788674568.859879}, {"event_id": "7b0e20934d2c48c0a8d195aa529aed6b", "step": 46, "value": 0.8414163948058595, "stage": "debug", "created_at": 1788674029.0916317}, {"event_id": "651cded1097f4e96af80ada18adf7edb", "step": 47, "value": 0.7486738789739652, "stage": "evolution", "created_at": 1788674633.228053}, {"event_id": "c45810fbae144ec8b1c7a88faa04ec26", "step": 53, "value": 0.8550534126527218, "stage": "debug", "created_at": 1788681915.5998747}, {"event_id": "679111482fc14ceeb915ca33b644095f", "step": 54, "value": 0.9438536071919759, "stage": "improve", "created_at": 1788682170.5332372}, {"event_id": "d5874d07768c483cb7c061c0f01b0d49", "step": 55, "value": 0.9507587579922328, "stage": "improve", "created_at": 1788682570.369291}, {"event_id": "44ff727556864b21af02253f1f99bced", "step": 56, "value": 0.8285207491131096, "stage": "debug", "created_at": 1788682063.7103643}, {"event_id": "b1fe094e00d14a1390ba08c72474acc0", "step": 57, "value": 0.8668907955889227, "stage": "improve", "created_at": 1788683244.379582}, {"event_id": "417f4b1a42f0407294e5ed5d8eb15645", "step": 58, "value": 0.9416472824826114, "stage": "improve", "created_at": 1788682911.0979}, {"event_id": "56a51b5a2b664d8e846b949e0664ff17", "step": 59, "value": 0.9126777748984828, "stage": "improve", "created_at": 1788681824.4462616}], "maximize": true, "elapsed_seconds": 28768.179161548615, "node_count": 60, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.bo.mlsp-2013-birds.yaml", "note": ""}, {"id": "xixian.bo.new-york-city-taxi-fare-prediction", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "bo", "dataset": "new-york-city-taxi-fare-prediction", "status": "archived", "official_score": 5.68469, "medal": "none", "valid_submission": true, "score_maximize": false, "thresholds": {"gold": 2.83377, "silver": 2.88191, "bronze": 2.92371}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:33", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-four-methods-muse13/runs/bo/11_new-york-city-taxi-fare-prediction/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-four-methods-muse13/runs/bo/11_new-york-city-taxi-fare-prediction/logs/journal.json", "metrics": [{"event_id": "b96a4c3ecc7c48929334c540d73b6e26", "step": 2, "value": 3.6988322812410646, "stage": "draft", "created_at": 1788671156.64213}, {"event_id": "e00c6c9d452942d8903952b74dafb9e2", "step": 3, "value": 2.762585549700826, "stage": "draft", "created_at": 1788671327.858628}, {"event_id": "c76efdc676364fdd9daf53ab69e07cd9", "step": 4, "value": 3.528448448367279, "stage": "debug", "created_at": 1788671608.107167}, {"event_id": "1e4e98a2bc944baabdbca7a249ad48f6", "step": 5, "value": 2.8764998433067075, "stage": "improve", "created_at": 1788671985.4323266}, {"event_id": "93e5e21838104220b11830278ada4e39", "step": 6, "value": 2.7323705764735795, "stage": "improve", "created_at": 1788672300.8131347}, {"event_id": "0ca3f5887945428582f079477cef4616", "step": 7, "value": 3.6063101654537597, "stage": "improve", "created_at": 1788672436.3061311}, {"event_id": "8fb3b910bd264a4a840f2606eb4ba2f1", "step": 9, "value": 3.0360239333404864, "stage": "improve", "created_at": 1788672926.7612956}, {"event_id": "7d16ef55ae314aa4bee975fac44329f9", "step": 10, "value": 2.8762149639823167, "stage": "improve", "created_at": 1788672851.8149655}, {"event_id": "acbef8b27c484f4bbf01ab96e12c7155", "step": 11, "value": 7.927156191289908, "stage": "debug", "created_at": 1788673305.6824698}, {"event_id": "f2b37d0ec3d945bab8fafde959d2d822", "step": 12, "value": 2.9196011491297087, "stage": "improve", "created_at": 1788673723.6823606}, {"event_id": "1701122dbbaf42c1811c87ab9b50fd1d", "step": 13, "value": 2.855341849029856, "stage": "improve", "created_at": 1788673467.9182997}, {"event_id": "324418d45c44425cb621ab0a5178df56", "step": 14, "value": 2.9196011491297087, "stage": "improve", "created_at": 1788673841.1603506}, {"event_id": "6f64989b1df147b0940528de95156d44", "step": 21, "value": 2.8544716184685175, "stage": "improve", "created_at": 1788681908.4728498}, {"event_id": "2441bb7167f0409c8aa56cd0eeae2cbb", "step": 23, "value": 2.961584952594734, "stage": "debug", "created_at": 1788682534.0626783}, {"event_id": "6e89ff3db72f494b8ea86c99dd457c3c", "step": 24, "value": 4.3437750271655124, "stage": "debug", "created_at": 1788682982.5075123}, {"event_id": "cb014d6557f0409a88663e42f24d9128", "step": 25, "value": 2.7905221831163534, "stage": "improve", "created_at": 1788682969.0263991}, {"event_id": "d991148cebb541c68b29cf2510f521a8", "step": 26, "value": 2.961615303799805, "stage": "improve", "created_at": 1788683337.3300977}, {"event_id": "b03f7056f0594f3eb0a526929c144670", "step": 27, "value": 3.025537642231636, "stage": "improve", "created_at": 1788684251.726648}, {"event_id": "3ce692b3c4e24062b2c5ed349df8250a", "step": 28, "value": 2.7963888711041087, "stage": "improve", "created_at": 1788684250.187351}, {"event_id": "6aa9f2a03103432fa004d2085588751a", "step": 29, "value": 3.4045575353200537, "stage": "improve", "created_at": 1788684115.9463923}, {"event_id": "7c786244226945978f757e52edbf13c7", "step": 30, "value": 2.898044538570641, "stage": "improve", "created_at": 1788685776.212049}, {"event_id": "a43286bbf9434aa89a0e413da2677c99", "step": 31, "value": 3.384762115003851, "stage": "improve", "created_at": 1788685798.4005659}, {"event_id": "7047892c3e7f45f38a3069319cd5e2ef", "step": 32, "value": 2.8015599389301236, "stage": "improve", "created_at": 1788687141.4729059}, {"event_id": "f5aeb72239874ab9a3f6a136c358751b", "step": 33, "value": 3.7793171207317253, "stage": "improve", "created_at": 1788685037.043343}, {"event_id": "267b954962b74a389a519a91a62d027f", "step": 34, "value": 3.416723423993107, "stage": "improve", "created_at": 1788687998.5111115}, {"event_id": "e70229c13a654729ac0eddc2ee52729e", "step": 35, "value": 3.572345217358438, "stage": "fusion", "created_at": 1788690329.846323}, {"event_id": "8c29f895a97c411bb82bbd0c52dcc612", "step": 36, "value": 2.669657399496629, "stage": "fusion", "created_at": 1788691601.3383448}, {"event_id": "16f8f8879bbe461d9817a779d9f2c46f", "step": 37, "value": 2.631871292514002, "stage": "improve", "created_at": 1788693388.9521112}, {"event_id": "bacfaf9ac8ed4f02a04112d3b5b18926", "step": 38, "value": 2.5654054954602388, "stage": "improve", "created_at": 1788695076.727569}, {"event_id": "e3411ff8bd134f6bb144b3dd7bd345d0", "step": 39, "value": 2.6872513312048096, "stage": "improve", "created_at": 1788696601.9590237}, {"event_id": "c4f400976e3244b9aea0028066bb3b9a", "step": 40, "value": 3.368584154489888, "stage": "improve", "created_at": 1788690473.0246503}], "maximize": false, "elapsed_seconds": 28768.929530620575, "node_count": 41, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.bo.new-york-city-taxi-fare-prediction.yaml", "note": ""}, {"id": "xixian.bo.nomad2018-predict-transparent-conductors", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "bo", "dataset": "nomad2018-predict-transparent-conductors", "status": "archived", "official_score": 0.05915, "medal": "silver", "valid_submission": true, "score_maximize": false, "thresholds": {"gold": 0.05589, "silver": 0.06229, "bronze": 0.06582}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:34", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-four-methods-muse13/runs/bo/12_nomad2018-predict-transparent-conductors/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-four-methods-muse13/runs/bo/12_nomad2018-predict-transparent-conductors/logs/journal.json", "metrics": [{"event_id": "5864dcde884d438fbd82702e1dfe48ff", "step": 4, "value": 0.057813222537245676, "stage": "debug", "created_at": 1788671268.1133678}, {"event_id": "df18d205dceb4e75812b579abc5d0cde", "step": 6, "value": 0.06252171821194541, "stage": "debug", "created_at": 1788671299.5475981}, {"event_id": "c061f3c61e7a41df8eee2857e43b37b1", "step": 7, "value": 0.05893479620522812, "stage": "improve", "created_at": 1788671419.9295785}, {"event_id": "6a08bd4f6b3941edb28a15d06e4e43ed", "step": 8, "value": 0.060140559503803814, "stage": "improve", "created_at": 1788671469.901528}, {"event_id": "9f5e560ca3344704be913abd8d5cb434", "step": 9, "value": 0.06192767238169916, "stage": "debug", "created_at": 1788671405.372952}, {"event_id": "aa98cbb0e612401cbd8ac22fb5d0f8aa", "step": 10, "value": 0.06355143464766827, "stage": "improve", "created_at": 1788671700.2284462}, {"event_id": "c5c1803677f7406180f5f8c4a05a5ac8", "step": 12, "value": 0.060140559503803814, "stage": "improve", "created_at": 1788671657.9617147}, {"event_id": "bd5c25935fd04689b7ab253ef974a8a3", "step": 13, "value": 0.06028703466428183, "stage": "improve", "created_at": 1788672298.0302544}, {"event_id": "d549cb6f794f4061bee672695734fc5f", "step": 14, "value": 0.05696959388552985, "stage": "debug", "created_at": 1788672215.9609218}, {"event_id": "ac408f781c434882a3eaf4465ff5d93a", "step": 15, "value": 0.05906862720142021, "stage": "improve", "created_at": 1788671574.6412973}, {"event_id": "175c96ee56a343f990ee086713995974", "step": 16, "value": 0.06004004147700896, "stage": "improve", "created_at": 1788673394.574141}, {"event_id": "97f674c4dee14e9a9e0372b37c023211", "step": 17, "value": 0.059761017620591016, "stage": "improve", "created_at": 1788673473.5520065}, {"event_id": "30d5a96b1aad4c75b4df3879dacb5d5f", "step": 23, "value": 0.19084595828591028, "stage": "draft", "created_at": 1788681992.0874217}, {"event_id": "fb738b05f44f42ae979f09d0c256b489", "step": 25, "value": 0.0558970446276677, "stage": "debug", "created_at": 1788682160.085684}, {"event_id": "85763b2d80c84e66a9f663b3a7bb6e04", "step": 26, "value": 0.05501074290624543, "stage": "improve", "created_at": 1788682349.4185328}, {"event_id": "c118bb331a86450aaa557817e15bee61", "step": 27, "value": 0.053972303087397325, "stage": "improve", "created_at": 1788682669.8552778}, {"event_id": "9423512d302544ad87af9d5a4fd2d68c", "step": 28, "value": 0.056960962968283735, "stage": "improve", "created_at": 1788682168.4780958}, {"event_id": "e25a48949452476289af462b9ea1bc2f", "step": 29, "value": 0.057079487659206694, "stage": "improve", "created_at": 1788681924.4156291}, {"event_id": "cbcfc37e2e5649df8e1c4cb2a6fd1dab", "step": 31, "value": 0.054667204649616975, "stage": "improve", "created_at": 1788683503.9102278}, {"event_id": "e6ae0c74d9cf48f7affd5d0eef51b777", "step": 32, "value": 0.05448021840083186, "stage": "improve", "created_at": 1788683620.1184113}, {"event_id": "769a692a9591481b90ab65c6bc7aad94", "step": 33, "value": 0.05390469625561542, "stage": "improve", "created_at": 1788683514.9818327}, {"event_id": "5ecde9fba7c94d518a7c5e67dda805ba", "step": 34, "value": 0.052870432501519314, "stage": "improve", "created_at": 1788684060.3624108}, {"event_id": "b065b230dfdc4ffea8566508d23307db", "step": 36, "value": 0.05467466407897897, "stage": "improve", "created_at": 1788684126.6380405}, {"event_id": "8dd52af2836244ac9108ad762a8e826a", "step": 37, "value": 0.0534175298163547, "stage": "debug", "created_at": 1788684356.9424596}, {"event_id": "515789256a5e45028c6830a58c0106f1", "step": 38, "value": 0.053017977456995775, "stage": "improve", "created_at": 1788684680.8171983}, {"event_id": "7adb5838c634498684a4cf7417ea7fe7", "step": 39, "value": 0.05307508615050899, "stage": "improve", "created_at": 1788684191.9184444}, {"event_id": "7d149df5497a44f29f2599064fca47af", "step": 40, "value": 0.06173335060501835, "stage": "improve", "created_at": 1788685207.8940053}, {"event_id": "41108b0151254490a276477aa68edda8", "step": 41, "value": 0.05691197103024444, "stage": "improve", "created_at": 1788684996.5993872}, {"event_id": "d6c0a2de7a5c4ad6b93a1f2ba4bb0f52", "step": 42, "value": 0.06131086668467465, "stage": "improve", "created_at": 1788686559.2768195}, {"event_id": "63736e788dfb4ad19b486d4e82f8d91f", "step": 43, "value": 0.06496018950902249, "stage": "improve", "created_at": 1788687621.4903655}, {"event_id": "690b4ea4ae334baa9b33ef2edde82eac", "step": 44, "value": 0.060366237004972914, "stage": "improve", "created_at": 1788687880.5991561}, {"event_id": "accf61971f9947689880ee165bfc23bf", "step": 45, "value": 0.05293816589195188, "stage": "evolution", "created_at": 1788685044.26327}, {"event_id": "8c39770eef3141e18ac9c603eac469bc", "step": 46, "value": 0.05928175363156575, "stage": "improve", "created_at": 1788688212.204901}, {"event_id": "0b32b00a346d4bdf8bef29e8e9e3eaf2", "step": 47, "value": 0.05491059118170866, "stage": "evolution", "created_at": 1788687087.4005125}, {"event_id": "a6cf54416cff466c80cc6f3423b1600b", "step": 48, "value": 0.06364730028487607, "stage": "improve", "created_at": 1788689699.1124449}, {"event_id": "4ea9436b7ea049d5939419e254ea76ef", "step": 49, "value": 0.052185347117449404, "stage": "evolution", "created_at": 1788688980.1778975}, {"event_id": "2b43688047f245bbbdafadc9346f5f63", "step": 50, "value": 0.052762237952491554, "stage": "evolution", "created_at": 1788689203.8480983}, {"event_id": "f897d51b5c234d30962caff9521fc03c", "step": 53, "value": 0.04350663764184034, "stage": "evolution", "created_at": 1788689980.5636122}, {"event_id": "f72bc80133164871ad278d17b3e62d80", "step": 54, "value": 0.051151471599773506, "stage": "improve", "created_at": 1788693238.5162404}], "maximize": false, "elapsed_seconds": 28771.841128349304, "node_count": 55, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.bo.nomad2018-predict-transparent-conductors.yaml", "note": ""}, {"id": "xixian.bo.plant-pathology-2020-fgvc7", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "bo", "dataset": "plant-pathology-2020-fgvc7", "status": "archived", "official_score": 0.99433, "medal": "gold", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.97836, "silver": 0.97465, "bronze": 0.97361}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:35", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-four-methods-muse13/runs/bo/13_plant-pathology-2020-fgvc7/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-four-methods-muse13/runs/bo/13_plant-pathology-2020-fgvc7/logs/journal.json", "metrics": [{"event_id": "2324f79cce724b29a70a479c7b14e8df", "step": 1, "value": 0.981732343711061, "stage": "draft", "created_at": 1788671291.2418342}, {"event_id": "b4286e090c0d404da4fa8f449dcf6ba8", "step": 2, "value": 0.9855025138486848, "stage": "draft", "created_at": 1788670868.8572412}, {"event_id": "43cb6b9389794d9cbf8c1a246c7e9013", "step": 3, "value": 0.9853237148490432, "stage": "draft", "created_at": 1788671069.1330736}, {"event_id": "3e0be2bd9969415db850cf17477f0a2c", "step": 6, "value": 0.9640691254670484, "stage": "improve", "created_at": 1788672143.8110507}, {"event_id": "8fea228eaaef467db4bf790b177332e2", "step": 7, "value": 0.9897607888073308, "stage": "debug", "created_at": 1788672277.2563493}, {"event_id": "62624d6044e3468cb33a748373f39d48", "step": 9, "value": 0.9773401832224052, "stage": "improve", "created_at": 1788672845.5028954}, {"event_id": "87111f6df48c4b75898ed1969a913f3a", "step": 11, "value": 0.9833888546296123, "stage": "debug", "created_at": 1788673371.041624}, {"event_id": "3adab1a9d3974c1f9ec7154e33b9d43b", "step": 14, "value": 0.9974443782669667, "stage": "debug", "created_at": 1788682276.521913}, {"event_id": "9b337ba6a4de403cb67a2b22d196ea5a", "step": 15, "value": 0.984669176063831, "stage": "draft", "created_at": 1788682076.7861104}, {"event_id": "4614e996a52c4561acdf512663a95a3a", "step": 19, "value": 0.984318989461846, "stage": "improve", "created_at": 1788683262.5585423}, {"event_id": "3033b484c05d4abc8aa0e7101d8903c5", "step": 20, "value": 0.984722754256552, "stage": "improve", "created_at": 1788687299.3062747}, {"event_id": "a44ab5b7de3c4c33be661b7cc27f520a", "step": 21, "value": 0.9653096443953078, "stage": "improve", "created_at": 1788687874.072312}, {"event_id": "a3f30a734aeb47f48d1a0825cfbec0a2", "step": 22, "value": 0.9729971092296392, "stage": "improve", "created_at": 1788688020.4624145}, {"event_id": "3b200d59e65b45ebac65ef31aac15bad", "step": 23, "value": 0.8690201044389041, "stage": "improve", "created_at": 1788689501.5957346}, {"event_id": "b3265d3b4679472caf7a302111fd6046", "step": 24, "value": 0.9519310515510099, "stage": "evolution", "created_at": 1788689056.4918225}, {"event_id": "5482618b664f4737a3ca0d382dc0be3e", "step": 25, "value": 0.9117178505326826, "stage": "improve", "created_at": 1788691516.2494059}, {"event_id": "288a1d8edeab49e798bbb31c76fdfd67", "step": 28, "value": 0.9486, "stage": "fusion_draft", "created_at": 1788695009.9690504}, {"event_id": "5c91e180b7af418f9ba103b6623374fb", "step": 29, "value": 0.9731781688762084, "stage": "fusion", "created_at": 1788692774.520494}, {"event_id": "cb04428988eb49d0bbc71f01ebc1b7a2", "step": 30, "value": 0.9697, "stage": "improve", "created_at": 1788696322.1470995}, {"event_id": "9e78b0655a84486585a80e6056d4b5d1", "step": 31, "value": 0.9743465934911028, "stage": "fusion", "created_at": 1788698092.1532745}], "maximize": true, "elapsed_seconds": 28763.982608795166, "node_count": 33, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.bo.plant-pathology-2020-fgvc7.yaml", "note": ""}, {"id": "xixian.bo.random-acts-of-pizza", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "bo", "dataset": "random-acts-of-pizza", "status": "archived", "official_score": 0.70611, "medal": "bronze", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.97908, "silver": 0.76482, "bronze": 0.6921}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:36", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-four-methods-muse13/runs/bo/14_random-acts-of-pizza/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-four-methods-muse13/runs/bo/14_random-acts-of-pizza/logs/journal.json", "metrics": [{"event_id": "1c9e3f4cdd5d4876b572bd4f432492fd", "step": 5, "value": 0.6502803738317757, "stage": "debug", "created_at": 1788671487.7995563}, {"event_id": "5b09734a087e4b339ff19ffcc70becf2", "step": 6, "value": 0.6616966211358735, "stage": "draft", "created_at": 1788671258.6608229}, {"event_id": "4234a0acb4fb4e94b5351f61dbec7b8a", "step": 7, "value": 0.6759166067577282, "stage": "debug", "created_at": 1788671572.3890595}, {"event_id": "4a8589842b8047aca4013941fd1aca2a", "step": 8, "value": 0.654291876347951, "stage": "improve", "created_at": 1788671845.1191692}, {"event_id": "add86c9937174c58b1793ea3a763b840", "step": 9, "value": 0.6548670021567218, "stage": "improve", "created_at": 1788671811.373}, {"event_id": "dd5dee1407b644d5b148ee93572be66a", "step": 10, "value": 0.6232063263838965, "stage": "improve", "created_at": 1788671950.2640886}, {"event_id": "5d63b7d9ef324e86a8f830f8d150190f", "step": 11, "value": 0.6578289000718908, "stage": "improve", "created_at": 1788673102.182326}, {"event_id": "706d9b32e88742d79d48a15c0fb97439", "step": 13, "value": 0.6554421279654924, "stage": "improve", "created_at": 1788673095.4357548}, {"event_id": "abdbdee5af9d4b1bbc16ee9408a9ae24", "step": 18, "value": 0.678763479511143, "stage": "improve", "created_at": 1788681848.4874613}, {"event_id": "ecadb2cf0dfc46e98c5996eefb3765be", "step": 19, "value": 0.637469446441409, "stage": "draft", "created_at": 1788682002.0155985}, {"event_id": "df62faf117fc448fa1967d315470d658", "step": 20, "value": 0.670472714352622, "stage": "debug", "created_at": 1788682081.8976696}, {"event_id": "f68b267e36e04a0aa5a427fd845a2b3f", "step": 22, "value": 0.6292451473759885, "stage": "improve", "created_at": 1788682221.4935102}, {"event_id": "df5e1706449240178df1483fb814bdec", "step": 23, "value": 0.5855068296189792, "stage": "debug", "created_at": 1788682225.0039852}, {"event_id": "173b702ccd594948a8c92b65ceaa0d5f", "step": 25, "value": 0.6454924514737599, "stage": "improve", "created_at": 1788682591.317823}, {"event_id": "e1e346243b5840b8926cdbe32485d5a9", "step": 27, "value": 0.6620560747663551, "stage": "improve", "created_at": 1788683611.731614}, {"event_id": "c4e52fb2586b408e924286e93deb95b2", "step": 28, "value": 0.701509705248023, "stage": "improve", "created_at": 1788682302.6540802}, {"event_id": "ae2b8afc70034475841ce7eaacc31f06", "step": 29, "value": 0.6835093708880117, "stage": "improve", "created_at": 1788684254.2035956}, {"event_id": "8a140b09ed624d07b3d5792dffdbb131", "step": 30, "value": 0.6679511143062544, "stage": "debug", "created_at": 1788684114.8026347}, {"event_id": "21082d930a6149b283f6509b7d7ce3f4", "step": 31, "value": 0.690911030716856, "stage": "improve", "created_at": 1788686197.8495896}], "maximize": true, "elapsed_seconds": 28772.22519135475, "node_count": 32, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.bo.random-acts-of-pizza.yaml", "note": ""}, {"id": "xixian.bo.ranzcr-clip-catheter-line-classification", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "bo", "dataset": "ranzcr-clip-catheter-line-classification", "status": "archived", "official_score": 0.85467, "medal": "none", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.97357, "silver": 0.97152, "bronze": 0.9709}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:37", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-four-methods-muse13/runs/bo/15_ranzcr-clip-catheter-line-classification/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-four-methods-muse13/runs/bo/15_ranzcr-clip-catheter-line-classification/logs/journal.json", "metrics": [{"event_id": "871cd18eb3b04a588fd32f2c2d510a1b", "step": 4, "value": 0.6956051306516842, "stage": "draft", "created_at": 1788671331.8240201}, {"event_id": "5e3e6ddcd8cd4321a4e64ddc83ffead8", "step": 5, "value": 0.8273826728090914, "stage": "debug", "created_at": 1788684917.19335}], "maximize": true, "elapsed_seconds": 28743.49157834053, "node_count": 6, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.bo.ranzcr-clip-catheter-line-classification.yaml", "note": ""}, {"id": "xixian.bo.siim-isic-melanoma-classification", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "bo", "dataset": "siim-isic-melanoma-classification", "status": "archived", "official_score": 0.91612, "medal": "none", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.9455, "silver": 0.9401, "bronze": 0.937}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:38", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-four-methods-muse13/runs/bo/16_siim-isic-melanoma-classification/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-four-methods-muse13/runs/bo/16_siim-isic-melanoma-classification/logs/journal.json", "metrics": [{"event_id": "27b6a58ce31f4b64b6c3797f9cc49f23", "step": 2, "value": 0.8989093243674527, "stage": "draft", "created_at": 1788670952.595438}, {"event_id": "763d74f274c642a894873196834c69ae", "step": 3, "value": 0.9403918918918919, "stage": "debug", "created_at": 1788671443.5202684}, {"event_id": "850becc0da144d99a301d6ba397922bf", "step": 5, "value": 0.8084239864864865, "stage": "debug", "created_at": 1788693054.6164548}], "maximize": true, "elapsed_seconds": 28763.865121603012, "node_count": 6, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.bo.siim-isic-melanoma-classification.yaml", "note": ""}, {"id": "xixian.bo.spooky-author-identification", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "bo", "dataset": "spooky-author-identification", "status": "archived", "official_score": 0.2107, "medal": "silver", "valid_submission": true, "score_maximize": false, "thresholds": {"gold": 0.16506, "silver": 0.26996, "bronze": 0.29381}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:39", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-four-methods-muse13/runs/bo/17_spooky-author-identification/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-four-methods-muse13/runs/bo/17_spooky-author-identification/logs/journal.json", "metrics": [{"event_id": "4c81e9a6c0e9406b9745e4a244815d7b", "step": 6, "value": 0.5977120549920673, "stage": "debug", "created_at": 1788671436.476422}, {"event_id": "95d28e9e75d34eb99b0d2738031babef", "step": 7, "value": 0.3639765981562474, "stage": "debug", "created_at": 1788671827.712366}, {"event_id": "945ee352c0714685a5f9b1e5f31d7efa", "step": 8, "value": 0.40349695191996926, "stage": "draft", "created_at": 1788671054.9137456}, {"event_id": "9b8c88c8fb844e029951a7ef605014b5", "step": 9, "value": 0.30481290391105736, "stage": "improve", "created_at": 1788672242.3893893}, {"event_id": "cbda5cac0a674e87a7bf57fc0f6220ef", "step": 13, "value": 0.7113784559877797, "stage": "draft", "created_at": 1788681986.144502}, {"event_id": "a754f8c8e1d84ff2b8412db2643ff588", "step": 14, "value": 0.3935228946286598, "stage": "improve", "created_at": 1788681867.9966035}, {"event_id": "f6af87bd92294535ab83040f41206bdd", "step": 15, "value": 0.4080659790839455, "stage": "improve", "created_at": 1788682249.548994}, {"event_id": "c85696490da44c1e98ca95455d03d9df", "step": 16, "value": 0.318446307157304, "stage": "draft", "created_at": 1788682020.2134356}, {"event_id": "5a9c2baef5114a8b8bae7100af91b00d", "step": 17, "value": 0.2814012646622895, "stage": "improve", "created_at": 1788682598.6240077}, {"event_id": "4f86a827562f490987c86e8a0ff37f84", "step": 18, "value": 0.3149555746560111, "stage": "improve", "created_at": 1788682775.9671657}, {"event_id": "b06576e5200b41bb8776a54c72254c49", "step": 19, "value": 0.32070572100362144, "stage": "improve", "created_at": 1788682781.87328}, {"event_id": "7ce4d311f3434007a7fd3a6b5420c43a", "step": 20, "value": 0.21846549599795334, "stage": "improve", "created_at": 1788683845.099326}, {"event_id": "19e54076e031479f903926d807cfef4a", "step": 21, "value": 0.3517962673160027, "stage": "improve", "created_at": 1788683291.0803}, {"event_id": "a4ea4fba97d5422e95345f33f556d242", "step": 23, "value": 0.2935182868539098, "stage": "improve", "created_at": 1788684998.6333027}, {"event_id": "2b5b4e27258b4d928f3026bbb7b93a89", "step": 26, "value": 0.3845871400838193, "stage": "improve", "created_at": 1788685736.1216764}, {"event_id": "ba724fde618547f2b92ca9e5a3b862e5", "step": 33, "value": 0.49028968150834484, "stage": "debug", "created_at": 1788688930.4634333}, {"event_id": "bbce89e64a7f4b55a9d9166226098a59", "step": 34, "value": 0.3497090819112031, "stage": "improve", "created_at": 1788691038.061892}, {"event_id": "0582af4c48d54a4691008f67fb416906", "step": 35, "value": 0.2731484986894379, "stage": "improve", "created_at": 1788693399.0012712}, {"event_id": "2483fe2137a142ffba3e0c2b577f9588", "step": 36, "value": 0.24201922171624715, "stage": "debug", "created_at": 1788687316.3977284}], "maximize": false, "elapsed_seconds": 28763.81413912773, "node_count": 37, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.bo.spooky-author-identification.yaml", "note": ""}, {"id": "xixian.bo.tabular-playground-series-dec-2021", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "bo", "dataset": "tabular-playground-series-dec-2021", "status": "archived", "official_score": 0.96309, "medal": "gold", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.9566, "silver": 0.95658, "bronze": 0.95658}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:40", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-four-methods-muse13/runs/bo/18_tabular-playground-series-dec-2021/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-four-methods-muse13/runs/bo/18_tabular-playground-series-dec-2021/logs/journal.json", "metrics": [{"event_id": "85102bcb03f24436b8be25049cd8512f", "step": 6, "value": 0.9455944444444444, "stage": "debug", "created_at": 1788671313.0754676}, {"event_id": "7684ae096d124bdb9eada65bc2108f9b", "step": 7, "value": 0.9580027777777778, "stage": "debug", "created_at": 1788671451.4575262}, {"event_id": "d0b73775fc9b4b438106d315cbf724c9", "step": 8, "value": 0.9617203703703704, "stage": "improve", "created_at": 1788671679.7528927}, {"event_id": "ebb4846284da463d8243908d4e54369b", "step": 11, "value": 0.9413333333333334, "stage": "debug", "created_at": 1788681989.5693338}, {"event_id": "5d2c8d16b2bc475385937c8d8cee7131", "step": 12, "value": 0.9597222222222223, "stage": "improve", "created_at": 1788682437.2185178}, {"event_id": "bf89bdde521b48e78dc0845a93944037", "step": 15, "value": 0.9588194444444444, "stage": "debug", "created_at": 1788687504.0457268}, {"event_id": "43bdbc3f525943cfa85d68b62f8bc6c4", "step": 16, "value": 0.9610416666666667, "stage": "improve", "created_at": 1788688075.8089445}, {"event_id": "7c039fc0b835486a90fa5907e61736ee", "step": 17, "value": 0.9622851851851851, "stage": "improve", "created_at": 1788688872.1633122}, {"event_id": "40622e83fd4a4e7492d5bcdb931e26ee", "step": 20, "value": 0.9624055555555555, "stage": "improve", "created_at": 1788691832.7298243}, {"event_id": "eb5daf245e6a425fbf82412e1d8f9d0e", "step": 24, "value": 0.9624805555555556, "stage": "improve", "created_at": 1788693725.360775}, {"event_id": "8777da9ea41a4651a3f1352fa9001a00", "step": 25, "value": 0.9624583333333333, "stage": "improve", "created_at": 1788695731.59384}], "maximize": true, "elapsed_seconds": 28767.763100862503, "node_count": 26, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.bo.tabular-playground-series-dec-2021.yaml", "note": ""}, {"id": "xixian.bo.tabular-playground-series-may-2022", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "bo", "dataset": "tabular-playground-series-may-2022", "status": "archived", "official_score": 0.99408, "medal": "none", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.99823, "silver": 0.99822, "bronze": 0.99818}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:41", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-four-methods-muse13/runs/bo/19_tabular-playground-series-may-2022/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-four-methods-muse13/runs/bo/19_tabular-playground-series-may-2022/logs/journal.json", "metrics": [{"event_id": "824dcda8faeb41a185722261014674fa", "step": 2, "value": 0.9570655042192885, "stage": "draft", "created_at": 1788671219.1188982}, {"event_id": "e03ad7040b4e41c8aeeff1f231129892", "step": 4, "value": 0.9722316789184375, "stage": "debug", "created_at": 1788671629.451879}, {"event_id": "389808383773433aab198472cd5ab4d4", "step": 5, "value": 0.9831603764168173, "stage": "improve", "created_at": 1788671958.132202}, {"event_id": "17cc5e29d01a409b9f84b62961bb69ec", "step": 6, "value": 0.9908236587138766, "stage": "improve", "created_at": 1788672549.7216766}, {"event_id": "c3eb75523f8d48c1b36f3db41ad699b2", "step": 9, "value": 0.7683183328787614, "stage": "debug", "created_at": 1788682144.3853533}, {"event_id": "fcb09118008543f197d4a1555d657915", "step": 10, "value": 0.8475734564934726, "stage": "improve", "created_at": 1788682468.9408908}, {"event_id": "75e77b59af28480bb61f225b60a262b7", "step": 12, "value": 0.9675027099690247, "stage": "debug", "created_at": 1788682930.6413672}, {"event_id": "f13a6bd1d8e84c05b098b216500b4d9b", "step": 14, "value": 0.9873585761268534, "stage": "improve", "created_at": 1788684642.4287329}, {"event_id": "f0c4af54d1d342b4a7ed2f2c05970c65", "step": 15, "value": 0.9896525500737109, "stage": "improve", "created_at": 1788687664.8332002}, {"event_id": "09a18be379b54350bdfb4530471f41f2", "step": 18, "value": 0.9937441481541724, "stage": "improve", "created_at": 1788692029.4107335}], "maximize": true, "elapsed_seconds": 28768.330781698227, "node_count": 19, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.bo.tabular-playground-series-may-2022.yaml", "note": ""}, {"id": "xixian.bo.text-normalization-challenge-english-language", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "bo", "dataset": "text-normalization-challenge-english-language", "status": "archived", "official_score": 0.99435, "medal": "silver", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.99724, "silver": 0.99135, "bronze": 0.99038}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:42", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-four-methods-muse13/runs/bo/20_text-normalization-challenge-english-language/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-four-methods-muse13/runs/bo/20_text-normalization-challenge-english-language/logs/journal.json", "metrics": [{"event_id": "f22e870be33444de98aa47bd9c865ca9", "step": 3, "value": 0.9254268097687962, "stage": "debug", "created_at": 1788671390.2328453}, {"event_id": "48c68f518c7b474abd0c8485aca9c9ff", "step": 4, "value": 0.9291565670167878, "stage": "debug", "created_at": 1788671410.4706755}, {"event_id": "4f66d905b82f4b398f3e18a96ea79fdd", "step": 5, "value": 0.9837571293440723, "stage": "draft", "created_at": 1788671092.7401743}, {"event_id": "4d8d69ae15f441ff8293d424514b1488", "step": 14, "value": 0.9855752783152464, "stage": "debug", "created_at": 1788682385.5518174}, {"event_id": "ac3c98630c9444eabf3cf7e2f8a4620c", "step": 15, "value": 0.9880669192837913, "stage": "debug", "created_at": 1788682083.5417852}, {"event_id": "118b7efc2e8c419b92cb735a324c3126", "step": 16, "value": 0.9765351467815783, "stage": "improve", "created_at": 1788683249.502349}, {"event_id": "ff622dd1926b44eab616a2ba631a8995", "step": 17, "value": 0.978944534496974, "stage": "debug", "created_at": 1788682582.8601265}, {"event_id": "7642beeed1a04b1f89328ecdcb5d4133", "step": 19, "value": 0.9515375250363273, "stage": "improve", "created_at": 1788685834.4037156}, {"event_id": "43db8207cbe649669e8799cad686835c", "step": 20, "value": 0.023722955381991203, "stage": "debug", "created_at": 1788687138.9015226}, {"event_id": "c12bf67b10ac479185463d31a0b079ce", "step": 21, "value": 0.942886316840682, "stage": "improve", "created_at": 1788687803.1115687}, {"event_id": "caa3edb3552848dbab445b4ed90f9143", "step": 22, "value": 0.9890799997761148, "stage": "improve", "created_at": 1788685173.724505}, {"event_id": "86e0f42df51548a4a90a39a4df29cd60", "step": 23, "value": 0.9870839292223998, "stage": "improve", "created_at": 1788690654.867261}, {"event_id": "31b72f87f9c94cabb4d00d7248719044", "step": 24, "value": 0.9900900143013376, "stage": "improve", "created_at": 1788691931.1900942}, {"event_id": "37a63e185e424fe88d4909eae051505f", "step": 25, "value": 0.9921528240318365, "stage": "improve", "created_at": 1788690283.3423536}, {"event_id": "38ee3613136345a79b49ed8738b1e59d", "step": 26, "value": 0.9820686405931875, "stage": "improve", "created_at": 1788690425.7409055}, {"event_id": "fe604370fa614df58d121888b0f41094", "step": 27, "value": 0.9857763264206841, "stage": "improve", "created_at": 1788693237.4713006}, {"event_id": "1d0350e474e44b7496b25afa61804297", "step": 28, "value": 0.93285416105575, "stage": "improve", "created_at": 1788696090.153499}, {"event_id": "cbdbd6b7e44e4f54a498bddbf869200a", "step": 30, "value": 0.9874008608385619, "stage": "improve", "created_at": 1788696597.033807}], "maximize": true, "elapsed_seconds": 28770.17403960228, "node_count": 31, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.bo.text-normalization-challenge-english-language.yaml", "note": ""}, {"id": "xixian.bo.text-normalization-challenge-russian-language", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "bo", "dataset": "text-normalization-challenge-russian-language", "status": "archived", "official_score": 0.92867, "medal": "none", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.99012, "silver": 0.98232, "bronze": 0.97592}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:43", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-four-methods-muse13/runs/bo/21_text-normalization-challenge-russian-language/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-four-methods-muse13/runs/bo/21_text-normalization-challenge-russian-language/logs/journal.json", "metrics": [{"event_id": "392c6b42601342a5b00da0df1fd03b85", "step": 3, "value": 0.34788464301106165, "stage": "draft", "created_at": 1788671345.585388}, {"event_id": "5045d4bc82f24c3fb4600a9e2e3ec099", "step": 4, "value": 0.8712, "stage": "debug", "created_at": 1788671427.442456}, {"event_id": "b5107ff0cc564a949959a4c07b1ff5f5", "step": 5, "value": 0.869648757362448, "stage": "improve", "created_at": 1788672625.8276432}, {"event_id": "769a2f4dd9d74a57b6d8cd4a7162955c", "step": 12, "value": 0.7261, "stage": "improve", "created_at": 1788685588.6148853}, {"event_id": "186f863d2edc46ccaadbce5e02f1e41b", "step": 13, "value": 0.9037, "stage": "improve", "created_at": 1788687451.216214}, {"event_id": "9de78c37dc824d9e935a4b43b505c640", "step": 15, "value": 0.9159970094161565, "stage": "debug", "created_at": 1788682063.256493}, {"event_id": "54eb8e9e95ee45c79308affc25f19b8f", "step": 16, "value": 0.9251, "stage": "improve", "created_at": 1788690011.7373662}], "maximize": true, "elapsed_seconds": 28768.005497455597, "node_count": 17, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.bo.text-normalization-challenge-russian-language.yaml", "note": ""}, {"id": "xixian.bo.the-icml-2013-whale-challenge-right-whale-redux", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "bo", "dataset": "the-icml-2013-whale-challenge-right-whale-redux", "status": "archived", "official_score": 0.9887, "medal": "silver", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.98961, "silver": 0.95017, "bronze": 0.90521}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:44", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-four-methods-muse13/runs/bo/22_the-icml-2013-whale-challenge-right-whale-redux/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-four-methods-muse13/runs/bo/22_the-icml-2013-whale-challenge-right-whale-redux/logs/journal.json", "metrics": [{"event_id": "9370b02952c446b58d0626804fecfdae", "step": 3, "value": 0.811136360332773, "stage": "debug", "created_at": 1788672913.216935}, {"event_id": "a5452bcedc2d4df0999de5b65f8eac70", "step": 5, "value": 0.775152891402946, "stage": "improve", "created_at": 1788673377.507206}, {"event_id": "8dc771b559974594ba734b4126462831", "step": 7, "value": 0.8042793295110544, "stage": "improve", "created_at": 1788673892.6602428}, {"event_id": "cb16526d5b854785b2a2b3f67386f057", "step": 8, "value": 0.8037731215256931, "stage": "improve", "created_at": 1788674447.6042438}, {"event_id": "24fb1f9ca10b4a0d8fcac2be211617db", "step": 13, "value": 0.8286237343760346, "stage": "evolution", "created_at": 1788681869.5610113}, {"event_id": "9f381b675c444e84b4846cef7603fce9", "step": 14, "value": 0.7966455143869419, "stage": "draft", "created_at": 1788681957.0770824}, {"event_id": "b3b1f60b052f4af094814b9849c8d3e7", "step": 15, "value": 0.7720286978767406, "stage": "improve", "created_at": 1788682391.632471}, {"event_id": "a8f5bfd6a9834759a3d2062484073d48", "step": 16, "value": 0.7726526849897024, "stage": "improve", "created_at": 1788682436.875874}, {"event_id": "e9b71e4faf6948b9a80e05e522c4297a", "step": 18, "value": 0.9697610348862608, "stage": "improve", "created_at": 1788683060.8815064}, {"event_id": "4c77c19fff914e9d9786287ec4dfabb1", "step": 20, "value": 0.495763328410249, "stage": "debug", "created_at": 1788683320.2583182}, {"event_id": "fbe91310f32d4831a234d5e68cfd4f30", "step": 22, "value": 0.8332090449084251, "stage": "improve", "created_at": 1788683683.624175}, {"event_id": "cb0817280cd3492e9d227feb828fda9f", "step": 23, "value": 0.9368076683241884, "stage": "improve", "created_at": 1788684508.2955797}, {"event_id": "88f3a4429825460bbae4be3f988b1e89", "step": 24, "value": 0.8926759295435618, "stage": "debug", "created_at": 1788683623.4217947}, {"event_id": "f2377a1c837848669c1ec87b0b0d22fe", "step": 25, "value": 0.8414279381879085, "stage": "debug", "created_at": 1788683908.8368144}, {"event_id": "c9e2b8b32ecf4726a060a4dfc855be22", "step": 26, "value": 0.9110922488315446, "stage": "improve", "created_at": 1788686210.9451432}, {"event_id": "8d635c34d267434893c10a868530e44b", "step": 27, "value": 0.8935583553364712, "stage": "improve", "created_at": 1788686348.696269}, {"event_id": "9bc84ab9955b4a7f995882b73849fe00", "step": 29, "value": 0.8132616214326787, "stage": "improve", "created_at": 1788685690.726601}, {"event_id": "ff7e69e6dbf84cd4bd0149afbd0c2671", "step": 32, "value": 0.968076277022577, "stage": "debug", "created_at": 1788689909.7699149}, {"event_id": "bbc36f28abf64b01a6a9aa15f18abbe7", "step": 33, "value": 0.9292290354009356, "stage": "improve", "created_at": 1788691208.1090772}, {"event_id": "6bfcbdecb85842e99fa9b4f6ad4bb92a", "step": 34, "value": 0.8965368482755721, "stage": "improve", "created_at": 1788689948.0200436}, {"event_id": "8aa57e3ef4e0406da52195aa03a91c21", "step": 35, "value": 0.9748517974901587, "stage": "improve", "created_at": 1788691909.689995}, {"event_id": "fc4575b00b0a4eea86e7ea6fe4299e6a", "step": 36, "value": 0.9778291376017978, "stage": "improve", "created_at": 1788690819.641648}, {"event_id": "e067c93ab91e4553808c185bd5a89dc8", "step": 37, "value": 0.980493634437439, "stage": "improve", "created_at": 1788692667.182381}, {"event_id": "d776a0f366ca4ff59a7b41d04ac3093d", "step": 38, "value": 0.9746041723225363, "stage": "improve", "created_at": 1788692721.97033}, {"event_id": "5dc9b7312c52407694e7c9b73c51c776", "step": 40, "value": 0.9573909473685138, "stage": "improve", "created_at": 1788693464.888814}, {"event_id": "c76faa661c86463c8d883ba3476c012d", "step": 41, "value": 0.957712129801457, "stage": "fusion_draft", "created_at": 1788693582.462684}, {"event_id": "e37e47f856c24e199c2f517bb4ff0373", "step": 42, "value": 0.9751289048870775, "stage": "improve", "created_at": 1788694252.031113}, {"event_id": "c41733efcff046798ab97c32893362df", "step": 43, "value": 0.9863452072215221, "stage": "improve", "created_at": 1788694487.4986575}, {"event_id": "9597e243574941369ef0d08fc799be5a", "step": 44, "value": 0.9839280555265575, "stage": "improve", "created_at": 1788693598.837152}], "maximize": true, "elapsed_seconds": 28020.631314516068, "node_count": 45, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.bo.the-icml-2013-whale-challenge-right-whale-redux.yaml", "note": ""}, {"id": "xixian.bnvs.aerial-cactus-identification", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "bnvs", "dataset": "aerial-cactus-identification", "status": "archived", "official_score": 0.99999, "medal": "none", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 1.0, "silver": 1.0, "bronze": 1.0}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:45", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-four-methods-muse13/runs/bnvs/01_aerial-cactus-identification/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-four-methods-muse13/runs/bnvs/01_aerial-cactus-identification/logs/journal.json", "metrics": [{"event_id": "a29769785e4b4d47baa52684cf631b80", "step": 3, "value": 0.9964291606759846, "stage": "debug", "created_at": 1788671306.9094822}, {"event_id": "dc4b1f0065584ac594086e4c0d391d6a", "step": 4, "value": 0.999751337591628, "stage": "draft", "created_at": 1788670763.056687}, {"event_id": "f9b5ea219fcf401296854b0c31c9ed98", "step": 6, "value": 0.9999776365874844, "stage": "debug", "created_at": 1788671283.4569519}, {"event_id": "ddc97c50f3344d68bd6ffb156d11f373", "step": 7, "value": 0.999979965587951, "stage": "improve", "created_at": 1788671679.8738334}, {"event_id": "e415491a4b45476abe454a5349727b16", "step": 8, "value": 0.9975074834421477, "stage": "debug", "created_at": 1788671832.4953651}, {"event_id": "2763ad9686ef43b4b5a245fa2232ca1b", "step": 9, "value": 0.9952011690668678, "stage": "improve", "created_at": 1788672080.133684}, {"event_id": "e0efcf3e54fc4f8c8d6f7aecc38087e5", "step": 11, "value": 0.9999976430103472, "stage": "debug", "created_at": 1788672662.725187}, {"event_id": "40de4bcb350d46efb534137c8f814168", "step": 12, "value": 0.999994107525868, "stage": "improve", "created_at": 1788672634.816118}, {"event_id": "3bb7d4deeb2e4237856ba3e3d8c7ca02", "step": 13, "value": 0.9999611096707285, "stage": "improve", "created_at": 1788672605.8240914}, {"event_id": "d66b1c1bea4142d38a3e487c1e612fdb", "step": 19, "value": 0.9999964645155208, "stage": "debug", "created_at": 1788682148.5951846}, {"event_id": "133165c8a7304370894476575f74bcb0", "step": 21, "value": 0.9999927050896404, "stage": "improve", "created_at": 1788681966.9695632}, {"event_id": "388860e6973d4c68aa19641bc4528cee", "step": 22, "value": 0.9999976430103471, "stage": "improve", "created_at": 1788684238.2529588}, {"event_id": "19e6569e56de45d1ad8c016ccdadae0d", "step": 23, "value": 0.9999905720413887, "stage": "fusion", "created_at": 1788685276.8862307}, {"event_id": "019449fdb08b4ff593b44c9f6aac7e4a", "step": 24, "value": 0.9984867040045821, "stage": "improve", "created_at": 1788683440.023772}, {"event_id": "79b42b85de6944d5937986ef5e1487a7", "step": 25, "value": 1.0, "stage": "improve", "created_at": 1788685855.581877}, {"event_id": "7c9cff06b72a4461a034dcf6ee8ae13d", "step": 26, "value": 0.9949312937516205, "stage": "improve", "created_at": 1788686752.609865}, {"event_id": "8e88a95b930c4b09bcd9cf291d2e1a0e", "step": 27, "value": 0.9999918297003973, "stage": "evolution", "created_at": 1788686020.4507153}, {"event_id": "b1e469797ac94f08832532b76acf2849", "step": 28, "value": 0.9998768708136259, "stage": "evolution", "created_at": 1788687390.8019714}, {"event_id": "66fdb1102bc04986b5f3663cbcddc4be", "step": 29, "value": 0.9978878236653806, "stage": "evolution", "created_at": 1788688029.198491}, {"event_id": "d7437b3a8fdc46d38c1e91ba822b5771", "step": 30, "value": 0.9999836812892567, "stage": "evolution", "created_at": 1788689266.523983}, {"event_id": "29ea03c2203e43b2a0971cfc158d10a4", "step": 31, "value": 0.9999788136091958, "stage": "improve", "created_at": 1788689705.6957629}, {"event_id": "814a150d5598461a9b1e6d275e1da4c6", "step": 32, "value": 0.9999976921556317, "stage": "evolution", "created_at": 1788691183.10983}, {"event_id": "0bafc3a126cc4f81b2b0e3855c3452d6", "step": 33, "value": 0.9999787870931247, "stage": "debug", "created_at": 1788682066.8876452}, {"event_id": "bdc72d3bcc574fe3a111d3e5e0f6dbde", "step": 34, "value": 0.9999976430103471, "stage": "fusion_draft", "created_at": 1788694116.581397}, {"event_id": "f9e5e0af88c34282a99c3d9eaf15f254", "step": 36, "value": 0.9999893935465624, "stage": "improve", "created_at": 1788693571.5424633}, {"event_id": "2a2da4478a9d48a4a9ad8374c449e4f1", "step": 37, "value": 0.9999929290310415, "stage": "debug", "created_at": 1788694778.5871725}, {"event_id": "d6613f29c4e441da9f839d554a8a8206", "step": 40, "value": 0.9998285800469623, "stage": "fusion", "created_at": 1788691560.931086}], "maximize": true, "elapsed_seconds": 28708.88761615753, "node_count": 41, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.bnvs.aerial-cactus-identification.yaml", "note": ""}, {"id": "xixian.bnvs.aptos2019-blindness-detection", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "bnvs", "dataset": "aptos2019-blindness-detection", "status": "archived", "official_score": 0.91396, "medal": "none", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.930508, "silver": 0.919654, "bronze": 0.914492}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:46", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-four-methods-muse13/runs/bnvs/02_aptos2019-blindness-detection/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-four-methods-muse13/runs/bnvs/02_aptos2019-blindness-detection/logs/journal.json", "metrics": [{"event_id": "10b449a7c17740be92e38c25ce678c77", "step": 3, "value": 0.9388450108661951, "stage": "debug", "created_at": 1788671295.1467245}, {"event_id": "40f803471f6b41ef94731bcde1dd6355", "step": 4, "value": 0.9044377776646031, "stage": "draft", "created_at": 1788670860.9964006}, {"event_id": "ef9906ea79b146659ecbee49ac6c6874", "step": 5, "value": 0.8716159787530928, "stage": "debug", "created_at": 1788671476.9043088}, {"event_id": "2741358611fe4749a7e47bd8ab6ab2c1", "step": 7, "value": 0.9132864327731839, "stage": "debug", "created_at": 1788672421.643568}, {"event_id": "22baf524be4f48e9890eae086699f090", "step": 9, "value": 0.927817858217502, "stage": "improve", "created_at": 1788671771.0796688}, {"event_id": "5d27579eaa8a4d5bbac1b5f52aa69065", "step": 11, "value": 0.924944690667904, "stage": "improve", "created_at": 1788672009.3257794}, {"event_id": "8ab9885137694db4811d0029129f7a34", "step": 13, "value": 0.9072512647554806, "stage": "debug", "created_at": 1788673515.2894137}, {"event_id": "6d3c2e5715cb4c5ca23b9c5e5735adb3", "step": 14, "value": 0.9301716776540643, "stage": "debug", "created_at": 1788673827.5783088}, {"event_id": "072480413bea49c89283b09b9acc17ae", "step": 15, "value": 0.905956055950792, "stage": "debug", "created_at": 1788674196.1742203}, {"event_id": "f2db098b84d54054913bdd8781bea649", "step": 17, "value": 0.9218729189017509, "stage": "evolution", "created_at": 1788674384.5597498}, {"event_id": "bcd39ffc2a044f4b91c453772caa0ac3", "step": 23, "value": 0.8582827452759675, "stage": "debug", "created_at": 1788682373.283706}, {"event_id": "18a3a398a07d4d8cb47ebe7b6948c006", "step": 24, "value": 0.060555960320573754, "stage": "improve", "created_at": 1788681800.0227795}, {"event_id": "f951574a986c4063b26cc6a4fb0e0707", "step": 25, "value": 0.9134322431755045, "stage": "evolution", "created_at": 1788682978.1990788}, {"event_id": "21349a1a2e77430eab8635468e33466e", "step": 27, "value": 0.8960233491426487, "stage": "improve", "created_at": 1788683066.380394}, {"event_id": "8e496b399d3f4567ab71b5e2aedfe362", "step": 31, "value": 0.9258132044587541, "stage": "evolution", "created_at": 1788683499.492353}, {"event_id": "419fa29ab4df4bdf9829e5b2b3103d85", "step": 32, "value": 0.9143249910035326, "stage": "improve", "created_at": 1788684923.8788743}, {"event_id": "b0f9f80245a64def9d5ecbb11a32f82d", "step": 34, "value": 0.9203050759881833, "stage": "debug", "created_at": 1788683468.6441581}, {"event_id": "de9ed2422ca14361b6c4f43d11614c40", "step": 35, "value": 0.9264780281322973, "stage": "evolution", "created_at": 1788685260.590111}, {"event_id": "ffa3f040a57446d88dda36b4797be59e", "step": 36, "value": 0.9215809793489718, "stage": "debug", "created_at": 1788686320.4540548}, {"event_id": "d3b65d9b75c44e2ca40f0e8fb3995fe4", "step": 37, "value": 0.9179474394062576, "stage": "evolution", "created_at": 1788687965.5124035}, {"event_id": "04a12327955d49e4b6f653145a570b64", "step": 38, "value": 0.9200700775442264, "stage": "improve", "created_at": 1788690065.4910858}, {"event_id": "7ba5d2dac6334392b882339179f12ef5", "step": 39, "value": 0.9205294847928154, "stage": "improve", "created_at": 1788687256.0045586}, {"event_id": "7ae1dada075743279705c9c9384eacc2", "step": 41, "value": 0.9364974752465846, "stage": "evolution", "created_at": 1788691355.125212}, {"event_id": "7d467700a7ee424bab50bfeb77e08da2", "step": 43, "value": 0.9203916212645299, "stage": "improve", "created_at": 1788688061.4042022}, {"event_id": "84488294466b46f8b6cd9c0c2a82a7af", "step": 44, "value": 0.8715178812006991, "stage": "debug", "created_at": 1788691641.681385}, {"event_id": "e283f705ef4c4696819e13a895725a59", "step": 46, "value": 0.9321845041636312, "stage": "evolution", "created_at": 1788692118.5300782}, {"event_id": "5305459a64bb4b16a650d2ed1a298e7b", "step": 49, "value": 0.910013131090198, "stage": "evolution", "created_at": 1788692661.8618324}, {"event_id": "5ce05fa6cddc487eaf91048391f81e40", "step": 51, "value": 0.9371403135035452, "stage": "evolution", "created_at": 1788693244.2790105}, {"event_id": "b08ba2ef995846e3be321bafd955f6b2", "step": 53, "value": 0.944090236153001, "stage": "evolution", "created_at": 1788693623.3816967}, {"event_id": "7946f0a81aba487485784ed56897afc8", "step": 54, "value": 0.9417785563909127, "stage": "improve", "created_at": 1788694100.8032084}, {"event_id": "3e738928afaf4ad19c4c90cf222a2fdd", "step": 55, "value": 0.901, "stage": "debug", "created_at": 1788692807.581971}, {"event_id": "3b6b2be474564fb7b6cd743b51c603bd", "step": 56, "value": 0.0296, "stage": "debug", "created_at": 1788693958.9386797}, {"event_id": "ea43fd42bdd9400c8e2fc7a5bf71018c", "step": 57, "value": 0.927771347804652, "stage": "improve", "created_at": 1788694591.4209974}, {"event_id": "265692f6aab8427cb7e7a156fa05401b", "step": 59, "value": 0.9253843920769389, "stage": "improve", "created_at": 1788696813.2234552}], "maximize": true, "elapsed_seconds": 28759.069001436234, "node_count": 60, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.bnvs.aptos2019-blindness-detection.yaml", "note": ""}, {"id": "xixian.bnvs.denoising-dirty-documents", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "bnvs", "dataset": "denoising-dirty-documents", "status": "archived", "official_score": 0.01328, "medal": "gold", "valid_submission": true, "score_maximize": false, "thresholds": {"gold": 0.01794, "silver": 0.02609, "bronze": 0.04517}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:47", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-four-methods-muse13/runs/bnvs/03_denoising-dirty-documents/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-four-methods-muse13/runs/bnvs/03_denoising-dirty-documents/logs/journal.json", "metrics": [{"event_id": "2102e13a1ee14eafa7ab7efec5ee3875", "step": 4, "value": 0.07773481712706501, "stage": "draft", "created_at": 1788670693.9596536}, {"event_id": "d910be565d4d4c4d882e32bac98bea99", "step": 5, "value": 0.018153239045181527, "stage": "draft", "created_at": 1788671107.5055778}, {"event_id": "c05392fe5a3547cc84919c5f17064362", "step": 7, "value": 0.026832911350450368, "stage": "debug", "created_at": 1788671374.9704854}, {"event_id": "fd5a1081db9844f8815538dda370f87f", "step": 10, "value": 0.06295046918647466, "stage": "debug", "created_at": 1788671716.5760958}, {"event_id": "a60814c9672c40b388668429b885d18a", "step": 11, "value": 0.019438437985239414, "stage": "improve", "created_at": 1788671652.0402517}, {"event_id": "12ce3b403b414548872cdef8d145e3ec", "step": 12, "value": 0.01949639551900032, "stage": "debug", "created_at": 1788671987.287146}, {"event_id": "c5b31efd092f4e99aced8a188599c70a", "step": 13, "value": 0.032500612532268575, "stage": "improve", "created_at": 1788672198.773132}, {"event_id": "07f8df0f4deb46e3b776d3381ea3dd53", "step": 14, "value": 0.018192590834113592, "stage": "improve", "created_at": 1788672205.2887766}, {"event_id": "161e62f3012e49c4b3200c5dcdfbc83e", "step": 15, "value": 0.02914584907915313, "stage": "improve", "created_at": 1788672499.2596695}, {"event_id": "ee1ac872ba724a498e5453a9c7f0bf59", "step": 16, "value": 0.01822506793110232, "stage": "improve", "created_at": 1788672620.5452797}, {"event_id": "46051210ba5944d19038484a23654205", "step": 17, "value": 0.028272647904109896, "stage": "improve", "created_at": 1788673057.347097}, {"event_id": "ddfd452cc4d742b384a7b7de00df3374", "step": 18, "value": 0.016412183392429794, "stage": "improve", "created_at": 1788672840.030429}, {"event_id": "7eccbb23ac3e43419fc046d2b3bb4bb9", "step": 19, "value": 0.020435330395817634, "stage": "evolution", "created_at": 1788673398.9173064}, {"event_id": "785ff164765c4d5f9e195d030642ebde", "step": 20, "value": 0.014324748487626287, "stage": "improve", "created_at": 1788673718.1324232}, {"event_id": "10a568a2acef4dfcae7b3137e942c3d3", "step": 21, "value": 0.1966296350725271, "stage": "draft", "created_at": 1788674323.5197845}, {"event_id": "9bbea410fe514166ab348cd4f1a8cc89", "step": 22, "value": 0.037576321951687836, "stage": "evolution", "created_at": 1788673282.5925963}, {"event_id": "897b77f3a9ca442a85c6a96600670902", "step": 26, "value": 0.025525480360536566, "stage": "draft", "created_at": 1788682062.874447}, {"event_id": "9bb22df18de44f7da447b37d6406f02c", "step": 27, "value": 0.01917098069686098, "stage": "debug", "created_at": 1788682168.799611}, {"event_id": "332689dfcf054792aab6d5a24a766044", "step": 28, "value": 0.024287357348604266, "stage": "evolution", "created_at": 1788681804.2483315}, {"event_id": "ba19893cd4424728b97ea3f232f09686", "step": 30, "value": 0.021323730106559392, "stage": "improve", "created_at": 1788683430.689752}, {"event_id": "3e7054391da146b084acb0635516f384", "step": 31, "value": 0.025598205117713636, "stage": "debug", "created_at": 1788684689.6366167}, {"event_id": "84f64bf5da7c44f99f2b011671a116b1", "step": 32, "value": 0.014048981640502878, "stage": "improve", "created_at": 1788684995.7409315}, {"event_id": "d2e21d0f82a84edfa557c9133d605a76", "step": 34, "value": 0.02824114371904454, "stage": "improve", "created_at": 1788684112.0217693}, {"event_id": "b680c19271364665bc93ef67145cb414", "step": 35, "value": 0.014278935283924432, "stage": "improve", "created_at": 1788686286.9576006}, {"event_id": "ffb12e8207554e739fe5242aa3d2d8ca", "step": 36, "value": 0.013987921730165867, "stage": "debug", "created_at": 1788686436.875701}, {"event_id": "1d1843ffeb3f4db787baf48d4b3c99d8", "step": 37, "value": 0.014006566091026377, "stage": "improve", "created_at": 1788686731.035773}, {"event_id": "301cd278483a43bbba1869e17ab0ed2f", "step": 39, "value": 0.014041090891981588, "stage": "improve", "created_at": 1788687310.8043063}, {"event_id": "b3da3b65224e4dabbb19b0155ffa2505", "step": 40, "value": 0.03943913088182068, "stage": "improve", "created_at": 1788687662.676966}, {"event_id": "f74f000d342947fba1c4f46cef852791", "step": 41, "value": 0.014045807508882784, "stage": "debug", "created_at": 1788687934.825099}, {"event_id": "e35e0cfa74134d48be4c16d3d4b61d32", "step": 42, "value": 0.017306689949863032, "stage": "improve", "created_at": 1788688361.6447127}, {"event_id": "c1673a95d2c8444999f78dd776092933", "step": 45, "value": 0.01653568578580252, "stage": "evolution", "created_at": 1788688986.2022228}, {"event_id": "fa530b085de24eb686570355820143a1", "step": 46, "value": 0.013513327320715909, "stage": "evolution", "created_at": 1788688841.8752034}, {"event_id": "44b75efc0b3e4d1a96262be203efb3b7", "step": 48, "value": 0.013726296273896859, "stage": "evolution", "created_at": 1788690882.6984255}, {"event_id": "7153d035be5a4a90aaf43e692b37068c", "step": 51, "value": 0.11998412263148651, "stage": "debug", "created_at": 1788693363.3493228}, {"event_id": "d67e319737f54cf395f65a54e6e7a0c4", "step": 52, "value": 0.013573187877583959, "stage": "debug", "created_at": 1788691433.6248786}, {"event_id": "03df9b233c714cd4bf58aa07c6e725c2", "step": 53, "value": 0.02379, "stage": "fusion_draft", "created_at": 1788694327.1582851}], "maximize": false, "elapsed_seconds": 28775.324388742447, "node_count": 56, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.bnvs.denoising-dirty-documents.yaml", "note": ""}, {"id": "xixian.bnvs.detecting-insults-in-social-commentary", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "bnvs", "dataset": "detecting-insults-in-social-commentary", "status": "archived", "official_score": 0.95675, "medal": "gold", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.83321, "silver": 0.82307, "bronze": 0.79111}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:48", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-four-methods-muse13/runs/bnvs/04_detecting-insults-in-social-commentary/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-four-methods-muse13/runs/bnvs/04_detecting-insults-in-social-commentary/logs/journal.json", "metrics": [{"event_id": "a5ea78adca5f44fbba17702a69bc64f4", "step": 2, "value": 0.9461409713888713, "stage": "draft", "created_at": 1788670885.8351557}, {"event_id": "09bbcc4950c547a9af6eb1e0f7afde42", "step": 3, "value": 0.9625345555070566, "stage": "draft", "created_at": 1788670728.8234987}, {"event_id": "a1339fe91153465480be62be154022b7", "step": 4, "value": 0.9506860521802288, "stage": "improve", "created_at": 1788671433.9932778}, {"event_id": "a295d6707da24b43b8e27352310ade7e", "step": 5, "value": 0.9416575348025488, "stage": "debug", "created_at": 1788671198.8570173}, {"event_id": "4ef2f424a6a94a5ab7a2018268ded752", "step": 6, "value": 0.962621853630147, "stage": "improve", "created_at": 1788671420.0126975}, {"event_id": "ed9d7f728ac74821881224d9bc3cfc7e", "step": 7, "value": 0.9495117108475586, "stage": "improve", "created_at": 1788672245.5282195}, {"event_id": "f4a8579fb0664fcba27ae12b2aad5091", "step": 8, "value": 0.9492106010795892, "stage": "improve", "created_at": 1788674078.1813424}, {"event_id": "15eafdba89f94d4886a1a6522b43324f", "step": 13, "value": 0.8498213860442962, "stage": "draft", "created_at": 1788681985.7061362}, {"event_id": "82719a6d7578497c91cc7857c40e4c96", "step": 14, "value": 0.9492829058228796, "stage": "debug", "created_at": 1788682086.8358872}, {"event_id": "cf1d4c9d7e9d43abbe70b596f15b94b3", "step": 15, "value": 0.9632984140840972, "stage": "improve", "created_at": 1788682237.4686549}, {"event_id": "e09ffb831f3d4896b130543199254dcc", "step": 17, "value": 0.9474120507800164, "stage": "debug", "created_at": 1788683277.8012164}, {"event_id": "947e3d433eba47ca9c74c1b8af949de6", "step": 18, "value": 0.906794703913866, "stage": "improve", "created_at": 1788681834.0262682}, {"event_id": "224e59408d674179956519035b8892b1", "step": 19, "value": 0.9569765750036374, "stage": "improve", "created_at": 1788682368.818493}, {"event_id": "163ec23cb01c4f509d119dba2fa07634", "step": 20, "value": 0.9607303942965227, "stage": "improve", "created_at": 1788683646.4058673}, {"event_id": "2350bb81f55a4d2a855cf76fbed16368", "step": 21, "value": 0.9593481740142586, "stage": "improve", "created_at": 1788684773.888648}], "maximize": true, "elapsed_seconds": 28770.630490779877, "node_count": 22, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.bnvs.detecting-insults-in-social-commentary.yaml", "note": ""}, {"id": "xixian.bnvs.dog-breed-identification", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "bnvs", "dataset": "dog-breed-identification", "status": "archived", "official_score": 0.27628, "medal": "none", "valid_submission": true, "score_maximize": false, "thresholds": {"gold": 0.0005, "silver": 0.00539, "bronze": 0.04598}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:49", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-four-methods-muse13/runs/bnvs/05_dog-breed-identification/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-four-methods-muse13/runs/bnvs/05_dog-breed-identification/logs/journal.json", "metrics": [{"event_id": "b7ba49f5adb847638161e19dbc0c1732", "step": 4, "value": 0.5403768052141025, "stage": "debug", "created_at": 1788671608.5212371}, {"event_id": "0b78805425b3488e82787d9179a8ce9f", "step": 7, "value": 0.6399986653100127, "stage": "debug", "created_at": 1788671965.3352828}, {"event_id": "0098110f686844a0857171acf9f75073", "step": 8, "value": 0.5022123945390016, "stage": "improve", "created_at": 1788672856.7469602}, {"event_id": "e500bb1b1d6b4d2b9b31f374b91ae7de", "step": 9, "value": 0.552112151030722, "stage": "debug", "created_at": 1788672370.0490346}, {"event_id": "7b4da386cb58491cb94153a701a000b7", "step": 10, "value": 0.5239266205804962, "stage": "debug", "created_at": 1788672558.7874494}, {"event_id": "42844b9609db4e5798d691a0818b6544", "step": 11, "value": 0.5718332426653463, "stage": "improve", "created_at": 1788673365.1485894}, {"event_id": "6cc9f35e21084ff8b6c496154fa1cc9e", "step": 13, "value": 4.7888771596520145, "stage": "improve", "created_at": 1788673462.1477857}, {"event_id": "162320a131a94fc585f50cfb313d67f6", "step": 14, "value": 0.9252121176902972, "stage": "debug", "created_at": 1788674187.495689}, {"event_id": "1f2e70274af24852bccd8d91f2da5414", "step": 19, "value": 0.26813341402696783, "stage": "draft", "created_at": 1788681953.9017117}, {"event_id": "16863cd951644202b7c84f73c5835009", "step": 20, "value": 0.3940153921700219, "stage": "draft", "created_at": 1788681978.774567}, {"event_id": "e2a1515ed9fc49e69dce6ebcc9f8f800", "step": 23, "value": 0.2550204936480498, "stage": "improve", "created_at": 1788683226.3340185}, {"event_id": "610d914224564db5b3ce6361d31e107f", "step": 24, "value": 0.44135136143354264, "stage": "improve", "created_at": 1788683407.9241185}, {"event_id": "af740b298bd8482eb090480346a7dc8f", "step": 28, "value": 0.31573954786330577, "stage": "debug", "created_at": 1788687203.5525575}, {"event_id": "690df455cbcd42c4849d9f3138aaa679", "step": 29, "value": 0.25025639733648514, "stage": "improve", "created_at": 1788684651.109413}, {"event_id": "5a9c9769cc124d24b7f03e595d1236c0", "step": 30, "value": 4.782577427448993, "stage": "improve", "created_at": 1788684546.881048}, {"event_id": "0babc63980a84991bc7cf5e7533cf7c6", "step": 31, "value": 0.2204426253041001, "stage": "improve", "created_at": 1788689066.5496264}, {"event_id": "bac6ff75c9024ea196362fa36a6937e8", "step": 32, "value": 0.27777940198449436, "stage": "evolution", "created_at": 1788692854.0840175}], "maximize": false, "elapsed_seconds": 28775.84938955307, "node_count": 34, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.bnvs.dog-breed-identification.yaml", "note": ""}, {"id": "xixian.bnvs.dogs-vs-cats-redux-kernels-edition", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "bnvs", "dataset": "dogs-vs-cats-redux-kernels-edition", "status": "archived", "official_score": 0.00732, "medal": "gold", "valid_submission": true, "score_maximize": false, "thresholds": {"gold": 0.03882, "silver": 0.05038, "bronze": 0.06127}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:50", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-four-methods-muse13/runs/bnvs/06_dogs-vs-cats-redux-kernels-edition/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-four-methods-muse13/runs/bnvs/06_dogs-vs-cats-redux-kernels-edition/logs/journal.json", "metrics": [{"event_id": "9dc86f1c95ac4288a038b22d3c66c36b", "step": 3, "value": 0.0857993974908426, "stage": "debug", "created_at": 1788671212.686152}, {"event_id": "ccbe65710af74a239b24cd9d01f882da", "step": 4, "value": 0.009160646626219746, "stage": "draft", "created_at": 1788670739.5308347}, {"event_id": "ed744d3349d640839f93658eee0b1002", "step": 5, "value": 0.021157721479949133, "stage": "debug", "created_at": 1788671207.8275685}, {"event_id": "166184f18018468aaa5321d8f9ab10bb", "step": 6, "value": 0.009462469790157423, "stage": "improve", "created_at": 1788671770.1907234}, {"event_id": "215cc993221b4678af10ffd3902be89b", "step": 8, "value": 0.07018619094042289, "stage": "improve", "created_at": 1788671495.598855}, {"event_id": "e9fe609443db45a3baaba52e29006b19", "step": 9, "value": 0.0481611368456521, "stage": "improve", "created_at": 1788672484.2398877}, {"event_id": "5bc9c3a3c7b449dc99f53b8353520536", "step": 10, "value": 0.010525626164843387, "stage": "debug", "created_at": 1788672729.4943597}, {"event_id": "e788b85532d648a58cc44125f494e5f7", "step": 11, "value": 0.010042585054444733, "stage": "improve", "created_at": 1788673460.5275586}, {"event_id": "a4ee2854d827436a959b1fbc401ffbb5", "step": 18, "value": 0.011562923609940833, "stage": "evolution", "created_at": 1788681828.4789808}, {"event_id": "a6d28ac634dc4cb285c62e72080cd3f2", "step": 20, "value": 0.0037792392250677797, "stage": "debug", "created_at": 1788682106.4525898}, {"event_id": "35461be5df804c3f9be36d68c81f3862", "step": 21, "value": 0.010260380859967416, "stage": "debug", "created_at": 1788682351.5480928}, {"event_id": "d372caa9200d45fb8f25ba3af2890258", "step": 23, "value": 0.004609475844505092, "stage": "improve", "created_at": 1788684007.1412463}, {"event_id": "c848c034a0e2423cbe7b8b42b1e66a42", "step": 24, "value": 0.006297566814315325, "stage": "improve", "created_at": 1788683347.921868}, {"event_id": "6c75363eb5204234a1e6ccd3b0aabf52", "step": 27, "value": 0.003960783453529661, "stage": "improve", "created_at": 1788683451.4814312}, {"event_id": "82cff3625bf7473fa4892c8da8f43e3c", "step": 28, "value": 0.008594645360950967, "stage": "debug", "created_at": 1788684984.3200867}, {"event_id": "ede8669f7f4449a887f8753888271616", "step": 29, "value": 0.003965503131378883, "stage": "evolution", "created_at": 1788686282.7753792}, {"event_id": "c3df0152adea43f59d1da8d9e21283dc", "step": 30, "value": 7.650359767029437e-05, "stage": "debug", "created_at": 1788685831.7159443}, {"event_id": "5b058783fff84483970bbef2ef78b489", "step": 31, "value": 0.041755197544590644, "stage": "improve", "created_at": 1788686502.360673}, {"event_id": "a4752bb9b6554902b8441e22411ecc57", "step": 36, "value": 0.008365978790446413, "stage": "improve", "created_at": 1788687826.2962422}, {"event_id": "ebf4bcefee7f4ceaa15efbf1f5c9539d", "step": 37, "value": 0.007718513686075083, "stage": "debug", "created_at": 1788688748.2871866}, {"event_id": "96a1d2ffca75498291f39ace7587df3d", "step": 38, "value": 0.010949705236996225, "stage": "improve", "created_at": 1788693729.3631136}, {"event_id": "073e0239c1174edeaf79d77607802c70", "step": 39, "value": 0.020948374658542282, "stage": "improve", "created_at": 1788695909.0433757}, {"event_id": "d9a5d1e8d790451ab8a7757bba712d07", "step": 40, "value": 0.00886119312579936, "stage": "improve", "created_at": 1788693075.0449128}], "maximize": false, "elapsed_seconds": 28766.966770410538, "node_count": 42, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.bnvs.dogs-vs-cats-redux-kernels-edition.yaml", "note": ""}, {"id": "xixian.bnvs.histopathologic-cancer-detection", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "bnvs", "dataset": "histopathologic-cancer-detection", "status": "archived", "official_score": 0.99659, "medal": "gold", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.9835, "silver": 0.9798, "bronze": 0.9738}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:51", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-four-methods-muse13/runs/bnvs/07_histopathologic-cancer-detection/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-four-methods-muse13/runs/bnvs/07_histopathologic-cancer-detection/logs/journal.json", "metrics": [{"event_id": "eccc1d34db3548d39936836c1a3fe69e", "step": 10, "value": 0.9817201509767575, "stage": "draft", "created_at": 1788681970.7098675}, {"event_id": "d10660e49c55416cb9ce0e9b637c0f6f", "step": 12, "value": 0.9971629548241734, "stage": "debug", "created_at": 1788687046.629681}, {"event_id": "d2776eca9c4c4521931d68587e2e1cfa", "step": 13, "value": 0.991434552558077, "stage": "debug", "created_at": 1788681842.7399743}, {"event_id": "3755a874b986440ca7e5b767ca729d3a", "step": 14, "value": 0.9955543481122837, "stage": "improve", "created_at": 1788684722.3112876}], "maximize": true, "elapsed_seconds": 28770.353021621704, "node_count": 15, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.bnvs.histopathologic-cancer-detection.yaml", "note": ""}, {"id": "xixian.bnvs.jigsaw-toxic-comment-classification-challenge", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "bnvs", "dataset": "jigsaw-toxic-comment-classification-challenge", "status": "archived", "official_score": 0.98435, "medal": "none", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.9874, "silver": 0.98668, "bronze": 0.98639}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:52", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-four-methods-muse13/runs/bnvs/08_jigsaw-toxic-comment-classification-challenge/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-four-methods-muse13/runs/bnvs/08_jigsaw-toxic-comment-classification-challenge/logs/journal.json", "metrics": [{"event_id": "9ce7689c7ead45cc8f174529518d12d5", "step": 3, "value": 0.985003429205427, "stage": "debug", "created_at": 1788671435.3044581}, {"event_id": "7350eaea40ed43c79c7cd4bbb0e99c77", "step": 10, "value": 0.9813925092441905, "stage": "debug", "created_at": 1788682137.1307964}, {"event_id": "5e2c58796bb94826912f0ff1433124ab", "step": 11, "value": 0.9839398143189978, "stage": "improve", "created_at": 1788681880.0747714}, {"event_id": "9693643b1b2d4aaca78131cb5f5a3152", "step": 13, "value": 0.9913306822296142, "stage": "debug", "created_at": 1788682290.9786656}, {"event_id": "078abd4d244a4648ba0378a077dc1c94", "step": 14, "value": 0.9906532280559822, "stage": "improve", "created_at": 1788687072.4854627}, {"event_id": "8b44532c8cd94aa2957a1337ef7ed8ca", "step": 15, "value": 0.988716470963387, "stage": "improve", "created_at": 1788686423.3390543}, {"event_id": "5bf5d51838df425eb2ebe4843c6befb6", "step": 16, "value": 0.9826558628557823, "stage": "improve", "created_at": 1788689458.5990486}, {"event_id": "b1a926b98c3c4e408e82affbb103204a", "step": 17, "value": 0.9653106344187551, "stage": "improve", "created_at": 1788693249.708246}, {"event_id": "cd0ae60924d8466fb36b218528edbccd", "step": 18, "value": 0.9910605273156213, "stage": "improve", "created_at": 1788692688.6338294}], "maximize": true, "elapsed_seconds": 28767.228397130966, "node_count": 19, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.bnvs.jigsaw-toxic-comment-classification-challenge.yaml", "note": ""}, {"id": "xixian.bnvs.leaf-classification", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "bnvs", "dataset": "leaf-classification", "status": "archived", "official_score": 9e-05, "medal": "silver", "valid_submission": true, "score_maximize": false, "thresholds": {"gold": 0.0, "silver": 0.00791, "bronze": 0.01526}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:53", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-four-methods-muse13/runs/bnvs/09_leaf-classification/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-four-methods-muse13/runs/bnvs/09_leaf-classification/logs/journal.json", "metrics": [{"event_id": "73a47c721f2d4063b0f15d9d0df5943b", "step": 2, "value": 0.05424908589275161, "stage": "draft", "created_at": 1788671133.5702367}, {"event_id": "dd7ccbaa80d94d9b9bf81b031675ac86", "step": 5, "value": 0.023547870938949687, "stage": "debug", "created_at": 1788671492.7237628}, {"event_id": "8c7ebbdd4c8740d485fcf5ba61206cd9", "step": 6, "value": 0.014987842676901697, "stage": "debug", "created_at": 1788671270.6517515}, {"event_id": "a7f762862fd14fa6bde6d114d4390c0f", "step": 7, "value": 0.023987033232846802, "stage": "debug", "created_at": 1788671258.9556978}, {"event_id": "45b1c3666ffe4bc49f7960467af562c4", "step": 8, "value": 0.02298277112215896, "stage": "improve", "created_at": 1788671762.176526}, {"event_id": "0cc35bd8c5064aacb9fb55366361e863", "step": 9, "value": 0.022006909622927184, "stage": "improve", "created_at": 1788671705.7660327}, {"event_id": "e1ad1e79310d4bd79db1eab612a5c05d", "step": 12, "value": 0.003128071769303398, "stage": "improve", "created_at": 1788672171.5737193}, {"event_id": "d8e58b3748304da6b2e1994ee914b9cb", "step": 13, "value": 0.00013139737988409388, "stage": "debug", "created_at": 1788672516.1279907}, {"event_id": "273a5dbcf71a414390a4fab4fca378c0", "step": 14, "value": 0.010703514536399918, "stage": "debug", "created_at": 1788672686.8588707}, {"event_id": "511034fdd63a43b59fb1f21a6cb90b2f", "step": 15, "value": 0.01836798115223914, "stage": "improve", "created_at": 1788673356.908803}, {"event_id": "04d32287bf2d401e946100b36ad82466", "step": 16, "value": 0.00011213153357343763, "stage": "improve", "created_at": 1788673422.4582453}, {"event_id": "5a96e1a73ed14f5d9c4802320d4920db", "step": 17, "value": 0.0019398476887376676, "stage": "improve", "created_at": 1788672808.6737769}, {"event_id": "91c9a765d4324b19a9b87aa5f1af64a7", "step": 23, "value": 0.053835379472296906, "stage": "debug", "created_at": 1788682084.290548}, {"event_id": "53b3f24920454a67bf93de1b26211779", "step": 24, "value": 0.053967391118360235, "stage": "debug", "created_at": 1788682117.5929453}, {"event_id": "ef2b38fb9c834bb1b8c043832efbee4f", "step": 25, "value": 2.4979509228125754e-05, "stage": "improve", "created_at": 1788682522.5157273}, {"event_id": "d2ee1f7ede3c437ea246fae099ac81fc", "step": 26, "value": 0.04405426732815407, "stage": "improve", "created_at": 1788682492.3158777}, {"event_id": "02e94276c85e43f184a3c27496247f04", "step": 28, "value": 2.1644747271628767e-05, "stage": "improve", "created_at": 1788683136.1284442}, {"event_id": "431becc8616f463bbd6ca6a2590b0bae", "step": 29, "value": 0.00030279538051992467, "stage": "debug", "created_at": 1788683142.3442976}, {"event_id": "b540e1f8e07043fb8cd5e6934af60cce", "step": 30, "value": 2.174529512387124e-06, "stage": "improve", "created_at": 1788689056.0892901}], "maximize": false, "elapsed_seconds": 28778.411016225815, "node_count": 31, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.bnvs.leaf-classification.yaml", "note": ""}, {"id": "xixian.bnvs.mlsp-2013-birds", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "bnvs", "dataset": "mlsp-2013-birds", "status": "archived", "official_score": 0.86775, "medal": "none", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.93527, "silver": 0.90038, "bronze": 0.87372}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:54", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-four-methods-muse13/runs/bnvs/10_mlsp-2013-birds/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-four-methods-muse13/runs/bnvs/10_mlsp-2013-birds/logs/journal.json", "metrics": [{"event_id": "1207bc8afed04a209122c25710cb8ca4", "step": 4, "value": 0.7764736120630569, "stage": "debug", "created_at": 1788671451.2165284}, {"event_id": "31d0da4e418541cca92424614a203aee", "step": 5, "value": 0.7553618832957676, "stage": "debug", "created_at": 1788671388.5910802}, {"event_id": "9686582258294bbf9c29d254aee0709a", "step": 7, "value": 0.7975582590815627, "stage": "improve", "created_at": 1788671667.9935734}, {"event_id": "b674664378c04390af772b656e5bf867", "step": 8, "value": 0.6007813673929376, "stage": "improve", "created_at": 1788671698.4283655}, {"event_id": "4aac0957a7b640ccb88145be2e4a9c12", "step": 9, "value": 0.8411897779639715, "stage": "debug", "created_at": 1788671651.3201857}, {"event_id": "d8c56393148a4bf58cdc87bfef141655", "step": 10, "value": 0.7959989718985606, "stage": "improve", "created_at": 1788671955.7540278}, {"event_id": "3cca7f3c96af42549db7b43f5acb01a4", "step": 11, "value": 0.752206361131981, "stage": "improve", "created_at": 1788671914.717526}, {"event_id": "0a81c48dcab74d3a9c4b1905ad1f66ee", "step": 12, "value": 0.779026730637423, "stage": "improve", "created_at": 1788672117.9771302}, {"event_id": "b92ce9118bfd457584082c298965ee79", "step": 13, "value": 0.8404692082111437, "stage": "improve", "created_at": 1788672119.9896162}, {"event_id": "5e4a9e577b5945a6b8d90a3403fe5917", "step": 14, "value": 0.8457478005865103, "stage": "improve", "created_at": 1788672160.8209863}, {"event_id": "35a1f29653a641ce8ba95e2add481001", "step": 15, "value": 0.8441055718475073, "stage": "improve", "created_at": 1788672344.2689397}, {"event_id": "11bbe4df10094c69a1944b7dc72ff9f6", "step": 17, "value": 0.7837217272104181, "stage": "improve", "created_at": 1788672726.669145}, {"event_id": "9a1a9a45260a45d2a20964ebd8299e0c", "step": 22, "value": 0.8506912442396313, "stage": "debug", "created_at": 1788673108.029821}, {"event_id": "634863b3b3214778816fa5ee38b2dc82", "step": 23, "value": 0.8647004608294931, "stage": "debug", "created_at": 1788673356.0641885}, {"event_id": "7a94c72a9a0b438a82402d73421daea3", "step": 24, "value": 0.8380393799748638, "stage": "improve", "created_at": 1788673606.0955055}, {"event_id": "af024ed72a1d4efe9f96d1d3e28c2fbc", "step": 25, "value": 0.7803796456214418, "stage": "debug", "created_at": 1788673400.138051}, {"event_id": "b638055eae594541acaa23f7bd7f361e", "step": 27, "value": 0.857260159195643, "stage": "improve", "created_at": 1788673972.7899065}, {"event_id": "215520bf4d0f4f5894f44397b51beb24", "step": 29, "value": 0.8329283619606201, "stage": "debug", "created_at": 1788674461.5254898}, {"event_id": "a4ec09e31f644c49a50dacf70fb85c08", "step": 39, "value": 0.8677167993297025, "stage": "evolution", "created_at": 1788681900.4132988}, {"event_id": "449925f9c1c849a69118dd89023690aa", "step": 40, "value": 0.7526312527118328, "stage": "evolution", "created_at": 1788682363.05533}, {"event_id": "775d422bd1264157aae951caf6005374", "step": 41, "value": 0.7940461945206896, "stage": "evolution", "created_at": 1788682272.0756145}, {"event_id": "edfbfbb531264ec298ca5c59fb391c2a", "step": 43, "value": 0.8608965228320067, "stage": "improve", "created_at": 1788682862.8906767}, {"event_id": "e16fc630256b47599a2ca8251056d9c8", "step": 44, "value": 0.800184331797235, "stage": "improve", "created_at": 1788683340.0844724}, {"event_id": "bddcffd5b6d84824a8d2c426956988a8", "step": 45, "value": 0.8574277335567658, "stage": "debug", "created_at": 1788683557.432746}, {"event_id": "75102b655fa54e04a706df762c3ca333", "step": 47, "value": 0.7714318729170214, "stage": "evolution", "created_at": 1788683818.9942236}, {"event_id": "4ba3a4790c8e40efb86b46e2404b477d", "step": 51, "value": 0.7686589960289177, "stage": "evolution", "created_at": 1788684719.191937}, {"event_id": "cb269072e4a8442d9b0ed330a1603bb9", "step": 52, "value": 0.7479754365764728, "stage": "debug", "created_at": 1788684855.6372983}, {"event_id": "f037a7f4339f4566b6871fd03e634c4b", "step": 53, "value": 0.7821660544432822, "stage": "debug", "created_at": 1788685626.663206}, {"event_id": "a1457eeeb2d94cbba861ae9fca55979f", "step": 54, "value": 0.9037285295349812, "stage": "evolution", "created_at": 1788685995.2999406}, {"event_id": "48f92075a338447697c1c587ffdf1d91", "step": 56, "value": 0.8903393380812736, "stage": "evolution", "created_at": 1788685951.4955099}, {"event_id": "790f0d9997c0403db4afbd2c212c6073", "step": 58, "value": 0.8886635944700461, "stage": "improve", "created_at": 1788687375.5142226}, {"event_id": "54c2ed7d0fe14a62bca6ae683508faa0", "step": 60, "value": 0.9172182656053623, "stage": "debug", "created_at": 1788688447.9463086}, {"event_id": "8a5bf7654aba4ea6b10cf9b13b9f988d", "step": 61, "value": 0.8326872026045579, "stage": "improve", "created_at": 1788686713.199404}, {"event_id": "7d9b3afc56564ca6a48091e8ac4ccfb3", "step": 62, "value": 0.9062421449518223, "stage": "debug", "created_at": 1788687711.441868}, {"event_id": "d23f3f912db54ecb893675cab503feba", "step": 63, "value": 0.8895684960201089, "stage": "improve", "created_at": 1788689258.9057817}, {"event_id": "9c522b2d9be04dc8b02883baf41cd9fd", "step": 64, "value": 0.9028906577293674, "stage": "improve", "created_at": 1788689532.7700112}, {"event_id": "7830b000e1334948a70eed2c231652dc", "step": 65, "value": 0.8912442396313365, "stage": "improve", "created_at": 1788689423.556608}, {"event_id": "b2b14806c14b4b8c8f869d830828c9d1", "step": 66, "value": 0.5218600754084626, "stage": "improve", "created_at": 1788690212.2410362}, {"event_id": "62c28cfc16c9482aa0322fabe3a10e49", "step": 67, "value": 0.9359195643066611, "stage": "improve", "created_at": 1788690368.1494727}, {"event_id": "fd78569dff194040b4e1b391c6ba431f", "step": 68, "value": 0.9088060326770004, "stage": "improve", "created_at": 1788690401.1043484}, {"event_id": "f84e7641143c4958b7ac937933d3854f", "step": 69, "value": 0.8634939254294094, "stage": "improve", "created_at": 1788691347.1671457}, {"event_id": "a43ee58393474656bb578c0058ffad3d", "step": 70, "value": 0.995056556346879, "stage": "evolution", "created_at": 1788691243.1310184}, {"event_id": "2f7c304fe3ff4526b67f8567457a0986", "step": 71, "value": 0.9281105990783409, "stage": "improve", "created_at": 1788691422.0094676}, {"event_id": "de01d3c46a4e4b05a3f5a511d58bfa3f", "step": 73, "value": 0.523616753244915, "stage": "debug", "created_at": 1788692446.728167}, {"event_id": "56baaa21b7af49ba8c30ee9c84d4f50f", "step": 74, "value": 0.867381650607457, "stage": "improve", "created_at": 1788692315.7390869}, {"event_id": "6c8e0aa646ce40c1a387f2a9737cbc79", "step": 75, "value": 0.93865189289012, "stage": "improve", "created_at": 1788692225.674761}, {"event_id": "a5fc77415df7482fb7c855d58a1c07ff", "step": 76, "value": 0.8434687892752408, "stage": "improve", "created_at": 1788692730.691401}, {"event_id": "9e0347ef9f8d47c6afeb114fcb3fd32f", "step": 78, "value": 0.7797703899806537, "stage": "debug", "created_at": 1788693382.5168102}, {"event_id": "ff1a96409f9349cd98adc8d7e22285c6", "step": 79, "value": 0.9901466275659824, "stage": "improve", "created_at": 1788693267.7428296}, {"event_id": "b57fedba5ba049bcb7d6cb4c5749a024", "step": 80, "value": 0.8780728948470884, "stage": "improve", "created_at": 1788693371.2777715}, {"event_id": "87747d84ef64427c99faad5e8b96d556", "step": 83, "value": 0.8709677419354839, "stage": "debug", "created_at": 1788694254.0679796}, {"event_id": "61691fb3cc3744178f6a4b2aa92abe1b", "step": 85, "value": 0.9931126937578552, "stage": "debug", "created_at": 1788694328.8468022}, {"event_id": "44a3f041b8514f9f8594fcfcd2407179", "step": 86, "value": 0.8502387934645999, "stage": "debug", "created_at": 1788695090.8926635}, {"event_id": "04dc7e6063734aaf827687648956d7ee", "step": 87, "value": 0.9264348554671136, "stage": "fusion", "created_at": 1788695100.921045}, {"event_id": "d3ef5aa0d651480f8d493f2c4c70ed77", "step": 88, "value": 0.997503142019271, "stage": "evolution", "created_at": 1788695242.4264987}, {"event_id": "82e39905b86e4e03a022c53ebd259f8a", "step": 89, "value": 0.8818265605362379, "stage": "evolution", "created_at": 1788696082.9156244}, {"event_id": "6f5d512c3bf54f4cae1a3151d66e62df", "step": 90, "value": 0.9958944281524927, "stage": "improve", "created_at": 1788696205.7495542}, {"event_id": "1a91f14d257d4b0a8dc8905dec1761be", "step": 91, "value": 0.8811730205278592, "stage": "improve", "created_at": 1788697426.7025268}, {"event_id": "f5d09214cdd64fc0b84259f10cfc9ee7", "step": 92, "value": 0.821327322814926, "stage": "improve", "created_at": 1788696153.2493956}], "maximize": true, "elapsed_seconds": 28770.68932199478, "node_count": 93, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.bnvs.mlsp-2013-birds.yaml", "note": ""}, {"id": "xixian.bnvs.new-york-city-taxi-fare-prediction", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "bnvs", "dataset": "new-york-city-taxi-fare-prediction", "status": "archived", "official_score": 7.13191, "medal": "none", "valid_submission": true, "score_maximize": false, "thresholds": {"gold": 2.83377, "silver": 2.88191, "bronze": 2.92371}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:55", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-four-methods-muse13/runs/bnvs/11_new-york-city-taxi-fare-prediction/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-four-methods-muse13/runs/bnvs/11_new-york-city-taxi-fare-prediction/logs/journal.json", "metrics": [{"event_id": "69ceee15158547dc9505e0082027ad5c", "step": 3, "value": 3.711270570755005, "stage": "debug", "created_at": 1788672046.4304447}, {"event_id": "5879895a0c244b3b8b31450d63bddec7", "step": 4, "value": 5.814533372969124, "stage": "draft", "created_at": 1788671180.8504431}, {"event_id": "e98b5a90310a45acb61812a17448131e", "step": 5, "value": 3.379563937671729, "stage": "improve", "created_at": 1788672604.6168926}, {"event_id": "9dee8e6b00c14d7d99f98d540d3266e6", "step": 11, "value": 3.493284824900364, "stage": "draft", "created_at": 1788681978.7132838}, {"event_id": "ad9cf437b6184fd19ead1165be9c46f3", "step": 12, "value": 3.77741100484431, "stage": "debug", "created_at": 1788682319.1518145}, {"event_id": "7cf1f0eb66e94d2998add423b4ee9628", "step": 13, "value": 4.911446068013592, "stage": "improve", "created_at": 1788683108.4728274}, {"event_id": "95f55a1586a741608bfab68e3dc735ef", "step": 14, "value": 2.9960505273359463, "stage": "improve", "created_at": 1788682653.255047}, {"event_id": "a8ecbe93342b4f4c98b11a7566e6c82e", "step": 15, "value": 2.533526350984209, "stage": "debug", "created_at": 1788682016.439835}, {"event_id": "52b80a383fc549808fb6305798b8d403", "step": 16, "value": 4.924515009416846, "stage": "improve", "created_at": 1788685101.5672197}, {"event_id": "189d51d19a594a02a549b6d4c0bfac40", "step": 17, "value": 2.538660390596135, "stage": "improve", "created_at": 1788685230.3381517}, {"event_id": "d66412f24b024feabb1f70e7c0ae82b7", "step": 18, "value": 2.5691141370393824, "stage": "improve", "created_at": 1788688141.1507432}, {"event_id": "ba1660a2c31d40a598306eaeddd03616", "step": 19, "value": 2.5478066841944798, "stage": "improve", "created_at": 1788691472.9156976}, {"event_id": "fd0890fa6c414850bbd187053fc5c5ce", "step": 20, "value": 2.5291189116856443, "stage": "improve", "created_at": 1788687323.6573956}, {"event_id": "e7494238377841648cf8e346781c2c8f", "step": 21, "value": 2.5468870753820907, "stage": "improve", "created_at": 1788686819.4694648}, {"event_id": "0f99343cd24d42d3a61018c3f8e18bfe", "step": 23, "value": 2.543188230235649, "stage": "improve", "created_at": 1788694151.160954}, {"event_id": "8d847b70073241e8a195240c3880a0c5", "step": 24, "value": 2.959565293364575, "stage": "fusion_draft", "created_at": 1788695290.978425}], "maximize": false, "elapsed_seconds": 28767.21543931961, "node_count": 25, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.bnvs.new-york-city-taxi-fare-prediction.yaml", "note": ""}, {"id": "xixian.bnvs.nomad2018-predict-transparent-conductors", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "bnvs", "dataset": "nomad2018-predict-transparent-conductors", "status": "archived", "official_score": 0.06153, "medal": "silver", "valid_submission": true, "score_maximize": false, "thresholds": {"gold": 0.05589, "silver": 0.06229, "bronze": 0.06582}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:56", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-four-methods-muse13/runs/bnvs/12_nomad2018-predict-transparent-conductors/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-four-methods-muse13/runs/bnvs/12_nomad2018-predict-transparent-conductors/logs/journal.json", "metrics": [{"event_id": "cb0fb37870f74f3e92b81dddb8279efe", "step": 3, "value": 0.08185142896514168, "stage": "draft", "created_at": 1788671281.7404618}, {"event_id": "dddc0e71f36d41f49c1b6651bf04667f", "step": 4, "value": 0.06451382546872152, "stage": "debug", "created_at": 1788671445.9322112}, {"event_id": "61006441b57746b9924d8b4d74dce8b2", "step": 5, "value": 0.08264881380780742, "stage": "improve", "created_at": 1788671571.3686845}, {"event_id": "6889a339279d4905b1e90221ca91bb32", "step": 6, "value": 0.05426318467933333, "stage": "improve", "created_at": 1788671634.2384732}, {"event_id": "029927d8e1b74ba68491a6fe3f4f146a", "step": 7, "value": 0.07268851591843997, "stage": "improve", "created_at": 1788671856.8045216}, {"event_id": "0f322d53298a46dd85d2c1038dd79924", "step": 8, "value": 0.07424537037122074, "stage": "improve", "created_at": 1788672155.833597}, {"event_id": "01c68a4a6f2e47c681f7c58e559ca178", "step": 9, "value": 0.07185004313049048, "stage": "improve", "created_at": 1788672429.6671991}, {"event_id": "e1006abba98d4588940bf57b820c985c", "step": 10, "value": 0.10935060016381028, "stage": "draft", "created_at": 1788671073.0486553}, {"event_id": "13285437fd1744768322ac3bc9cc23bd", "step": 11, "value": 0.07105108243695007, "stage": "improve", "created_at": 1788672171.9842045}, {"event_id": "91d4faef31ff4b98a6cc60024fc9524c", "step": 12, "value": 0.05481877687457379, "stage": "improve", "created_at": 1788672782.137529}, {"event_id": "61984c1cb8a341058068a8201fcc11b9", "step": 16, "value": 0.06687025028426388, "stage": "draft", "created_at": 1788682058.665007}, {"event_id": "e9aedf23f28a48cab252921b307ca70e", "step": 17, "value": 0.06440479273175223, "stage": "improve", "created_at": 1788682215.6084726}, {"event_id": "63cb7e0ddc674dd78f8afeb4c27e34c1", "step": 18, "value": 0.06327845168256359, "stage": "improve", "created_at": 1788682467.8743484}, {"event_id": "f31616adc8dd44d0aca876eba8bb2d0f", "step": 19, "value": 0.06733454740019149, "stage": "improve", "created_at": 1788681886.601813}, {"event_id": "6900aff65ca446cf8eb6b458cc5eaf4b", "step": 21, "value": 0.06439226343754272, "stage": "evolution", "created_at": 1788683426.5913043}, {"event_id": "a99f583d5a0c4f2eb522753818ecb9d9", "step": 22, "value": 0.054497328392584615, "stage": "improve", "created_at": 1788686257.270368}, {"event_id": "6bd112f734304d30aea1f2df67fb4722", "step": 23, "value": 0.062013991278064305, "stage": "debug", "created_at": 1788685874.8760486}, {"event_id": "ba3770e662344a25af672c9b132a2a23", "step": 24, "value": 0.053054510523403924, "stage": "fusion", "created_at": 1788687748.8457856}, {"event_id": "5359dcd88c8e47358c1ed9d8434b489f", "step": 25, "value": 0.05448792412725338, "stage": "evolution", "created_at": 1788682643.3839257}], "maximize": false, "elapsed_seconds": 28766.534383535385, "node_count": 26, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.bnvs.nomad2018-predict-transparent-conductors.yaml", "note": ""}, {"id": "xixian.bnvs.plant-pathology-2020-fgvc7", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "bnvs", "dataset": "plant-pathology-2020-fgvc7", "status": "archived", "official_score": 0.99269, "medal": "gold", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.97836, "silver": 0.97465, "bronze": 0.97361}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:57", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-four-methods-muse13/runs/bnvs/13_plant-pathology-2020-fgvc7/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-four-methods-muse13/runs/bnvs/13_plant-pathology-2020-fgvc7/logs/journal.json", "metrics": [{"event_id": "49a559f495e448d9adababa1b30e66c4", "step": 3, "value": 0.9945839138702316, "stage": "draft", "created_at": 1788670863.437702}, {"event_id": "8a647b8882284d1bae7ee8d9fe48de76", "step": 4, "value": 0.9933136152445772, "stage": "debug", "created_at": 1788671562.69099}, {"event_id": "107945acc91c4509937b8d9cc05ec666", "step": 7, "value": 0.9814361070067672, "stage": "debug", "created_at": 1788671378.4372509}, {"event_id": "4f887198d1564788b11dead6eafa42bf", "step": 8, "value": 0.9920802141267813, "stage": "improve", "created_at": 1788672212.6481261}, {"event_id": "73e20d0761904b10bb38503dd47929a1", "step": 9, "value": 0.9922555871663552, "stage": "improve", "created_at": 1788672877.8191812}, {"event_id": "dbf0b804cdd84ef2a58b9a543a2a4562", "step": 10, "value": 0.9900880538756537, "stage": "improve", "created_at": 1788672617.811642}, {"event_id": "9d0c18c2b30a46a2b035f1235c762cad", "step": 11, "value": 0.9976518753396673, "stage": "debug", "created_at": 1788672343.303227}, {"event_id": "86334576c056490e99693178af7b4571", "step": 12, "value": 0.9991311868725266, "stage": "improve", "created_at": 1788673730.3146245}, {"event_id": "4f6e8add1e1946b696038551f7c088eb", "step": 16, "value": 0.9771299514176816, "stage": "improve", "created_at": 1788681923.1897535}, {"event_id": "f6620f7fb21c46139aac28b6f801929c", "step": 18, "value": 0.9777300409733745, "stage": "improve", "created_at": 1788682616.3465948}, {"event_id": "470c08d3a79e4dc38f9efd0e0b736b1e", "step": 19, "value": 0.9859423669404859, "stage": "debug", "created_at": 1788682216.294436}, {"event_id": "faecf4902194465eb90e2c36d8d28c01", "step": 20, "value": 0.9664566216326727, "stage": "improve", "created_at": 1788683351.9242826}, {"event_id": "d8e01744a99a4c8685f0e6e3899ccb55", "step": 21, "value": 0.9860571685988828, "stage": "debug", "created_at": 1788682711.5948637}, {"event_id": "3d33f1b1341f4df2b99398bd23688c20", "step": 22, "value": 0.9978585055479998, "stage": "improve", "created_at": 1788684667.1886818}, {"event_id": "c1c419891bfa4986b3f3b25888968cb1", "step": 23, "value": 0.9918870310609679, "stage": "evolution", "created_at": 1788684637.8793669}, {"event_id": "0d83018a498847ba93ff39e3ab140034", "step": 24, "value": 0.99308310287179, "stage": "improve", "created_at": 1788684291.2995586}, {"event_id": "10cb839623d64d7180046934a28af731", "step": 25, "value": 0.9760408467285445, "stage": "evolution", "created_at": 1788686698.66223}, {"event_id": "4f04704301d24898b00679241384b193", "step": 28, "value": 0.9319087480855461, "stage": "fusion", "created_at": 1788688606.4404206}, {"event_id": "89456fe8743b4d2caf6ced21da3e3e49", "step": 32, "value": 0.9880215377977577, "stage": "debug", "created_at": 1788689624.4597514}, {"event_id": "138e75ea7c43473f840edb8247565e92", "step": 36, "value": 0.9818123468802421, "stage": "fusion", "created_at": 1788696720.939163}], "maximize": true, "elapsed_seconds": 28766.866595506668, "node_count": 38, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.bnvs.plant-pathology-2020-fgvc7.yaml", "note": ""}, {"id": "xixian.bnvs.random-acts-of-pizza", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "bnvs", "dataset": "random-acts-of-pizza", "status": "archived", "official_score": 0.68962, "medal": "none", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.97908, "silver": 0.76482, "bronze": 0.6921}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:58", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-four-methods-muse13/runs/bnvs/14_random-acts-of-pizza/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-four-methods-muse13/runs/bnvs/14_random-acts-of-pizza/logs/journal.json", "metrics": [{"event_id": "cdfbf2c01ebe4960b304b99f5424a23a", "step": 4, "value": 0.6422573687994249, "stage": "debug", "created_at": 1788671416.1392527}, {"event_id": "a265ffc6363e44228eb017f4643b5426", "step": 5, "value": 0.5760929211633437, "stage": "debug", "created_at": 1788671558.0050402}, {"event_id": "c2d75f903e6e40c7a0c43c10700e3869", "step": 6, "value": 0.6845434938892883, "stage": "improve", "created_at": 1788671769.021231}, {"event_id": "36926b8e94d2450896f99aabdfca1e56", "step": 7, "value": 0.6500071890726096, "stage": "improve", "created_at": 1788671869.9066846}, {"event_id": "bbc883bef0b44dbebf6f1ff306da9323", "step": 8, "value": 0.6729834651329978, "stage": "draft", "created_at": 1788671135.4997215}, {"event_id": "e2c4b5c909a142bcbb0eed1cd97ef328", "step": 9, "value": 0.5856959941466984, "stage": "improve", "created_at": 1788673329.348983}, {"event_id": "023894b1f9a646d9adae53107c42fe62", "step": 10, "value": 0.7015672178289001, "stage": "improve", "created_at": 1788673207.4831266}, {"event_id": "0d3fb8a9e8594aad937f94b8bf4a37f1", "step": 16, "value": 0.6325815886699508, "stage": "debug", "created_at": 1788682149.7578661}, {"event_id": "2e0f69a0495d4c7ebc849721ec2a4899", "step": 17, "value": 0.6216340157018123, "stage": "debug", "created_at": 1788682176.1342223}, {"event_id": "5d84aa78734048ab866872bdd9a71c9a", "step": 19, "value": 0.6867864845434939, "stage": "improve", "created_at": 1788681832.0442126}, {"event_id": "d7acd50ce12743a7b287ee691267737b", "step": 21, "value": 0.6210286888252989, "stage": "improve", "created_at": 1788682530.5725484}, {"event_id": "75d08060a2d14eb7ba0d9f661b5f35f9", "step": 22, "value": 0.6622286125089865, "stage": "debug", "created_at": 1788686118.8566732}, {"event_id": "09f3cc40e8544567a738c7c2e1b242ab", "step": 23, "value": 0.6830276519596907, "stage": "improve", "created_at": 1788682857.759973}, {"event_id": "6bccc3a19d6244738ba36f794e1a0a07", "step": 25, "value": 0.6531991373112869, "stage": "improve", "created_at": 1788696636.47039}], "maximize": true, "elapsed_seconds": 28775.450289964676, "node_count": 26, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.bnvs.random-acts-of-pizza.yaml", "note": ""}, {"id": "xixian.bnvs.ranzcr-clip-catheter-line-classification", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "bnvs", "dataset": "ranzcr-clip-catheter-line-classification", "status": "archived", "official_score": 0.84278, "medal": "none", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.97357, "silver": 0.97152, "bronze": 0.9709}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:59", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-four-methods-muse13/runs/bnvs/15_ranzcr-clip-catheter-line-classification/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-four-methods-muse13/runs/bnvs/15_ranzcr-clip-catheter-line-classification/logs/journal.json", "metrics": [{"event_id": "d47ecd08e0704f9dbe202f9270619875", "step": 6, "value": 0.8124746880892838, "stage": "draft", "created_at": 1788682007.6141376}, {"event_id": "f00d0cbbb087438e883f8889987759e4", "step": 7, "value": 0.8384528524466256, "stage": "debug", "created_at": 1788681821.7375987}, {"event_id": "ca7daad32d1845eb8f34722a50f9c883", "step": 11, "value": 0.8187686062968167, "stage": "improve", "created_at": 1788686748.8602338}, {"event_id": "0dd54e77a4374071920808c886fea06e", "step": 13, "value": 0.847714670168507, "stage": "debug", "created_at": 1788692759.1100116}], "maximize": true, "elapsed_seconds": 28756.626715183258, "node_count": 14, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.bnvs.ranzcr-clip-catheter-line-classification.yaml", "note": ""}, {"id": "xixian.bnvs.siim-isic-melanoma-classification", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "bnvs", "dataset": "siim-isic-melanoma-classification", "status": "archived", "official_score": 0.89999, "medal": "none", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.9455, "silver": 0.9401, "bronze": 0.937}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:60", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-four-methods-muse13/runs/bnvs/16_siim-isic-melanoma-classification/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-four-methods-muse13/runs/bnvs/16_siim-isic-melanoma-classification/logs/journal.json", "metrics": [{"event_id": "09e85e9ec296487caa2ebc781c4b43b7", "step": 1, "value": 0.8969791633797186, "stage": "draft", "created_at": 1788670934.8271189}, {"event_id": "25c08abc5e224ca1b33bfcb13265a69a", "step": 2, "value": 0.9065120483805604, "stage": "draft", "created_at": 1788671337.7532072}], "maximize": true, "elapsed_seconds": 28769.725088119507, "node_count": 4, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.bnvs.siim-isic-melanoma-classification.yaml", "note": ""}, {"id": "xixian.bnvs.spooky-author-identification", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "bnvs", "dataset": "spooky-author-identification", "status": "archived", "official_score": 0.24127, "medal": "silver", "valid_submission": true, "score_maximize": false, "thresholds": {"gold": 0.16506, "silver": 0.26996, "bronze": 0.29381}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:61", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-four-methods-muse13/runs/bnvs/17_spooky-author-identification/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-four-methods-muse13/runs/bnvs/17_spooky-author-identification/logs/journal.json", "metrics": [{"event_id": "36cb3bdb46a4482aac28bfcdbe3c0308", "step": 5, "value": 0.29214692180071694, "stage": "debug", "created_at": 1788671344.0868099}, {"event_id": "c65ea756c3694ab59e5ac172d05d2cfb", "step": 6, "value": 0.39945069092716706, "stage": "debug", "created_at": 1788671367.5892248}, {"event_id": "77eb9dd1688b4e4287043957911d2b96", "step": 8, "value": 0.40995322507114185, "stage": "improve", "created_at": 1788671928.0747242}, {"event_id": "b7cf41be794c4ca2abc4b71c01a98279", "step": 9, "value": 0.40995322507114185, "stage": "improve", "created_at": 1788671916.8968801}, {"event_id": "34f9728462d8447099d31a3982ecfd27", "step": 10, "value": 0.31555517430896185, "stage": "debug", "created_at": 1788672013.678702}, {"event_id": "1190658ee336434aa450715c6a4e1bb4", "step": 11, "value": 0.40995322507114185, "stage": "improve", "created_at": 1788672630.2350993}, {"event_id": "45504b4049d74fee8eb9eb87b7af63db", "step": 15, "value": 0.49231302713762276, "stage": "draft", "created_at": 1788682043.6078918}, {"event_id": "1e9ea14cef324bb78d35acd72f4637fc", "step": 17, "value": 0.4105646609142095, "stage": "fusion", "created_at": 1788694540.234984}, {"event_id": "fdebe41f13fa4cf5934fccd446c628a3", "step": 18, "value": 0.31532604683570314, "stage": "improve", "created_at": 1788695415.7421618}, {"event_id": "290208f7ec654c5f8c99e1f0a5fa7250", "step": 20, "value": 0.28251895818851386, "stage": "debug", "created_at": 1788697476.2648013}], "maximize": false, "elapsed_seconds": 28765.25500202179, "node_count": 21, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.bnvs.spooky-author-identification.yaml", "note": ""}, {"id": "xixian.bnvs.tabular-playground-series-dec-2021", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "bnvs", "dataset": "tabular-playground-series-dec-2021", "status": "archived", "official_score": 0.96332, "medal": "gold", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.9566, "silver": 0.95658, "bronze": 0.95658}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:62", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-four-methods-muse13/runs/bnvs/18_tabular-playground-series-dec-2021/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-four-methods-muse13/runs/bnvs/18_tabular-playground-series-dec-2021/logs/journal.json", "metrics": [{"event_id": "58f77da7c6254d9eb751f5ebcdbdd367", "step": 6, "value": 0.9555888888888889, "stage": "debug", "created_at": 1788671366.7347722}, {"event_id": "202008864c434d4b82f2239f473c3c8c", "step": 7, "value": 0.960425, "stage": "debug", "created_at": 1788671338.2709608}, {"event_id": "f97b783b477d4e6ea5d104c5354c7bf5", "step": 8, "value": 0.9613527777777777, "stage": "improve", "created_at": 1788671868.6945405}, {"event_id": "2bfbee14cc1d419d98de435a07d6009e", "step": 9, "value": 0.9621277777777778, "stage": "improve", "created_at": 1788672671.4187806}, {"event_id": "8ff85da8e3b046e88f1903d969b5a512", "step": 10, "value": 0.9623777777777778, "stage": "improve", "created_at": 1788674373.2315447}, {"event_id": "a6c8c18dde6c4366a8c994d73243b4c1", "step": 11, "value": 0.96215, "stage": "improve", "created_at": 1788682219.5049899}], "maximize": true, "elapsed_seconds": 28773.430681467056, "node_count": 23, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.bnvs.tabular-playground-series-dec-2021.yaml", "note": ""}, {"id": "xixian.bnvs.tabular-playground-series-may-2022", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "bnvs", "dataset": "tabular-playground-series-may-2022", "status": "archived", "official_score": 0.99268, "medal": "none", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.99823, "silver": 0.99822, "bronze": 0.99818}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:63", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-four-methods-muse13/runs/bnvs/19_tabular-playground-series-may-2022/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-four-methods-muse13/runs/bnvs/19_tabular-playground-series-may-2022/logs/journal.json", "metrics": [{"event_id": "f8108521764c4e1e9960843eafb600fe", "step": 2, "value": 0.9682750452067962, "stage": "draft", "created_at": 1788671145.728705}, {"event_id": "edd39e4993fc40b891e22835ea949e6a", "step": 3, "value": 0.9132686413280408, "stage": "debug", "created_at": 1788671259.3297656}, {"event_id": "0a76b5cd6fee4907a2007b4c3e2bac05", "step": 6, "value": 0.9906877389231465, "stage": "draft", "created_at": 1788670802.496992}, {"event_id": "8a87ade57cf443e9ae805a604f7e9d68", "step": 7, "value": 0.9382925152418363, "stage": "debug", "created_at": 1788671881.1866252}, {"event_id": "eecdb401ceca4ec7bf6290eb484f6ecd", "step": 9, "value": 0.9692931120668512, "stage": "draft", "created_at": 1788682024.088835}, {"event_id": "222a8fa8460c4382b61b7cc5f1e13e41", "step": 10, "value": 0.9910111995907275, "stage": "improve", "created_at": 1788682573.4300306}, {"event_id": "7a22da2ea65c41deb38ddff5dffb43cf", "step": 11, "value": 0.9907182495634319, "stage": "improve", "created_at": 1788672679.2177746}, {"event_id": "1d7e5b5988a04f37afb614a199bfd1fe", "step": 14, "value": 0.9901000266943318, "stage": "draft", "created_at": 1788689120.7823722}, {"event_id": "27b8b27cac3b453ba0abf9ef56442add", "step": 15, "value": 0.9714289563382814, "stage": "improve", "created_at": 1788689548.735433}], "maximize": true, "elapsed_seconds": 28767.00555920601, "node_count": 18, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.bnvs.tabular-playground-series-may-2022.yaml", "note": ""}, {"id": "xixian.bnvs.text-normalization-challenge-english-language", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "bnvs", "dataset": "text-normalization-challenge-english-language", "status": "archived", "official_score": 0.99183, "medal": "silver", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.99724, "silver": 0.99135, "bronze": 0.99038}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:64", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-four-methods-muse13/runs/bnvs/20_text-normalization-challenge-english-language/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-four-methods-muse13/runs/bnvs/20_text-normalization-challenge-english-language/logs/journal.json", "metrics": [{"event_id": "fa4f9151e8bf4e719bcd108e78802fc9", "step": 4, "value": 0.987693493189493, "stage": "debug", "created_at": 1788671380.470682}, {"event_id": "b628577583434529bd66bd5dfed8096c", "step": 5, "value": 0.9911666666666666, "stage": "draft", "created_at": 1788671077.4472008}, {"event_id": "76af6d244d4548b7be5278cf458df40f", "step": 6, "value": 0.9777926272413409, "stage": "debug", "created_at": 1788671879.4059567}, {"event_id": "37f49706d8e244eab38658045a73edb4", "step": 13, "value": 0.99205, "stage": "improve", "created_at": 1788673797.2960722}, {"event_id": "f327afc509ff4e0c861162b591762f8e", "step": 14, "value": 0.9752077243731802, "stage": "debug", "created_at": 1788682305.678971}, {"event_id": "aae66e0f328b4bd1922bfef9661d0a8e", "step": 15, "value": 0.9848165471827187, "stage": "debug", "created_at": 1788682259.7403557}], "maximize": true, "elapsed_seconds": 28773.65512752533, "node_count": 19, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.bnvs.text-normalization-challenge-english-language.yaml", "note": ""}, {"id": "xixian.bnvs.text-normalization-challenge-russian-language", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "bnvs", "dataset": "text-normalization-challenge-russian-language", "status": "archived", "official_score": 0.98755, "medal": "silver", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.99012, "silver": 0.98232, "bronze": 0.97592}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:65", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-four-methods-muse13/runs/bnvs/21_text-normalization-challenge-russian-language/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-four-methods-muse13/runs/bnvs/21_text-normalization-challenge-russian-language/logs/journal.json", "metrics": [{"event_id": "0895e323c0624bd986a42deaa6c0c987", "step": 6, "value": 0.9641229869048202, "stage": "debug", "created_at": 1788671896.0511315}, {"event_id": "dae51c9f8b9844f3931e45b3311e2ff5", "step": 7, "value": 0.8759607240330018, "stage": "debug", "created_at": 1788671887.9310184}, {"event_id": "26d5987b511a4b5c86ec1b5dfef7f21f", "step": 8, "value": 0.8813125107833552, "stage": "debug", "created_at": 1788671887.6835938}, {"event_id": "48ac4bc3c9cb46b79059ba45a970d2d3", "step": 15, "value": 0.8749432924573733, "stage": "debug", "created_at": 1788682574.866754}, {"event_id": "602f48508eb940db90007b5a67bff4f6", "step": 16, "value": 0.9383584204279881, "stage": "draft", "created_at": 1788682031.023108}, {"event_id": "4f032cb2423b409391d5333c27c14bb3", "step": 18, "value": 0.9859644469880443, "stage": "debug", "created_at": 1788683676.1871624}, {"event_id": "bda28e4284674023b91f81e372c9015b", "step": 20, "value": 0.9389073912384258, "stage": "improve", "created_at": 1788683568.5615773}, {"event_id": "cb68b3a5e20e45f4905d83ef223b2ba1", "step": 21, "value": 0.9501220806516545, "stage": "improve", "created_at": 1788684674.4049864}, {"event_id": "609122adb9044d258d62a8e03f4ce2ef", "step": 22, "value": 0.8761280337965722, "stage": "improve", "created_at": 1788686315.5449297}, {"event_id": "b0972d9b5bd94e248c5e76d579ca6f0f", "step": 23, "value": 0.9153308027731594, "stage": "improve", "created_at": 1788686791.7740798}, {"event_id": "7417ab9c185b462982961ed934d43c60", "step": 25, "value": 0.8805596365290406, "stage": "debug", "created_at": 1788685347.9584239}, {"event_id": "4af77b6586674500aad33465940f1cea", "step": 26, "value": 0.8660580774016794, "stage": "improve", "created_at": 1788687992.128912}, {"event_id": "348cfa5d067d40ac89f401a3dc937273", "step": 30, "value": 0.9855228554847413, "stage": "improve", "created_at": 1788688212.0757468}, {"event_id": "7227833576044b8080c9e1f6bc2f3195", "step": 31, "value": 0.9138063544678382, "stage": "improve", "created_at": 1788691103.0811613}, {"event_id": "d6ab68583ebe41319ebd3d0f63d018a6", "step": 34, "value": 0.9763727243257939, "stage": "debug", "created_at": 1788695084.9653218}], "maximize": true, "elapsed_seconds": 28771.419050455093, "node_count": 36, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.bnvs.text-normalization-challenge-russian-language.yaml", "note": ""}, {"id": "xixian.bnvs.the-icml-2013-whale-challenge-right-whale-redux", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "bnvs", "dataset": "the-icml-2013-whale-challenge-right-whale-redux", "status": "archived", "official_score": 0.99389, "medal": "gold", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.98961, "silver": 0.95017, "bronze": 0.90521}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:66", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-four-methods-muse13/runs/bnvs/22_the-icml-2013-whale-challenge-right-whale-redux/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-four-methods-muse13/runs/bnvs/22_the-icml-2013-whale-challenge-right-whale-redux/logs/journal.json", "metrics": [{"event_id": "4ec1bfeba3d1439d83c3187cf7f2ec47", "step": 3, "value": 0.818894782005346, "stage": "debug", "created_at": 1788672263.483154}, {"event_id": "a1b2a44c12da4e60afc4e51f19689997", "step": 4, "value": 0.9818064650830279, "stage": "improve", "created_at": 1788672815.112727}, {"event_id": "d64b4cbc59cf42d88a2c71278ab4a962", "step": 5, "value": 0.9828420061889225, "stage": "improve", "created_at": 1788673150.9687018}, {"event_id": "f49714cea7b145d98dec093b262c7bf3", "step": 6, "value": 0.8693852477690607, "stage": "draft", "created_at": 1788671675.6758723}, {"event_id": "b15d19c11e31460da2d5a8187ddf9bf5", "step": 7, "value": 0.984485970824742, "stage": "improve", "created_at": 1788673479.1599176}, {"event_id": "380de8f56dc04f819e8c739d13b543ea", "step": 8, "value": 0.9808304130814754, "stage": "improve", "created_at": 1788673739.099234}, {"event_id": "bd47983052424b05b12f3bf4e5595e62", "step": 9, "value": 0.8673515328391846, "stage": "draft", "created_at": 1788671876.969903}, {"event_id": "6dd5d41cddf5498ea93066f27fc21d2c", "step": 10, "value": 0.9757061278378028, "stage": "improve", "created_at": 1788673852.8593018}, {"event_id": "64f8412620064218958e76ee217e8eef", "step": 11, "value": 0.7959586366947295, "stage": "improve", "created_at": 1788674074.5814505}, {"event_id": "5de3d03579ab4cd4a7c891d9b3b60b18", "step": 16, "value": 0.9838741702909504, "stage": "improve", "created_at": 1788681933.774719}, {"event_id": "0dee8abc4fd9435ea13f3eee9f1e2d9c", "step": 19, "value": 0.9866733149594958, "stage": "improve", "created_at": 1788682410.523482}, {"event_id": "6d60367ff0954de4b5a4164f6ccc1cfe", "step": 20, "value": 0.8869460349398524, "stage": "debug", "created_at": 1788682708.0556257}, {"event_id": "3ed9b08773844315950d6280045faeda", "step": 21, "value": 0.9772619722495439, "stage": "improve", "created_at": 1788683238.5450494}, {"event_id": "3fab7a823853457caefa39e7797ddb3a", "step": 22, "value": 0.9802916830806185, "stage": "improve", "created_at": 1788683465.6349404}, {"event_id": "a1abe531d7c8456287a8c6094b80b736", "step": 24, "value": 0.814365926168026, "stage": "improve", "created_at": 1788683588.5196493}, {"event_id": "7083a4b7c7ff4721b55f11cb76cb7f27", "step": 25, "value": 0.9768304703807142, "stage": "improve", "created_at": 1788684512.0834727}, {"event_id": "e17528a8a86a470986a175cc4733aec4", "step": 28, "value": 0.9814220129770748, "stage": "evolution", "created_at": 1788684917.2925148}, {"event_id": "cf6f5c424ebe496cb197fc67f3618bef", "step": 29, "value": 0.8992502953532474, "stage": "debug", "created_at": 1788685493.8023238}, {"event_id": "65c26e356544435089abd4c81675d17c", "step": 30, "value": 0.987309279686024, "stage": "evolution", "created_at": 1788685706.358885}, {"event_id": "872b3a309fe14836a4635bacbc3b2f4b", "step": 31, "value": 0.46388196480741073, "stage": "improve", "created_at": 1788686319.2402103}, {"event_id": "ae0b92fa43ef4bb1ad2088a6b448b750", "step": 32, "value": 0.9833842119604412, "stage": "improve", "created_at": 1788686623.065422}, {"event_id": "3df34a8d6bee47c38497a3e2a145a54e", "step": 33, "value": 0.9796430470518989, "stage": "improve", "created_at": 1788687256.646278}, {"event_id": "7e03f5503db24da295731a5c29bec970", "step": 34, "value": 0.9918411273242684, "stage": "improve", "created_at": 1788687489.3979704}, {"event_id": "bca62468333445a19fb4126f96d6d791", "step": 35, "value": 0.9922225873968322, "stage": "improve", "created_at": 1788688470.058899}, {"event_id": "22aab0c7234e4a13934f2fa826343462", "step": 36, "value": 0.9834141782676823, "stage": "improve", "created_at": 1788687643.1661797}, {"event_id": "16e0a533067241e08023af1ebc96c28e", "step": 37, "value": 0.9919918878808129, "stage": "improve", "created_at": 1788690143.9456913}, {"event_id": "30f6b491633b42d2a7831f004707ffb7", "step": 38, "value": 0.9719671569272639, "stage": "improve", "created_at": 1788690408.7943327}, {"event_id": "72388ab25db14d68bc74ee6fb942ab99", "step": 39, "value": 0.9945813916448145, "stage": "improve", "created_at": 1788691666.6783836}, {"event_id": "834e9505205c42d4a015222a2f7e3fc1", "step": 40, "value": 0.9934403062085608, "stage": "improve", "created_at": 1788693150.8198988}, {"event_id": "7180e2d3e2a54b13bc98190b62a1f8ab", "step": 41, "value": 0.9805527308055971, "stage": "fusion", "created_at": 1788692344.2157915}, {"event_id": "784635d661f141ceb5eac093c041738c", "step": 42, "value": 0.9191714369293384, "stage": "debug", "created_at": 1788682818.8468714}, {"event_id": "8ea88dc8c48b45dcb0b9b435bbf4593a", "step": 43, "value": 0.9805508558918414, "stage": "improve", "created_at": 1788694494.4548173}, {"event_id": "e471597e42fb42c9a08443cefbe6f095", "step": 44, "value": 0.99336152312323, "stage": "fusion_draft", "created_at": 1788694294.9423575}, {"event_id": "917ca746ebb14db79eef8fe9724a6b9a", "step": 46, "value": 0.9942035072203028, "stage": "improve", "created_at": 1788694142.0288901}, {"event_id": "9a9a5c65fc9144abae9a463463db474f", "step": 47, "value": 0.9932864021064478, "stage": "improve", "created_at": 1788695830.125221}, {"event_id": "1ce134a108554ea59c5a17a0e34c97c4", "step": 49, "value": 0.9933275814731393, "stage": "evolution", "created_at": 1788695956.03163}, {"event_id": "1c92a6fc617b4889b9f8b61e70cd8347", "step": 50, "value": 0.8039072910294056, "stage": "debug", "created_at": 1788697397.3297706}, {"event_id": "57dda01afc9c49ee8a3cf4f4ea0805f5", "step": 51, "value": 0.9930773077146107, "stage": "improve", "created_at": 1788697922.054448}, {"event_id": "eb6fbeadcadb4b30a31af0b644c12ba5", "step": 52, "value": 0.9941760579100293, "stage": "evolution", "created_at": 1788696181.9725}], "maximize": true, "elapsed_seconds": 28032.288772583008, "node_count": 53, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.bnvs.the-icml-2013-whale-challenge-right-whale-redux.yaml", "note": ""}, {"id": "xixian.bnvs-root.aerial-cactus-identification", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "bnvs_root", "dataset": "aerial-cactus-identification", "status": "archived", "official_score": 1.0, "medal": "gold", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 1.0, "silver": 1.0, "bronze": 1.0}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:67", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-four-methods-muse13/runs/bnvs_root/01_aerial-cactus-identification/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-four-methods-muse13/runs/bnvs_root/01_aerial-cactus-identification/logs/journal.json", "metrics": [{"event_id": "e96be04899ec4fb291e77c853d051d32", "step": 2, "value": 0.9999705376293397, "stage": "draft", "created_at": 1788683034.0052762}, {"event_id": "68a168bfd151485e823f90fa95cbf407", "step": 3, "value": 0.9999414833578669, "stage": "debug", "created_at": 1788683366.599574}, {"event_id": "a8c8fda191f24461a3fc7f09ab22e203", "step": 4, "value": 0.9995073891625617, "stage": "draft", "created_at": 1788682855.4344854}, {"event_id": "ef10f23b212d4252a93efc95a02c2ce3", "step": 5, "value": 0.9999516817121173, "stage": "improve", "created_at": 1788683537.709451}, {"event_id": "0c38f37fd4304cda98426d4966983134", "step": 6, "value": 0.9999405080804982, "stage": "improve", "created_at": 1788683661.2740803}, {"event_id": "5d9e49d6dbc64a49b34d6a977649e6e5", "step": 7, "value": 0.9999577379806817, "stage": "improve", "created_at": 1788683696.5747092}, {"event_id": "1a00879e83644de4847cd85b5c51cacc", "step": 8, "value": 0.9999139698776722, "stage": "improve", "created_at": 1788684250.302722}, {"event_id": "783bcf197ccf412f997f02da58d3261d", "step": 9, "value": 0.9999233978362835, "stage": "improve", "created_at": 1788684409.8708503}, {"event_id": "dce6cff8b20a40c890bc8aeb2756c218", "step": 10, "value": 0.9999528602069437, "stage": "improve", "created_at": 1788684564.3795168}, {"event_id": "32639f9d1e80448a9ccfaf89facd035d", "step": 13, "value": 0.9998939354656232, "stage": "improve", "created_at": 1788685009.456506}, {"event_id": "7d45c83b06ea453b8fb9c8de4ea07194", "step": 14, "value": 0.9998432601880878, "stage": "debug", "created_at": 1788685071.2817936}, {"event_id": "0a42a5354ce7432fb20e42bdcf731941", "step": 16, "value": 0.9999819484127284, "stage": "improve", "created_at": 1788684893.4601302}, {"event_id": "def5bdecaa9744b5b60fef53fbf81d5e", "step": 18, "value": 0.9999231723166918, "stage": "debug", "created_at": 1788687289.3474143}, {"event_id": "af4148473467406c8d6ee10bf77621f5", "step": 22, "value": 0.9999863651493642, "stage": "debug", "created_at": 1788688537.5496397}, {"event_id": "819c51daa74a44fa97a3c707b59668d2", "step": 23, "value": 0.9999701802625821, "stage": "debug", "created_at": 1788689581.8264804}, {"event_id": "9ba7e0fe6d244bd09bab5b3f3212ae6b", "step": 24, "value": 0.9998780903288895, "stage": "debug", "created_at": 1788691713.288986}, {"event_id": "d6456f4acc804cbaaa4e72f20467b40f", "step": 25, "value": 0.9999921977810489, "stage": "improve", "created_at": 1788692853.9750988}, {"event_id": "097f6f03157748cabd918b6167024786", "step": 26, "value": 0.9999782188054283, "stage": "improve", "created_at": 1788693509.044534}, {"event_id": "f29e2c4945774c368aa5b766d7afecda", "step": 27, "value": 0.999987505808075, "stage": "improve", "created_at": 1788692760.6569126}, {"event_id": "4773dd794bca4014b381b4e936885311", "step": 28, "value": 0.9999791940827971, "stage": "improve", "created_at": 1788696590.0988677}, {"event_id": "df30e65d984e408e92a328e1ba93290d", "step": 29, "value": 0.9999903972452721, "stage": "improve", "created_at": 1788694434.0280838}, {"event_id": "4e8ca78d7d534b5ea5ccfd7a117744c1", "step": 30, "value": 0.9999774520952521, "stage": "improve", "created_at": 1788693229.8897693}, {"event_id": "92d9db7b2fc14257846b8b74635cc610", "step": 31, "value": 0.9997914053541352, "stage": "improve", "created_at": 1788697724.9277248}, {"event_id": "448bc7f6c03f43d684bc235c63fc503d", "step": 33, "value": 0.9999624378433847, "stage": "improve", "created_at": 1788698675.043147}, {"event_id": "7945b9eb7e4947bcaf3fbbc842deedd3", "step": 35, "value": 0.999983261496593, "stage": "improve", "created_at": 1788698874.776812}, {"event_id": "1e58ea7516984c11a18c2a353212828a", "step": 36, "value": 0.9999884077242648, "stage": "improve", "created_at": 1788701124.087969}, {"event_id": "597bc583a689417b9fecf6083c90834f", "step": 37, "value": 0.9998656515897895, "stage": "improve", "created_at": 1788705807.2243612}, {"event_id": "53078aa62ac247a2bde39d6f237aa20f", "step": 38, "value": 0.9999917235926102, "stage": "fusion_draft", "created_at": 1788705425.5864027}, {"event_id": "344d2aafeb894548aad30e0d1232e18c", "step": 40, "value": 0.9999815372450536, "stage": "debug", "created_at": 1788704053.7390583}, {"event_id": "de89c05f503d4a5ca4afab39059ef88d", "step": 41, "value": 0.9999847470056117, "stage": "improve", "created_at": 1788707548.676262}, {"event_id": "8bc2fb88b1c348c1a6846448dc252c0b", "step": 42, "value": 0.9999888321554131, "stage": "fusion", "created_at": 1788707900.5439491}], "maximize": true, "elapsed_seconds": 28683.090075969696, "node_count": 44, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.bnvs-root.aerial-cactus-identification.yaml", "note": ""}, {"id": "xixian.bnvs-root.aptos2019-blindness-detection", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "bnvs_root", "dataset": "aptos2019-blindness-detection", "status": "archived", "official_score": 0.91553, "medal": "bronze", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.930508, "silver": 0.919654, "bronze": 0.914492}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:68", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-four-methods-muse13/runs/bnvs_root/02_aptos2019-blindness-detection/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-four-methods-muse13/runs/bnvs_root/02_aptos2019-blindness-detection/logs/journal.json", "metrics": [{"event_id": "8b1c2f47e092499485fc0ce9d3672397", "step": 1, "value": 0.9159132282322635, "stage": "draft", "created_at": 1788682822.08935}, {"event_id": "a23ccc55dd72489db1efa162c54fd3df", "step": 5, "value": 0.9175112100150492, "stage": "debug", "created_at": 1788685194.250715}, {"event_id": "fcb225c97cfe47e594ef3451b3c8306b", "step": 6, "value": 0.9034959387737983, "stage": "debug", "created_at": 1788684897.2057686}, {"event_id": "41175f48531b42d58c449611b2ea22a9", "step": 7, "value": 0.9128282265208221, "stage": "improve", "created_at": 1788686411.7981565}, {"event_id": "28be41750de04b30ba95f707431e1d39", "step": 10, "value": 0.8888185195686034, "stage": "debug", "created_at": 1788684369.7017186}, {"event_id": "9aab20515c6d43d4a0b115a2486e3432", "step": 11, "value": 0.9175313716537856, "stage": "debug", "created_at": 1788690061.2427008}, {"event_id": "fd724793e71e4d62afbae252c2177547", "step": 16, "value": 0.9147680530383132, "stage": "improve", "created_at": 1788691433.846684}, {"event_id": "d748d52a91c24e0da680af4055858234", "step": 18, "value": 0.9130179197876174, "stage": "improve", "created_at": 1788691886.003183}, {"event_id": "32d80273dc2a4e6aa5ca638faa2df68a", "step": 19, "value": 0.9336050515581045, "stage": "improve", "created_at": 1788692558.2494283}, {"event_id": "4852beb5cba742298bf26dce2216c2b6", "step": 21, "value": 0.9198208116624274, "stage": "improve", "created_at": 1788693864.8454788}, {"event_id": "920c8750212d4b3db765df926519f269", "step": 22, "value": 0.8490183381548986, "stage": "debug", "created_at": 1788693111.5602148}, {"event_id": "87c6bca2674748d38ddbf9b66ce5ad37", "step": 24, "value": 0.9232283691652214, "stage": "improve", "created_at": 1788696267.7449675}, {"event_id": "9223b6785cb64704b7c8acaa2d52d756", "step": 25, "value": 0.9325795808367918, "stage": "improve", "created_at": 1788697682.8809655}, {"event_id": "9138a7fd057142489184f7374c479325", "step": 26, "value": 0.9254579326281211, "stage": "debug", "created_at": 1788695379.2045465}, {"event_id": "b28880c5f92b46a1816e49c43a81588a", "step": 30, "value": 0.9249070020495755, "stage": "improve", "created_at": 1788699422.1212559}, {"event_id": "46525d1b7d82454d95b0e331d7896b44", "step": 31, "value": 0.924475392064914, "stage": "evolution", "created_at": 1788699316.6182818}, {"event_id": "9c41b4b73f4f44e19e6523b1a8a7be32", "step": 34, "value": 0.9287078712931882, "stage": "fusion", "created_at": 1788703134.0926013}, {"event_id": "d3210e031a5141df8d8bbbae60e2932f", "step": 35, "value": 0.9231597317141269, "stage": "fusion", "created_at": 1788703358.7350252}, {"event_id": "949ecb766c1b4644818671783cabf7dc", "step": 36, "value": 0.8816906517285821, "stage": "fusion_draft", "created_at": 1788706830.4278429}, {"event_id": "8ad9bd26f61549a98ad544439dabc82b", "step": 38, "value": 0.9219191068691868, "stage": "evolution", "created_at": 1788706855.866662}, {"event_id": "4db1146cc14542cd9d0f9b481f7c7059", "step": 39, "value": 0.8774972246972471, "stage": "debug", "created_at": 1788709119.894068}, {"event_id": "107fe97e9d084be9bf1cb198afa35ce3", "step": 40, "value": 0.934015149057873, "stage": "evolution", "created_at": 1788709404.833421}, {"event_id": "55106d296398487ea007e175489a6e8b", "step": 41, "value": 0.9192523760771659, "stage": "evolution", "created_at": 1788709064.9016542}], "maximize": true, "elapsed_seconds": 28763.39432835579, "node_count": 42, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.bnvs-root.aptos2019-blindness-detection.yaml", "note": ""}, {"id": "xixian.bnvs-root.denoising-dirty-documents", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "bnvs_root", "dataset": "denoising-dirty-documents", "status": "archived", "official_score": 0.01166, "medal": "gold", "valid_submission": true, "score_maximize": false, "thresholds": {"gold": 0.01794, "silver": 0.02609, "bronze": 0.04517}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:69", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-four-methods-muse13/runs/bnvs_root/03_denoising-dirty-documents/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-four-methods-muse13/runs/bnvs_root/03_denoising-dirty-documents/logs/journal.json", "metrics": [{"event_id": "d2204471ccfa4c28af3c22a926f9333d", "step": 3, "value": 0.02426915880551473, "stage": "debug", "created_at": 1788683339.2860413}, {"event_id": "da0670eb92c9474bab9db98b62611035", "step": 5, "value": 0.03147936431227169, "stage": "improve", "created_at": 1788683702.2698824}, {"event_id": "22b4359c2dba49dc83d36e8232fe14d6", "step": 6, "value": 0.024745442830950797, "stage": "improve", "created_at": 1788684370.245312}, {"event_id": "df7c9e8c1c6d46aca20cc99720ec1295", "step": 9, "value": 0.019583846250764845, "stage": "debug", "created_at": 1788685391.8370676}, {"event_id": "f6daaa38ce6c42548265f4703cd8c216", "step": 14, "value": 0.019023563732390433, "stage": "draft", "created_at": 1788682958.5908387}, {"event_id": "ca7fac610d9144ddb282d62a0fa62a5b", "step": 19, "value": 0.03360993223560404, "stage": "debug", "created_at": 1788688949.238206}, {"event_id": "057feab093cb4bb489334bcf5c517b2a", "step": 20, "value": 0.020804158436433944, "stage": "debug", "created_at": 1788688257.3494556}, {"event_id": "d40a8d48e2464b87aa4213aaec170a44", "step": 22, "value": 0.018520802342850917, "stage": "debug", "created_at": 1788689994.2820327}, {"event_id": "d9c5ae772e1d46ac8a83be577ea1a494", "step": 23, "value": 0.05732405926807878, "stage": "improve", "created_at": 1788690459.121136}, {"event_id": "584278c67d7044bc8b0ec4f6c7b3f683", "step": 24, "value": 0.049259946508940194, "stage": "improve", "created_at": 1788689764.6848762}, {"event_id": "c4ba600b6b2a40d8a609d52908df96c3", "step": 25, "value": 0.01669799807865903, "stage": "improve", "created_at": 1788690966.104773}, {"event_id": "9b0f6c9905f74e0faa518db3295fd917", "step": 26, "value": 0.01672578863120029, "stage": "improve", "created_at": 1788691203.7165556}, {"event_id": "a4bbc87dce504a7aaedfce82a31a59a3", "step": 31, "value": 0.02970208994638868, "stage": "debug", "created_at": 1788688806.8734927}, {"event_id": "6e690e2ba68948f089885f8f9a1d3ad7", "step": 32, "value": 0.016826710562436578, "stage": "improve", "created_at": 1788692444.3217456}, {"event_id": "b8ddfdfd29534e7faddf497b6893069d", "step": 33, "value": 0.02401524510170003, "stage": "improve", "created_at": 1788691550.818305}, {"event_id": "2357dad083004725938fb7c1937c5549", "step": 34, "value": 0.014310115544916653, "stage": "draft", "created_at": 1788694693.025637}, {"event_id": "99253890a3264b019c0e8ee8e6f4d9b2", "step": 38, "value": 0.26125717851992875, "stage": "improve", "created_at": 1788698213.8972197}, {"event_id": "b1a23b050ad14f21939dbda966084d2b", "step": 39, "value": 0.01912206942827307, "stage": "improve", "created_at": 1788693236.6338186}, {"event_id": "878669d1a31d445c93fa3467ce896471", "step": 41, "value": 0.014019865284813872, "stage": "improve", "created_at": 1788700060.8276231}, {"event_id": "09a96d10b73c4da4af0adfed3418261d", "step": 42, "value": 0.015438901263791521, "stage": "debug", "created_at": 1788699990.2685804}, {"event_id": "71dbe892a5aa4b4b8780304db4cfce8f", "step": 43, "value": 0.014447567106193668, "stage": "improve", "created_at": 1788701364.1635077}, {"event_id": "e003501fff5d468aba27b9e0bb82135e", "step": 45, "value": 0.01354120597000436, "stage": "improve", "created_at": 1788702063.0094025}, {"event_id": "1a84504d632543c28c923c61cc6fb364", "step": 46, "value": 0.01785749408738887, "stage": "debug", "created_at": 1788698596.2633107}, {"event_id": "46ed8885e67a4dac88fe79711eeeaa94", "step": 47, "value": 0.014962441935005219, "stage": "improve", "created_at": 1788703233.5065033}, {"event_id": "05427d2df1c742e192f38a7c52c1e9c6", "step": 48, "value": 0.015005528405077571, "stage": "debug", "created_at": 1788702788.8669722}, {"event_id": "5d6be65fa4c6442aa900bab883a5b595", "step": 50, "value": 0.014133327890983835, "stage": "debug", "created_at": 1788705147.494576}, {"event_id": "1afa0907d9d24b3ea1f638dc67188f4c", "step": 51, "value": 0.015016389562672355, "stage": "improve", "created_at": 1788703243.791124}, {"event_id": "b522597d830d4c39bee55fc68f36fd25", "step": 53, "value": 0.013910894820273296, "stage": "improve", "created_at": 1788704222.5397038}, {"event_id": "eca01d73d2e8438b8787ded09f744d85", "step": 59, "value": 0.023477657502354057, "stage": "evolution", "created_at": 1788706507.1969829}, {"event_id": "396ee37e5c514fac8bd7c53e61900e99", "step": 60, "value": 0.03294624484403561, "stage": "debug", "created_at": 1788707909.2292178}, {"event_id": "2731957fa2fd4675b47b4935a993cf46", "step": 62, "value": 0.016933111203882564, "stage": "improve", "created_at": 1788708962.8538115}, {"event_id": "96c96f1b5b754a658390b80c55aa56ef", "step": 63, "value": 0.014413868398316803, "stage": "debug", "created_at": 1788710696.7794487}], "maximize": false, "elapsed_seconds": 28768.243178844452, "node_count": 64, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.bnvs-root.denoising-dirty-documents.yaml", "note": ""}, {"id": "xixian.bnvs-root.detecting-insults-in-social-commentary", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "bnvs_root", "dataset": "detecting-insults-in-social-commentary", "status": "archived", "official_score": 0.94697, "medal": "gold", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.83321, "silver": 0.82307, "bronze": 0.79111}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:70", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-four-methods-muse13/runs/bnvs_root/04_detecting-insults-in-social-commentary/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-four-methods-muse13/runs/bnvs_root/04_detecting-insults-in-social-commentary/logs/journal.json", "metrics": [{"event_id": "978ca74f05de4f789a8bed23b9c09a01", "step": 6, "value": 0.9564655172413793, "stage": "debug", "created_at": 1788683296.7313395}, {"event_id": "0bbb91cb193d462d9aa2b6ba3817f6c8", "step": 7, "value": 0.9060090208060526, "stage": "debug", "created_at": 1788683415.6830087}, {"event_id": "92b95884e9ff422f9b9171511d6af2b9", "step": 10, "value": 0.9525898443183471, "stage": "improve", "created_at": 1788683718.9447718}, {"event_id": "659aaf34e1f64ee0b28cb7827246ea46", "step": 11, "value": 0.873541393860032, "stage": "debug", "created_at": 1788683739.886983}, {"event_id": "598239e10eaa41e69215ff918b29efa3", "step": 14, "value": 0.9458751636839807, "stage": "improve", "created_at": 1788684075.0633712}, {"event_id": "88dca642a84b4fa9a2cfdfde8be7805f", "step": 16, "value": 0.951171249818129, "stage": "debug", "created_at": 1788684809.2994587}, {"event_id": "ef5414ae4b7f486b9d23df7f66f130f1", "step": 17, "value": 0.9574639895242253, "stage": "debug", "created_at": 1788684542.0364377}, {"event_id": "cedbc5c8341e49b584593c9f4af784d2", "step": 18, "value": 0.9541903099083371, "stage": "improve", "created_at": 1788685074.0161676}, {"event_id": "9d182c7f19034736bf4c8705a821cc97", "step": 19, "value": 0.8361478163493842, "stage": "debug", "created_at": 1788683778.3941662}, {"event_id": "f94b581390964d25b592b8698cd3be89", "step": 20, "value": 0.9591081041757602, "stage": "improve", "created_at": 1788685831.7988071}, {"event_id": "ea2d97f334ee4d738051bac1468eb49e", "step": 21, "value": 0.9480123180291153, "stage": "improve", "created_at": 1788686231.5963285}, {"event_id": "1bd62435c2644733a50f321d69f6823e", "step": 23, "value": 0.9532642777155655, "stage": "improve", "created_at": 1788686631.2609103}, {"event_id": "5f76879e803a45abb8b422cddf1ba7d7", "step": 24, "value": 0.9551063829787234, "stage": "debug", "created_at": 1788687276.625436}, {"event_id": "f14b3fba5f6c4ede98d48333d388653e", "step": 25, "value": 0.9508286674132139, "stage": "improve", "created_at": 1788687515.7361557}, {"event_id": "5514ac41d68b44488a50ec77df0809f7", "step": 27, "value": 0.9562199912701878, "stage": "debug", "created_at": 1788687907.4758027}, {"event_id": "f5b022a8ae614adfa10065c37e85d33d", "step": 28, "value": 0.547508398656215, "stage": "improve", "created_at": 1788688534.4572933}, {"event_id": "9e9b7d3fc9264928bf29e53cc1559a3a", "step": 29, "value": 0.9513885778275476, "stage": "improve", "created_at": 1788687460.5731144}, {"event_id": "f0ec57d86213423594294e23f47a0742", "step": 30, "value": 0.9417788211981439, "stage": "evolution", "created_at": 1788690220.068343}, {"event_id": "9055ff1ef4fb4fa98a154952384c5a8b", "step": 31, "value": 0.9443474465298995, "stage": "improve", "created_at": 1788685701.9775207}, {"event_id": "3ca6e6754a254aadba6a2b0d9b7b4363", "step": 32, "value": 0.9436954087346024, "stage": "evolution", "created_at": 1788690857.0410895}], "maximize": true, "elapsed_seconds": 28766.734939813614, "node_count": 35, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.bnvs-root.detecting-insults-in-social-commentary.yaml", "note": ""}, {"id": "xixian.bnvs-root.dog-breed-identification", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "bnvs_root", "dataset": "dog-breed-identification", "status": "archived", "official_score": 0.27892, "medal": "none", "valid_submission": true, "score_maximize": false, "thresholds": {"gold": 0.0005, "silver": 0.00539, "bronze": 0.04598}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:71", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-four-methods-muse13/runs/bnvs_root/05_dog-breed-identification/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-four-methods-muse13/runs/bnvs_root/05_dog-breed-identification/logs/journal.json", "metrics": [{"event_id": "ade35b88fe1f4315abaa8a77380b27d8", "step": 4, "value": 0.4526382348343772, "stage": "debug", "created_at": 1788683361.724656}, {"event_id": "447a21e443d54862b571083aebc117bd", "step": 5, "value": 0.5144413944793103, "stage": "draft", "created_at": 1788682757.2105548}, {"event_id": "3f9ad58f4e014865bbd574e868ccbbc8", "step": 6, "value": 0.47182064031576226, "stage": "debug", "created_at": 1788683498.450247}, {"event_id": "2f0e795c69d24ca68805192ee7d99e9a", "step": 9, "value": 0.6141530911379975, "stage": "draft", "created_at": 1788684930.5045295}, {"event_id": "c15fd6685d1245c1a46410090876b42c", "step": 10, "value": 0.4270753440771632, "stage": "debug", "created_at": 1788685245.1373277}, {"event_id": "52ae6c20e534477caeb92cc01cef714f", "step": 11, "value": 0.4013542435860638, "stage": "debug", "created_at": 1788685427.3604364}, {"event_id": "100d36a381ee46bbb9f7a55a2084c486", "step": 13, "value": 0.3594256833660675, "stage": "improve", "created_at": 1788686113.5340846}, {"event_id": "680e5f74964049b7a9e84bd006260c16", "step": 14, "value": 0.5182419624150757, "stage": "debug", "created_at": 1788687813.801417}, {"event_id": "56f8365859d0447bbbeacb9b93ff2808", "step": 17, "value": 0.5168385890606743, "stage": "debug", "created_at": 1788689899.2076426}, {"event_id": "b6cc3eb7a4af472284de6384e784d4f8", "step": 18, "value": 0.364768915171949, "stage": "debug", "created_at": 1788689564.812504}, {"event_id": "d7d805ab7ac24e939be5738f215d48a0", "step": 20, "value": 0.24896858206733072, "stage": "improve", "created_at": 1788687585.5407593}, {"event_id": "d38eaf3f0baa4d9e8ce65a70359299fe", "step": 21, "value": 0.2459352881914411, "stage": "debug", "created_at": 1788692203.340341}, {"event_id": "78f103871ffb400dbad726e362a9c580", "step": 29, "value": 0.4151165318481985, "stage": "debug", "created_at": 1788699716.1400683}, {"event_id": "c038f8214b9943a994791b0ddb3b9cd9", "step": 30, "value": 0.43353971683233605, "stage": "debug", "created_at": 1788698137.6062574}, {"event_id": "4bb88794c65745f1962f5e743e9108e6", "step": 31, "value": 0.43689873016692277, "stage": "improve", "created_at": 1788703719.822764}, {"event_id": "77d1af6d4a57456fb486dc54eb592a08", "step": 32, "value": 0.38592711696464954, "stage": "improve", "created_at": 1788707469.3041658}, {"event_id": "4aef35594dd6430aa84e801207b771bf", "step": 36, "value": 0.41553773264857363, "stage": "improve", "created_at": 1788709622.38039}], "maximize": false, "elapsed_seconds": 28772.587955713272, "node_count": 37, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.bnvs-root.dog-breed-identification.yaml", "note": ""}, {"id": "xixian.bnvs-root.dogs-vs-cats-redux-kernels-edition", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "bnvs_root", "dataset": "dogs-vs-cats-redux-kernels-edition", "status": "archived", "official_score": 0.0034, "medal": "gold", "valid_submission": true, "score_maximize": false, "thresholds": {"gold": 0.03882, "silver": 0.05038, "bronze": 0.06127}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:72", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-four-methods-muse13/runs/bnvs_root/06_dogs-vs-cats-redux-kernels-edition/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-four-methods-muse13/runs/bnvs_root/06_dogs-vs-cats-redux-kernels-edition/logs/journal.json", "metrics": [{"event_id": "cc475b30305c42f490671c817c23334a", "step": 3, "value": 0.006065932119418488, "stage": "debug", "created_at": 1788683359.2239003}, {"event_id": "f3c2995643a54c7ba067b2f4a3634e8d", "step": 4, "value": 0.0026413574663663045, "stage": "draft", "created_at": 1788682770.656081}, {"event_id": "bb603087c189473bb9e58f1a1f93027b", "step": 7, "value": 0.022986987452516417, "stage": "debug", "created_at": 1788683552.200118}, {"event_id": "557bd667ba28434cbe9796ec1970358f", "step": 8, "value": 0.0023538629067923274, "stage": "improve", "created_at": 1788684071.8936117}, {"event_id": "fd6cb22f116e4a62b923435f9f3390ba", "step": 10, "value": 0.0006507349060296502, "stage": "debug", "created_at": 1788684824.1583383}, {"event_id": "72e354ac6e5f4a0b8d180eec1855a25d", "step": 11, "value": 0.017356565794787192, "stage": "debug", "created_at": 1788686073.387115}, {"event_id": "89f9200c9a7448248efa6e0a00c74e7e", "step": 14, "value": 0.0026666552957633864, "stage": "improve", "created_at": 1788687103.4653234}, {"event_id": "0ff3d2fe28a64de38f2da527d592bb0c", "step": 15, "value": 0.0032046520603322523, "stage": "debug", "created_at": 1788687815.5941002}, {"event_id": "ce4daa95b9c441499aa97e48150d712c", "step": 16, "value": 0.0014332223975257856, "stage": "debug", "created_at": 1788687563.7448487}, {"event_id": "b9cf623a4af64968b387826d55502de4", "step": 17, "value": 0.014947554124182168, "stage": "improve", "created_at": 1788690882.3831239}, {"event_id": "7e7019b5c7374dccb8538f0a7db5eef3", "step": 18, "value": 0.0027305522338031654, "stage": "improve", "created_at": 1788691012.874606}, {"event_id": "3b43ece3c6df47eb8f5e9bc7ab32d1b6", "step": 19, "value": 0.00613905559270955, "stage": "improve", "created_at": 1788693263.2005723}, {"event_id": "524f507085b7468f8f31abf41740baf2", "step": 20, "value": 0.0027628159831178394, "stage": "improve", "created_at": 1788695967.3644698}, {"event_id": "fa397bc755fe4e6b9219f924ff33697e", "step": 21, "value": 0.0038315835553148375, "stage": "improve", "created_at": 1788692046.2440226}, {"event_id": "057f60b4951341e7b7d763dee9517994", "step": 23, "value": 0.011562239452905904, "stage": "evolution", "created_at": 1788698870.9938402}, {"event_id": "1eb0e6e15bf9421782bbb2579709e0b2", "step": 25, "value": 0.0010736129534535811, "stage": "debug", "created_at": 1788703705.4438453}, {"event_id": "aec9c0ee0c414c058b580b284e537d80", "step": 26, "value": 0.007681703010677078, "stage": "fusion_draft", "created_at": 1788706807.5251107}, {"event_id": "8ab2aefc00e24eb8aead5ceefafcff26", "step": 27, "value": 0.004301064266778284, "stage": "improve", "created_at": 1788695291.7517066}], "maximize": false, "elapsed_seconds": 28769.30473923683, "node_count": 28, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.bnvs-root.dogs-vs-cats-redux-kernels-edition.yaml", "note": ""}, {"id": "xixian.bnvs-root.histopathologic-cancer-detection", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "bnvs_root", "dataset": "histopathologic-cancer-detection", "status": "archived", "official_score": 0.99676, "medal": "gold", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.9835, "silver": 0.9798, "bronze": 0.9738}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:73", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-four-methods-muse13/runs/bnvs_root/07_histopathologic-cancer-detection/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-four-methods-muse13/runs/bnvs_root/07_histopathologic-cancer-detection/logs/journal.json", "metrics": [{"event_id": "5b9f30094519414c9259a534c5e2dbfd", "step": 2, "value": 0.9951171021668791, "stage": "draft", "created_at": 1788683440.933644}, {"event_id": "9b5b6240f2a74214afd40a709d5d3702", "step": 3, "value": 0.9961308193363094, "stage": "debug", "created_at": 1788683563.4213}, {"event_id": "0a1b188c4b2c415aa14f10dbaae2e6ef", "step": 4, "value": 0.9960029085801587, "stage": "draft", "created_at": 1788683231.0463142}], "maximize": true, "elapsed_seconds": 28762.859552145004, "node_count": 7, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.bnvs-root.histopathologic-cancer-detection.yaml", "note": ""}, {"id": "xixian.bnvs-root.jigsaw-toxic-comment-classification-challenge", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "bnvs_root", "dataset": "jigsaw-toxic-comment-classification-challenge", "status": "archived", "official_score": 0.98808, "medal": "gold", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.9874, "silver": 0.98668, "bronze": 0.98639}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:74", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-four-methods-muse13/runs/bnvs_root/08_jigsaw-toxic-comment-classification-challenge/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-four-methods-muse13/runs/bnvs_root/08_jigsaw-toxic-comment-classification-challenge/logs/journal.json", "metrics": [{"event_id": "c92ed1aee565429eb0fb31d67694ba5c", "step": 4, "value": 0.9753417144262116, "stage": "debug", "created_at": 1788683524.8390093}, {"event_id": "63840882d90e4902ae7553e782e1fa04", "step": 5, "value": 0.9901048010633998, "stage": "debug", "created_at": 1788683282.9053538}, {"event_id": "f806e7e0c4ba4e93b7b1cec37d588263", "step": 6, "value": 0.979919105353114, "stage": "improve", "created_at": 1788686812.7896583}, {"event_id": "47ed8c95d8854f64bbebe3be1c2e8343", "step": 7, "value": 0.9932995277442497, "stage": "draft", "created_at": 1788682985.6438987}, {"event_id": "2f36854c5e3f405aa681c6c7f166de45", "step": 9, "value": 0.9796829861820876, "stage": "improve", "created_at": 1788694638.678088}, {"event_id": "12358727fa13410a8f7328a43e560a56", "step": 10, "value": 0.976695535686756, "stage": "improve", "created_at": 1788701793.119875}], "maximize": true, "elapsed_seconds": 28770.19590163231, "node_count": 11, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.bnvs-root.jigsaw-toxic-comment-classification-challenge.yaml", "note": ""}, {"id": "xixian.bnvs-root.leaf-classification", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "bnvs_root", "dataset": "leaf-classification", "status": "archived", "official_score": 0.03474, "medal": "none", "valid_submission": true, "score_maximize": false, "thresholds": {"gold": 0.0, "silver": 0.00791, "bronze": 0.01526}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:75", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-four-methods-muse13/runs/bnvs_root/09_leaf-classification/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-four-methods-muse13/runs/bnvs_root/09_leaf-classification/logs/journal.json", "metrics": [{"event_id": "4550281d8f884e42821668d2a17aff5f", "step": 2, "value": 0.1351700163668469, "stage": "draft", "created_at": 1788682939.7754757}, {"event_id": "36993f11e8624971a5e56d2ee5c3ca82", "step": 3, "value": 7.207319571255197e-05, "stage": "debug", "created_at": 1788683233.563274}, {"event_id": "fc9e7242e2cc4551b72c897a23cb33e7", "step": 5, "value": 0.008135935742155613, "stage": "improve", "created_at": 1788683329.3144076}, {"event_id": "512d84f8a48f440ca1df81ce81ee30b7", "step": 6, "value": 0.011120878159999847, "stage": "debug", "created_at": 1788683491.818606}, {"event_id": "ff1272bf2ff443f797c086b973321c9a", "step": 7, "value": 0.00020470754486948993, "stage": "improve", "created_at": 1788683528.4215734}, {"event_id": "78a351943ce0475486eca2dc5b6b3053", "step": 8, "value": 0.010447228327393532, "stage": "improve", "created_at": 1788683878.3204148}, {"event_id": "c0094cef3b2549dfbe34cba4745852dd", "step": 9, "value": 4.5776150884016514e-05, "stage": "draft", "created_at": 1788684063.8808692}, {"event_id": "0bb37eb6edc84d7f8c77a942746b2280", "step": 10, "value": 0.10120873293455088, "stage": "improve", "created_at": 1788684161.5246024}, {"event_id": "606c4f7472b5445f9c172ffbc2655b2d", "step": 11, "value": 0.013308369145079567, "stage": "improve", "created_at": 1788684220.9697695}, {"event_id": "402e2845be704678a8ad7b3807809b86", "step": 12, "value": 0.05272689692345526, "stage": "improve", "created_at": 1788683799.7495928}, {"event_id": "9ce6144ee4c4471b8c34920bd463a6ed", "step": 13, "value": 1.8040900295796407, "stage": "improve", "created_at": 1788684413.9852502}, {"event_id": "d9b7604f0b014fe29ad7d5620f44d33c", "step": 14, "value": 0.02506792805437609, "stage": "improve", "created_at": 1788684549.837961}, {"event_id": "14e15d08a56f413fb7e850493cec4ec6", "step": 16, "value": 0.05324946275740266, "stage": "improve", "created_at": 1788684423.8016129}, {"event_id": "5d3b44657e9643a3a2833bbc84cb723c", "step": 21, "value": 4.906385129288537e-07, "stage": "debug", "created_at": 1788685069.9742284}, {"event_id": "e96efbd8943e41e88befe5aaf3dc98ff", "step": 22, "value": 0.030280242365785692, "stage": "improve", "created_at": 1788685280.2366045}, {"event_id": "3bcb6ec6d9794ff7b1313a18995af8ca", "step": 23, "value": 0.01126624215733932, "stage": "improve", "created_at": 1788685194.5332706}, {"event_id": "a38c69d8562d477ab7620fb6e5f3ec4e", "step": 24, "value": 0.008713087067008018, "stage": "improve", "created_at": 1788685741.7672544}, {"event_id": "11138417984a4f968690c68505b5ad5e", "step": 25, "value": 0.03028570581533903, "stage": "improve", "created_at": 1788685657.294838}, {"event_id": "f68bb9aaaa254d43ad38b48f900fdbda", "step": 26, "value": 0.14351167741138918, "stage": "improve", "created_at": 1788684828.3027718}, {"event_id": "311f9b31332843bfbfc6d489188a328e", "step": 27, "value": 0.01952751995771969, "stage": "improve", "created_at": 1788686011.9517844}, {"event_id": "e13ed5b67e7f4813b2c8f6d1a770135e", "step": 28, "value": 0.010669155455574796, "stage": "improve", "created_at": 1788686919.973998}, {"event_id": "17e747de934542a1a7c3cbe7150e5634", "step": 29, "value": 0.008153487347742969, "stage": "improve", "created_at": 1788687286.6389396}, {"event_id": "6e0653785cd64e6296b8abcfee5b5715", "step": 30, "value": 0.007896572693361938, "stage": "improve", "created_at": 1788687927.4645948}, {"event_id": "aafeb89d460a468686d525ec4ddabcf3", "step": 31, "value": 0.008929270049512184, "stage": "improve", "created_at": 1788688549.964631}, {"event_id": "a8003533ee2f4d1ea018dea581d8bc7b", "step": 32, "value": 0.03804892579789597, "stage": "evolution", "created_at": 1788686389.6980605}, {"event_id": "2cc98a68251f4f2785cc37b8f06d3f17", "step": 33, "value": 0.00020788749847250538, "stage": "improve", "created_at": 1788686852.4216342}, {"event_id": "4ad39309502e47e5b91cd486ecebc316", "step": 35, "value": 0.32999383767839446, "stage": "debug", "created_at": 1788689703.680581}, {"event_id": "16127441585341d9a7eea7c1903a1de1", "step": 36, "value": 0.010473489613812332, "stage": "improve", "created_at": 1788689568.4850783}, {"event_id": "eca63c18859842bbacfe4ee0ab709652", "step": 37, "value": 0.03143684410163124, "stage": "evolution", "created_at": 1788690019.632465}, {"event_id": "18e2c7d3c65749e7aff528b9f755c2e8", "step": 38, "value": 0.10012630746764654, "stage": "improve", "created_at": 1788691929.4276323}, {"event_id": "924bfcb6e22b4098bfceff18a11735bd", "step": 39, "value": 0.04493538095885257, "stage": "evolution", "created_at": 1788692508.2545955}, {"event_id": "addd027ebcb8426ba2604573c0b2088f", "step": 40, "value": 0.006959302668806343, "stage": "improve", "created_at": 1788693207.8527117}, {"event_id": "19fa10cdf8034df8bc8feea7d28bcbf7", "step": 41, "value": 0.0010465552658033017, "stage": "evolution", "created_at": 1788693997.217136}, {"event_id": "f7ed597f908a4cec850de24ef0d4a66e", "step": 42, "value": 0.010473489613812332, "stage": "improve", "created_at": 1788690413.842784}, {"event_id": "99dbfa3cb8e4471cb88ce75c73968e9c", "step": 43, "value": 0.007642636775461523, "stage": "improve", "created_at": 1788689400.760099}, {"event_id": "3bda0d35505d4bfa9de0180f0b28c23c", "step": 44, "value": 0.0010465552658033017, "stage": "evolution", "created_at": 1788694999.1481104}, {"event_id": "b4cf1a28bac74f60abc6b451f701640e", "step": 46, "value": 0.043906996343133914, "stage": "improve", "created_at": 1788695942.165513}, {"event_id": "9d9158f23d5e4d418405a4490b406b51", "step": 47, "value": 0.06586219294716274, "stage": "evolution", "created_at": 1788695868.5311117}, {"event_id": "f12720fbe1a24358a2bab3b5a9a6421f", "step": 49, "value": 0.003177301672039782, "stage": "debug", "created_at": 1788696238.2724683}, {"event_id": "2fc6c1072d864130a978c298dbb317e7", "step": 50, "value": 0.043906996343133914, "stage": "evolution", "created_at": 1788697440.8769107}, {"event_id": "855760db09aa4535bfb3ddb8948fca64", "step": 51, "value": 0.017187756992223188, "stage": "evolution", "created_at": 1788697367.2257676}, {"event_id": "1994e9dbb00941f6985e94c16ac59f92", "step": 52, "value": 0.041272903554085576, "stage": "evolution", "created_at": 1788698197.8053002}, {"event_id": "5ac8236b5c5f4eaf8349befb73a6f7a7", "step": 53, "value": 0.03173981455881878, "stage": "evolution", "created_at": 1788699172.2129517}, {"event_id": "96441061522e42e4a584095f0eb0ce9e", "step": 54, "value": 0.04671166923827441, "stage": "fusion", "created_at": 1788699017.4092803}, {"event_id": "6d5a0a2e8c694efa9b472b4d1fb76306", "step": 55, "value": 0.025845108145502362, "stage": "evolution", "created_at": 1788700863.143581}, {"event_id": "7269a5001fcf45f597100a50611c4c05", "step": 56, "value": 0.016201058759237132, "stage": "fusion", "created_at": 1788701119.0023575}, {"event_id": "11b0d75859b8474c8feef934aa79411d", "step": 57, "value": 0.009067758365351121, "stage": "evolution", "created_at": 1788698786.1339903}, {"event_id": "cb8d3a8a7e994756ad5dc858caaff6d7", "step": 58, "value": 0.010934653546075772, "stage": "evolution", "created_at": 1788702088.7941663}, {"event_id": "b016f52117694f95a39cb271a7833eb1", "step": 60, "value": 0.016574548837684597, "stage": "evolution", "created_at": 1788702555.3983169}, {"event_id": "21605248059e41a2bfa5b3709f045ddc", "step": 61, "value": 0.16712465496126977, "stage": "evolution", "created_at": 1788702641.7972965}, {"event_id": "55aa2b4bad014da7bb2308cecdeb2b77", "step": 64, "value": 0.08039316169163341, "stage": "fusion_draft", "created_at": 1788706257.9791694}, {"event_id": "340a22bf9c4245f49bf335cb21db5a51", "step": 65, "value": 0.0777948542024241, "stage": "improve", "created_at": 1788707148.8567567}, {"event_id": "65137a594317475684c38a43f191b223", "step": 67, "value": 0.015660046813908934, "stage": "debug", "created_at": 1788708609.3443842}, {"event_id": "2f5ca4dc7dd04705b8d39ffd12adc25d", "step": 68, "value": 0.5888309225419727, "stage": "debug", "created_at": 1788706608.9510999}, {"event_id": "7aba3ec71f0d44b297f9b01485cb6c5c", "step": 69, "value": 0.015221928779083757, "stage": "improve", "created_at": 1788709425.85544}, {"event_id": "02dc42755d6840e6ad38f20c29bcf858", "step": 70, "value": 0.006757198234910052, "stage": "improve", "created_at": 1788710073.083784}, {"event_id": "17a08d4ebb21453680ab0fac3c58376c", "step": 71, "value": 0.006933639744643625, "stage": "improve", "created_at": 1788710387.940852}], "maximize": false, "elapsed_seconds": 28770.310168027878, "node_count": 72, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.bnvs-root.leaf-classification.yaml", "note": ""}, {"id": "xixian.bnvs-root.mlsp-2013-birds", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "bnvs_root", "dataset": "mlsp-2013-birds", "status": "archived", "official_score": 0.88077, "medal": "bronze", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.93527, "silver": 0.90038, "bronze": 0.87372}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:76", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-four-methods-muse13/runs/bnvs_root/10_mlsp-2013-birds/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-four-methods-muse13/runs/bnvs_root/10_mlsp-2013-birds/logs/journal.json", "metrics": [{"event_id": "4733ddf214c441cdaf029707139f3a78", "step": 3, "value": 0.7701834619858307, "stage": "draft", "created_at": 1788682781.2539701}, {"event_id": "48a090f1d1194443b5f6603288af106a", "step": 5, "value": 0.8605150367628704, "stage": "debug", "created_at": 1788683304.3053963}, {"event_id": "e9f88b1adc9640da88053839610c502f", "step": 7, "value": 0.8422729195305065, "stage": "improve", "created_at": 1788683540.9272935}, {"event_id": "5994d7a4968641a49b3f31fe127d3086", "step": 8, "value": 0.819949960863245, "stage": "debug", "created_at": 1788683413.362831}, {"event_id": "8ddff1e0fdba46cfbc3f1b9f3bac5a24", "step": 10, "value": 0.8444340171301681, "stage": "improve", "created_at": 1788683813.183726}, {"event_id": "a489092227644225acbc301268d56c53", "step": 11, "value": 0.7919951358604496, "stage": "improve", "created_at": 1788683818.9493074}, {"event_id": "970a740f2d85469fbc541a1ae50ce508", "step": 12, "value": 0.845002379190018, "stage": "improve", "created_at": 1788684081.4475667}, {"event_id": "70d3f9902aac449f8257859fd067caea", "step": 13, "value": 0.7862084870848709, "stage": "improve", "created_at": 1788684207.2411714}, {"event_id": "1299693a5f004820b8b07de276f7ec0d", "step": 14, "value": 0.8174480040254948, "stage": "improve", "created_at": 1788684403.5197804}, {"event_id": "7fa9c568a17348598690255026d6f2f0", "step": 15, "value": 0.8523708664056538, "stage": "improve", "created_at": 1788684600.9240675}, {"event_id": "08cf317c7d504211bd3fdb50d65e5603", "step": 17, "value": 0.8392130168129428, "stage": "debug", "created_at": 1788684939.1795485}, {"event_id": "4c1630ef783b4d73bd95e1d5dfde3f0a", "step": 18, "value": 0.8204087507196316, "stage": "evolution", "created_at": 1788684822.453881}, {"event_id": "2fb4ed8412d94f2cb9beafd74c42c4c3", "step": 19, "value": 0.5881060881595743, "stage": "improve", "created_at": 1788685246.2568681}, {"event_id": "05c480065fb0459fa868f73f4a10462e", "step": 21, "value": 0.8073353460807334, "stage": "improve", "created_at": 1788685521.1191757}, {"event_id": "b863acd6656240a3bea89e01e5f291c7", "step": 22, "value": 0.7687978190132796, "stage": "debug", "created_at": 1788685830.5934455}, {"event_id": "8a3e8b3f9cae4bb2a835e7ad8b4b611e", "step": 23, "value": 0.7998294755674829, "stage": "improve", "created_at": 1788685922.4079833}, {"event_id": "3a711c020f064684ad262ff1ee68a275", "step": 24, "value": 0.7506139098787064, "stage": "improve", "created_at": 1788686242.6608477}, {"event_id": "dd097408f52b4b0da091003bc7a57656", "step": 25, "value": 0.8449825526065349, "stage": "improve", "created_at": 1788686592.87103}, {"event_id": "9ee06d0bf88a4e408feb588d1d535e2f", "step": 26, "value": 0.8163516279664812, "stage": "improve", "created_at": 1788686525.2252414}, {"event_id": "feb39c3b4bd14379994765d04b6c6bad", "step": 28, "value": 0.8194657396637411, "stage": "improve", "created_at": 1788687013.0596056}, {"event_id": "8785e710ff09443f9984cc9813f453a0", "step": 29, "value": 0.8836443903986465, "stage": "evolution", "created_at": 1788687255.0512788}, {"event_id": "0f493a93470646c38327cee3609db1e0", "step": 30, "value": 0.8213360473723168, "stage": "improve", "created_at": 1788687661.5562205}, {"event_id": "099bb5f4edbb449a84d4cfb997deb69c", "step": 32, "value": 0.9038452312416043, "stage": "evolution", "created_at": 1788687945.4130576}, {"event_id": "cd9d8eecabd1476fb057c3a63ce48fdc", "step": 34, "value": 0.7186659820428888, "stage": "debug", "created_at": 1788688842.7515788}, {"event_id": "806184b7d91445d2be3f4a33ec5e5ee8", "step": 35, "value": 0.8239237510394679, "stage": "improve", "created_at": 1788689270.011026}, {"event_id": "7e1e916281a9454db74064b55e8b85c3", "step": 37, "value": 0.9171688095695003, "stage": "debug", "created_at": 1788689970.425702}, {"event_id": "cce6183fb7954202aec80836a55d3384", "step": 38, "value": 0.9180603530992133, "stage": "improve", "created_at": 1788690478.4162197}, {"event_id": "672b90ad397b47829813b3d5455e8611", "step": 39, "value": 0.9098741444380477, "stage": "improve", "created_at": 1788691042.147103}, {"event_id": "6063685b5193463f97f6271f5526053e", "step": 40, "value": 0.8022643101589235, "stage": "debug", "created_at": 1788688317.4588208}, {"event_id": "4e1449e4689d4f67841add0fa58eead6", "step": 41, "value": 0.9157631292778098, "stage": "improve", "created_at": 1788691591.727739}, {"event_id": "6fabd2235c4e46dcb86b4b4cece60842", "step": 42, "value": 0.8993123520757372, "stage": "improve", "created_at": 1788691885.8019812}, {"event_id": "0f73ca7fcb424cba837d4c646ab179fe", "step": 43, "value": 0.8194588370754173, "stage": "debug", "created_at": 1788687122.9381535}, {"event_id": "2ddb6d31e9a345188d2eb0720a3d2a33", "step": 44, "value": 0.8968600076760699, "stage": "improve", "created_at": 1788692219.277332}, {"event_id": "b422810e083146308ddbed6bf88e7744", "step": 45, "value": 0.856623009019382, "stage": "evolution", "created_at": 1788692545.8650682}, {"event_id": "9cc8722681e64e02b5e5822ee7ac5560", "step": 46, "value": 0.8849005309281648, "stage": "evolution", "created_at": 1788692648.3651733}, {"event_id": "a9da65602e5949f495bca44aaeafe43b", "step": 47, "value": 0.9064415019510011, "stage": "evolution", "created_at": 1788692791.8380444}, {"event_id": "f0de2fa63b80474aba14181e528f491a", "step": 48, "value": 0.9206470287212947, "stage": "evolution", "created_at": 1788693610.6879292}, {"event_id": "2e920ed9269f46149daf753b96b921bc", "step": 49, "value": 0.8707125951512826, "stage": "evolution", "created_at": 1788693509.8983514}, {"event_id": "16ea51b1d28a44c3a31af80f4b45875b", "step": 50, "value": 0.9269230154161069, "stage": "improve", "created_at": 1788694111.5826724}, {"event_id": "203b06d30c1448329e60d6e04ea86d95", "step": 51, "value": 0.7847885882428196, "stage": "evolution", "created_at": 1788694024.526952}, {"event_id": "b936b7c10ab0487d9052e149f515f497", "step": 52, "value": 0.8524707073732555, "stage": "improve", "created_at": 1788694915.4025388}, {"event_id": "2602781f64fc4316b72399fe6b6919f1", "step": 53, "value": 0.9293217872449305, "stage": "improve", "created_at": 1788694995.2647007}, {"event_id": "c4dbb6d38a9b4030a9937d2f078a41fd", "step": 54, "value": 0.9241900147124673, "stage": "improve", "created_at": 1788695213.3699384}, {"event_id": "a4a6f89aabe9422c9bcac44c7f003654", "step": 55, "value": 0.8459716625087954, "stage": "improve", "created_at": 1788695312.2510977}, {"event_id": "daf20b13a16741a7bc9d8d77e71406ae", "step": 56, "value": 0.9257188319580375, "stage": "improve", "created_at": 1788695619.4727864}, {"event_id": "e87b60a7b5bc49c19385df500ebdbcd4", "step": 59, "value": 0.931282383419689, "stage": "debug", "created_at": 1788696639.5161088}, {"event_id": "fc74917900e147548caba05744b91318", "step": 60, "value": 0.8813959252862534, "stage": "improve", "created_at": 1788696104.5059557}, {"event_id": "d3e0c4a9ca2b45a090356f57dbeec83f", "step": 61, "value": 0.9230146165163436, "stage": "debug", "created_at": 1788697219.2604194}, {"event_id": "364433ddfe6743efbb82882fcacb79a5", "step": 62, "value": 0.9282295464722062, "stage": "improve", "created_at": 1788697352.2728686}, {"event_id": "b723622eee14408a98b9ebb426b84390", "step": 63, "value": 0.9276570395957269, "stage": "improve", "created_at": 1788697642.2323098}, {"event_id": "0a8560c1c3f04d08b273f3799ed737fb", "step": 64, "value": 0.912530384443165, "stage": "improve", "created_at": 1788698175.035267}, {"event_id": "bcbc22b6a23d465b8d2ae5cd3ae8b3ba", "step": 65, "value": 0.8868707221902385, "stage": "evolution", "created_at": 1788698285.327448}, {"event_id": "6b5b4e42209b4e39a0dcc0210c2df102", "step": 66, "value": 0.8975868355402034, "stage": "evolution", "created_at": 1788698702.2713242}, {"event_id": "cb2f0941004b4a459c3900224b4c6170", "step": 67, "value": 0.8971222733960212, "stage": "fusion", "created_at": 1788698969.0689967}, {"event_id": "82518ed04f304f35b4ffce1f021f09c8", "step": 68, "value": 0.9332829591249281, "stage": "evolution", "created_at": 1788699434.7160103}, {"event_id": "949cc10cefd84017ba58a25357fb3091", "step": 69, "value": 0.9246641719439648, "stage": "evolution", "created_at": 1788698505.7094495}, {"event_id": "280a2f1231b94dcca14c347a873bc1ed", "step": 70, "value": 0.908168617667754, "stage": "evolution", "created_at": 1788699543.33553}, {"event_id": "dfc351bf1dab4811ada74141e7ce6bb5", "step": 71, "value": 0.9359711827544298, "stage": "improve", "created_at": 1788700525.6240368}, {"event_id": "100032bf789e4730a2c8fb26e0847079", "step": 72, "value": 0.9249656176037868, "stage": "improve", "created_at": 1788700687.8916326}, {"event_id": "d52aaa58acb843caba254a4ef89edc4f", "step": 73, "value": 0.8987646325081557, "stage": "improve", "created_at": 1788701103.8850896}, {"event_id": "97f2f1628a30463c808b010b44edd2dc", "step": 74, "value": 0.9241992100044778, "stage": "improve", "created_at": 1788701398.4605463}, {"event_id": "d2509252ea604006a5fa9b15717044a2", "step": 75, "value": 0.9396405040619203, "stage": "improve", "created_at": 1788701712.5460217}, {"event_id": "bd0c55513e024a19b8ec4079ac3fd31a", "step": 76, "value": 0.9290331350348622, "stage": "fusion", "created_at": 1788702285.9478672}, {"event_id": "cedc239143b246878aa2a2fab1295d04", "step": 77, "value": 0.9253654129085909, "stage": "improve", "created_at": 1788702890.2223637}, {"event_id": "973fc58469354175967e17aa34ac8aa9", "step": 78, "value": 0.8999856073690271, "stage": "improve", "created_at": 1788703532.1512625}, {"event_id": "ce0c14e6204d42b69172ccbfe2d461c6", "step": 80, "value": 0.8269, "stage": "debug", "created_at": 1788705007.1134906}, {"event_id": "12c01fdefa8741e281ec58d62bb41025", "step": 81, "value": 0.9373360839250304, "stage": "evolution", "created_at": 1788705731.8971558}, {"event_id": "f2989080b9c34e72ba1287bcbd1665e4", "step": 82, "value": 0.9439103179172263, "stage": "evolution", "created_at": 1788706760.664441}], "maximize": true, "elapsed_seconds": 28764.445328950882, "node_count": 83, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.bnvs-root.mlsp-2013-birds.yaml", "note": ""}, {"id": "xixian.bnvs-root.new-york-city-taxi-fare-prediction", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "bnvs_root", "dataset": "new-york-city-taxi-fare-prediction", "status": "archived", "official_score": 9.99279, "medal": "none", "valid_submission": true, "score_maximize": false, "thresholds": {"gold": 2.83377, "silver": 2.88191, "bronze": 2.92371}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:77", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-four-methods-muse13/runs/bnvs_root/11_new-york-city-taxi-fare-prediction/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-four-methods-muse13/runs/bnvs_root/11_new-york-city-taxi-fare-prediction/logs/journal.json", "metrics": [{"event_id": "d6c3232dceaa49469e64b1ebc5881808", "step": 2, "value": 3.7355499642040426, "stage": "draft", "created_at": 1788683295.5556312}, {"event_id": "0b4ad16096fd4152a8e1059fe2f2ef70", "step": 4, "value": 3.136592504687215, "stage": "debug", "created_at": 1788685960.847963}, {"event_id": "050a8702d6914a769609ecfe2a75a59f", "step": 6, "value": 2.8482066619971085, "stage": "debug", "created_at": 1788690605.3179822}, {"event_id": "38689ecbf2f0411b96e9582f3f857f9c", "step": 7, "value": 4.257108082451264, "stage": "improve", "created_at": 1788692989.137112}, {"event_id": "6f366a6b790241cea31ec58161f8e7cc", "step": 8, "value": 2.738788425782655, "stage": "improve", "created_at": 1788693811.2995787}, {"event_id": "e2f27830aa0846c8805171dfdf295871", "step": 9, "value": 2.715340624018159, "stage": "improve", "created_at": 1788698094.9843469}, {"event_id": "4481cf4744bc4e9b8b62884f0c33caae", "step": 13, "value": 4.220211122760808, "stage": "debug", "created_at": 1788705920.4242325}], "maximize": false, "elapsed_seconds": 28756.32645368576, "node_count": 15, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.bnvs-root.new-york-city-taxi-fare-prediction.yaml", "note": ""}, {"id": "xixian.bnvs-root.nomad2018-predict-transparent-conductors", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "bnvs_root", "dataset": "nomad2018-predict-transparent-conductors", "status": "archived", "official_score": 0.05999, "medal": "silver", "valid_submission": true, "score_maximize": false, "thresholds": {"gold": 0.05589, "silver": 0.06229, "bronze": 0.06582}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:78", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-four-methods-muse13/runs/bnvs_root/12_nomad2018-predict-transparent-conductors/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-four-methods-muse13/runs/bnvs_root/12_nomad2018-predict-transparent-conductors/logs/journal.json", "metrics": [{"event_id": "62ead2ca136d4fd59699b81443695467", "step": 1, "value": 0.07024432878902583, "stage": "draft", "created_at": 1788683118.9109955}, {"event_id": "7dbaf88961284d5294559a43527ec6d2", "step": 2, "value": 0.06904552344840503, "stage": "draft", "created_at": 1788682866.4466069}, {"event_id": "c4638d5e000e48beb97d38cd61f7ae8a", "step": 3, "value": 0.06836412700829309, "stage": "improve", "created_at": 1788683558.127439}, {"event_id": "79d0bd66568943d4a98314c4a541d879", "step": 4, "value": 0.06794089277428406, "stage": "improve", "created_at": 1788683562.3256214}, {"event_id": "8486f013afab40b7803ff989d5188394", "step": 5, "value": 0.06972639553890701, "stage": "improve", "created_at": 1788683816.1884007}, {"event_id": "8a55ef491cee4da68aeae3a019adc679", "step": 6, "value": 0.181035195737853, "stage": "draft", "created_at": 1788683311.4940374}, {"event_id": "14f940f93cb54b9a80c77d3e17d44047", "step": 7, "value": 0.06939950286495253, "stage": "improve", "created_at": 1788684078.0276186}, {"event_id": "d47cea37bb1b4293b574172302eac271", "step": 9, "value": 0.0655049834851148, "stage": "improve", "created_at": 1788684318.0666456}, {"event_id": "9de31ca44ef943b4bbf4e29806172e71", "step": 11, "value": 0.06293454179604124, "stage": "debug", "created_at": 1788684496.6377413}, {"event_id": "ec6c08f6d1ec45c4a83d8cadbd26a9ee", "step": 12, "value": 0.06666516587426022, "stage": "improve", "created_at": 1788684577.5686567}, {"event_id": "ef4b7a4d3ae54166b5646e3bfd1cac02", "step": 13, "value": 0.05821841041489449, "stage": "improve", "created_at": 1788684686.3963459}, {"event_id": "274e16c318f74de393311617e3c9504f", "step": 14, "value": 0.05949475220454246, "stage": "improve", "created_at": 1788684830.5705812}, {"event_id": "8893e17644084f9ebb650422c098700b", "step": 15, "value": 0.05807261133228757, "stage": "improve", "created_at": 1788684900.1407065}, {"event_id": "e9d99cc1edab4a2daffaabaa867cafea", "step": 16, "value": 0.06686328170678543, "stage": "improve", "created_at": 1788683774.4916623}, {"event_id": "ce9b1307ef62463db01279b2a9a8736c", "step": 17, "value": 0.056806565766793465, "stage": "improve", "created_at": 1788685143.6561594}, {"event_id": "d718fdbf73e44147b3c1d3051f5cea1d", "step": 19, "value": 0.05722449704251946, "stage": "improve", "created_at": 1788685392.7076569}, {"event_id": "8e43d919370f4af084c5f42f9aef5d6d", "step": 20, "value": 0.05799824954154413, "stage": "debug", "created_at": 1788685511.634686}, {"event_id": "afea75ec2db24b0b9d935369f1f1a64d", "step": 21, "value": 0.05743012075067181, "stage": "improve", "created_at": 1788685585.441703}, {"event_id": "e3b3ff80faf549e3ba22aaeeefb5b663", "step": 22, "value": 0.181035195737853, "stage": "improve", "created_at": 1788685028.975741}, {"event_id": "911f72079d164d5fb528c05806229483", "step": 23, "value": 0.18101243740878795, "stage": "improve", "created_at": 1788685861.0434606}, {"event_id": "6659c63005ea48aa841759eaccc9be2b", "step": 24, "value": 0.06862563089471543, "stage": "improve", "created_at": 1788689369.0530713}, {"event_id": "f0c72bf8572a4b4ba524327d6df55dc3", "step": 25, "value": 0.059337301148864305, "stage": "improve", "created_at": 1788689643.3848436}, {"event_id": "62d745134bc94d4e98b1dfee0689ea4d", "step": 26, "value": 0.0596380112188252, "stage": "improve", "created_at": 1788689886.1185033}, {"event_id": "3830eda50a8445cb84e08a67bf88914b", "step": 27, "value": 0.05951442116237836, "stage": "evolution", "created_at": 1788690257.0475576}, {"event_id": "207d7c7816ab4cc5a102a61159c83bd6", "step": 28, "value": 0.05681313934757938, "stage": "evolution", "created_at": 1788691062.8922098}, {"event_id": "ab4bd0227cd143398161420918547ff9", "step": 29, "value": 0.05943354678362171, "stage": "improve", "created_at": 1788691811.7921145}, {"event_id": "924fb19c7e2242bd8fe4550ba2557e65", "step": 30, "value": 0.05945905505785086, "stage": "improve", "created_at": 1788692230.7924914}, {"event_id": "f0fbe87f8cb149a09636c1853e507daf", "step": 31, "value": 0.05915179953717807, "stage": "evolution", "created_at": 1788692606.646614}, {"event_id": "32828ea6b4e34126be91ee005df2e22f", "step": 33, "value": 0.05936204936476584, "stage": "improve", "created_at": 1788697166.011541}, {"event_id": "c975aaba9d6d4652a069f7a17d8c520b", "step": 35, "value": 0.058928822537425804, "stage": "improve", "created_at": 1788697933.715032}, {"event_id": "44b344bcd8b94449acffad772cdcb99b", "step": 36, "value": 0.05909911233768618, "stage": "improve", "created_at": 1788701871.4891407}, {"event_id": "8522fa6e50a7422aba174ecef81c69fe", "step": 38, "value": 0.05951584261065808, "stage": "improve", "created_at": 1788705982.2855322}], "maximize": false, "elapsed_seconds": 28769.268060445786, "node_count": 41, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.bnvs-root.nomad2018-predict-transparent-conductors.yaml", "note": ""}, {"id": "xixian.bnvs-root.plant-pathology-2020-fgvc7", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "bnvs_root", "dataset": "plant-pathology-2020-fgvc7", "status": "archived", "official_score": 0.99303, "medal": "gold", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.97836, "silver": 0.97465, "bronze": 0.97361}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:79", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-four-methods-muse13/runs/bnvs_root/13_plant-pathology-2020-fgvc7/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-four-methods-muse13/runs/bnvs_root/13_plant-pathology-2020-fgvc7/logs/journal.json", "metrics": [{"event_id": "9a153a11250b4d17a5b23fa1aa846964", "step": 1, "value": 0.9889708569465923, "stage": "draft", "created_at": 1788682979.2993922}, {"event_id": "46b8f0a7647a4fe6833cb9aa03bb797f", "step": 7, "value": 0.9886605411221623, "stage": "debug", "created_at": 1788683620.623611}, {"event_id": "c76e2a6cb12e4fab9a78532a70fc8e3c", "step": 8, "value": 0.9901631879607657, "stage": "debug", "created_at": 1788683998.8501837}, {"event_id": "1f4571291ebb49beb29d0d84825cfaa5", "step": 10, "value": 0.9704953785680597, "stage": "improve", "created_at": 1788684855.3840833}, {"event_id": "df0f8dfe698a4fd8bfe4f6458cf7bb34", "step": 12, "value": 0.9668422031233681, "stage": "debug", "created_at": 1788685564.5720766}, {"event_id": "269ff2ca8b3b494f85cc26592f4aa911", "step": 13, "value": 0.9704953785680597, "stage": "debug", "created_at": 1788686478.9867513}, {"event_id": "5b43909bc5b044d5bf29cc37afb284fd", "step": 14, "value": 0.9873248450534213, "stage": "improve", "created_at": 1788687250.1742008}, {"event_id": "8f9f4c2d580e46e4b6f55e4ad375ef37", "step": 16, "value": 0.692399301734321, "stage": "debug", "created_at": 1788684763.4927049}, {"event_id": "33977493ad5e409592c108153c94a547", "step": 17, "value": 0.9866532571011754, "stage": "improve", "created_at": 1788688629.6834042}, {"event_id": "40fc9268228c4d318e24f105d2ac8a5b", "step": 18, "value": 0.7115282853748257, "stage": "debug", "created_at": 1788689308.1280107}, {"event_id": "f321607af0684cf994a60f54bf0a936a", "step": 21, "value": 0.9762123717250231, "stage": "improve", "created_at": 1788691109.9584975}, {"event_id": "5086ed4d2a6e485aaaeb79cec0ea0c74", "step": 22, "value": 0.9801390374521037, "stage": "debug", "created_at": 1788691112.2595932}, {"event_id": "6221d9e4433e428789ae743e1a7dbf61", "step": 23, "value": 0.9934710959468102, "stage": "improve", "created_at": 1788692490.9871993}, {"event_id": "cf25e0be3522411b88327b075d67d4be", "step": 24, "value": 0.9850891271041153, "stage": "improve", "created_at": 1788692582.1196418}, {"event_id": "62fb28f10cbd45568178e60771b98f14", "step": 26, "value": 0.993132257223631, "stage": "improve", "created_at": 1788694464.5390146}, {"event_id": "1b74b00a5d7940c9a133a22b57a56a9d", "step": 27, "value": 0.9933169251400102, "stage": "improve", "created_at": 1788696251.7770467}, {"event_id": "95e38cbfbd91469eb5304638b6d59efa", "step": 28, "value": 0.9935867988016982, "stage": "improve", "created_at": 1788696269.0613298}, {"event_id": "1b116b47062746dba11c0bf3fb1bc785", "step": 29, "value": 0.992505863362392, "stage": "improve", "created_at": 1788700828.0249941}, {"event_id": "f17d308fbe5844e3a2bad50379bd6664", "step": 30, "value": 0.708019939426771, "stage": "debug", "created_at": 1788691600.2604978}, {"event_id": "14ae7d8cac6946fb9c0ae5999cb57e13", "step": 31, "value": 0.9871473599836831, "stage": "improve", "created_at": 1788704460.151517}, {"event_id": "011d8c183770448bb410a2c0c9c8d8e1", "step": 32, "value": 0.9940474589823746, "stage": "improve", "created_at": 1788701535.7513578}, {"event_id": "60dafbb34f9243659f2ba063d8574e8a", "step": 36, "value": 0.9984680443476067, "stage": "debug", "created_at": 1788710031.4977233}, {"event_id": "885ebac6334f4639abfd06ebbf80079e", "step": 37, "value": 0.994944827275895, "stage": "improve", "created_at": 1788706655.349863}], "maximize": true, "elapsed_seconds": 28765.172204971313, "node_count": 38, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.bnvs-root.plant-pathology-2020-fgvc7.yaml", "note": ""}, {"id": "xixian.bnvs-root.random-acts-of-pizza", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "bnvs_root", "dataset": "random-acts-of-pizza", "status": "archived", "official_score": 0.69121, "medal": "none", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.97908, "silver": 0.76482, "bronze": 0.6921}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:80", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-four-methods-muse13/runs/bnvs_root/14_random-acts-of-pizza/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-four-methods-muse13/runs/bnvs_root/14_random-acts-of-pizza/logs/journal.json", "metrics": [{"event_id": "1545454360b04567bb24299a110b319b", "step": 3, "value": 0.6054349388928828, "stage": "draft", "created_at": 1788682761.0124948}, {"event_id": "47d9d6bc2ffd4f2e975bd2d91c3eca71", "step": 5, "value": 0.6059305726600985, "stage": "debug", "created_at": 1788683438.7769895}, {"event_id": "6aa6afd4ae7e4b559c2a048214decc83", "step": 6, "value": 0.6256937455068295, "stage": "improve", "created_at": 1788683433.3212109}, {"event_id": "97ba35ded564452ead34197abadbfda5", "step": 7, "value": 0.6378540640394089, "stage": "improve", "created_at": 1788683805.3517232}, {"event_id": "5997cc10d6174c61bb8140b274b5c502", "step": 8, "value": 0.641106065270936, "stage": "improve", "created_at": 1788684007.9248738}, {"event_id": "01b2449c5927476699455609c87a32d4", "step": 10, "value": 0.6218442118226601, "stage": "debug", "created_at": 1788683306.965443}, {"event_id": "0230a0f5afee4bda8eb7290c22a4f522", "step": 16, "value": 0.6394127155172413, "stage": "debug", "created_at": 1788684638.7500143}, {"event_id": "294c483fbac740139fe8a3638d3ba986", "step": 17, "value": 0.6220751231527094, "stage": "debug", "created_at": 1788684874.267506}, {"event_id": "b376bb1e70e5452f8f035ebe034096c0", "step": 18, "value": 0.6414909174876847, "stage": "debug", "created_at": 1788684494.0287423}, {"event_id": "fbb38bdec62040dcb64e93a2e97363e9", "step": 19, "value": 0.6210639827462258, "stage": "improve", "created_at": 1788685545.102047}, {"event_id": "72e0cc1cb6df41f98f5b9920a83ec003", "step": 20, "value": 0.6585398706896551, "stage": "improve", "created_at": 1788685407.8370144}, {"event_id": "d500f48058bc4cf6b4b73bc19c008791", "step": 21, "value": 0.6450123152709359, "stage": "improve", "created_at": 1788685914.9599173}, {"event_id": "d7e573ab8bda4e80bbc5ceac90b2ab7c", "step": 22, "value": 0.6980301941049605, "stage": "improve", "created_at": 1788685832.1564388}, {"event_id": "981768fc04224998a6939b9791ce251d", "step": 23, "value": 0.6508428263546799, "stage": "improve", "created_at": 1788686390.0989397}, {"event_id": "2ad2c52fbc0147f8b656685646409372", "step": 24, "value": 0.655151967773327, "stage": "improve", "created_at": 1788686875.2015262}, {"event_id": "577084cf54484bbe989ea7e0d42b3c93", "step": 25, "value": 0.6980301941049605, "stage": "improve", "created_at": 1788686745.938199}, {"event_id": "7040b8c2a4594c6692fe1cecbc37a4bb", "step": 26, "value": 0.6885549964054638, "stage": "improve", "created_at": 1788687756.1590936}, {"event_id": "2afc18d8d89f40c9afa3ec7c27be3f88", "step": 27, "value": 0.6934004313443565, "stage": "improve", "created_at": 1788688127.6987247}, {"event_id": "560a76534c6d4d9cbe24e5349383fd51", "step": 28, "value": 0.6826002476487913, "stage": "improve", "created_at": 1788688839.8903265}, {"event_id": "77f5a42fff634e0385a9638c00f06032", "step": 29, "value": 0.7036484551047659, "stage": "improve", "created_at": 1788689960.4749835}, {"event_id": "4b02240da6694142a171f91c6e8a67a0", "step": 31, "value": 0.6244708282019704, "stage": "debug", "created_at": 1788707101.991081}], "maximize": true, "elapsed_seconds": 28768.63463497162, "node_count": 32, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.bnvs-root.random-acts-of-pizza.yaml", "note": ""}, {"id": "xixian.bnvs-root.ranzcr-clip-catheter-line-classification", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "bnvs_root", "dataset": "ranzcr-clip-catheter-line-classification", "status": "archived", "official_score": 0.86963, "medal": "none", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.97357, "silver": 0.97152, "bronze": 0.9709}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:81", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-four-methods-muse13/runs/bnvs_root/15_ranzcr-clip-catheter-line-classification/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-four-methods-muse13/runs/bnvs_root/15_ranzcr-clip-catheter-line-classification/logs/journal.json", "metrics": [{"event_id": "1615166d4055451191c2dc1466fb4f45", "step": 5, "value": 0.88936358871644, "stage": "draft", "created_at": 1788682831.9220896}, {"event_id": "e00899847f684195a32f5d3f346c5da5", "step": 6, "value": 0.8559640200401204, "stage": "draft", "created_at": 1788690258.9460452}, {"event_id": "3ff88999d5c04dc691d9f02980d60b6b", "step": 7, "value": 0.8587398374002339, "stage": "improve", "created_at": 1788693023.6489365}, {"event_id": "008a47d7f2334bb89bd8f589d794ad52", "step": 8, "value": 0.7467227902305976, "stage": "debug", "created_at": 1788685564.4393303}, {"event_id": "75f3e3db2e6d4c109ac979023ef21313", "step": 11, "value": 0.923077095791997, "stage": "improve", "created_at": 1788698505.7246497}], "maximize": true, "elapsed_seconds": 28765.581112861633, "node_count": 13, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.bnvs-root.ranzcr-clip-catheter-line-classification.yaml", "note": ""}, {"id": "xixian.bnvs-root.siim-isic-melanoma-classification", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "bnvs_root", "dataset": "siim-isic-melanoma-classification", "status": "archived", "official_score": 0.89244, "medal": "none", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.9455, "silver": 0.9401, "bronze": 0.937}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:82", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-four-methods-muse13/runs/bnvs_root/16_siim-isic-melanoma-classification/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-four-methods-muse13/runs/bnvs_root/16_siim-isic-melanoma-classification/logs/journal.json", "metrics": [{"event_id": "40937cdd3b554e3a9f21adce2738479c", "step": 2, "value": 0.8935405775912544, "stage": "draft", "created_at": 1788682797.8658245}, {"event_id": "93ce044c4203404385e47d59e168a768", "step": 4, "value": 0.8487891991326006, "stage": "debug", "created_at": 1788686054.4342213}, {"event_id": "4af2d6779901411a82a18d6ab604cc68", "step": 5, "value": 0.8912642565887966, "stage": "improve", "created_at": 1788686061.9438145}, {"event_id": "b8bb094b3e1e4e87a38e96be4ff149a2", "step": 8, "value": 0.8382015223389747, "stage": "debug", "created_at": 1788691163.7341046}, {"event_id": "b605ec6a846e4c5daa3dc5d993fc9d85", "step": 10, "value": 0.8890712049337527, "stage": "draft", "created_at": 1788683196.3377569}, {"event_id": "11e8217498e845b29f95fe360baf13fa", "step": 12, "value": 0.8806496060921607, "stage": "debug", "created_at": 1788697105.9723485}], "maximize": true, "elapsed_seconds": 28768.485810995102, "node_count": 14, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.bnvs-root.siim-isic-melanoma-classification.yaml", "note": ""}, {"id": "xixian.bnvs-root.spooky-author-identification", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "bnvs_root", "dataset": "spooky-author-identification", "status": "archived", "official_score": 0.20503, "medal": "silver", "valid_submission": true, "score_maximize": false, "thresholds": {"gold": 0.16506, "silver": 0.26996, "bronze": 0.29381}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:83", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-four-methods-muse13/runs/bnvs_root/17_spooky-author-identification/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-four-methods-muse13/runs/bnvs_root/17_spooky-author-identification/logs/journal.json", "metrics": [{"event_id": "f70776437ae5415e81919f101e4309c8", "step": 5, "value": 0.4143343740951677, "stage": "debug", "created_at": 1788683335.914297}, {"event_id": "612d6575b45d4e4c9d61087c9f4b9151", "step": 6, "value": 0.49022686894620426, "stage": "draft", "created_at": 1788683719.735944}, {"event_id": "c15b3a89ad6c43ddab3a4d491133d48a", "step": 7, "value": 0.2980685024501976, "stage": "debug", "created_at": 1788683260.5989292}, {"event_id": "9f95963e7923457c9a01f4296c141241", "step": 9, "value": 0.4656885609521858, "stage": "debug", "created_at": 1788684071.0049014}, {"event_id": "b5d1de81e43b4d1895f82833deef3d3c", "step": 10, "value": 0.37889057880110355, "stage": "improve", "created_at": 1788684545.5414364}, {"event_id": "7dccfaeb781443ff92c8ec7718ad04e6", "step": 11, "value": 0.28408396066779396, "stage": "improve", "created_at": 1788685142.8966491}, {"event_id": "f271d49f0afc4c218ee6d3b15503f689", "step": 12, "value": 0.2295316622907179, "stage": "improve", "created_at": 1788687134.3723204}, {"event_id": "9f26925c4f6444ee9ec901b87df1ab29", "step": 14, "value": 0.2702688571761791, "stage": "debug", "created_at": 1788694782.9973888}, {"event_id": "eccee90f48514efe853cd7eece9f0eb5", "step": 15, "value": 0.265482890522442, "stage": "improve", "created_at": 1788698355.1172636}, {"event_id": "3fc8b64d5859404db5143c54579a88de", "step": 18, "value": 0.29565, "stage": "fusion_draft", "created_at": 1788705239.6522593}, {"event_id": "d55de5fe09d143d38879bac6a479ff89", "step": 19, "value": 0.25133753258226876, "stage": "fusion_draft", "created_at": 1788706679.4372616}, {"event_id": "10a7c01d1bbd4933a445724ba4a3fc56", "step": 20, "value": 0.21965155665136338, "stage": "improve", "created_at": 1788707883.58775}], "maximize": false, "elapsed_seconds": 28768.554517269135, "node_count": 21, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.bnvs-root.spooky-author-identification.yaml", "note": ""}, {"id": "xixian.bnvs-root.tabular-playground-series-dec-2021", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "bnvs_root", "dataset": "tabular-playground-series-dec-2021", "status": "archived", "official_score": 0.96336, "medal": "gold", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.9566, "silver": 0.95658, "bronze": 0.95658}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:84", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-four-methods-muse13/runs/bnvs_root/18_tabular-playground-series-dec-2021/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-four-methods-muse13/runs/bnvs_root/18_tabular-playground-series-dec-2021/logs/journal.json", "metrics": [{"event_id": "1ff006a2eadc47fc8f91555f02ae8ecd", "step": 4, "value": 0.9529128852663283, "stage": "debug", "created_at": 1788683043.1774437}, {"event_id": "a650c38bbd9f41eaa8f58f31fff47be1", "step": 5, "value": 0.9590833333333333, "stage": "debug", "created_at": 1788683062.3298678}, {"event_id": "18ec29cc853744d49f391873a634e1c4", "step": 7, "value": 0.9614009468216396, "stage": "improve", "created_at": 1788683795.9475322}, {"event_id": "f9841d60242a4d618c7ce1bdadd8d890", "step": 8, "value": 0.9625590277777778, "stage": "debug", "created_at": 1788683032.7687247}, {"event_id": "d6fe137c11734da694309286c62d6550", "step": 12, "value": 0.9618096753584311, "stage": "improve", "created_at": 1788700387.2542634}, {"event_id": "7950ccc1f39c4f05874a32dd9222caf5", "step": 13, "value": 0.9625398311911461, "stage": "improve", "created_at": 1788703942.3911986}, {"event_id": "21e1b223b3d34f929092d4f0ff8d8ca0", "step": 14, "value": 0.9625715770969163, "stage": "improve", "created_at": 1788700999.5758295}, {"event_id": "7bba5fd117a84a759e988de3d6d361d1", "step": 15, "value": 0.9623472222222222, "stage": "improve", "created_at": 1788706012.6093016}, {"event_id": "ebefdf6e54074b57a8ecadc2479ba098", "step": 16, "value": 0.9626588783377844, "stage": "improve", "created_at": 1788700011.8554442}, {"event_id": "5e58ed68121d48df94d427bab2541097", "step": 19, "value": 0.9618305555555555, "stage": "improve", "created_at": 1788708099.7217083}], "maximize": true, "elapsed_seconds": 28770.713515281677, "node_count": 20, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.bnvs-root.tabular-playground-series-dec-2021.yaml", "note": ""}, {"id": "xixian.bnvs-root.tabular-playground-series-may-2022", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "bnvs_root", "dataset": "tabular-playground-series-may-2022", "status": "archived", "official_score": 0.99102, "medal": "none", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.99823, "silver": 0.99822, "bronze": 0.99818}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:85", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-four-methods-muse13/runs/bnvs_root/19_tabular-playground-series-may-2022/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-four-methods-muse13/runs/bnvs_root/19_tabular-playground-series-may-2022/logs/journal.json", "metrics": [{"event_id": "48bd3e7572844298ab1e7e939490f231", "step": 2, "value": 0.7278654181083053, "stage": "debug", "created_at": 1788683216.9308953}, {"event_id": "47a6e496e8d045cd9b4bc09382a65f67", "step": 4, "value": 0.7975156366116698, "stage": "improve", "created_at": 1788683983.0071073}, {"event_id": "674df6a2e9c049a498055aa46165f688", "step": 5, "value": 0.9314051840088213, "stage": "debug", "created_at": 1788684119.2399795}, {"event_id": "da81548002b64007beee9149b065b78f", "step": 6, "value": 0.7976287233824639, "stage": "improve", "created_at": 1788686216.5044594}, {"event_id": "68228d1e638549018ad39e2c8f4dac8d", "step": 7, "value": 0.9907568825409103, "stage": "improve", "created_at": 1788687431.8576293}, {"event_id": "3b6456fd5ae04cf7a5af0eb6a31d6c7b", "step": 8, "value": 0.8468436020194345, "stage": "improve", "created_at": 1788684728.6548984}, {"event_id": "a8e10458a7cd43ecad23b967409b4534", "step": 9, "value": 0.9906853849261865, "stage": "improve", "created_at": 1788689580.3304958}, {"event_id": "08cec91a31204097aacab9a3b4664f50", "step": 10, "value": 0.9912182046479691, "stage": "improve", "created_at": 1788690860.455039}, {"event_id": "841317128288432c90e3fda564ab5d6b", "step": 19, "value": 0.9908966799998093, "stage": "improve", "created_at": 1788688904.9842882}, {"event_id": "91b1962a5b8842808a2f7f70f116f431", "step": 21, "value": 0.859627057725239, "stage": "improve", "created_at": 1788693979.3844724}, {"event_id": "1be575e8cf094c7abd383ef5e2ca5e16", "step": 22, "value": 0.8665018110086408, "stage": "fusion_draft", "created_at": 1788706008.7803476}], "maximize": true, "elapsed_seconds": 28761.77113342285, "node_count": 23, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.bnvs-root.tabular-playground-series-may-2022.yaml", "note": ""}, {"id": "xixian.bnvs-root.text-normalization-challenge-english-language", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "bnvs_root", "dataset": "text-normalization-challenge-english-language", "status": "archived", "official_score": 0.99535, "medal": "silver", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.99724, "silver": 0.99135, "bronze": 0.99038}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:86", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-four-methods-muse13/runs/bnvs_root/20_text-normalization-challenge-english-language/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-four-methods-muse13/runs/bnvs_root/20_text-normalization-challenge-english-language/logs/journal.json", "metrics": [{"event_id": "6354523d0d284253aefff2ddcd915496", "step": 5, "value": 0.7707996678337373, "stage": "debug", "created_at": 1788683427.2104156}, {"event_id": "06456c4f2da744a0bd5ecf8951ffecfc", "step": 7, "value": 0.8288614328036628, "stage": "improve", "created_at": 1788685407.2986465}, {"event_id": "18460b6ced704ab4be727169f970ba6f", "step": 10, "value": 0.994417137983661, "stage": "debug", "created_at": 1788684080.3989956}, {"event_id": "b718d8ceead04cbdbb64430c9b6f0540", "step": 12, "value": 0.9719047272034217, "stage": "debug", "created_at": 1788691033.7595143}, {"event_id": "c64815e8353243ceab1bb2cfc2ca3e4e", "step": 13, "value": 0.9181198940658946, "stage": "improve", "created_at": 1788692580.4791517}, {"event_id": "ac00f07bcd544933ab0b55a15c8920a2", "step": 14, "value": 0.9798395100235348, "stage": "debug", "created_at": 1788689407.4409652}, {"event_id": "9c89b881c65b4ebe9a3ee5487c73125b", "step": 17, "value": 0.9657565759942545, "stage": "debug", "created_at": 1788695328.2518184}, {"event_id": "89d26df441f24ae5a1b7064e22307e7f", "step": 18, "value": 0.8264599604991472, "stage": "debug", "created_at": 1788689915.9592578}, {"event_id": "f53364665ef9465285c83c80d27dbc65", "step": 19, "value": 0.9177102971541431, "stage": "debug", "created_at": 1788699162.8291256}, {"event_id": "41b3636f937e43268f451a9bb5e30d53", "step": 20, "value": 0.9685339797109256, "stage": "improve", "created_at": 1788700097.0428758}, {"event_id": "8397b5217e114030937fc455c7110314", "step": 21, "value": 0.970329473022713, "stage": "improve", "created_at": 1788704054.108507}], "maximize": true, "elapsed_seconds": 28769.52293586731, "node_count": 22, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.bnvs-root.text-normalization-challenge-english-language.yaml", "note": ""}, {"id": "xixian.bnvs-root.text-normalization-challenge-russian-language", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "bnvs_root", "dataset": "text-normalization-challenge-russian-language", "status": "archived", "official_score": 0.97591, "medal": "none", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.99012, "silver": 0.98232, "bronze": 0.97592}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:87", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-four-methods-muse13/runs/bnvs_root/21_text-normalization-challenge-russian-language/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-four-methods-muse13/runs/bnvs_root/21_text-normalization-challenge-russian-language/logs/journal.json", "metrics": [{"event_id": "827c1eb75aa1496faa70efa8c94fa84f", "step": 5, "value": 0.9176909764883644, "stage": "debug", "created_at": 1788683299.0859375}, {"event_id": "f98de571f6e5462a8b53652041ea953f", "step": 6, "value": 0.9412287535225627, "stage": "debug", "created_at": 1788684318.5052955}, {"event_id": "4c783b49e2844313b8f4b4eaa54c8356", "step": 7, "value": 0.8761051305243456, "stage": "improve", "created_at": 1788685001.2200584}, {"event_id": "e1529eebcea24505b91ddc30cfa75936", "step": 8, "value": 0.9503102992152331, "stage": "improve", "created_at": 1788690348.3198292}, {"event_id": "0b8de0d26a16441895d176caffc56cd3", "step": 9, "value": 0.8761051305243456, "stage": "improve", "created_at": 1788699428.1144216}, {"event_id": "babf802cce8844df8a0eb061953a069b", "step": 11, "value": 0.9414117437927086, "stage": "improve", "created_at": 1788703359.7070591}, {"event_id": "86335c6e260c446f9d2973b3f1aa1088", "step": 12, "value": 0.9763472005102815, "stage": "improve", "created_at": 1788689125.5763547}, {"event_id": "ab0cb10e676540a18fab2c780a11b1d2", "step": 13, "value": 0.8962, "stage": "debug", "created_at": 1788705012.3961234}, {"event_id": "97db274ad1a84681b8487591b936887a", "step": 14, "value": 0.9737801084348058, "stage": "fusion_draft", "created_at": 1788708824.1059406}], "maximize": true, "elapsed_seconds": 28766.203969955444, "node_count": 15, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.bnvs-root.text-normalization-challenge-russian-language.yaml", "note": ""}, {"id": "xixian.bnvs-root.the-icml-2013-whale-challenge-right-whale-redux", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "bnvs_root", "dataset": "the-icml-2013-whale-challenge-right-whale-redux", "status": "archived", "official_score": 0.99347, "medal": "gold", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.98961, "silver": 0.95017, "bronze": 0.90521}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:88", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-four-methods-muse13/runs/bnvs_root/22_the-icml-2013-whale-challenge-right-whale-redux/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-four-methods-muse13/runs/bnvs_root/22_the-icml-2013-whale-challenge-right-whale-redux/logs/journal.json", "metrics": [{"event_id": "3ce224c72d6745d3883b836ad7482809", "step": 1, "value": 0.9864220165873138, "stage": "draft", "created_at": 1788683301.2529182}, {"event_id": "501a0bba29a44ab196d3711edce45f40", "step": 4, "value": 0.9041188607976223, "stage": "debug", "created_at": 1788691220.783384}, {"event_id": "1427395ca9b24327bb23f97ea3c90251", "step": 6, "value": 0.9693182920277282, "stage": "improve", "created_at": 1788692227.6402352}, {"event_id": "896a79ea0be1443a8e879815ec7d0f53", "step": 7, "value": 0.8471625904995312, "stage": "improve", "created_at": 1788693769.7786355}, {"event_id": "6cacae63cd04472da28d6fcb1b9e95b2", "step": 9, "value": 0.9912542236215636, "stage": "improve", "created_at": 1788689733.32364}, {"event_id": "dcda1d4925ee4b159c62e67501d8a67a", "step": 10, "value": 0.8792049023818651, "stage": "improve", "created_at": 1788695327.828359}, {"event_id": "636e8304f4314dddaee778074eb41205", "step": 13, "value": 0.8424755242673957, "stage": "debug", "created_at": 1788697906.0635364}, {"event_id": "2f219d40bbe14e3dbb730e4f050d2e00", "step": 15, "value": 0.9900600906158807, "stage": "improve", "created_at": 1788696328.6951263}, {"event_id": "3283a3cb11514587a9ba37b68a0aa9d4", "step": 16, "value": 0.9284448853147463, "stage": "debug", "created_at": 1788695317.2707865}, {"event_id": "8979da2e8466411c8afc6435fc7a6153", "step": 17, "value": 0.9694626261166716, "stage": "debug", "created_at": 1788701588.0275342}, {"event_id": "2935694e8017464eb655d11fadda50a0", "step": 18, "value": 0.9666457932360233, "stage": "improve", "created_at": 1788702945.86003}, {"event_id": "85a8d8e13c8b425eac20b2a66bba024e", "step": 19, "value": 0.9919309629857165, "stage": "fusion_draft", "created_at": 1788704901.7332432}, {"event_id": "12502d000e124ba1ae86cad604d6c17d", "step": 20, "value": 0.992690734910152, "stage": "improve", "created_at": 1788705954.7991774}, {"event_id": "5ff4532efc284d0391ceaad2ee2f9ff2", "step": 21, "value": 0.9916007525725695, "stage": "improve", "created_at": 1788707401.55458}, {"event_id": "79ef80cb0634422fa4c7988f349d140a", "step": 23, "value": 0.979975234219014, "stage": "improve", "created_at": 1788702355.7617776}, {"event_id": "d6c313fc6efa4203a55982aa3a73bc38", "step": 24, "value": 0.9916554676700968, "stage": "improve", "created_at": 1788702768.7573981}, {"event_id": "e18b5f7133aa455e89e2a924ad24ae60", "step": 25, "value": 0.990448375825526, "stage": "improve", "created_at": 1788709810.1244984}], "maximize": true, "elapsed_seconds": 28260.95790910721, "node_count": 26, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.bnvs-root.the-icml-2013-whale-challenge-right-whale-redux.yaml", "note": ""}, {"id": "xixian.bnvs-root-only.aerial-cactus-identification", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "bnvs_root_only", "dataset": "aerial-cactus-identification", "status": "archived", "official_score": 1.0, "medal": "gold", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 1.0, "silver": 1.0, "bronze": 1.0}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:89", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-root-only-muse13/runs/bnvs_root_only/01_aerial-cactus-identification/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-root-only-muse13/runs/bnvs_root_only/01_aerial-cactus-identification/logs/journal.json", "metrics": [{"event_id": "5026a187fbcc48e68445fec1303cc506", "step": 2, "value": 0.9994779267919014, "stage": "draft", "created_at": 1788727536.637692}, {"event_id": "79a85715e1904e37b4c5352172e77e31", "step": 3, "value": 0.9999139698776722, "stage": "draft", "created_at": 1788727939.4778504}, {"event_id": "8a7060240de1483baf80198f19386932", "step": 4, "value": 0.9998926263463132, "stage": "debug", "created_at": 1788728528.3112302}, {"event_id": "4659d46889484f799ef8c12620734602", "step": 6, "value": 0.9999457892379853, "stage": "improve", "created_at": 1788729014.763677}, {"event_id": "51989eb78943476fa8f87834d59bbef5", "step": 7, "value": 0.9999905720413889, "stage": "debug", "created_at": 1788729097.92846}, {"event_id": "49ffa3a3249d4e31b8bfc21d94b682d0", "step": 8, "value": 0.9999884009942005, "stage": "improve", "created_at": 1788729071.0620618}, {"event_id": "6d86e99769a549f4b36166489b4419fc", "step": 9, "value": 0.9999449875724937, "stage": "improve", "created_at": 1788729894.7572196}, {"event_id": "71ca4cedb30140f484f30ed8d37c877b", "step": 10, "value": 0.9999599311759021, "stage": "improve", "created_at": 1788729601.9571044}, {"event_id": "a687acbf4cdd4e1ea6a07d2100acaa4d", "step": 12, "value": 0.9999589063794532, "stage": "improve", "created_at": 1788730937.9740815}, {"event_id": "127d894a8be0492ea1de0f85b431f5fc", "step": 13, "value": 0.9999917505362151, "stage": "improve", "created_at": 1788729864.0580537}, {"event_id": "a84c519f713c4987ba1d17627394e5bf", "step": 14, "value": 0.9999787870931247, "stage": "debug", "created_at": 1788731259.652386}, {"event_id": "14e33f444fd0470181cf109351ea5c62", "step": 15, "value": 0.9998748723921225, "stage": "improve", "created_at": 1788731922.490314}, {"event_id": "51d2a55630ca4bcc9c80ce57f296a134", "step": 17, "value": 0.9999493247224644, "stage": "improve", "created_at": 1788734084.536229}, {"event_id": "dd34e6bbce36486e885d6bd97e44edfa", "step": 18, "value": 0.9999893935465622, "stage": "improve", "created_at": 1788733411.2598584}, {"event_id": "9705e5ee0d5e4561a88a8d15f1f56a43", "step": 20, "value": 0.9999870365569096, "stage": "improve", "created_at": 1788737025.0265248}, {"event_id": "99e3898a005f49598549f9bf4eed27dc", "step": 21, "value": 0.999994107525868, "stage": "debug", "created_at": 1788735786.588763}, {"event_id": "91abbe8e393c46c8af112872095a3b82", "step": 22, "value": 0.9999870365569095, "stage": "debug", "created_at": 1788737392.4630322}, {"event_id": "271f49583c1b4b4dbd3600d0705b261d", "step": 23, "value": 0.9999917608480207, "stage": "draft", "created_at": 1788741275.8404238}, {"event_id": "020bd1050e384e73850a5416e9983d5b", "step": 24, "value": 0.9999964689348659, "stage": "improve", "created_at": 1788741592.384985}, {"event_id": "020bb155cf204a42b1596af058a3ee77", "step": 25, "value": 0.9999882150517361, "stage": "improve", "created_at": 1788739871.1942255}, {"event_id": "832ba1a4f3e048aa92a7eb1d6db54b58", "step": 26, "value": 0.9999988229782887, "stage": "improve", "created_at": 1788742041.4792717}, {"event_id": "5cbeb3ff43fd45ae9e9af32c85570839", "step": 29, "value": 1.0, "stage": "debug", "created_at": 1788743281.7533808}, {"event_id": "f5ae23455ad243a79265f63d23ba8471", "step": 30, "value": 1.0, "stage": "improve", "created_at": 1788744534.9156485}, {"event_id": "f5674311546842169e5d98ea4cf4c141", "step": 32, "value": 0.9998267612605181, "stage": "improve", "created_at": 1788739910.5424943}, {"event_id": "9feb5e868ef94fe4b57edc09318cc3d8", "step": 33, "value": 0.9999917608480205, "stage": "debug", "created_at": 1788746126.1016405}, {"event_id": "bb339a1265434168a1bdef307adf392f", "step": 35, "value": 0.9999195505740543, "stage": "debug", "created_at": 1788748186.5785177}, {"event_id": "d6ded75786944b65b236f7c0321cd354", "step": 36, "value": 0.999970767304668, "stage": "improve", "created_at": 1788748713.8506951}, {"event_id": "0b3259d906ef4a05ac0d6fb2febda74c", "step": 37, "value": 0.9997961203950314, "stage": "improve", "created_at": 1788747471.5073137}, {"event_id": "654d0fd95ddd4eaa85be209d002c88b1", "step": 38, "value": 0.9833902939166097, "stage": "fusion_draft", "created_at": 1788749991.0563195}, {"event_id": "f0c76a6416d847c58a66238b68c3cc96", "step": 39, "value": 0.9999904370356922, "stage": "improve", "created_at": 1788752091.3560076}, {"event_id": "9b39924fda1d47c2898124b500863666", "step": 40, "value": 0.9999472113759432, "stage": "fusion_draft", "created_at": 1788751347.6887705}, {"event_id": "f5788efd0a5846edafb797dbabddaec7", "step": 43, "value": 0.9999951057783224, "stage": "improve", "created_at": 1788754105.3615403}], "maximize": true, "elapsed_seconds": 28671.288162231445, "node_count": 44, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.bnvs-root-only.aerial-cactus-identification.yaml", "note": ""}, {"id": "xixian.bnvs-root-only.aptos2019-blindness-detection", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "bnvs_root_only", "dataset": "aptos2019-blindness-detection", "status": "archived", "official_score": 0.92965, "medal": "silver", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.930508, "silver": 0.919654, "bronze": 0.914492}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:90", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-root-only-muse13/runs/bnvs_root_only/02_aptos2019-blindness-detection/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-root-only-muse13/runs/bnvs_root_only/02_aptos2019-blindness-detection/logs/journal.json", "metrics": [{"event_id": "95f7ee511015406097056ce84e2ded30", "step": 1, "value": 0.9076969921564277, "stage": "draft", "created_at": 1788727511.57578}, {"event_id": "95dabd4a94534e6198e201c873807d23", "step": 2, "value": 0.9291175993033913, "stage": "draft", "created_at": 1788727930.0598774}, {"event_id": "2265e52d789b4d7f9236b8fb282a0530", "step": 5, "value": 0.9136365935066249, "stage": "debug", "created_at": 1788730598.538626}, {"event_id": "6ff12582e203498889a022168576df57", "step": 6, "value": 0.9102385975307633, "stage": "improve", "created_at": 1788731610.4542522}, {"event_id": "cb9ff27a676b453eb9132418b390b6af", "step": 7, "value": 0.9049359158863106, "stage": "debug", "created_at": 1788731025.0720768}, {"event_id": "55fe0061e5ea4ab78a60e56f41cf8ab4", "step": 8, "value": 0.9150399477838347, "stage": "improve", "created_at": 1788733377.4433506}, {"event_id": "ffced548d81a41969de7b8507e127efa", "step": 9, "value": 0.7261753758081735, "stage": "draft", "created_at": 1788728439.3513775}, {"event_id": "3c01f733d96e4f5f801666aafd275a9d", "step": 10, "value": 0.8428625484624158, "stage": "improve", "created_at": 1788735173.2273505}, {"event_id": "d7ffb80a648a4a82b5a68260af4723aa", "step": 11, "value": 0.9203467974146233, "stage": "improve", "created_at": 1788736791.7075584}, {"event_id": "4d1a10acab3a472cac9975f4f3214a16", "step": 16, "value": 0.9048440648280216, "stage": "improve", "created_at": 1788737341.8217888}, {"event_id": "6b06244891cf46d2b659c98b030723f9", "step": 17, "value": 0.9269004909256446, "stage": "debug", "created_at": 1788752200.6324754}, {"event_id": "7d7e03e73baa4bf9ad4556c602d1f7ae", "step": 18, "value": 0.9224036577400392, "stage": "improve", "created_at": 1788753279.3266394}, {"event_id": "a3ef0068b00a4923b7c5c7c9571ed6fd", "step": 19, "value": 0.6960899989486105, "stage": "improve", "created_at": 1788752559.0387108}], "maximize": true, "elapsed_seconds": 28701.719312906265, "node_count": 23, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.bnvs-root-only.aptos2019-blindness-detection.yaml", "note": ""}, {"id": "xixian.bnvs-root-only.denoising-dirty-documents", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "bnvs_root_only", "dataset": "denoising-dirty-documents", "status": "archived", "official_score": 0.00942, "medal": "gold", "valid_submission": true, "score_maximize": false, "thresholds": {"gold": 0.01794, "silver": 0.02609, "bronze": 0.04517}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:91", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-root-only-muse13/runs/bnvs_root_only/03_denoising-dirty-documents/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-root-only-muse13/runs/bnvs_root_only/03_denoising-dirty-documents/logs/journal.json", "metrics": [{"event_id": "366f2677f8e34d8d867e81957742c2c2", "step": 3, "value": 0.03605860507197882, "stage": "draft", "created_at": 1788727586.5745888}, {"event_id": "2fd86eeace6a43f4b7db864e270f438a", "step": 4, "value": 0.010457645410333873, "stage": "draft", "created_at": 1788727933.6394773}, {"event_id": "76536fe1c8704e7389847f43261ff892", "step": 5, "value": 0.017777514194375142, "stage": "debug", "created_at": 1788728617.3722181}, {"event_id": "68c6647426dd4235855dc2a9c91353c2", "step": 6, "value": 0.032023037505824366, "stage": "improve", "created_at": 1788728770.061986}, {"event_id": "76df93954e4a4c288a4580ec6944359a", "step": 7, "value": 0.023347860667710333, "stage": "improve", "created_at": 1788729246.6221702}, {"event_id": "e3b8745ee0c4409ea373cfe96a7b3844", "step": 8, "value": 0.016392168519068877, "stage": "improve", "created_at": 1788729152.2596376}, {"event_id": "4de3ee1b67bd4594966db8615b9b7f36", "step": 10, "value": 0.010962985682153693, "stage": "improve", "created_at": 1788729003.5962965}, {"event_id": "e2d69ae7d4dc4313998c5848d8fa775e", "step": 11, "value": 0.02157545709434617, "stage": "debug", "created_at": 1788729800.1283543}, {"event_id": "6ecd919e15a2479d99f4e714e4a378b2", "step": 12, "value": 0.011645870994916365, "stage": "improve", "created_at": 1788729958.4963489}, {"event_id": "655f1ebd4b0a4550b882a23bb81a80e6", "step": 13, "value": 0.015784863745631025, "stage": "improve", "created_at": 1788729826.74197}, {"event_id": "13f8cfcc500d4c5ea83ae9f223d40798", "step": 14, "value": 0.019220413744264375, "stage": "improve", "created_at": 1788730349.683403}, {"event_id": "3eb1034d7c24406eb08cdf6cfdeaedfc", "step": 15, "value": 0.013844806159136577, "stage": "improve", "created_at": 1788730647.4893885}, {"event_id": "80bd954aa20f4642918fb49343ffa26e", "step": 16, "value": 0.015527553012205654, "stage": "improve", "created_at": 1788730706.3231122}, {"event_id": "c45ab195105a45dbb2505d469cc1badd", "step": 17, "value": 0.01952848910432215, "stage": "improve", "created_at": 1788730883.8188713}, {"event_id": "c842d721199c42b2af3613843195e36d", "step": 18, "value": 0.015743643798771172, "stage": "improve", "created_at": 1788731368.0366924}, {"event_id": "684b8f6df0fd42a4b7764c9c480d7798", "step": 19, "value": 0.01680027787296896, "stage": "evolution", "created_at": 1788731149.3443327}, {"event_id": "1c18b6663a0047949b87b7732637e1fd", "step": 20, "value": 0.019491434287787317, "stage": "improve", "created_at": 1788731602.232782}, {"event_id": "b044ffb1ee6c4a50a10f78c5575ae321", "step": 22, "value": 0.020002221085666655, "stage": "improve", "created_at": 1788732316.0509875}, {"event_id": "d01019bd7fcb444cbad9b565f056d06f", "step": 23, "value": 0.09696150161043025, "stage": "evolution", "created_at": 1788732039.9055798}, {"event_id": "d4b830369977471b8e6aa1168216a86e", "step": 24, "value": 0.015156428864200662, "stage": "debug", "created_at": 1788732398.5311828}, {"event_id": "141b17c1cde54cadad557b3c1aea82f2", "step": 31, "value": 0.01564414815895843, "stage": "improve", "created_at": 1788733263.352849}, {"event_id": "639a0ab60c5e4d1f9c7ceeb8acb970f6", "step": 34, "value": 0.027230223610785743, "stage": "evolution", "created_at": 1788732789.9423118}, {"event_id": "e49647eb4cec40398e25d27769ba2ba1", "step": 37, "value": 0.015352682962295888, "stage": "improve", "created_at": 1788734361.445744}, {"event_id": "b3d9cc4dc16a4203afa9bba2069821cd", "step": 38, "value": 0.022093178616936826, "stage": "draft", "created_at": 1788734776.3370836}, {"event_id": "00da661991a44a7c858bd2c2dd64c86c", "step": 39, "value": 0.015548159019679462, "stage": "debug", "created_at": 1788734627.0780292}, {"event_id": "04482f19702f4383b2cb1f8470d61c84", "step": 40, "value": 0.01918117589905145, "stage": "improve", "created_at": 1788735051.050566}, {"event_id": "35085527e9ec4a04801062b74513f3c6", "step": 41, "value": 0.01962395319844406, "stage": "improve", "created_at": 1788735269.9340508}, {"event_id": "39e39b792ce74539b19d434066a28068", "step": 43, "value": 0.013736832983285333, "stage": "improve", "created_at": 1788735665.0395503}, {"event_id": "0634485afa07415585ef37c4ba3b0507", "step": 45, "value": 0.017951573920521283, "stage": "improve", "created_at": 1788736989.570132}, {"event_id": "7a4fc79c7dfd4cb9b9e1b5c90a207c47", "step": 47, "value": 0.0161214729913992, "stage": "improve", "created_at": 1788737841.0461476}, {"event_id": "a11f1bf0c60c49bdba5d1f481f8dd613", "step": 48, "value": 0.035107404660145114, "stage": "improve", "created_at": 1788738884.3851814}, {"event_id": "a050750fccc545b1b2b142f4a042d1fb", "step": 49, "value": 0.018885886187298917, "stage": "debug", "created_at": 1788737290.2784028}, {"event_id": "89377012bcbc47a69f98519f3f7e195a", "step": 54, "value": 0.023665286110072594, "stage": "debug", "created_at": 1788741193.753047}, {"event_id": "ca0936ab49fc4a489c0b09011c23fb32", "step": 59, "value": 0.016796283656054223, "stage": "debug", "created_at": 1788740384.942916}, {"event_id": "c776c9f2b53e490fb5049434f109bbc8", "step": 66, "value": 0.016565167294999253, "stage": "debug", "created_at": 1788743269.9516594}, {"event_id": "9dff8221ff5d4ce0b5edc243b1639745", "step": 72, "value": 0.010351525067184888, "stage": "debug", "created_at": 1788744112.4457152}, {"event_id": "a72db64db6d2428a902fa79c87d3463c", "step": 73, "value": 0.012085271626863365, "stage": "evolution", "created_at": 1788744326.6415756}, {"event_id": "59fe0e6d8a8940d88766445693266188", "step": 74, "value": 0.01860755308622246, "stage": "evolution", "created_at": 1788742691.2359238}, {"event_id": "fbcb433e73494beb9553ea150d9b0692", "step": 75, "value": 0.00996874297553871, "stage": "improve", "created_at": 1788745071.186622}, {"event_id": "4abf9c23e6e04712b724bfb4bcd4c353", "step": 76, "value": 0.013659457151690044, "stage": "improve", "created_at": 1788745997.7512236}, {"event_id": "f5d81ca0665b408d9e35487de78038ec", "step": 77, "value": 0.01237697355309161, "stage": "improve", "created_at": 1788745512.5865998}, {"event_id": "31842e70033146d38bedb5b6622d840e", "step": 78, "value": 0.01230433540531148, "stage": "improve", "created_at": 1788746737.4414716}, {"event_id": "b8056ff76e50472cb23d3df3032d289e", "step": 79, "value": 0.01013018515302912, "stage": "improve", "created_at": 1788746587.9417884}, {"event_id": "d2d3ff09ba54439e890daa14d7c3bf5e", "step": 82, "value": 0.010767333020143214, "stage": "debug", "created_at": 1788748133.111901}, {"event_id": "cbc176bbd48042269a71961681358a98", "step": 83, "value": 0.016335588430715007, "stage": "evolution", "created_at": 1788745614.2191062}, {"event_id": "7d1c11503d1246d8942780362c0c5d7c", "step": 87, "value": 0.027090670413738003, "stage": "debug", "created_at": 1788749229.7450047}, {"event_id": "61c22fe9e4df44779a56241e29ce311d", "step": 88, "value": 0.010807016869108739, "stage": "evolution", "created_at": 1788748631.199426}, {"event_id": "d347500af9614caabf9ad2a0c3532827", "step": 89, "value": 0.009435984216527245, "stage": "fusion", "created_at": 1788748779.9729488}, {"event_id": "25dabb23826b4a098ae9bdd75bc638a3", "step": 90, "value": 0.024203988513751964, "stage": "improve", "created_at": 1788749769.0486224}, {"event_id": "94c3bf57892340fdbc1a37b22d35b357", "step": 92, "value": 0.01620546123331326, "stage": "fusion", "created_at": 1788749748.776756}, {"event_id": "5f75ff2acda04ce381aa257ec77b28e3", "step": 93, "value": 0.06924923996871839, "stage": "debug", "created_at": 1788750519.182908}, {"event_id": "f0212529a7854bb0a0b9c435f84ff79c", "step": 94, "value": 0.009378656861091137, "stage": "improve", "created_at": 1788750064.191651}, {"event_id": "0bc3008c1799436dbd9099cebdde253c", "step": 95, "value": 0.06937430823055003, "stage": "improve", "created_at": 1788751138.3705034}, {"event_id": "35ff080a2cde4657a08e729884cf54f9", "step": 96, "value": 0.015960589067603805, "stage": "improve", "created_at": 1788750994.4148018}, {"event_id": "3cfbfc6c6b3540cb9231a2a26db4c2a0", "step": 98, "value": 0.07087319086761147, "stage": "improve", "created_at": 1788751768.6944048}, {"event_id": "54ef6845915b4107a81cce124e819dce", "step": 102, "value": 0.015749376318957682, "stage": "improve", "created_at": 1788751897.6168823}, {"event_id": "a0a3582db7f34b08a676a8b6d874c6c6", "step": 106, "value": 0.010653627285159338, "stage": "debug", "created_at": 1788753162.560714}, {"event_id": "169145dd20134ecab5fbc7245a19f589", "step": 108, "value": 0.008587638838962599, "stage": "evolution", "created_at": 1788753710.800791}, {"event_id": "2222dc0894e14b838bb8f7c7e47c1bb5", "step": 109, "value": 0.009638755304154726, "stage": "debug", "created_at": 1788753390.812677}, {"event_id": "9eb0fc4bb50843f4b996266226b5953d", "step": 111, "value": 0.009721855136460535, "stage": "improve", "created_at": 1788754812.6343942}], "maximize": false, "elapsed_seconds": 28735.766402244568, "node_count": 113, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.bnvs-root-only.denoising-dirty-documents.yaml", "note": ""}, {"id": "xixian.bnvs-root-only.detecting-insults-in-social-commentary", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "bnvs_root_only", "dataset": "detecting-insults-in-social-commentary", "status": "archived", "official_score": 0.94747, "medal": "gold", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.83321, "silver": 0.82307, "bronze": 0.79111}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:92", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-root-only-muse13/runs/bnvs_root_only/04_detecting-insults-in-social-commentary/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-root-only-muse13/runs/bnvs_root_only/04_detecting-insults-in-social-commentary/logs/journal.json", "metrics": [{"event_id": "b14033d061d147bcb8813ba263dcac3c", "step": 3, "value": 0.958751636839808, "stage": "draft", "created_at": 1788727417.792073}, {"event_id": "437c670ffe5f4b1aba9cbca29c5ecf6f", "step": 7, "value": 0.9285095856524429, "stage": "debug", "created_at": 1788728570.6311638}, {"event_id": "5012cd471c804028a9daed3e781ede7d", "step": 8, "value": 0.9749045078863315, "stage": "debug", "created_at": 1788728605.672517}, {"event_id": "1ce7fb27a69144c58edf843a1fa50ea0", "step": 9, "value": 0.9513603957514913, "stage": "improve", "created_at": 1788728609.5085921}, {"event_id": "6230df884f2c4e9d80b808203b25713f", "step": 10, "value": 0.9461966604823748, "stage": "improve", "created_at": 1788728909.755572}, {"event_id": "3d33be0b452c4c88b9b3dc241d3d67ef", "step": 11, "value": 0.9637006486878066, "stage": "improve", "created_at": 1788729095.0121439}, {"event_id": "9d7fa538066245b0abbe1df1126b3275", "step": 12, "value": 0.9425974025974027, "stage": "improve", "created_at": 1788729326.9946365}, {"event_id": "b99eafcab27f487087a50e3bf1115f5c", "step": 13, "value": 0.9378873854212134, "stage": "improve", "created_at": 1788729150.4455178}, {"event_id": "867989aa5cff419581176da9748f10bd", "step": 14, "value": 0.9123314780457639, "stage": "improve", "created_at": 1788729742.2793083}, {"event_id": "3eab670f21a542d98a8a163b05ac9c94", "step": 16, "value": 0.9412210913019137, "stage": "improve", "created_at": 1788730003.3862789}, {"event_id": "439862ed61494986aa5b9adcba8c6570", "step": 18, "value": 0.9470212519597027, "stage": "debug", "created_at": 1788733885.490705}, {"event_id": "98ad6580cf7b451999c84dca857c5658", "step": 19, "value": 0.9250893584938431, "stage": "improve", "created_at": 1788729797.3174934}, {"event_id": "bd543142951f47f38dbfde5d617f1d11", "step": 20, "value": 0.9256428120770974, "stage": "debug", "created_at": 1788732017.8775156}, {"event_id": "b20450abaf9b4c099ae07d375fedcb9d", "step": 21, "value": 0.9687798412855214, "stage": "improve", "created_at": 1788734279.4532776}, {"event_id": "31f265dda4c944778f1880852c788fb4", "step": 23, "value": 0.9359610618677223, "stage": "evolution", "created_at": 1788736437.166577}, {"event_id": "c047d972df6348b588970fa0df7fd403", "step": 26, "value": 0.9202087525150906, "stage": "debug", "created_at": 1788739689.327269}, {"event_id": "3c8fdcf2bff446969a1c12fe57128423", "step": 27, "value": 0.9542918063869695, "stage": "evolution", "created_at": 1788740211.4703255}, {"event_id": "e6b4e9b952b94b9b89b3c9d67f7fb6c8", "step": 28, "value": 0.8965332917544134, "stage": "debug", "created_at": 1788736355.7134943}, {"event_id": "296bfc53af904348bee96a4842396d11", "step": 29, "value": 0.9510293085333497, "stage": "evolution", "created_at": 1788742017.2421737}, {"event_id": "65dc3ee4c55c42dc98884ff813ef0e19", "step": 30, "value": 0.9499819408013548, "stage": "evolution", "created_at": 1788736275.043515}, {"event_id": "00a256ff3f5d4cb88f735c732c96b6e6", "step": 32, "value": 0.9700434653758767, "stage": "fusion", "created_at": 1788743149.5864618}, {"event_id": "0515219dbba64804bd365a3b0ba8ed6f", "step": 33, "value": 0.9064661799564606, "stage": "debug", "created_at": 1788744362.7980452}, {"event_id": "51eee893ec4d4345833b1221c16f94b1", "step": 34, "value": 0.9361888577704882, "stage": "evolution", "created_at": 1788742281.3966992}, {"event_id": "317f3f76124c46d18635e2806f3b3063", "step": 35, "value": 0.927578995013819, "stage": "improve", "created_at": 1788745541.5439305}, {"event_id": "9be2c9a417d04bc38c38f45d21bc2148", "step": 36, "value": 0.9375752055426279, "stage": "fusion", "created_at": 1788746337.2490866}, {"event_id": "24b43fa4b9314e62b87f2a51d5376f60", "step": 37, "value": 0.9256964304628748, "stage": "fusion", "created_at": 1788747532.3268576}, {"event_id": "990fd3794211489b9fe39bb0d04afb64", "step": 38, "value": 0.9452006939469119, "stage": "fusion", "created_at": 1788748690.4602726}, {"event_id": "dd12adf5475849fcbf4ee548724db280", "step": 39, "value": 0.9418095777568566, "stage": "fusion", "created_at": 1788745984.6706822}, {"event_id": "3407710d134e48efa4a8f92e69265c96", "step": 40, "value": 0.9403727365968838, "stage": "fusion", "created_at": 1788750044.2965338}, {"event_id": "a706ea1d7923462c96cd77c00ee7b45a", "step": 41, "value": 0.9490100643458176, "stage": "fusion_draft", "created_at": 1788751332.2445076}, {"event_id": "adfbfcda44f940c1abcb2c47354cff41", "step": 42, "value": 0.9732951364878659, "stage": "evolution", "created_at": 1788750594.6599183}, {"event_id": "63054d87e44e4201af8f34c053b3307b", "step": 43, "value": 0.9710477789851493, "stage": "evolution", "created_at": 1788751952.3861601}, {"event_id": "242ad9c3f0004ad09a6c25c62b522a7a", "step": 44, "value": 0.950385723430445, "stage": "improve", "created_at": 1788752130.1547909}, {"event_id": "1478fafe4a3c42968eb0f680b96dcb39", "step": 45, "value": 0.9505122036103923, "stage": "fusion", "created_at": 1788745171.5003574}, {"event_id": "5c2d1dbbabe2483dae419041350e8297", "step": 46, "value": 0.9471426334587937, "stage": "fusion_draft", "created_at": 1788753619.3257833}, {"event_id": "ba4eaca4d4c4447583f0942fce19bd70", "step": 47, "value": 0.9767114491751456, "stage": "fusion", "created_at": 1788753329.0513852}, {"event_id": "b4a8098059624ccea3f2c3762ce41059", "step": 48, "value": 0.9498528290441915, "stage": "improve", "created_at": 1788754688.2161791}], "maximize": true, "elapsed_seconds": 28721.53304886818, "node_count": 49, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.bnvs-root-only.detecting-insults-in-social-commentary.yaml", "note": ""}, {"id": "xixian.bnvs-root-only.dog-breed-identification", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "bnvs_root_only", "dataset": "dog-breed-identification", "status": "archived", "official_score": 0.33973, "medal": "none", "valid_submission": true, "score_maximize": false, "thresholds": {"gold": 0.0005, "silver": 0.00539, "bronze": 0.04598}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:93", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-root-only-muse13/runs/bnvs_root_only/05_dog-breed-identification/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-root-only-muse13/runs/bnvs_root_only/05_dog-breed-identification/logs/journal.json", "metrics": [{"event_id": "77c768485fea414e86d1db50085617de", "step": 2, "value": 0.442416242527683, "stage": "draft", "created_at": 1788728275.2802775}, {"event_id": "043c5394f9a1498dbfeaa34c133a9dad", "step": 3, "value": 0.49803053491246035, "stage": "draft", "created_at": 1788727470.7398446}, {"event_id": "bd5a91e0cfe2430fb5086d5d4da6566a", "step": 4, "value": 0.5831119650648999, "stage": "debug", "created_at": 1788728461.5968747}, {"event_id": "340a290087524acc909324776b081ae8", "step": 5, "value": 0.4374602361819317, "stage": "improve", "created_at": 1788728883.900066}, {"event_id": "98e81e50a78c4feba7622710faa5043e", "step": 8, "value": 0.5768413410141139, "stage": "improve", "created_at": 1788729207.6025932}, {"event_id": "f4a81af8ab03494ca65ae2d68a81f66f", "step": 17, "value": 0.44113678234260034, "stage": "debug", "created_at": 1788730272.6153157}, {"event_id": "b35fc6ab3d6549e29d770e9fc22571ba", "step": 18, "value": 2.8122904005785556, "stage": "debug", "created_at": 1788732644.7656753}, {"event_id": "8d7795be30a14713b32f24a6f20c91ca", "step": 23, "value": 0.5, "stage": "improve", "created_at": 1788733649.2051187}, {"event_id": "dd7f9a2034cd4cf581114c92329e1dcd", "step": 25, "value": 0.5647905048390618, "stage": "improve", "created_at": 1788737220.2275484}, {"event_id": "273d6890b94f4dfeb4669fe58e232a32", "step": 26, "value": 0.5, "stage": "debug", "created_at": 1788737711.6800401}, {"event_id": "3bad272498f74127a9a2f6ea454ef3f5", "step": 27, "value": 2.0, "stage": "evolution", "created_at": 1788742415.713224}, {"event_id": "8aaefcd1d5284cadb590c36ab8cc221a", "step": 30, "value": 2.466972950129845, "stage": "improve", "created_at": 1788748385.3247263}, {"event_id": "c25cdbf48e764653b9d7a3f03a95802e", "step": 31, "value": 0.5, "stage": "debug", "created_at": 1788746209.111782}, {"event_id": "4da5898ba7f34819a05d534410d2808a", "step": 32, "value": 0.38121375974798644, "stage": "improve", "created_at": 1788749202.0627127}, {"event_id": "1477d315e2234538a3a528ab958e5cfc", "step": 33, "value": 0.42767141436107364, "stage": "improve", "created_at": 1788750376.190994}, {"event_id": "726bc8aaf4b644f0aa70ffeab4d0c0ca", "step": 35, "value": 0.34670485777053617, "stage": "fusion_draft", "created_at": 1788753273.4404166}, {"event_id": "dc8f948af70e471e9ca1533ab425bfee", "step": 36, "value": 0.5, "stage": "fusion", "created_at": 1788750288.4453185}, {"event_id": "41ae9ef1eb24457a9aca9fba8ce1be39", "step": 37, "value": 0.3912514929814763, "stage": "fusion_draft", "created_at": 1788753539.0223699}, {"event_id": "4cd7175a96e644c79f3983cf9171e4a5", "step": 38, "value": 0.46272069942475424, "stage": "improve", "created_at": 1788753906.6267045}, {"event_id": "66c27859236040a9a41c9a5ec1d1a6eb", "step": 39, "value": 0.6507265204705796, "stage": "improve", "created_at": 1788754558.8716338}], "maximize": false, "elapsed_seconds": 28763.622351169586, "node_count": 40, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.bnvs-root-only.dog-breed-identification.yaml", "note": ""}, {"id": "xixian.bnvs-root-only.dogs-vs-cats-redux-kernels-edition", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "bnvs_root_only", "dataset": "dogs-vs-cats-redux-kernels-edition", "status": "archived", "official_score": 0.00891, "medal": "gold", "valid_submission": true, "score_maximize": false, "thresholds": {"gold": 0.03882, "silver": 0.05038, "bronze": 0.06127}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:94", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-root-only-muse13/runs/bnvs_root_only/06_dogs-vs-cats-redux-kernels-edition/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-root-only-muse13/runs/bnvs_root_only/06_dogs-vs-cats-redux-kernels-edition/logs/journal.json", "metrics": [{"event_id": "a3155a3eadb94354acea553663af2b3d", "step": 1, "value": 0.0196280043211339, "stage": "draft", "created_at": 1788727913.9858994}, {"event_id": "1b75f76144e8493594ac3dadf3fb3fbe", "step": 2, "value": 0.0002431368122746613, "stage": "draft", "created_at": 1788728233.6497443}, {"event_id": "3ba2a1d6a40145239d3cf360ccb09b79", "step": 4, "value": 0.0006798826494328931, "stage": "improve", "created_at": 1788729097.960256}, {"event_id": "9ce9e90eaf544460938f093816e0e13e", "step": 5, "value": 0.005592346364257541, "stage": "improve", "created_at": 1788729090.7132974}, {"event_id": "9bc97cfd9b5649bfa7252af91ab49961", "step": 6, "value": 0.03415590496339419, "stage": "debug", "created_at": 1788729083.3556104}, {"event_id": "b147a4a915394b5c9464343526100983", "step": 8, "value": 0.00045560303085393037, "stage": "improve", "created_at": 1788729957.3859956}, {"event_id": "dcc8d77de0b5419bb70efb7068d2bd83", "step": 10, "value": 0.0002554724983140242, "stage": "improve", "created_at": 1788732017.5305316}, {"event_id": "9fbd6bf8bdb440b2912a4f5111ad52e3", "step": 11, "value": 0.004271275919178558, "stage": "debug", "created_at": 1788733007.0021086}, {"event_id": "d3511990d31f4c57bd03b7cd27f05533", "step": 12, "value": 0.00024884743316204785, "stage": "evolution", "created_at": 1788734527.7458017}, {"event_id": "f78dc38db872416c8cb90acb795496e9", "step": 13, "value": 0.006005471741926807, "stage": "improve", "created_at": 1788734875.9637458}, {"event_id": "6752251ffe0e4195b07c24e05763828d", "step": 14, "value": 0.003806229725158711, "stage": "evolution", "created_at": 1788737270.6730385}, {"event_id": "077a8313729141a781b3498e5adbcacf", "step": 15, "value": 0.00014480893316854988, "stage": "evolution", "created_at": 1788739084.2409244}, {"event_id": "fb47acb280c541f688d319a55f2b92a8", "step": 16, "value": 0.0007912792696346018, "stage": "improve", "created_at": 1788740923.0294309}, {"event_id": "fd06aa89b5b04aff84ce762f583243ac", "step": 17, "value": 0.004231422686701979, "stage": "improve", "created_at": 1788730637.2052095}, {"event_id": "d469333d87bf4b7abe9dc49cfc0203ce", "step": 18, "value": 1.49451475376841e-05, "stage": "improve", "created_at": 1788741854.2564726}, {"event_id": "3890d0b06c344169b7b79ce58a2cd011", "step": 19, "value": 2.5011761291942435e-05, "stage": "improve", "created_at": 1788742543.970673}, {"event_id": "53639c69eaf2467998ff2812497e1f82", "step": 20, "value": 0.003762208175572654, "stage": "improve", "created_at": 1788742959.9650757}, {"event_id": "625ebe74f5c64b938faddf696f950072", "step": 22, "value": 2.5011761291942435e-05, "stage": "improve", "created_at": 1788743658.2073042}, {"event_id": "1063f8c2aeee4d48a1209251447535c0", "step": 25, "value": 2.5011761291942435e-05, "stage": "fusion", "created_at": 1788745031.330046}, {"event_id": "163e8906b3f843f3a53277ee35d75287", "step": 27, "value": 0.0012921699389076531, "stage": "debug", "created_at": 1788747608.0327065}, {"event_id": "730fff71f0894b42817750492510287e", "step": 28, "value": 0.013205084834931824, "stage": "evolution", "created_at": 1788749936.9325557}, {"event_id": "279f1fe0728a4c32b6495d64bea45bc4", "step": 29, "value": 2.0, "stage": "fusion_draft", "created_at": 1788752621.0841944}, {"event_id": "e2262dc3488a4b4bb24c50e3a7460340", "step": 32, "value": 0.0038598360243279977, "stage": "debug", "created_at": 1788746502.1082742}, {"event_id": "8ba74848a0164a8ca9822c58a2174a47", "step": 33, "value": 0.018278312749165422, "stage": "fusion_draft", "created_at": 1788753848.3250954}], "maximize": false, "elapsed_seconds": 28744.873403310776, "node_count": 34, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.bnvs-root-only.dogs-vs-cats-redux-kernels-edition.yaml", "note": ""}, {"id": "xixian.bnvs-root-only.histopathologic-cancer-detection", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "bnvs_root_only", "dataset": "histopathologic-cancer-detection", "status": "archived", "official_score": 0.99549, "medal": "gold", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.9835, "silver": 0.9798, "bronze": 0.9738}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:95", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-root-only-muse13/runs/bnvs_root_only/07_histopathologic-cancer-detection/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-root-only-muse13/runs/bnvs_root_only/07_histopathologic-cancer-detection/logs/journal.json", "metrics": [{"event_id": "08df1d7506a94951b52282d16ccf158b", "step": 3, "value": 0.984111763294536, "stage": "draft", "created_at": 1788728110.865719}, {"event_id": "3e708202bea648cd810dce085e5786f9", "step": 6, "value": 0.9813647490345263, "stage": "debug", "created_at": 1788730085.1425922}, {"event_id": "4626b640d34c47ac91aad746c4594785", "step": 7, "value": 0.994041754779194, "stage": "draft", "created_at": 1788727709.8987527}, {"event_id": "280722aa2071462fa837a627de3b740f", "step": 9, "value": 0.9847533385052848, "stage": "debug", "created_at": 1788730868.188993}, {"event_id": "4f6ae94aab634ac4983a18ff59c73918", "step": 10, "value": 0.9855072985563488, "stage": "improve", "created_at": 1788734845.3314114}, {"event_id": "86319c8922c140389253581e373c3598", "step": 11, "value": 0.9930076827189664, "stage": "improve", "created_at": 1788731681.4382398}, {"event_id": "79a260f3a0b549e0b584a2232da65492", "step": 12, "value": 0.9861287806923383, "stage": "improve", "created_at": 1788741912.9185812}, {"event_id": "356d5ec085a44f02bea3da3dbf081d96", "step": 13, "value": 0.9958082239603328, "stage": "debug", "created_at": 1788732799.1766634}, {"event_id": "ae84e19e1c7b42c39c3f7b731fdf20d1", "step": 14, "value": 0.98359770485808, "stage": "improve", "created_at": 1788747184.4980726}, {"event_id": "b161e04915c74ddf8342744f59bef661", "step": 15, "value": 0.992609761042366, "stage": "improve", "created_at": 1788747267.046228}], "maximize": true, "elapsed_seconds": 28743.013998270035, "node_count": 16, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.bnvs-root-only.histopathologic-cancer-detection.yaml", "note": ""}, {"id": "xixian.bnvs-root-only.jigsaw-toxic-comment-classification-challenge", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "bnvs_root_only", "dataset": "jigsaw-toxic-comment-classification-challenge", "status": "archived", "official_score": 0.98684, "medal": "silver", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.9874, "silver": 0.98668, "bronze": 0.98639}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:96", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-root-only-muse13/runs/bnvs_root_only/08_jigsaw-toxic-comment-classification-challenge/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-root-only-muse13/runs/bnvs_root_only/08_jigsaw-toxic-comment-classification-challenge/logs/journal.json", "metrics": [{"event_id": "6d9e746e71b84604954c597ec8fde604", "step": 3, "value": 0.9878343776656232, "stage": "debug", "created_at": 1788728430.8526518}, {"event_id": "86bf5247fe7c4bb99101fe186dcab811", "step": 4, "value": 0.9921663738572422, "stage": "debug", "created_at": 1788728435.644447}, {"event_id": "c6776b1e4daa40508b01634d3852fea7", "step": 5, "value": 0.9753694549278814, "stage": "draft", "created_at": 1788727901.8646808}, {"event_id": "89202d78c9fe4806ae8f0e714c8f7b45", "step": 6, "value": 0.9013727877820816, "stage": "improve", "created_at": 1788735398.7258966}, {"event_id": "6b4a69cfddef4070ae079f2023f233bf", "step": 7, "value": 0.9917689647155726, "stage": "improve", "created_at": 1788733538.8657901}, {"event_id": "1b8c9f2d69bf4542886022fa1f3acf21", "step": 8, "value": 0.9805997096557132, "stage": "improve", "created_at": 1788744911.0173142}, {"event_id": "bf8aa9f44aa74c0bb3f7986e7da3eb9b", "step": 9, "value": 0.9834361287768969, "stage": "fusion_draft", "created_at": 1788751108.9067528}, {"event_id": "91cf24a8613a4a8aa4bec04b3f894632", "step": 10, "value": 0.9845674472956589, "stage": "improve", "created_at": 1788752502.5330749}], "maximize": true, "elapsed_seconds": 28758.61337661743, "node_count": 15, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.bnvs-root-only.jigsaw-toxic-comment-classification-challenge.yaml", "note": ""}, {"id": "xixian.bnvs-root-only.leaf-classification", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "bnvs_root_only", "dataset": "leaf-classification", "status": "archived", "official_score": 0.00222, "medal": "silver", "valid_submission": true, "score_maximize": false, "thresholds": {"gold": 0.0, "silver": 0.00791, "bronze": 0.01526}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:97", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-root-only-muse13/runs/bnvs_root_only/09_leaf-classification/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-root-only-muse13/runs/bnvs_root_only/09_leaf-classification/logs/journal.json", "metrics": [{"event_id": "6498a3be5f9348f29fa14b47192464c5", "step": 2, "value": 0.0003150956541659128, "stage": "draft", "created_at": 1788727854.8315043}, {"event_id": "ee9fde88db704f4397f190e6fe6c84e9", "step": 5, "value": 0.001143581051598708, "stage": "improve", "created_at": 1788728609.8513975}, {"event_id": "031397cbdf2f4ea8a527089a2f7bf539", "step": 6, "value": 0.02618481864673, "stage": "debug", "created_at": 1788728729.0953922}, {"event_id": "e0a46d851ac54d7a9eec6dac91044823", "step": 7, "value": 0.004266532811207114, "stage": "draft", "created_at": 1788728288.8991747}, {"event_id": "5d583d9a463d4c788c91ff2489cd255b", "step": 8, "value": 0.0004076080428107315, "stage": "improve", "created_at": 1788728905.152135}, {"event_id": "cf7ef53fcfad4e139da9b0db65cb6f63", "step": 9, "value": 0.0002676525648233829, "stage": "improve", "created_at": 1788729081.2411}, {"event_id": "32e5bb94408f46629786b23bf0340c3a", "step": 10, "value": 0.021190256685168257, "stage": "improve", "created_at": 1788729168.9036946}, {"event_id": "3265bf9e13e440fcbf3c568919ed8f8c", "step": 11, "value": 0.019213294726504886, "stage": "improve", "created_at": 1788729308.1774583}], "maximize": false, "elapsed_seconds": 28763.429817914963, "node_count": 15, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.bnvs-root-only.leaf-classification.yaml", "note": ""}, {"id": "xixian.bnvs-root-only.mlsp-2013-birds", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "bnvs_root_only", "dataset": "mlsp-2013-birds", "status": "archived", "official_score": 0.87361, "medal": "none", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.93527, "silver": 0.90038, "bronze": 0.87372}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:98", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-root-only-muse13/runs/bnvs_root_only/10_mlsp-2013-birds/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-root-only-muse13/runs/bnvs_root_only/10_mlsp-2013-birds/logs/journal.json", "metrics": [{"event_id": "c339503bfe2840b0b93dce5db7c13e64", "step": 5, "value": 0.7272248808907261, "stage": "debug", "created_at": 1788729108.3009999}, {"event_id": "c0fbe44cc04b4c439be2c0c2994f0fe3", "step": 7, "value": 0.8319653485265404, "stage": "debug", "created_at": 1788729493.2806044}, {"event_id": "08e0d41d04d24c269e5b759f52a51b54", "step": 8, "value": 0.8009069561379718, "stage": "improve", "created_at": 1788729568.847721}, {"event_id": "f626e87f39734519b57f0f5242a12ba4", "step": 9, "value": 0.8209971646489812, "stage": "improve", "created_at": 1788729937.4723172}, {"event_id": "53971824e4624649a711b4f0ca839076", "step": 10, "value": 0.8668723806643459, "stage": "improve", "created_at": 1788730334.2115967}, {"event_id": "b568a4c5ea1b44d394287cc284af50d5", "step": 11, "value": 0.7642772960511327, "stage": "improve", "created_at": 1788730213.8674664}, {"event_id": "4976bb3f09a6422f9082a6864ecb2703", "step": 12, "value": 0.8457340551365576, "stage": "improve", "created_at": 1788730725.0921273}, {"event_id": "51fdc8cd07f44e69b5557514f15a608a", "step": 13, "value": 0.7902330889578042, "stage": "debug", "created_at": 1788728907.3756506}, {"event_id": "8d3fc81f129a4cd5b3acd7ea2f66de6e", "step": 14, "value": 0.7827481194196497, "stage": "improve", "created_at": 1788730804.8047066}, {"event_id": "07adba48dbc84598a995192b09e607df", "step": 15, "value": 0.8431216534845002, "stage": "improve", "created_at": 1788731075.389716}, {"event_id": "6adb42b8cac343f9bc90b39b0c5a557d", "step": 16, "value": 0.5732572791535522, "stage": "improve", "created_at": 1788731376.5965889}, {"event_id": "c85ced414150443e9b318a5b48b9b350", "step": 17, "value": 0.8339170491294293, "stage": "improve", "created_at": 1788731519.562839}, {"event_id": "aa7c752c6f9a4612a44165aea7062906", "step": 19, "value": 0.8430166005360684, "stage": "debug", "created_at": 1788731921.390986}, {"event_id": "7613ed84a91a4af18f7f4e32ab1b3f16", "step": 20, "value": 0.7090428893498031, "stage": "improve", "created_at": 1788731442.0776708}, {"event_id": "8b51c77ee5fc4c98bc4b88fae63b672a", "step": 21, "value": 0.5216720565591758, "stage": "improve", "created_at": 1788731967.7932484}, {"event_id": "f05548cf3dc34415bfb1a980c1cd5aeb", "step": 23, "value": 0.8118543588614784, "stage": "evolution", "created_at": 1788732335.2476907}, {"event_id": "c3542294d14248d698e0ddf6683575ea", "step": 24, "value": 0.7833292204989709, "stage": "evolution", "created_at": 1788732818.8711052}, {"event_id": "fd460ab986c144148de9727ee8bb7467", "step": 25, "value": 0.8984127689714669, "stage": "evolution", "created_at": 1788733408.3272219}, {"event_id": "4f88255472014c378436579900c042c5", "step": 26, "value": 0.8400072176445357, "stage": "debug", "created_at": 1788732659.4001179}, {"event_id": "26a94e9c83504f05a5f2cbec1ff55a29", "step": 27, "value": 0.8978224627134457, "stage": "improve", "created_at": 1788734068.9644456}, {"event_id": "95a99964fc1d4d8ca2c1420e08f20d89", "step": 28, "value": 0.8451316470941612, "stage": "improve", "created_at": 1788734695.0097556}, {"event_id": "5efda79c24244244ab71e7eabe1d978d", "step": 30, "value": 0.8418998510272605, "stage": "improve", "created_at": 1788734533.2064922}, {"event_id": "a47a57e130bf40be8003b1a3acb0cfb7", "step": 31, "value": 0.8451316470941612, "stage": "debug", "created_at": 1788735739.8627653}, {"event_id": "e93b841f8e5841f2aa3ef87d7495fd6d", "step": 33, "value": 0.8418279728031086, "stage": "improve", "created_at": 1788735988.1625068}, {"event_id": "30a85ddbbe12484ebcbd5dfa290818d4", "step": 34, "value": 0.8948572347060801, "stage": "debug", "created_at": 1788736509.7237067}, {"event_id": "7fec579300e3473da5caf5c27ba5ce05", "step": 36, "value": 0.8405889180684746, "stage": "improve", "created_at": 1788737256.417872}, {"event_id": "0b1aa7f3331a4abcb46f140a94b80560", "step": 37, "value": 0.8317184969169802, "stage": "debug", "created_at": 1788738437.6854086}, {"event_id": "f5bdef837b374173a6793a5df861c5de", "step": 38, "value": 0.8308275463112422, "stage": "improve", "created_at": 1788738879.8351297}, {"event_id": "c9709bce7cde4d2bb96395b3bcc65050", "step": 39, "value": 0.8090889909960911, "stage": "improve", "created_at": 1788732549.8851845}, {"event_id": "a0db638ae0264d718bd7841e17456805", "step": 40, "value": 0.8888258742820253, "stage": "evolution", "created_at": 1788740198.2686503}, {"event_id": "e863a7f987494cc6b06d1dc86b0a9de5", "step": 42, "value": 0.8233203124940252, "stage": "improve", "created_at": 1788739582.1825697}, {"event_id": "810e3d9c141648b2a5f1432a12474a8c", "step": 43, "value": 0.8942341482263929, "stage": "debug", "created_at": 1788741178.556992}, {"event_id": "1821ebad5da64bc9bf447e11195b9af9", "step": 44, "value": 0.8929312384288147, "stage": "evolution", "created_at": 1788741834.915976}, {"event_id": "8030f2b76e164874b804818177a46b37", "step": 45, "value": 0.8993540302357507, "stage": "evolution", "created_at": 1788742575.8854494}, {"event_id": "ddf797146eaa4237a7037740e45ced6c", "step": 46, "value": 0.9060775676276185, "stage": "improve", "created_at": 1788743201.6699433}, {"event_id": "d436be8e37884f1880c179613c304a21", "step": 47, "value": 0.9074092577536329, "stage": "improve", "created_at": 1788743932.5008588}, {"event_id": "a796f1a87483483ab13b3bedc6daea3e", "step": 48, "value": 0.9008353250378249, "stage": "improve", "created_at": 1788744683.948314}, {"event_id": "b1f8632b763642cc9f5e7e7d4c351b57", "step": 49, "value": 0.9133725069229405, "stage": "improve", "created_at": 1788745408.4593666}, {"event_id": "0670da32c134423e95496156d579013a", "step": 50, "value": 0.903065285830475, "stage": "improve", "created_at": 1788746078.5357108}, {"event_id": "83fb5dce682548b397b61396b6ebe499", "step": 52, "value": 0.8250764541603218, "stage": "debug", "created_at": 1788747323.49489}, {"event_id": "275dcc182cbf4e4394e42f0ef8e502a0", "step": 53, "value": 0.9068190189289225, "stage": "improve", "created_at": 1788747854.764939}, {"event_id": "55f5c1a8804d48939dfe374fb22c8b98", "step": 54, "value": 0.8933319937649692, "stage": "fusion", "created_at": 1788748632.169973}, {"event_id": "4607c81b3b324c2c92c6d35b90a7ece2", "step": 55, "value": 0.8179078537014535, "stage": "improve", "created_at": 1788740931.9597402}, {"event_id": "c01a75271fc24a4b9fe2803f392cabd8", "step": 56, "value": 0.7510102010673537, "stage": "fusion", "created_at": 1788749563.4668827}, {"event_id": "26a1757deba34ea2a14a52979d969800", "step": 57, "value": 0.7835335165669015, "stage": "fusion_draft", "created_at": 1788750367.5763214}, {"event_id": "43cecad10432481fb930345af6741f7e", "step": 58, "value": 0.7366109814746297, "stage": "fusion", "created_at": 1788750311.9950612}, {"event_id": "2c0efdee506344b88c4d51b4165c7914", "step": 59, "value": 0.762314544326356, "stage": "fusion_draft", "created_at": 1788750783.4743505}, {"event_id": "1f03210c945b4fa7a39ec4fe07b17802", "step": 60, "value": 0.9025893053353711, "stage": "evolution", "created_at": 1788751100.6447144}, {"event_id": "45a5780da4614bfea4c15bbaacc10343", "step": 62, "value": 0.8864606163938513, "stage": "fusion", "created_at": 1788752028.2793145}, {"event_id": "41665f2aafad41beb769c4ee0ff84961", "step": 63, "value": 0.8881807611773588, "stage": "debug", "created_at": 1788751720.4452374}, {"event_id": "c1ec4a52f1fa4cc599367c41b2fe5d18", "step": 64, "value": 0.8857725711657493, "stage": "evolution", "created_at": 1788752705.321835}, {"event_id": "a9d18b69bbaf433a9a26af1f30c8ded2", "step": 65, "value": 0.8941571196919837, "stage": "evolution", "created_at": 1788753454.7536397}, {"event_id": "cd58718343004e67976b350a5e502f11", "step": 67, "value": 0.882184180677649, "stage": "evolution", "created_at": 1788754140.404877}, {"event_id": "81854ad757de440982830e6487e39eae", "step": 68, "value": 0.8874958798439752, "stage": "debug", "created_at": 1788754544.460935}, {"event_id": "3b82ae63b21d45e29f5ff956a610b65d", "step": 69, "value": 0.8942599807619852, "stage": "evolution", "created_at": 1788755109.9280207}], "maximize": true, "elapsed_seconds": 28718.804617404938, "node_count": 70, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.bnvs-root-only.mlsp-2013-birds.yaml", "note": ""}, {"id": "xixian.bnvs-root-only.new-york-city-taxi-fare-prediction", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "bnvs_root_only", "dataset": "new-york-city-taxi-fare-prediction", "status": "archived", "official_score": 11.15793, "medal": "none", "valid_submission": true, "score_maximize": false, "thresholds": {"gold": 2.83377, "silver": 2.88191, "bronze": 2.92371}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:99", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-root-only-muse13/runs/bnvs_root_only/11_new-york-city-taxi-fare-prediction/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-root-only-muse13/runs/bnvs_root_only/11_new-york-city-taxi-fare-prediction/logs/journal.json", "metrics": [{"event_id": "0f31bf8ba07b4d7998310fdc771a6fc1", "step": 2, "value": 3.0091781343699844, "stage": "draft", "created_at": 1788728225.1644475}, {"event_id": "15ee0d902a4947449d638b816f86654b", "step": 3, "value": 4.579820197453086, "stage": "draft", "created_at": 1788728596.6104286}, {"event_id": "68c2b346333e498ba0732b8f28443eeb", "step": 4, "value": 3.5452185084147807, "stage": "debug", "created_at": 1788728919.4722133}, {"event_id": "8855532c80dc4c4390b3793b0f380bb5", "step": 5, "value": 3.073534940286209, "stage": "improve", "created_at": 1788729155.370865}, {"event_id": "4b66b662ce594cb0adafe326e0015d30", "step": 6, "value": 3.0026498487853783, "stage": "improve", "created_at": 1788729363.1895268}, {"event_id": "dcea64808234499e98aac8dfe94afe92", "step": 7, "value": 2.694263044697863, "stage": "improve", "created_at": 1788729771.5830088}, {"event_id": "fec4399db9d646acb0a7df38814e8df6", "step": 8, "value": 3.0755904535456713, "stage": "improve", "created_at": 1788730065.7482128}, {"event_id": "97c6e8ffdc844932a208052c8bf46ccb", "step": 9, "value": 3.0647106952219203, "stage": "improve", "created_at": 1788730321.197941}, {"event_id": "c2b6df9d0016469cb1c82e1dfc3351b5", "step": 10, "value": 2.781873092500952, "stage": "improve", "created_at": 1788731119.7451708}, {"event_id": "7d8125938ea246ebbf49ab77295ac051", "step": 11, "value": 3.0291876942807705, "stage": "improve", "created_at": 1788731321.33265}, {"event_id": "520701d9260b4df98f6a3aec3e86c862", "step": 12, "value": 2.590331844642763, "stage": "improve", "created_at": 1788731784.44636}, {"event_id": "34b0f961fefc4f80bee2b2a9b30ad97b", "step": 13, "value": 2.6775768995259965, "stage": "improve", "created_at": 1788732650.5285108}, {"event_id": "14a3ac9384024d72b74849696a62f32e", "step": 14, "value": 2.654209801801951, "stage": "improve", "created_at": 1788734140.3265646}, {"event_id": "9e56957202df47e1a9c5997bba6ccb3f", "step": 15, "value": 2.5803314922439853, "stage": "improve", "created_at": 1788733630.6847394}, {"event_id": "0f8e7f02371f45aa92f2ebb658753347", "step": 16, "value": 2.6188818783579597, "stage": "improve", "created_at": 1788735766.901573}, {"event_id": "fc2b7227e56e44ba8e232ebace68d083", "step": 17, "value": 2.628533852801147, "stage": "improve", "created_at": 1788739861.3500965}, {"event_id": "fac0986b49c44c04bf7efcf97b4b996d", "step": 18, "value": 2.5642746528978706, "stage": "improve", "created_at": 1788736052.764488}, {"event_id": "90ac4f9c0698430d84df0a04a5891085", "step": 20, "value": 2.590116074639094, "stage": "improve", "created_at": 1788743498.2974198}, {"event_id": "5ab92756d1f544b4b3929cc865cd4a83", "step": 22, "value": 3.5974887224670318, "stage": "debug", "created_at": 1788752889.5783396}, {"event_id": "3d68fe0fe58b402db788a69eb09a3d26", "step": 25, "value": 3.1975121433116778, "stage": "debug", "created_at": 1788755110.814898}, {"event_id": "bce35596463d4d4c8cd98760208f74fe", "step": 26, "value": 3.8464600566104266, "stage": "debug", "created_at": 1788755657.0930545}], "maximize": false, "elapsed_seconds": 28737.233855247498, "node_count": 27, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.bnvs-root-only.new-york-city-taxi-fare-prediction.yaml", "note": ""}, {"id": "xixian.bnvs-root-only.nomad2018-predict-transparent-conductors", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "bnvs_root_only", "dataset": "nomad2018-predict-transparent-conductors", "status": "archived", "official_score": 0.06135, "medal": "silver", "valid_submission": true, "score_maximize": false, "thresholds": {"gold": 0.05589, "silver": 0.06229, "bronze": 0.06582}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:100", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-root-only-muse13/runs/bnvs_root_only/12_nomad2018-predict-transparent-conductors/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-root-only-muse13/runs/bnvs_root_only/12_nomad2018-predict-transparent-conductors/logs/journal.json", "metrics": [{"event_id": "f21f6a39b5de45bf9391de9c0079d0dc", "step": 2, "value": 0.18293898023308638, "stage": "draft", "created_at": 1788728327.014055}, {"event_id": "801a7d990cb446da9d020a9dc37d03ab", "step": 3, "value": 0.05551411108666649, "stage": "draft", "created_at": 1788727959.0012195}, {"event_id": "571d16f32fcc46329019b274f963cd2f", "step": 4, "value": 0.07776278384702189, "stage": "debug", "created_at": 1788728485.0065088}, {"event_id": "d69960cf58a746b98a6b948d88567de5", "step": 5, "value": 0.07776278384702189, "stage": "improve", "created_at": 1788728795.8034875}, {"event_id": "5b78672587c74549ac231a74eebdea2e", "step": 6, "value": 0.06170518506038093, "stage": "improve", "created_at": 1788728622.037421}, {"event_id": "32d113477cda4c53aea5b4b8e57b6766", "step": 7, "value": 0.05551411108666649, "stage": "improve", "created_at": 1788728650.2723112}, {"event_id": "d162d6b94d74440f83681dd3c8bf9aba", "step": 8, "value": 0.09184240080093618, "stage": "improve", "created_at": 1788729161.903434}, {"event_id": "ca6c0bb834104ba982cbbabf34fbdb92", "step": 9, "value": 0.06204724078963594, "stage": "improve", "created_at": 1788729075.4819937}, {"event_id": "36631bce55d74cae8d53a876e26c3585", "step": 10, "value": 0.05474233147005693, "stage": "improve", "created_at": 1788729421.312804}, {"event_id": "699da2b2d6df42c99c0c91c772e6c9fc", "step": 11, "value": 0.09184240080093618, "stage": "improve", "created_at": 1788729597.4459965}, {"event_id": "faf7a0daafe74d8fa4af4afc224ae6bc", "step": 12, "value": 0.07059895943033397, "stage": "improve", "created_at": 1788729960.1675994}, {"event_id": "b9c709f870dd405b848fc6a3f7a17b33", "step": 13, "value": 0.07059895943033397, "stage": "improve", "created_at": 1788730313.7509966}, {"event_id": "98dcdb01a7a244bb82451630e40b9e62", "step": 14, "value": 0.07059895943033397, "stage": "improve", "created_at": 1788730664.3259435}, {"event_id": "9bb6cfafe4d649798663aa2ed6aea035", "step": 15, "value": 0.06050049068041875, "stage": "improve", "created_at": 1788729726.082404}, {"event_id": "189ef23d67b34698b1beeadacaa86ea4", "step": 16, "value": 0.05523500208141393, "stage": "improve", "created_at": 1788730980.2549207}, {"event_id": "1e97910e00794151a2fd567c2514d71f", "step": 17, "value": 0.05523500208141393, "stage": "improve", "created_at": 1788732588.7744658}, {"event_id": "92fd5c677d444f8c938d96c96e9dcc0d", "step": 18, "value": 0.05523500208141393, "stage": "improve", "created_at": 1788735098.1134102}, {"event_id": "434b19fdae924f689f12ba4332982439", "step": 19, "value": 0.05523500208141393, "stage": "improve", "created_at": 1788737452.9642174}, {"event_id": "8da38e6531164a678fdfd8625afddfca", "step": 20, "value": 0.06044328555413875, "stage": "improve", "created_at": 1788732544.8556957}, {"event_id": "0c178d83fe6a42bdb32efdc7dd1e0c55", "step": 21, "value": 0.05581698140305482, "stage": "improve", "created_at": 1788740764.2236247}, {"event_id": "3ec436b8feb14bb4af18415d900dbd66", "step": 22, "value": 0.055033205988728406, "stage": "improve", "created_at": 1788729821.464412}, {"event_id": "50a6eb0191fb4b3dbe8fc7261b737937", "step": 24, "value": 0.06029111159797839, "stage": "improve", "created_at": 1788744129.9711118}, {"event_id": "5d69d65113814b54a4b2ffeb6a1aa315", "step": 25, "value": 0.0647684539325285, "stage": "debug", "created_at": 1788749055.948866}], "maximize": false, "elapsed_seconds": 28746.11580467224, "node_count": 26, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.bnvs-root-only.nomad2018-predict-transparent-conductors.yaml", "note": ""}, {"id": "xixian.bnvs-root-only.plant-pathology-2020-fgvc7", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "bnvs_root_only", "dataset": "plant-pathology-2020-fgvc7", "status": "archived", "official_score": 0.99091, "medal": "gold", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.97836, "silver": 0.97465, "bronze": 0.97361}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:101", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-root-only-muse13/runs/bnvs_root_only/13_plant-pathology-2020-fgvc7/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-root-only-muse13/runs/bnvs_root_only/13_plant-pathology-2020-fgvc7/logs/journal.json", "metrics": [{"event_id": "d7e66fc4e91045e4a2fa3341a83daced", "step": 3, "value": 0.9858651957368312, "stage": "draft", "created_at": 1788727531.6298387}, {"event_id": "d859b284e9544ce5a382de7af5c2c0ff", "step": 5, "value": 0.9922644906168777, "stage": "debug", "created_at": 1788728796.8149676}, {"event_id": "2eecc8ec4a28481b86375b889faff276", "step": 6, "value": 0.9891896395774271, "stage": "draft", "created_at": 1788727984.9446483}, {"event_id": "259e932c773c49b0951dc5ce9dd3d784", "step": 9, "value": 0.9906775026187571, "stage": "debug", "created_at": 1788729287.6240118}, {"event_id": "9bdc0c2d0cae4beb988eea59360f496b", "step": 10, "value": 0.9947295214547855, "stage": "debug", "created_at": 1788730198.3741634}, {"event_id": "0cd8bc6113cc4384ba5e2b16ce46166b", "step": 13, "value": 0.9919175221213761, "stage": "improve", "created_at": 1788730682.0983746}, {"event_id": "94771bfd8e8c49e8a02dc0c6f78361bd", "step": 14, "value": 0.9861785278749146, "stage": "improve", "created_at": 1788729964.3970258}, {"event_id": "387929e77fd043edba179328a217f394", "step": 15, "value": 0.9977037765634148, "stage": "debug", "created_at": 1788731890.5819092}, {"event_id": "2a5d855348a84961ae3b9b21690bb5e5", "step": 20, "value": 0.9871345772187394, "stage": "improve", "created_at": 1788732111.317165}, {"event_id": "8a56f05092884d33b2c589aab3d8cd0c", "step": 21, "value": 0.9926769823147273, "stage": "debug", "created_at": 1788733895.9648087}, {"event_id": "175c3ac25a8a4658bb3fd447534f3108", "step": 22, "value": 0.9850364285688072, "stage": "debug", "created_at": 1788734454.498327}, {"event_id": "bad92dd7857749b9985a96b20835b326", "step": 23, "value": 0.9938452954456674, "stage": "improve", "created_at": 1788735133.4937873}, {"event_id": "0ab6b423284e4cd696d9063a49b462ca", "step": 24, "value": 0.9895164057083556, "stage": "improve", "created_at": 1788734683.7571347}, {"event_id": "766dabc3678843dbb9f9d6a5d1daf588", "step": 25, "value": 0.9783802900225662, "stage": "improve", "created_at": 1788736643.6382072}, {"event_id": "44290022412046969190bf929b07d56b", "step": 31, "value": 0.962193402237806, "stage": "improve", "created_at": 1788735869.0991044}, {"event_id": "4d3c78d68a6f43bbbea3a05216436baf", "step": 32, "value": 0.9880196972860811, "stage": "evolution", "created_at": 1788740365.9837108}, {"event_id": "d7e0deb2c6c9484ea7e3ab3f9f47acf8", "step": 35, "value": 0.9891690394926482, "stage": "debug", "created_at": 1788743294.8019319}, {"event_id": "1758f03ae71d43e586e569e38fcec1fd", "step": 37, "value": 0.9762994421162374, "stage": "improve", "created_at": 1788736988.2969937}, {"event_id": "ce3b30d7fe96408389afa3f67fea8f35", "step": 38, "value": 0.9848031269232076, "stage": "debug", "created_at": 1788745022.3036098}, {"event_id": "6813ec59d2234086bdc339e7bb693373", "step": 40, "value": 0.9928567204526338, "stage": "fusion", "created_at": 1788747570.7355156}, {"event_id": "ac038e004e05429d8e8fb25d2f9e5a63", "step": 44, "value": 0.9919339585793683, "stage": "debug", "created_at": 1788749933.0267913}, {"event_id": "dd38f6e6f42a45458154d2a4288d5987", "step": 47, "value": 0.9873312251898051, "stage": "debug", "created_at": 1788751519.4842272}, {"event_id": "431cf6bb71ce46658315223cf8d0cc07", "step": 51, "value": 0.9961786275780079, "stage": "evolution", "created_at": 1788752496.7334466}, {"event_id": "a5a8fcaf697b4ce39ddf232ab8a7ea21", "step": 52, "value": 0.979891348463301, "stage": "debug", "created_at": 1788754096.229734}], "maximize": true, "elapsed_seconds": 28719.866497516632, "node_count": 54, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.bnvs-root-only.plant-pathology-2020-fgvc7.yaml", "note": ""}, {"id": "xixian.bnvs-root-only.random-acts-of-pizza", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "bnvs_root_only", "dataset": "random-acts-of-pizza", "status": "archived", "official_score": 0.64494, "medal": "none", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.97908, "silver": 0.76482, "bronze": 0.6921}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:102", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-root-only-muse13/runs/bnvs_root_only/14_random-acts-of-pizza/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-root-only-muse13/runs/bnvs_root_only/14_random-acts-of-pizza/logs/journal.json", "metrics": [{"event_id": "b9b1133becd0437499ae0625de1bc8e1", "step": 3, "value": 0.6474103263941602, "stage": "draft", "created_at": 1788727668.7307434}, {"event_id": "dd5b1f1d9692453d8129fdd1fe8bac30", "step": 5, "value": 0.6726096333572968, "stage": "debug", "created_at": 1788728681.322634}, {"event_id": "99993d84e5b34183bb067b4b58edd99e", "step": 6, "value": 0.6456858066502463, "stage": "debug", "created_at": 1788728773.6845975}, {"event_id": "0533baa30524496fbe4bb632b86183f4", "step": 7, "value": 0.6654661735493145, "stage": "improve", "created_at": 1788728874.56671}, {"event_id": "855edd119add4bfa8195a660ce7f56d2", "step": 8, "value": 0.6439732142857143, "stage": "improve", "created_at": 1788729103.428466}, {"event_id": "e9a3b3fb6dbd47129f7e54bd0dc5831c", "step": 9, "value": 0.6735585909417685, "stage": "improve", "created_at": 1788729172.9315393}, {"event_id": "50a3250bd59949e19b65150375393245", "step": 10, "value": 0.6470905172413794, "stage": "improve", "created_at": 1788729508.208015}, {"event_id": "bd00d3901110499c8de0658400540d2f", "step": 11, "value": 0.6923884429658103, "stage": "improve", "created_at": 1788729295.7410293}, {"event_id": "e699308da4424d38bd8e966023855d17", "step": 12, "value": 0.6916750539180445, "stage": "improve", "created_at": 1788729662.7498553}, {"event_id": "b6278604bc124b478d9d5f58fa0a8c9c", "step": 14, "value": 0.6449545874384237, "stage": "improve", "created_at": 1788730088.6612532}, {"event_id": "54b90e3e6a1e46e68ea691fccf70266f", "step": 15, "value": 0.6916750539180445, "stage": "improve", "created_at": 1788730226.7031922}, {"event_id": "6be20745bc65409fa66fb2158230175f", "step": 18, "value": 0.6880805176132277, "stage": "improve", "created_at": 1788730879.1304977}, {"event_id": "c863bb3a42434a8891859dc0e6a85be2", "step": 19, "value": 0.6846202296548717, "stage": "debug", "created_at": 1788730765.6271014}, {"event_id": "ad16129b61ee4c13ba46b89c78291675", "step": 20, "value": 0.6400284790640395, "stage": "debug", "created_at": 1788730848.2070274}, {"event_id": "2c112163a2504346adfb2a6e98d01290", "step": 23, "value": 0.8456928185083525, "stage": "improve", "created_at": 1788731500.0505517}, {"event_id": "8a67b95df0d04f2db7c95879cb73589b", "step": 26, "value": 0.6860078432893967, "stage": "debug", "created_at": 1788732076.3416977}, {"event_id": "5ef8e56a390e4feeb4a46ce995849953", "step": 27, "value": 0.842432648257891, "stage": "improve", "created_at": 1788732193.7408705}, {"event_id": "4bdc98cd936e45f6a46e176b056b65ce", "step": 28, "value": 0.6908945557906296, "stage": "debug", "created_at": 1788732097.8345752}, {"event_id": "a5acc13ca3d247c7b53f96e209348910", "step": 30, "value": 0.6884157913284128, "stage": "improve", "created_at": 1788733068.1026855}, {"event_id": "f5ec341a1a914fe28c6fed4e1249dd7b", "step": 31, "value": 0.8418035039394263, "stage": "improve", "created_at": 1788733226.8605282}, {"event_id": "e53c85e71497456ea78f8d422e1872f0", "step": 32, "value": 0.6964624372391363, "stage": "debug", "created_at": 1788733611.4849238}, {"event_id": "9cccdfa6c1784a4781059f242ab5cefa", "step": 33, "value": 0.6884157913284128, "stage": "improve", "created_at": 1788733937.2594013}, {"event_id": "31d99db448c4490d82fbcdaf501e51db", "step": 37, "value": 0.6823907484101659, "stage": "debug", "created_at": 1788735929.778576}, {"event_id": "4b1aa97c88484bff90369d500d8ec327", "step": 38, "value": 0.8404016695278831, "stage": "improve", "created_at": 1788734194.9804723}, {"event_id": "db38e6ee1477400aa18548bca5864ffa", "step": 43, "value": 0.690735801415413, "stage": "improve", "created_at": 1788737584.5392163}, {"event_id": "e446076bdfad47fb8c97b82bfcdd0c2d", "step": 44, "value": 0.633156002875629, "stage": "evolution", "created_at": 1788739149.5495074}, {"event_id": "5cde8a62768e4989a8aac190b88d978d", "step": 45, "value": 0.7938870191297376, "stage": "evolution", "created_at": 1788738323.9430382}, {"event_id": "694c8d1f58d441ab9c69a33437c2d8ef", "step": 46, "value": 0.674829054440705, "stage": "improve", "created_at": 1788734866.6304662}, {"event_id": "ff7a4ee61e7f4a6994abb1810aa03889", "step": 47, "value": 0.8532121600082765, "stage": "evolution", "created_at": 1788739863.8798354}, {"event_id": "26e390aefe7b49738466ecf208da7cd0", "step": 48, "value": 0.8029232903019312, "stage": "evolution", "created_at": 1788740715.415588}, {"event_id": "65648aa6ef4d495aaa56bfbc99dbc5e0", "step": 50, "value": 0.8346643647614522, "stage": "debug", "created_at": 1788743784.117427}, {"event_id": "c2a75da9d2ae400d9e69d42248f38e06", "step": 51, "value": 0.8410928876948295, "stage": "fusion", "created_at": 1788742399.6853032}, {"event_id": "425da1b5b2004a079d849465c40cd7a7", "step": 52, "value": 0.8413353636654606, "stage": "improve", "created_at": 1788742744.5401328}, {"event_id": "990e5606fc1b41c098ab86bff5613d6e", "step": 54, "value": 0.8730518672266245, "stage": "evolution", "created_at": 1788745507.4758863}, {"event_id": "836115380b154c0397868d81dfed59ef", "step": 55, "value": 0.843813791386607, "stage": "improve", "created_at": 1788744705.1658158}, {"event_id": "7744f2a3ad6f4a44b0fe4585bcbda564", "step": 56, "value": 0.8733085684541996, "stage": "improve", "created_at": 1788749506.8066638}, {"event_id": "4e62a2be9634412eaf21eecd7e12d73a", "step": 57, "value": 0.8441105819746597, "stage": "improve", "created_at": 1788749546.651421}, {"event_id": "ae7f2568b54145aeaec052e5619eeb87", "step": 58, "value": 0.8886168847333896, "stage": "debug", "created_at": 1788747496.40057}], "maximize": true, "elapsed_seconds": 28734.99815273285, "node_count": 59, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.bnvs-root-only.random-acts-of-pizza.yaml", "note": ""}, {"id": "xixian.bnvs-root-only.ranzcr-clip-catheter-line-classification", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "bnvs_root_only", "dataset": "ranzcr-clip-catheter-line-classification", "status": "archived", "official_score": 0.90869, "medal": "none", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.97357, "silver": 0.97152, "bronze": 0.9709}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:103", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-root-only-muse13/runs/bnvs_root_only/15_ranzcr-clip-catheter-line-classification/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-root-only-muse13/runs/bnvs_root_only/15_ranzcr-clip-catheter-line-classification/logs/journal.json", "metrics": [{"event_id": "5f6b67ea2daf4b2f8a827e124e73ad1c", "step": 2, "value": 0.8520043633678522, "stage": "draft", "created_at": 1788728599.4878106}, {"event_id": "3b0658520ea0434c914c1ea3a56c979b", "step": 4, "value": 0.8650082065257534, "stage": "draft", "created_at": 1788728106.0058174}, {"event_id": "f85f9718db8749a79ee1bd7227f702c6", "step": 6, "value": 0.8235117604121022, "stage": "debug", "created_at": 1788730409.398061}, {"event_id": "9a6502da397f46a194473ce1984c9922", "step": 8, "value": 0.854843288647139, "stage": "debug", "created_at": 1788735498.0856864}, {"event_id": "64fe530856a448ea9feefc2855be5d2a", "step": 10, "value": 0.8711980089199971, "stage": "debug", "created_at": 1788736555.4146078}, {"event_id": "eee91648d61747b7ae225c7ee26830eb", "step": 11, "value": 0.7530776455668348, "stage": "improve", "created_at": 1788740023.9184873}, {"event_id": "3818a40893854853bca90d741bbbc9a5", "step": 12, "value": 0.9059861908819773, "stage": "improve", "created_at": 1788744755.7715554}], "maximize": true, "elapsed_seconds": 28722.604189157486, "node_count": 14, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.bnvs-root-only.ranzcr-clip-catheter-line-classification.yaml", "note": ""}, {"id": "xixian.bnvs-root-only.siim-isic-melanoma-classification", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "bnvs_root_only", "dataset": "siim-isic-melanoma-classification", "status": "archived", "official_score": 0.82927, "medal": "none", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.9455, "silver": 0.9401, "bronze": 0.937}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:104", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-root-only-muse13/runs/bnvs_root_only/16_siim-isic-melanoma-classification/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-root-only-muse13/runs/bnvs_root_only/16_siim-isic-melanoma-classification/logs/journal.json", "metrics": [{"event_id": "418e5932bed74de292c3777222fd93dd", "step": 6, "value": 0.9222163588390502, "stage": "debug", "created_at": 1788732024.9896238}, {"event_id": "4939e120036a43dd9d8c0e5de1b56744", "step": 7, "value": 0.9216481970096745, "stage": "improve", "created_at": 1788732402.6818862}, {"event_id": "7635bd82b8914adf9eb8da946f052afc", "step": 11, "value": 0.9166127466839211, "stage": "debug", "created_at": 1788735243.076527}, {"event_id": "7c848b3290504822b7ef63c4826b67ed", "step": 12, "value": 0.9294906358963299, "stage": "improve", "created_at": 1788738036.1724935}, {"event_id": "98c32b18d5ac409f9bc93780dd37bab8", "step": 13, "value": 0.9284158309069341, "stage": "improve", "created_at": 1788740236.5799284}], "maximize": true, "elapsed_seconds": 28724.000576019287, "node_count": 19, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.bnvs-root-only.siim-isic-melanoma-classification.yaml", "note": ""}, {"id": "xixian.bnvs-root-only.spooky-author-identification", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "bnvs_root_only", "dataset": "spooky-author-identification", "status": "archived", "official_score": 0.20661, "medal": "silver", "valid_submission": true, "score_maximize": false, "thresholds": {"gold": 0.16506, "silver": 0.26996, "bronze": 0.29381}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:105", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-root-only-muse13/runs/bnvs_root_only/17_spooky-author-identification/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-root-only-muse13/runs/bnvs_root_only/17_spooky-author-identification/logs/journal.json", "metrics": [{"event_id": "35d222b5c2b44ee7a63edb3c84521bbd", "step": 2, "value": 0.547758961867573, "stage": "draft", "created_at": 1788728161.551656}, {"event_id": "8f3bbe8911d24522a85288c31fa4845e", "step": 3, "value": 0.30813501960684503, "stage": "debug", "created_at": 1788728270.7744956}, {"event_id": "d3edf40990bd4c9b8d3d36e460fab7d9", "step": 4, "value": 0.3733210500897022, "stage": "draft", "created_at": 1788727852.6666942}, {"event_id": "6ae65dabb4a74964b6d8c1e3a04e7028", "step": 5, "value": 0.44445105704380283, "stage": "improve", "created_at": 1788728543.5702512}, {"event_id": "41d3ffc0661b485f8235408dae8db55f", "step": 6, "value": 0.4263506010789291, "stage": "improve", "created_at": 1788729228.5886042}, {"event_id": "3d4fe3e82b574fffb23d35eca7a1e608", "step": 7, "value": 0.28966324273830535, "stage": "improve", "created_at": 1788728729.964283}, {"event_id": "588eed0ab58f489cb595d0449dba3170", "step": 8, "value": 0.31215597666770917, "stage": "improve", "created_at": 1788730076.1397748}, {"event_id": "c2b9345fc2a84e7cacccc1ff4b792723", "step": 9, "value": 0.22583416498638062, "stage": "improve", "created_at": 1788730349.9103253}, {"event_id": "949997dc1cd7453db1eebc4d6749abd7", "step": 10, "value": 0.27190323551771434, "stage": "improve", "created_at": 1788731180.6798897}, {"event_id": "8536cc40516440649f3d438c5297e556", "step": 11, "value": 0.2325478826771245, "stage": "improve", "created_at": 1788732420.3684068}, {"event_id": "3ccedbd23b974ac3a7bb8957c2d0b301", "step": 12, "value": 0.29439511588363576, "stage": "improve", "created_at": 1788733081.7922482}, {"event_id": "ff59b8b04e4543898977d6143362d899", "step": 13, "value": 0.22146092799348382, "stage": "improve", "created_at": 1788735062.017548}, {"event_id": "b24fd6dfaf4d47e785efc7b0d33151e7", "step": 14, "value": 0.2883307508691463, "stage": "improve", "created_at": 1788735753.5536277}, {"event_id": "47c1f3e71fad4d07b324cce46d933ef2", "step": 15, "value": 0.21990168664862741, "stage": "improve", "created_at": 1788737343.564678}, {"event_id": "bc801a1149df4635bc3a18cf64f6f5dd", "step": 19, "value": 0.28867893841953013, "stage": "improve", "created_at": 1788739771.5837088}, {"event_id": "d046ccbeaf82470b9ea29429b53806ba", "step": 20, "value": 0.31296965894563467, "stage": "debug", "created_at": 1788741565.2523427}, {"event_id": "56f0313668cf4d19af057a3c6123992c", "step": 21, "value": 0.22582078711114448, "stage": "improve", "created_at": 1788745502.5416632}, {"event_id": "b61b5f26431b4d1cbd2afbeaa9d4416c", "step": 23, "value": 0.3458854748657404, "stage": "fusion", "created_at": 1788747480.2518137}, {"event_id": "a2b2858dd1fb4a6abb413194ab4f615b", "step": 24, "value": 0.23198481555676911, "stage": "improve", "created_at": 1788748066.8981745}, {"event_id": "f4eebae630604d4ebd5500398038b2ad", "step": 26, "value": 0.2746076006943611, "stage": "debug", "created_at": 1788751916.92465}, {"event_id": "2b53b0a52ca44839b9896bb5be4f52ee", "step": 27, "value": 0.2988941924679711, "stage": "evolution", "created_at": 1788751794.6602826}, {"event_id": "f8b308856ac34c48b58b0d0c6dfa473d", "step": 28, "value": 0.31823515064971175, "stage": "fusion_draft", "created_at": 1788753497.438216}], "maximize": false, "elapsed_seconds": 28753.109133720398, "node_count": 29, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.bnvs-root-only.spooky-author-identification.yaml", "note": ""}, {"id": "xixian.bnvs-root-only.tabular-playground-series-dec-2021", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "bnvs_root_only", "dataset": "tabular-playground-series-dec-2021", "status": "archived", "official_score": 0.96022, "medal": "gold", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.9566, "silver": 0.95658, "bronze": 0.95658}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:106", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-root-only-muse13/runs/bnvs_root_only/18_tabular-playground-series-dec-2021/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-root-only-muse13/runs/bnvs_root_only/18_tabular-playground-series-dec-2021/logs/journal.json", "metrics": [{"event_id": "294c5c0c57ae418789e20c627949bd5c", "step": 8, "value": 0.9471319444444445, "stage": "debug", "created_at": 1788728445.6524181}, {"event_id": "b34aafe681c74da4a3714095e768cbd2", "step": 9, "value": 0.9593972222222222, "stage": "debug", "created_at": 1788728655.3754742}, {"event_id": "735f129d88d24b768b0f85c2b24fedde", "step": 10, "value": 0.8773703703703704, "stage": "improve", "created_at": 1788728934.1715918}, {"event_id": "d7d757ce51034843b35767f30d5fc185", "step": 11, "value": 0.9598527777777778, "stage": "improve", "created_at": 1788729258.1539192}], "maximize": true, "elapsed_seconds": 28757.71179318428, "node_count": 15, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.bnvs-root-only.tabular-playground-series-dec-2021.yaml", "note": ""}, {"id": "xixian.bnvs-root-only.tabular-playground-series-may-2022", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "bnvs_root_only", "dataset": "tabular-playground-series-may-2022", "status": "archived", "official_score": 0.9884, "medal": "none", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.99823, "silver": 0.99822, "bronze": 0.99818}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:107", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-root-only-muse13/runs/bnvs_root_only/19_tabular-playground-series-may-2022/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-root-only-muse13/runs/bnvs_root_only/19_tabular-playground-series-may-2022/logs/journal.json", "metrics": [{"event_id": "fa91c87356c446f3b08c1cbf97bb947a", "step": 1, "value": 0.9060573269599064, "stage": "draft", "created_at": 1788727524.3155096}, {"event_id": "f5d8b3f111cc4d1d84e39065de92a7c4", "step": 2, "value": 0.7453367094265789, "stage": "draft", "created_at": 1788728139.4021223}, {"event_id": "2260590133aa40fd8837e0704879d2b3", "step": 3, "value": 0.9818488163775845, "stage": "improve", "created_at": 1788728578.9968948}, {"event_id": "5ddc13d0d5444ceda5899da66e403bc0", "step": 4, "value": 0.9917090552278215, "stage": "improve", "created_at": 1788728427.5591629}, {"event_id": "b2a19cf6f8b4437fa71d49148f2fb347", "step": 7, "value": 0.8045181059566381, "stage": "fusion_draft", "created_at": 1788751326.3654287}], "maximize": true, "elapsed_seconds": 28736.873949050903, "node_count": 8, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.bnvs-root-only.tabular-playground-series-may-2022.yaml", "note": ""}, {"id": "xixian.bnvs-root-only.text-normalization-challenge-english-language", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "bnvs_root_only", "dataset": "text-normalization-challenge-english-language", "status": "archived", "official_score": 0.99131, "medal": "bronze", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.99724, "silver": 0.99135, "bronze": 0.99038}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:108", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-root-only-muse13/runs/bnvs_root_only/20_text-normalization-challenge-english-language/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-root-only-muse13/runs/bnvs_root_only/20_text-normalization-challenge-english-language/logs/journal.json", "metrics": [{"event_id": "31df388df04b4b3cac3cad3b343a9395", "step": 5, "value": 0.988863392822078, "stage": "debug", "created_at": 1788728604.8770926}, {"event_id": "b0f52a26f9854bf2897416380a531530", "step": 6, "value": 0.9843301035750084, "stage": "draft", "created_at": 1788728087.8784537}, {"event_id": "332b577710f24d65b044e6f199d0a456", "step": 7, "value": 0.9839246824975116, "stage": "debug", "created_at": 1788729164.9549527}, {"event_id": "3eb2768a26a5414ebd95c1151c4eda22", "step": 11, "value": 0.6453781044659762, "stage": "improve", "created_at": 1788730348.0615952}, {"event_id": "e62c44ceadc54b31862e2e09fb59f0a0", "step": 13, "value": 0.9517429557857222, "stage": "improve", "created_at": 1788734748.9812977}, {"event_id": "7390cd017ebc40d08430aced9728f714", "step": 14, "value": 0.9878494264394698, "stage": "improve", "created_at": 1788734708.533345}, {"event_id": "dea99d4f713a4ddc89d26e404b642733", "step": 15, "value": 0.9892232508363207, "stage": "improve", "created_at": 1788730541.906639}, {"event_id": "73e7d3a528104273955f51f9be7d3eb5", "step": 16, "value": 0.9878494264394698, "stage": "improve", "created_at": 1788738820.7603476}, {"event_id": "73d07f63e7534e74ba10d6878bff0401", "step": 17, "value": 0.9517429557857222, "stage": "improve", "created_at": 1788738614.7326367}, {"event_id": "ec61342040084724adf4bb6c7c38134f", "step": 18, "value": 0.9878382893417975, "stage": "improve", "created_at": 1788744461.4219735}, {"event_id": "7505eb93ddb14f508fd9a5e431605a51", "step": 19, "value": 0.9910234992760887, "stage": "improve", "created_at": 1788746676.8002288}, {"event_id": "002235302cb94b92b9f6efd86d9f342b", "step": 20, "value": 0.9907673460296247, "stage": "improve", "created_at": 1788750587.0329568}], "maximize": true, "elapsed_seconds": 28736.074237823486, "node_count": 21, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.bnvs-root-only.text-normalization-challenge-english-language.yaml", "note": ""}, {"id": "xixian.bnvs-root-only.text-normalization-challenge-russian-language", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "bnvs_root_only", "dataset": "text-normalization-challenge-russian-language", "status": "archived", "official_score": 0.96559, "medal": "none", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.99012, "silver": 0.98232, "bronze": 0.97592}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:109", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-root-only-muse13/runs/bnvs_root_only/21_text-normalization-challenge-russian-language/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-root-only-muse13/runs/bnvs_root_only/21_text-normalization-challenge-russian-language/logs/journal.json", "metrics": [{"event_id": "3b96c74e9d404006992c7ed35fdb20ee", "step": 5, "value": 0.9261745668245652, "stage": "debug", "created_at": 1788728940.2279055}, {"event_id": "d22118e938854395a88f5900f1f1e838", "step": 6, "value": 0.9649747466825611, "stage": "improve", "created_at": 1788729849.8438034}, {"event_id": "ec7acdf7bd9744dfba6639f517c8f233", "step": 9, "value": 0.9206666666666666, "stage": "debug", "created_at": 1788729380.445161}, {"event_id": "d25cf5a82a494454bfcb9c219c39d552", "step": 10, "value": 0.9184381870010203, "stage": "draft", "created_at": 1788728602.060163}, {"event_id": "cf69bb1e94b943cea035e45b125dfcba", "step": 11, "value": 0.9487979839173489, "stage": "debug", "created_at": 1788731968.0767725}, {"event_id": "5e7d1db3276443fe814eb322a73f8ca7", "step": 13, "value": 0.957, "stage": "improve", "created_at": 1788732384.827946}, {"event_id": "571c420d0d4646c8bb5c0b4967ceef69", "step": 15, "value": 0.9399567085986762, "stage": "improve", "created_at": 1788743240.526179}, {"event_id": "c77b51db1fdc4c88bfc0104de12d6223", "step": 17, "value": 0.9574361779339217, "stage": "improve", "created_at": 1788734459.4359977}, {"event_id": "f5d3ce1dcb0841f8adfe96076b0c5ac6", "step": 18, "value": 0.9486666666666667, "stage": "improve", "created_at": 1788744815.653448}, {"event_id": "e4dfa2c35e3e4190bd52ae6c163f859a", "step": 19, "value": 0.9595, "stage": "fusion_draft", "created_at": 1788752393.1412864}, {"event_id": "25d04b2acdfa4041bbcc73bbf9bf45c2", "step": 20, "value": 0.9542490191334715, "stage": "improve", "created_at": 1788744929.6517622}], "maximize": true, "elapsed_seconds": 28745.569451332092, "node_count": 21, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.bnvs-root-only.text-normalization-challenge-russian-language.yaml", "note": ""}, {"id": "xixian.bnvs-root-only.the-icml-2013-whale-challenge-right-whale-redux", "experiment_id": "mlebench-baselines-20260906", "family": "MLEBench", "method": "bnvs_root_only", "dataset": "the-icml-2013-whale-challenge-right-whale-redux", "status": "archived", "official_score": 0.99366, "medal": "gold", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.98961, "silver": 0.95017, "bronze": 0.90521}, "grading_policy": "selected", "artifacts": [{"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-five-methods-muse13/results/private_grades.jsonl:110", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}, {"bundle_id": "bnvs-gpt-under-512mb", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "member": "mlebench-root-only-muse13/runs/bnvs_root_only/22_the-icml-2013-whale-challenge-right-whale-redux/logs/journal.json", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240"}], "alternate_scores": [], "journal_ref": "bnvs-gpt-under-512mb:mlebench-root-only-muse13/runs/bnvs_root_only/22_the-icml-2013-whale-challenge-right-whale-redux/logs/journal.json", "metrics": [{"event_id": "33ee386fd017443ca2aebc994b3d7607", "step": 4, "value": 0.9823921305434191, "stage": "debug", "created_at": 1788729026.7469127}, {"event_id": "adc56e77a1b8465bb4b67a26e61a6c7d", "step": 5, "value": 0.9700171243461276, "stage": "debug", "created_at": 1788729273.3617222}, {"event_id": "db575f2edd3c4b3b9dc077858199897b", "step": 7, "value": 0.9583255943661396, "stage": "debug", "created_at": 1788729718.193832}, {"event_id": "a8d0ed4fd6904988ac2207ecf08eb466", "step": 8, "value": 0.6740748098367522, "stage": "improve", "created_at": 1788729869.7233846}, {"event_id": "b20fefdffda6434d912282733cddb6a8", "step": 9, "value": 0.9771803613227733, "stage": "improve", "created_at": 1788730150.5597134}, {"event_id": "90d19ce900904082b418c8f1b6fbbb9d", "step": 12, "value": 0.9710947067030541, "stage": "improve", "created_at": 1788730653.653344}, {"event_id": "903d7d1cde204aff82b3fac822923188", "step": 13, "value": 0.942901643098361, "stage": "improve", "created_at": 1788730556.3866296}, {"event_id": "e6848c5287044f13aa333a93496ab193", "step": 14, "value": 0.9795398102994995, "stage": "evolution", "created_at": 1788731333.9328368}, {"event_id": "9e60ae47a51b402aab8eddb3ada4ea15", "step": 15, "value": 0.840016570811146, "stage": "debug", "created_at": 1788731093.4724572}, {"event_id": "be40c75a625f4aeda72e553f019fb6a3", "step": 16, "value": 0.9862922850296931, "stage": "improve", "created_at": 1788731351.5121596}, {"event_id": "89f963f3562647538eead9ef4953a7ef", "step": 17, "value": 0.9908520880626681, "stage": "evolution", "created_at": 1788731884.3056877}, {"event_id": "1638f36820ca4e608ca34beb7ecf32f2", "step": 18, "value": 0.9892354843106634, "stage": "improve", "created_at": 1788732171.1777153}, {"event_id": "c7f7d48f35ff441cbf49e56bf5199023", "step": 19, "value": 0.9757569786641385, "stage": "improve", "created_at": 1788732160.6173384}, {"event_id": "73b1ddd980bf48d894543df8448d5384", "step": 21, "value": 0.9784364599348101, "stage": "debug", "created_at": 1788733297.1242027}, {"event_id": "b16d8395ec42479d91ae4f2d1151f3dc", "step": 22, "value": 0.8310612704494101, "stage": "improve", "created_at": 1788733378.773017}, {"event_id": "055ce7a3f55445bdbfef76de55f1cf25", "step": 23, "value": 0.9886044651524513, "stage": "improve", "created_at": 1788733326.1819074}, {"event_id": "8985f36ba1e84e25a841369b05b1731b", "step": 25, "value": 0.9809193408499565, "stage": "debug", "created_at": 1788734231.2246275}, {"event_id": "2d470bb7f7294b34903db8ac30eefb2a", "step": 26, "value": 0.8523529861743993, "stage": "improve", "created_at": 1788734260.7699618}, {"event_id": "7bd817fcb3be4ad2914292095c416168", "step": 28, "value": 0.9897637552835746, "stage": "improve", "created_at": 1788734398.7901163}, {"event_id": "39152318ffdb45bbb96428237c968975", "step": 30, "value": 0.9801584627251941, "stage": "debug", "created_at": 1788735340.7362127}, {"event_id": "410ca24b6cf744cbbfc2eba0b40bd538", "step": 31, "value": 0.9180910148268745, "stage": "debug", "created_at": 1788735791.5818596}, {"event_id": "045e6282651f4cbd82e8f7b5a621d276", "step": 33, "value": 0.9881401955744246, "stage": "improve", "created_at": 1788735555.0700045}, {"event_id": "28e5a5f23455468f906f8712048bc64d", "step": 34, "value": 0.980910678100908, "stage": "debug", "created_at": 1788736684.9157047}, {"event_id": "af3a6959634d411aa1bf766f4594a2b2", "step": 35, "value": 0.9652960974119766, "stage": "evolution", "created_at": 1788737335.3158753}, {"event_id": "12f6179f344a4022980e0ccaf0ebd29b", "step": 36, "value": 0.9651506350668141, "stage": "evolution", "created_at": 1788736765.2068412}, {"event_id": "143f63d589844ea28fc2713324f84fe4", "step": 37, "value": 0.9872365650693532, "stage": "improve", "created_at": 1788736941.774271}, {"event_id": "cc430b80d1484271b47fe7ff1152a32d", "step": 38, "value": 0.9703943998839695, "stage": "evolution", "created_at": 1788738038.4458745}, {"event_id": "500890d75fa94c95a59c567c50734c15", "step": 39, "value": 0.9773961574528796, "stage": "evolution", "created_at": 1788738178.160036}, {"event_id": "93966d84027c4bca9d6694b1180b4688", "step": 41, "value": 0.9896331128666791, "stage": "debug", "created_at": 1788738757.913138}, {"event_id": "22b1b5356ac247d699056dcb6e0f7bfd", "step": 43, "value": 0.9902223386298803, "stage": "evolution", "created_at": 1788739184.7245593}, {"event_id": "1363b4a9be9743d8a55621565cdc0568", "step": 44, "value": 0.9919373168709569, "stage": "debug", "created_at": 1788739176.0875723}, {"event_id": "05370b47ac4c4e449405416a4a6843a4", "step": 46, "value": 0.989312398092677, "stage": "debug", "created_at": 1788740689.5380447}, {"event_id": "e8d84cf140be4d1597609c42f0eda777", "step": 47, "value": 0.9905223505441768, "stage": "improve", "created_at": 1788738474.6513293}, {"event_id": "5c05a59ee90f4de1aa8ea41fcd13996d", "step": 48, "value": 0.9912122282111779, "stage": "improve", "created_at": 1788740977.980122}, {"event_id": "d11ea3dbba474873b8bbebd837f243ef", "step": 49, "value": 0.9805114575134006, "stage": "evolution", "created_at": 1788741952.3513308}, {"event_id": "8763cbf49c3148b286a2b863d571a1ae", "step": 51, "value": 0.9905259217419748, "stage": "improve", "created_at": 1788742658.249798}, {"event_id": "ff642142c90542be8fde70271055ac14", "step": 52, "value": 0.9066915723148916, "stage": "debug", "created_at": 1788744178.695352}, {"event_id": "fdb1e88c2b974f80ae7d04ee88e3bd06", "step": 53, "value": 0.9915170287377377, "stage": "fusion", "created_at": 1788744415.4817557}, {"event_id": "a28e1bcfb97847268226182d8840bbf7", "step": 54, "value": 0.9922208373817736, "stage": "improve", "created_at": 1788742580.801396}, {"event_id": "ade5c6dd4fa543bb8f6510c3bcab1f47", "step": 56, "value": 0.9919257673170547, "stage": "evolution", "created_at": 1788745666.5048583}, {"event_id": "6ab6d062b53e433fa0565fbb8c5dffe8", "step": 58, "value": 0.9916730801301917, "stage": "debug", "created_at": 1788746701.7115233}, {"event_id": "2811554649944dcab273d4a297db54e8", "step": 59, "value": 0.9622846909206999, "stage": "improve", "created_at": 1788747589.178381}, {"event_id": "3b0fedff3d404c35b02e7bdf4d0ed342", "step": 60, "value": 0.9926517376348964, "stage": "evolution", "created_at": 1788747964.3471153}, {"event_id": "5ee44f85c3f14edaa1a5d2d05949f13a", "step": 61, "value": 0.657969633687581, "stage": "improve", "created_at": 1788748864.576396}, {"event_id": "f3ec5fbe144645789578c99c23e2d1c8", "step": 62, "value": 0.9913573021733286, "stage": "improve", "created_at": 1788746724.139721}, {"event_id": "cab77a4fe38b457db93b08354ec32d66", "step": 66, "value": 0.9953040614435904, "stage": "improve", "created_at": 1788750082.3449035}, {"event_id": "451931b83c6b4dd189a2e29fea0ab2d1", "step": 67, "value": 0.9861177460168025, "stage": "debug", "created_at": 1788751565.306113}, {"event_id": "99a8676610c74bb793a90d6064291e0b", "step": 69, "value": 0.9972816432753748, "stage": "improve", "created_at": 1788751889.68441}, {"event_id": "5190e43f7dbf4db6bc70b62c25533640", "step": 72, "value": 0.9618162593942321, "stage": "fusion_draft", "created_at": 1788750002.0031931}, {"event_id": "867d43b109ec4f728f39798a365f23d5", "step": 73, "value": 0.9981767219651261, "stage": "improve", "created_at": 1788754164.1228447}, {"event_id": "e67e37f770de4e818f66cc94f99cd422", "step": 74, "value": 0.9937221990663303, "stage": "improve", "created_at": 1788753304.3267395}], "maximize": true, "elapsed_seconds": 28338.779906749725, "node_count": 75, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-baselines-20260906/xixian.bnvs-root-only.the-icml-2013-whale-challenge-right-whale-redux.yaml", "note": ""}, {"id": "xixian.gp6.aerial-cactus-identification", "experiment_id": "mlebench-gp6-20260908", "family": "MLEBench", "method": "gp6", "dataset": "aerial-cactus-identification", "status": "archived", "official_score": 1.0, "medal": "gold", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 1.0, "silver": 1.0, "bronze": 1.0}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp6-gp6-draft-logs-with-private-scores", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp6-gp6-draft-logs-with-private-scores/logs-7b2a3e058322.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp6-gp6-draft-logs-with-private-scores", "member": "gp6_gp6-draft_logs/private_scores/rechecked_private_grades.jsonl:1", "sha256": "7b2a3e05832281a42f745f697155c42c6ef59359301c708d7b3496df1e02188f"}, {"bundle_id": "gp6-gp6-draft-logs-with-private-scores", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp6-gp6-draft-logs-with-private-scores/logs-7b2a3e058322.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp6-gp6-draft-logs-with-private-scores", "member": "gp6_gp6-draft_logs/runs/gp6/01_aerial-cactus-identification/logs/journal.json", "sha256": "7b2a3e05832281a42f745f697155c42c6ef59359301c708d7b3496df1e02188f"}], "alternate_scores": [], "journal_ref": "gp6-gp6-draft-logs-with-private-scores:gp6_gp6-draft_logs/runs/gp6/01_aerial-cactus-identification/logs/journal.json", "metrics": [{"event_id": "bfaee1a873da4195b29384826cc38af3", "step": 2, "value": 0.9999410752586796, "stage": "draft", "created_at": 1788845789.5026512}, {"event_id": "eeed157c8bf249e2849ac7859ad4eb22", "step": 3, "value": 0.9996376128408797, "stage": "draft", "created_at": 1788845218.4093907}, {"event_id": "e0d0e21ee05345abb2f4bd04b0a537e9", "step": 4, "value": 0.9999092558983665, "stage": "debug", "created_at": 1788846552.3329928}, {"event_id": "ff07903d4def4f7a9f911366b2568a9f", "step": 5, "value": 0.9999764301034718, "stage": "improve", "created_at": 1788847011.0834413}, {"event_id": "f64cc392617e464db09b67a66578f734", "step": 6, "value": 0.9998715440639215, "stage": "improve", "created_at": 1788847024.7214782}, {"event_id": "b42943ed89694a77a650a4f309d4a708", "step": 9, "value": 1.0, "stage": "debug", "created_at": 1788847670.689261}, {"event_id": "e8727d750f264e359bc3407e4b0ea6d3", "step": 10, "value": 0.9999469677328117, "stage": "improve", "created_at": 1788847193.3546026}, {"event_id": "b8999a67904e48189ec8c31980f37eb2", "step": 11, "value": 1.0, "stage": "improve", "created_at": 1788848463.4587843}, {"event_id": "a73fed6759dd4cc2be5754325b745f55", "step": 13, "value": 0.9997648902821317, "stage": "debug", "created_at": 1788848098.8875551}, {"event_id": "6eec99810bab477f906dfd5e4386ffda", "step": 15, "value": 1.0, "stage": "improve", "created_at": 1788849475.268584}, {"event_id": "e08fe6b00f5e485aa24e198f1c46fc6b", "step": 16, "value": 1.0, "stage": "debug", "created_at": 1788849853.9470792}, {"event_id": "664791ee341148249e24238bf1afbd0e", "step": 18, "value": 0.9999954904190504, "stage": "improve", "created_at": 1788849895.6435883}, {"event_id": "fb6fc1ec38bc4c6d984c3d5a48bb25fb", "step": 20, "value": 1.0, "stage": "debug", "created_at": 1788851039.6888523}, {"event_id": "623b44f81ce54348936c2bcddc4480c7", "step": 21, "value": 0.9999988215051736, "stage": "debug", "created_at": 1788852107.8936727}, {"event_id": "50555f05b0804d59a4440767c2a22a12", "step": 22, "value": 0.9999986338622417, "stage": "improve", "created_at": 1788850935.9572978}, {"event_id": "69edc8b86f21487d913564a5b0ea3100", "step": 23, "value": 0.9999493247224644, "stage": "improve", "created_at": 1788853131.1425443}, {"event_id": "53f19ab6aeab44c99132faabdb8a8c4f", "step": 24, "value": 0.9999493247224646, "stage": "improve", "created_at": 1788853100.1178987}, {"event_id": "1d56e0103df147eebf152f68f1203746", "step": 25, "value": 0.999992413293226, "stage": "improve", "created_at": 1788852875.3325222}, {"event_id": "d585bf83bc7c4813b947288a963ddd7d", "step": 26, "value": 0.9999967371855483, "stage": "improve", "created_at": 1788854615.1168258}, {"event_id": "77d7929457dd45b28da4367badddac91", "step": 27, "value": 0.9999991511377035, "stage": "improve", "created_at": 1788854623.094905}, {"event_id": "db805057b99a435abbdfef86b5685402", "step": 28, "value": 0.9999988858682359, "stage": "evolution", "created_at": 1788855414.4888043}, {"event_id": "3251ec83b04d4deea5fc0b44b11f44ca", "step": 29, "value": 0.999918111315345, "stage": "evolution", "created_at": 1788858799.2870336}, {"event_id": "c3f027d3cad94efaaa1728abd2cd8717", "step": 30, "value": 0.9999985144909813, "stage": "evolution", "created_at": 1788857661.807312}, {"event_id": "ffca9b04c6f1454c9306c3ec3fe1b22b", "step": 32, "value": 0.9999991511377035, "stage": "evolution", "created_at": 1788858680.6050165}, {"event_id": "17155b5805a14ab3a4c431bc89c10ec1", "step": 33, "value": 0.9999941075258679, "stage": "debug", "created_at": 1788860684.4321573}, {"event_id": "2cbd0cb775654214a826bde4fd7f0ca1", "step": 38, "value": 0.9999988215051736, "stage": "debug", "created_at": 1788863893.191136}, {"event_id": "edf5d0239a2249de81b694a424b778d4", "step": 39, "value": 1.0, "stage": "debug", "created_at": 1788864226.1438956}, {"event_id": "1bcae89e74ed4f3a85cf64f80781a6a3", "step": 40, "value": 1.0, "stage": "evolution", "created_at": 1788865121.2611668}, {"event_id": "ab3678bb7c564f0788d427bc07c496a2", "step": 46, "value": 0.9999210408466307, "stage": "debug", "created_at": 1788868501.4213502}, {"event_id": "f388a91124a6450f81bb99cd73e3a668", "step": 49, "value": 0.9999611096707285, "stage": "improve", "created_at": 1788870979.2937722}, {"event_id": "a45cd8d7f9aa486aad45be6f2dbeeb15", "step": 50, "value": 0.9999563956914229, "stage": "improve", "created_at": 1788870113.5006151}, {"event_id": "767e594c6db442d79c96d377bef0dc49", "step": 51, "value": 0.9999973473053239, "stage": "debug", "created_at": 1788869845.5890985}], "maximize": true, "elapsed_seconds": 28658.742649793625, "node_count": 52, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp6-20260908/xixian.gp6.aerial-cactus-identification.yaml", "note": ""}, {"id": "xixian.gp6.aptos2019-blindness-detection", "experiment_id": "mlebench-gp6-20260908", "family": "MLEBench", "method": "gp6", "dataset": "aptos2019-blindness-detection", "status": "archived", "official_score": 0.92971, "medal": "silver", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.930508, "silver": 0.919654, "bronze": 0.914492}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp6-gp6-draft-logs-with-private-scores", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp6-gp6-draft-logs-with-private-scores/logs-7b2a3e058322.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp6-gp6-draft-logs-with-private-scores", "member": "gp6_gp6-draft_logs/private_scores/rechecked_private_grades.jsonl:2", "sha256": "7b2a3e05832281a42f745f697155c42c6ef59359301c708d7b3496df1e02188f"}, {"bundle_id": "gp6-gp6-draft-logs-with-private-scores", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp6-gp6-draft-logs-with-private-scores/logs-7b2a3e058322.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp6-gp6-draft-logs-with-private-scores", "member": "gp6_gp6-draft_logs/runs/gp6/02_aptos2019-blindness-detection/logs/journal.json", "sha256": "7b2a3e05832281a42f745f697155c42c6ef59359301c708d7b3496df1e02188f"}], "alternate_scores": [], "journal_ref": "gp6-gp6-draft-logs-with-private-scores:gp6_gp6-draft_logs/runs/gp6/02_aptos2019-blindness-detection/logs/journal.json", "metrics": [{"event_id": "7874c1b7580a4f0f8c677dcd4adbbbb4", "step": 1, "value": 0.896840204037076, "stage": "draft", "created_at": 1788846796.2748008}, {"event_id": "c1d056b0730c4c2da34ed4e9609ce68e", "step": 5, "value": 0.8923884970912285, "stage": "debug", "created_at": 1788848964.2413225}, {"event_id": "224a3e28c9914d58b7e493c48fc2cf0f", "step": 6, "value": 0.922895427338404, "stage": "debug", "created_at": 1788848047.833019}, {"event_id": "9682a780d490472392650da4aa2a9022", "step": 7, "value": 0.8814168581757421, "stage": "improve", "created_at": 1788850777.5712972}, {"event_id": "cfceb916438349ea8634fc21746dce65", "step": 8, "value": 0.883583934592597, "stage": "improve", "created_at": 1788850692.1968896}, {"event_id": "5fb36a2806ba4bfd8fb2ccd121391f28", "step": 9, "value": 0.9093915886611669, "stage": "debug", "created_at": 1788847959.064249}, {"event_id": "fcfdb71cb38c422885794c604c53e81c", "step": 10, "value": 0.9266896553426456, "stage": "improve", "created_at": 1788853104.739957}, {"event_id": "0c2ac437714c4dcba6ddc9fe1bfbb11e", "step": 11, "value": 0.8876609600868322, "stage": "evolution", "created_at": 1788855126.441125}, {"event_id": "88d13c03f34d47e495f800dbd459a180", "step": 12, "value": 0.8901181615682753, "stage": "evolution", "created_at": 1788856990.6834629}, {"event_id": "240d02b2a09a450ba32835e4559b3743", "step": 13, "value": 0.9170425900048891, "stage": "improve", "created_at": 1788857374.1365895}, {"event_id": "681d5ee43c8240718628df1e7630421b", "step": 18, "value": 0.9127224775939267, "stage": "debug", "created_at": 1788863325.049705}, {"event_id": "11a0bc89dbe049a7a90e6a105b168d02", "step": 19, "value": 0.9194675131612774, "stage": "debug", "created_at": 1788865754.3827016}, {"event_id": "002d727eb90c4ed19d2382eef97d1bd7", "step": 21, "value": 0.9260899556626113, "stage": "evolution", "created_at": 1788870573.527485}], "maximize": true, "elapsed_seconds": 28649.861810207367, "node_count": 22, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp6-20260908/xixian.gp6.aptos2019-blindness-detection.yaml", "note": ""}, {"id": "xixian.gp6.denoising-dirty-documents", "experiment_id": "mlebench-gp6-20260908", "family": "MLEBench", "method": "gp6", "dataset": "denoising-dirty-documents", "status": "archived", "official_score": 0.00968, "medal": "gold", "valid_submission": true, "score_maximize": false, "thresholds": {"gold": 0.01794, "silver": 0.02609, "bronze": 0.04517}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp6-gp6-draft-logs-with-private-scores", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp6-gp6-draft-logs-with-private-scores/logs-7b2a3e058322.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp6-gp6-draft-logs-with-private-scores", "member": "gp6_gp6-draft_logs/private_scores/rechecked_private_grades.jsonl:3", "sha256": "7b2a3e05832281a42f745f697155c42c6ef59359301c708d7b3496df1e02188f"}, {"bundle_id": "gp6-gp6-draft-logs-with-private-scores", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp6-gp6-draft-logs-with-private-scores/logs-7b2a3e058322.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp6-gp6-draft-logs-with-private-scores", "member": "gp6_gp6-draft_logs/runs/gp6/03_denoising-dirty-documents/logs/journal.json", "sha256": "7b2a3e05832281a42f745f697155c42c6ef59359301c708d7b3496df1e02188f"}], "alternate_scores": [], "journal_ref": "gp6-gp6-draft-logs-with-private-scores:gp6_gp6-draft_logs/runs/gp6/03_denoising-dirty-documents/logs/journal.json", "metrics": [{"event_id": "b02508b3ae0d4d64ad9f0cb8b21de832", "step": 1, "value": 0.014270543413492544, "stage": "draft", "created_at": 1788845990.792226}, {"event_id": "a7d4000e147148b1ac2d9c7f4872df9e", "step": 2, "value": 0.04255793877343161, "stage": "draft", "created_at": 1788846749.6315696}, {"event_id": "eb9ad88a0de44a22b04c1e9b75a7eb08", "step": 3, "value": 0.021001353967819495, "stage": "draft", "created_at": 1788845400.1004286}, {"event_id": "77741353bfcd4e51831077d9c93caf64", "step": 5, "value": 0.023225086225454827, "stage": "improve", "created_at": 1788847543.3047245}, {"event_id": "2b9b34007a1f48e7b7ff951536b65cf3", "step": 6, "value": 0.024515731051736534, "stage": "improve", "created_at": 1788847535.667069}, {"event_id": "cb670eabe46a4788971701d3617c15b6", "step": 7, "value": 0.01883535125086256, "stage": "debug", "created_at": 1788847667.535355}, {"event_id": "1e555e16a2384bfbb0296e957b961c24", "step": 8, "value": 0.024088988560205166, "stage": "improve", "created_at": 1788848156.2355075}, {"event_id": "a2f1f5ab870a4324b9582cbd17f1f6ff", "step": 9, "value": 0.027308016135207128, "stage": "improve", "created_at": 1788848278.938167}, {"event_id": "06039a92e39445be92815f51940ae6cf", "step": 10, "value": 0.0251450445789864, "stage": "improve", "created_at": 1788848507.4525065}, {"event_id": "15839e801da648ca81b694d8bfef4d58", "step": 11, "value": 0.013550032317160413, "stage": "improve", "created_at": 1788848839.1314108}, {"event_id": "0bd7ba8525be485f870d1d94e0d1711e", "step": 12, "value": 0.014987870505391715, "stage": "improve", "created_at": 1788848787.245382}, {"event_id": "5c42a8a20b0043f5b5bd4c259bdc8ea2", "step": 14, "value": 0.01460353207836358, "stage": "improve", "created_at": 1788849552.2778494}, {"event_id": "850e1e3db480441db48c6c57ef63bd4e", "step": 15, "value": 0.013248308866483184, "stage": "improve", "created_at": 1788849559.716304}, {"event_id": "cff257ee33c64a958685d34ef443e70b", "step": 16, "value": 0.019545328111429706, "stage": "debug", "created_at": 1788849806.515719}, {"event_id": "6d2848ad0bba4b1b9a4bf0df7c2d9495", "step": 17, "value": 0.019116599396343414, "stage": "improve", "created_at": 1788850447.9293022}, {"event_id": "4785234d732b4b8584f28f8734e90034", "step": 18, "value": 0.18752145604061665, "stage": "improve", "created_at": 1788850689.780433}, {"event_id": "33df28e0916f4c91b692adf264b4dd19", "step": 19, "value": 0.013520904442054475, "stage": "evolution", "created_at": 1788851449.186441}, {"event_id": "33e2d743be0e41fdbc46533ba2871e82", "step": 20, "value": 0.009991915668521126, "stage": "improve", "created_at": 1788850651.9443746}, {"event_id": "ee239693f8c1450fa62d1328aa972394", "step": 22, "value": 0.01695609589003484, "stage": "improve", "created_at": 1788852078.162704}, {"event_id": "a947b3150ad747079a9587309e4d8282", "step": 23, "value": 0.01141083543530641, "stage": "debug", "created_at": 1788852572.3387315}, {"event_id": "8bb83693322f47818a3f2d34eabee33d", "step": 24, "value": 0.009922421587997152, "stage": "improve", "created_at": 1788853088.5935004}, {"event_id": "9b74c1368b134bc8886a30fd33bc82d5", "step": 25, "value": 0.020194945109729388, "stage": "improve", "created_at": 1788852763.9420817}, {"event_id": "d2808fe2523e4d2888c94e1af53f86d0", "step": 26, "value": 0.009948069692242094, "stage": "improve", "created_at": 1788853943.033474}, {"event_id": "85d2de8d97ba4df9a38bb8ed49705bf7", "step": 31, "value": 0.009482033950208683, "stage": "improve", "created_at": 1788854952.6990042}, {"event_id": "2d017117320343ca9a8d135c58fb112a", "step": 34, "value": 0.013103036321368382, "stage": "debug", "created_at": 1788855840.2037578}, {"event_id": "246e5c52435d4fffa25be0e75b09551a", "step": 35, "value": 0.010216991652839283, "stage": "improve", "created_at": 1788856911.1809688}, {"event_id": "00dad35b915a481c92dbed9cfa920d92", "step": 36, "value": 0.011479151069452164, "stage": "improve", "created_at": 1788857258.2628598}, {"event_id": "307e8addc9954c1b8cb66ab5fcbdc160", "step": 38, "value": 0.012040806266484337, "stage": "improve", "created_at": 1788857370.769978}, {"event_id": "898a3aad9e9948098a7413579e30f7ed", "step": 39, "value": 0.010084568008642894, "stage": "improve", "created_at": 1788858315.1684427}, {"event_id": "aebb123ad1a247b480d3af404e015a63", "step": 41, "value": 0.009489530077146133, "stage": "fusion", "created_at": 1788859682.0313835}, {"event_id": "48bb82453c7f490da3de409d0f1f912c", "step": 43, "value": 0.011377522229098413, "stage": "debug", "created_at": 1788860278.2872164}, {"event_id": "146138b35fdf4137ad3b80cf48cf1cb6", "step": 49, "value": 0.012173982336616403, "stage": "evolution", "created_at": 1788864800.7110407}, {"event_id": "d2e49eef5be24d29a0ca02a3bed0e8c6", "step": 50, "value": 0.012643826361315863, "stage": "debug", "created_at": 1788866653.6596446}, {"event_id": "71b55c9765c04536a86948f19e4c2a4a", "step": 51, "value": 0.008778715057205613, "stage": "debug", "created_at": 1788865615.3673859}, {"event_id": "40bebf01b53246a4a1691c18f9d678e8", "step": 53, "value": 0.012280033079764323, "stage": "debug", "created_at": 1788869806.880628}, {"event_id": "c7ba546e8bdc4c2fb153862f6f5316c8", "step": 55, "value": 0.012350748139518242, "stage": "improve", "created_at": 1788869622.7558863}, {"event_id": "211ca79f54a44003b92bff6b78939c5d", "step": 56, "value": 0.012069487012007031, "stage": "evolution", "created_at": 1788868897.579117}, {"event_id": "bb28ea3385d4472d8017744412471a8f", "step": 58, "value": 0.011259718213631803, "stage": "debug", "created_at": 1788871127.2614498}, {"event_id": "72aaf0a95f0147f087bc7ca716f60960", "step": 59, "value": 0.012824982120391936, "stage": "improve", "created_at": 1788871686.438475}], "maximize": false, "elapsed_seconds": 28705.908849477768, "node_count": 60, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp6-20260908/xixian.gp6.denoising-dirty-documents.yaml", "note": ""}, {"id": "xixian.gp6.detecting-insults-in-social-commentary", "experiment_id": "mlebench-gp6-20260908", "family": "MLEBench", "method": "gp6", "dataset": "detecting-insults-in-social-commentary", "status": "archived", "official_score": 0.9532, "medal": "gold", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.83321, "silver": 0.82307, "bronze": 0.79111}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp6-gp6-draft-logs-with-private-scores", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp6-gp6-draft-logs-with-private-scores/logs-7b2a3e058322.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp6-gp6-draft-logs-with-private-scores", "member": "gp6_gp6-draft_logs/private_scores/rechecked_private_grades.jsonl:4", "sha256": "7b2a3e05832281a42f745f697155c42c6ef59359301c708d7b3496df1e02188f"}, {"bundle_id": "gp6-gp6-draft-logs-with-private-scores", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp6-gp6-draft-logs-with-private-scores/logs-7b2a3e058322.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp6-gp6-draft-logs-with-private-scores", "member": "gp6_gp6-draft_logs/runs/gp6/04_detecting-insults-in-social-commentary/logs/journal.json", "sha256": "7b2a3e05832281a42f745f697155c42c6ef59359301c708d7b3496df1e02188f"}], "alternate_scores": [], "journal_ref": "gp6-gp6-draft-logs-with-private-scores:gp6_gp6-draft_logs/runs/gp6/04_detecting-insults-in-social-commentary/logs/journal.json", "metrics": [{"event_id": "4ade801edbf8407fbe863a718ca77f8e", "step": 3, "value": 0.9498679015213101, "stage": "draft", "created_at": 1788845863.7105203}, {"event_id": "cfad561acd65467c8593ec2005c5f18e", "step": 6, "value": 0.8742655452591996, "stage": "debug", "created_at": 1788846838.7067256}, {"event_id": "82a20a7e63464c17a95a699d2fed4752", "step": 7, "value": 0.9488578495562344, "stage": "debug", "created_at": 1788846724.1097715}, {"event_id": "48fb00899fe04d0b94878d3fdd024269", "step": 9, "value": 0.919621273166801, "stage": "improve", "created_at": 1788847360.8515854}, {"event_id": "648701c83d8e4b35ab9a2b7804944d53", "step": 11, "value": 0.9448494107376691, "stage": "debug", "created_at": 1788847996.3607676}, {"event_id": "47ee1951f88f4cfbbb4644f6eb7b6ec1", "step": 13, "value": 0.9585268842178609, "stage": "improve", "created_at": 1788846844.2042959}, {"event_id": "6e270bf56386494db68308c1828d58a3", "step": 14, "value": 0.9281577356970185, "stage": "debug", "created_at": 1788848921.050439}, {"event_id": "cebb7b7ff14b49b9b24f46464e539b69", "step": 16, "value": 0.9639095009457297, "stage": "improve", "created_at": 1788849445.497208}, {"event_id": "a5a9d943125a4688ad3291e039044010", "step": 18, "value": 0.9558416994034628, "stage": "debug", "created_at": 1788847528.0732768}, {"event_id": "e15a8ed65d8a4cf389837037fb2f9c3d", "step": 20, "value": 0.9583442455987197, "stage": "improve", "created_at": 1788851080.2961056}, {"event_id": "3d5d04d4a9e640de8234baf5c9f315b9", "step": 21, "value": 0.9461152335224792, "stage": "debug", "created_at": 1788849896.538025}, {"event_id": "bcbcdffb55b24b9eb3e9c2be441f94fc", "step": 22, "value": 0.9532445802415248, "stage": "debug", "created_at": 1788852014.519137}, {"event_id": "c08ec80080b64fcd9a6113b7b5a42629", "step": 23, "value": 0.9433408267494562, "stage": "evolution", "created_at": 1788852909.9968991}, {"event_id": "cd9297ba68324ef0bc5fe42bdb2abec7", "step": 24, "value": 0.957617791040927, "stage": "improve", "created_at": 1788852338.5752711}, {"event_id": "8bdb38a1ef1543aeb1aa99c94b5da42f", "step": 25, "value": 0.9625054561326931, "stage": "evolution", "created_at": 1788854115.6183584}, {"event_id": "df0ada269b1144c39461818cf334d9da", "step": 27, "value": 0.9373233964977655, "stage": "evolution", "created_at": 1788855069.9535394}, {"event_id": "b7741544745344f79242a047552f2512", "step": 28, "value": 0.9416201041973, "stage": "debug", "created_at": 1788855175.910486}, {"event_id": "f6c230bbf02d4fa988d4462c3df97ad8", "step": 31, "value": 0.9605412483631601, "stage": "evolution", "created_at": 1788857291.096019}, {"event_id": "ce13f42f79e449cd89000a46a413ba1c", "step": 32, "value": 0.9580023279499491, "stage": "fusion", "created_at": 1788860043.2776704}, {"event_id": "5f6ee337226d4bbb8140ace4eb0baf35", "step": 33, "value": 0.9580768784113344, "stage": "improve", "created_at": 1788854943.3741426}, {"event_id": "a2e017d7d0cb4a439a7368bc08e3c2c9", "step": 34, "value": 0.9548107072349321, "stage": "debug", "created_at": 1788859369.5306597}, {"event_id": "b59f2574bbc34973b758f81252281ebf", "step": 35, "value": 0.9598406108465916, "stage": "improve", "created_at": 1788861087.8237731}, {"event_id": "c998ad402e324e73ba5df51b871053a4", "step": 36, "value": 0.9547381256532342, "stage": "improve", "created_at": 1788864668.4029834}, {"event_id": "a09bfa2f2a2d4b468390572ff782a441", "step": 38, "value": 0.955013935663686, "stage": "improve", "created_at": 1788865384.9803069}, {"event_id": "8430c2b6e3974ad888a39b0e541eadb1", "step": 39, "value": 0.9583817210544652, "stage": "improve", "created_at": 1788866587.7361405}], "maximize": true, "elapsed_seconds": 28677.422318696976, "node_count": 40, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp6-20260908/xixian.gp6.detecting-insults-in-social-commentary.yaml", "note": ""}, {"id": "xixian.gp6.dog-breed-identification", "experiment_id": "mlebench-gp6-20260908", "family": "MLEBench", "method": "gp6", "dataset": "dog-breed-identification", "status": "archived", "official_score": 0.32111, "medal": "none", "valid_submission": true, "score_maximize": false, "thresholds": {"gold": 0.0005, "silver": 0.00539, "bronze": 0.04598}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp6-gp6-draft-logs-with-private-scores", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp6-gp6-draft-logs-with-private-scores/logs-7b2a3e058322.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp6-gp6-draft-logs-with-private-scores", "member": "gp6_gp6-draft_logs/private_scores/rechecked_private_grades.jsonl:5", "sha256": "7b2a3e05832281a42f745f697155c42c6ef59359301c708d7b3496df1e02188f"}, {"bundle_id": "gp6-gp6-draft-logs-with-private-scores", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp6-gp6-draft-logs-with-private-scores/logs-7b2a3e058322.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp6-gp6-draft-logs-with-private-scores", "member": "gp6_gp6-draft_logs/runs/gp6/05_dog-breed-identification/logs/journal.json", "sha256": "7b2a3e05832281a42f745f697155c42c6ef59359301c708d7b3496df1e02188f"}], "alternate_scores": [], "journal_ref": "gp6-gp6-draft-logs-with-private-scores:gp6_gp6-draft_logs/runs/gp6/05_dog-breed-identification/logs/journal.json", "metrics": [{"event_id": "661cdb06328a4202ae513b15c2a0cc95", "step": 3, "value": 0.4652738406260507, "stage": "debug", "created_at": 1788846632.2729378}, {"event_id": "ba9a61acbe464a6b98e8825c0d874cb0", "step": 4, "value": 0.4697542176632479, "stage": "draft", "created_at": 1788846446.940424}, {"event_id": "daec80855c684f0d99c1271eb5214d82", "step": 5, "value": 0.5069762296237676, "stage": "debug", "created_at": 1788846657.98921}, {"event_id": "ffd7020d538e499185251681c91c3625", "step": 6, "value": 0.46885364816825537, "stage": "improve", "created_at": 1788847932.4168189}, {"event_id": "4e6f1468eab843b69a0beec5b4350d7b", "step": 7, "value": 0.47507598918060734, "stage": "improve", "created_at": 1788847919.3823304}, {"event_id": "64e122ce1df243cf9c1dba3d67b97fed", "step": 8, "value": 0.4436027754541405, "stage": "improve", "created_at": 1788847870.331499}, {"event_id": "a8fe7d2051e846d995cb3a7a751cb07b", "step": 9, "value": 0.3920498957483562, "stage": "improve", "created_at": 1788848933.3228095}, {"event_id": "99e3a41eedc4477393350cd5ff1983a3", "step": 10, "value": 0.4215000519269953, "stage": "improve", "created_at": 1788849110.9433608}, {"event_id": "a48e5d7e02b04a339dd52228169d3291", "step": 11, "value": 0.38713040073220933, "stage": "improve", "created_at": 1788849839.183397}, {"event_id": "7cb99ce2a9f14132a0b8cf0fce2ab2f9", "step": 14, "value": 0.3157761350912167, "stage": "debug", "created_at": 1788852047.5819435}, {"event_id": "2ed3d52fd0e64743a13e3e1966ffffd6", "step": 18, "value": 0.35027011593677787, "stage": "improve", "created_at": 1788857373.988216}, {"event_id": "85cda580c8e440bc9ddd93087ea87641", "step": 19, "value": 0.3374093077866639, "stage": "debug", "created_at": 1788857066.446254}, {"event_id": "13ac308c04b24ef49a19bf750fa73155", "step": 23, "value": 0.47812815473210757, "stage": "debug", "created_at": 1788852392.0596323}, {"event_id": "8d341b10291140efa3720c859c9d5db0", "step": 25, "value": 0.3484510783333735, "stage": "improve", "created_at": 1788862886.1521268}, {"event_id": "57c2b2c3ca314627b387aaf8c02f02f5", "step": 27, "value": 0.3159472068030023, "stage": "improve", "created_at": 1788864868.3076284}, {"event_id": "2cbbdedefbd14de383f02346feb6129e", "step": 28, "value": 0.32191438465416533, "stage": "debug", "created_at": 1788868180.2217848}], "maximize": false, "elapsed_seconds": 28747.767112493515, "node_count": 29, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp6-20260908/xixian.gp6.dog-breed-identification.yaml", "note": ""}, {"id": "xixian.gp6.dogs-vs-cats-redux-kernels-edition", "experiment_id": "mlebench-gp6-20260908", "family": "MLEBench", "method": "gp6", "dataset": "dogs-vs-cats-redux-kernels-edition", "status": "archived", "official_score": 0.00308, "medal": "gold", "valid_submission": true, "score_maximize": false, "thresholds": {"gold": 0.03882, "silver": 0.05038, "bronze": 0.06127}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp6-gp6-draft-logs-with-private-scores", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp6-gp6-draft-logs-with-private-scores/logs-7b2a3e058322.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp6-gp6-draft-logs-with-private-scores", "member": "gp6_gp6-draft_logs/private_scores/rechecked_private_grades.jsonl:6", "sha256": "7b2a3e05832281a42f745f697155c42c6ef59359301c708d7b3496df1e02188f"}, {"bundle_id": "gp6-gp6-draft-logs-with-private-scores", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp6-gp6-draft-logs-with-private-scores/logs-7b2a3e058322.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp6-gp6-draft-logs-with-private-scores", "member": "gp6_gp6-draft_logs/runs/gp6/06_dogs-vs-cats-redux-kernels-edition/logs/journal.json", "sha256": "7b2a3e05832281a42f745f697155c42c6ef59359301c708d7b3496df1e02188f"}], "alternate_scores": [], "journal_ref": "gp6-gp6-draft-logs-with-private-scores:gp6_gp6-draft_logs/runs/gp6/06_dogs-vs-cats-redux-kernels-edition/logs/journal.json", "metrics": [{"event_id": "f4c5d21fb2e14dc2921519f544461efb", "step": 3, "value": 0.02673544020897588, "stage": "draft", "created_at": 1788845684.7644098}, {"event_id": "ecd97d7d28824164aae22e33b33a37f1", "step": 4, "value": 0.005727930195097786, "stage": "draft", "created_at": 1788845132.5924225}, {"event_id": "147f0200441849d181c55df9362275fa", "step": 5, "value": 0.0029481747156816377, "stage": "debug", "created_at": 1788846645.3315036}, {"event_id": "49434ebe3f954ff0b0cab99b00e5bcb7", "step": 7, "value": 0.026599528681918568, "stage": "improve", "created_at": 1788847100.2773273}, {"event_id": "987f82b31a0e457e90be6ec2874d0dbb", "step": 8, "value": 0.002729839416516931, "stage": "improve", "created_at": 1788847517.470956}, {"event_id": "f68e1b238ef54b48a44568dedc9208da", "step": 9, "value": 0.012881130507830565, "stage": "debug", "created_at": 1788847302.2119262}, {"event_id": "eaf22a88233f49bba7bcb66e1caa924f", "step": 11, "value": 0.00730740358435219, "stage": "improve", "created_at": 1788848436.7057939}, {"event_id": "044b6dc9e1484d72a3db01c5f746f9c7", "step": 12, "value": 0.0058342019698467765, "stage": "improve", "created_at": 1788849307.520455}, {"event_id": "f246ad87fece4042a29e07532f91ae46", "step": 13, "value": 0.03167062201035267, "stage": "improve", "created_at": 1788850438.039839}, {"event_id": "12fd8b0efe154fe6aa093c96d13cc639", "step": 14, "value": 0.015325177504128344, "stage": "debug", "created_at": 1788849373.217213}, {"event_id": "40f713850192480d9f429c733fc15c66", "step": 16, "value": 0.003785191164567337, "stage": "debug", "created_at": 1788852405.1380424}, {"event_id": "bf52d2124ff3413894c3dd13204035fb", "step": 17, "value": 0.008152358730693332, "stage": "evolution", "created_at": 1788852074.2809112}, {"event_id": "c1b8aaa7fb8a45418465b093fee781e9", "step": 18, "value": 0.008738778221914153, "stage": "evolution", "created_at": 1788851728.2470295}, {"event_id": "389c3ef94ea442c4b9f4820d50886e83", "step": 21, "value": 0.002703602101250254, "stage": "evolution", "created_at": 1788854258.9282029}, {"event_id": "f7dd6eec41004daba0a0d32d4564b76f", "step": 23, "value": 0.0028170547827449364, "stage": "debug", "created_at": 1788856775.963103}, {"event_id": "075f91eeeb1c4338af83aa4981e6156e", "step": 24, "value": 0.011513804994290177, "stage": "improve", "created_at": 1788858053.8014402}, {"event_id": "1b89be7a828e4940b6ee1cbe5efe6d29", "step": 25, "value": 0.007348234549538538, "stage": "debug", "created_at": 1788858946.4974992}, {"event_id": "ad5b2584d2ad418795711fb890375416", "step": 27, "value": 0.03194447277453797, "stage": "improve", "created_at": 1788861994.2336528}, {"event_id": "7ae277af055a44b4a334eac9edd30c44", "step": 29, "value": 0.01722531620913618, "stage": "fusion_draft", "created_at": 1788866998.5785558}, {"event_id": "a23d5dca61d94d2788838dd691497050", "step": 30, "value": 0.025333907119750372, "stage": "debug", "created_at": 1788864799.3285723}, {"event_id": "e36507c76cf54b2dbba7d712b975c7d7", "step": 34, "value": 0.01854251867309273, "stage": "debug", "created_at": 1788869944.6239378}, {"event_id": "b71f4653f16d4f35807630cb25917277", "step": 35, "value": 0.013559396179371406, "stage": "debug", "created_at": 1788869878.4534693}], "maximize": false, "elapsed_seconds": 28651.52621769905, "node_count": 36, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp6-20260908/xixian.gp6.dogs-vs-cats-redux-kernels-edition.yaml", "note": ""}, {"id": "xixian.gp6.histopathologic-cancer-detection", "experiment_id": "mlebench-gp6-20260908", "family": "MLEBench", "method": "gp6", "dataset": "histopathologic-cancer-detection", "status": "archived", "official_score": 0.99453, "medal": "gold", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.9835, "silver": 0.9798, "bronze": 0.9738}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp6-gp6-draft-logs-with-private-scores", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp6-gp6-draft-logs-with-private-scores/logs-7b2a3e058322.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp6-gp6-draft-logs-with-private-scores", "member": "gp6_gp6-draft_logs/private_scores/rechecked_private_grades.jsonl:7", "sha256": "7b2a3e05832281a42f745f697155c42c6ef59359301c708d7b3496df1e02188f"}, {"bundle_id": "gp6-gp6-draft-logs-with-private-scores", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp6-gp6-draft-logs-with-private-scores/logs-7b2a3e058322.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp6-gp6-draft-logs-with-private-scores", "member": "gp6_gp6-draft_logs/runs/gp6/07_histopathologic-cancer-detection/logs/journal.json", "sha256": "7b2a3e05832281a42f745f697155c42c6ef59359301c708d7b3496df1e02188f"}], "alternate_scores": [], "journal_ref": "gp6-gp6-draft-logs-with-private-scores:gp6_gp6-draft_logs/runs/gp6/07_histopathologic-cancer-detection/logs/journal.json", "metrics": [{"event_id": "ad918017798544da941895334c08577e", "step": 2, "value": 0.9907101720424785, "stage": "draft", "created_at": 1788845997.181239}, {"event_id": "11876243b5fb4a1ea5bae1aa8fa7e075", "step": 3, "value": 0.9930367964648914, "stage": "draft", "created_at": 1788845440.000484}, {"event_id": "2202cfccaac04f24b80249fe54beeb68", "step": 4, "value": 0.986808613209868, "stage": "debug", "created_at": 1788851311.0277545}, {"event_id": "6ef175fdeb9646e397c8a33c305f5427", "step": 7, "value": 0.9947469545837404, "stage": "improve", "created_at": 1788857001.3732033}], "maximize": true, "elapsed_seconds": 28703.555403470993, "node_count": 8, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp6-20260908/xixian.gp6.histopathologic-cancer-detection.yaml", "note": ""}, {"id": "xixian.gp6.jigsaw-toxic-comment-classification-challenge", "experiment_id": "mlebench-gp6-20260908", "family": "MLEBench", "method": "gp6", "dataset": "jigsaw-toxic-comment-classification-challenge", "status": "archived", "official_score": 0.98784, "medal": "gold", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.9874, "silver": 0.98668, "bronze": 0.98639}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp6-gp6-draft-logs-with-private-scores", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp6-gp6-draft-logs-with-private-scores/logs-7b2a3e058322.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp6-gp6-draft-logs-with-private-scores", "member": "gp6_gp6-draft_logs/private_scores/rechecked_private_grades.jsonl:8", "sha256": "7b2a3e05832281a42f745f697155c42c6ef59359301c708d7b3496df1e02188f"}, {"bundle_id": "gp6-gp6-draft-logs-with-private-scores", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp6-gp6-draft-logs-with-private-scores/logs-7b2a3e058322.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp6-gp6-draft-logs-with-private-scores", "member": "gp6_gp6-draft_logs/runs/gp6/08_jigsaw-toxic-comment-classification-challenge/logs/journal.json", "sha256": "7b2a3e05832281a42f745f697155c42c6ef59359301c708d7b3496df1e02188f"}], "alternate_scores": [], "journal_ref": "gp6-gp6-draft-logs-with-private-scores:gp6_gp6-draft_logs/runs/gp6/08_jigsaw-toxic-comment-classification-challenge/logs/journal.json", "metrics": [{"event_id": "9df9db3d01cc4f7299340d00ad89627d", "step": 7, "value": 0.988903530196802, "stage": "debug", "created_at": 1788847012.3483405}, {"event_id": "7a19e655dc6f4a16a441277231e3439f", "step": 9, "value": 0.9931825056742349, "stage": "debug", "created_at": 1788847308.3491347}, {"event_id": "d1364319294e4ea8a30384dd2852aa8e", "step": 10, "value": 0.9883233240448841, "stage": "improve", "created_at": 1788850038.0415542}, {"event_id": "275bb536734843a6ba9fa90814b3058a", "step": 11, "value": 0.9918241284915897, "stage": "debug", "created_at": 1788849891.122131}, {"event_id": "1c6ca2e895b34b82bdcb5dde610889bb", "step": 13, "value": 0.9937285122116354, "stage": "improve", "created_at": 1788852886.163889}, {"event_id": "f29b367d6cd44c4d994a4e6775568ec2", "step": 14, "value": 0.9816295178512694, "stage": "improve", "created_at": 1788865633.6402745}], "maximize": true, "elapsed_seconds": 28741.06242108345, "node_count": 15, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp6-20260908/xixian.gp6.jigsaw-toxic-comment-classification-challenge.yaml", "note": ""}, {"id": "xixian.gp6.leaf-classification", "experiment_id": "mlebench-gp6-20260908", "family": "MLEBench", "method": "gp6", "dataset": "leaf-classification", "status": "archived", "official_score": 0.01476, "medal": "bronze", "valid_submission": true, "score_maximize": false, "thresholds": {"gold": 0.0, "silver": 0.00791, "bronze": 0.01526}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp6-gp6-draft-logs-with-private-scores", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp6-gp6-draft-logs-with-private-scores/logs-7b2a3e058322.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp6-gp6-draft-logs-with-private-scores", "member": "gp6_gp6-draft_logs/private_scores/rechecked_private_grades.jsonl:9", "sha256": "7b2a3e05832281a42f745f697155c42c6ef59359301c708d7b3496df1e02188f"}, {"bundle_id": "gp6-gp6-draft-logs-with-private-scores", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp6-gp6-draft-logs-with-private-scores/logs-7b2a3e058322.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp6-gp6-draft-logs-with-private-scores", "member": "gp6_gp6-draft_logs/runs/gp6/09_leaf-classification/logs/journal.json", "sha256": "7b2a3e05832281a42f745f697155c42c6ef59359301c708d7b3496df1e02188f"}], "alternate_scores": [], "journal_ref": "gp6-gp6-draft-logs-with-private-scores:gp6_gp6-draft_logs/runs/gp6/09_leaf-classification/logs/journal.json", "metrics": [{"event_id": "8eb978d29ef84a1db72dc2211d99bce6", "step": 1, "value": 0.03276489850168549, "stage": "draft", "created_at": 1788845941.0883243}, {"event_id": "21ab672387264a818d793ba6ef760038", "step": 2, "value": 2.0169528002865156, "stage": "draft", "created_at": 1788846594.679768}, {"event_id": "48c5b0c42b5c437181f7f50e90863f01", "step": 3, "value": 0.06548837294637345, "stage": "draft", "created_at": 1788845296.6587927}, {"event_id": "c2cb551529ce4c27826050048d244197", "step": 4, "value": 2.1844060619434864, "stage": "improve", "created_at": 1788847373.8021352}, {"event_id": "a5bd19f84d7648768d0ece4bfb866991", "step": 5, "value": 0.04503830592931078, "stage": "improve", "created_at": 1788847366.8178735}, {"event_id": "c318201cbf974a6db579271be94e683a", "step": 6, "value": 0.0008878076887437128, "stage": "improve", "created_at": 1788848164.0454223}, {"event_id": "af665901bb834680bf7b51fe541491a6", "step": 7, "value": 0.05180063859169403, "stage": "improve", "created_at": 1788848742.475546}, {"event_id": "f01afa4f6cb5435192c546d23b3d3f1b", "step": 8, "value": 0.0010648170705519885, "stage": "improve", "created_at": 1788850219.0172925}, {"event_id": "1df724c49ecb4f76b4736b9c275fc9c4", "step": 9, "value": 0.0420033060775107, "stage": "improve", "created_at": 1788852421.938692}, {"event_id": "43a221135c484ba4afeaa7188dc8b2c2", "step": 11, "value": 0.021032147867062128, "stage": "fusion_draft", "created_at": 1788869127.1879618}], "maximize": false, "elapsed_seconds": 28745.328691482544, "node_count": 13, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp6-20260908/xixian.gp6.leaf-classification.yaml", "note": ""}, {"id": "xixian.gp6.mlsp-2013-birds", "experiment_id": "mlebench-gp6-20260908", "family": "MLEBench", "method": "gp6", "dataset": "mlsp-2013-birds", "status": "archived", "official_score": 0.80338, "medal": "none", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.93527, "silver": 0.90038, "bronze": 0.87372}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp6-gp6-draft-logs-with-private-scores", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp6-gp6-draft-logs-with-private-scores/logs-7b2a3e058322.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp6-gp6-draft-logs-with-private-scores", "member": "gp6_gp6-draft_logs/private_scores/rechecked_private_grades.jsonl:10", "sha256": "7b2a3e05832281a42f745f697155c42c6ef59359301c708d7b3496df1e02188f"}, {"bundle_id": "gp6-gp6-draft-logs-with-private-scores", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp6-gp6-draft-logs-with-private-scores/logs-7b2a3e058322.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp6-gp6-draft-logs-with-private-scores", "member": "gp6_gp6-draft_logs/runs/gp6/10_mlsp-2013-birds/logs/journal.json", "sha256": "7b2a3e05832281a42f745f697155c42c6ef59359301c708d7b3496df1e02188f"}], "alternate_scores": [], "journal_ref": "gp6-gp6-draft-logs-with-private-scores:gp6_gp6-draft_logs/runs/gp6/10_mlsp-2013-birds/logs/journal.json", "metrics": [{"event_id": "9bb113c4ca384af9a157d12b7e57a3e9", "step": 1, "value": 0.8057394049448549, "stage": "draft", "created_at": 1788845450.5901318}, {"event_id": "0233ff0e6f06448588a0dde145e49b5c", "step": 4, "value": 0.7659825257718227, "stage": "debug", "created_at": 1788847613.050129}, {"event_id": "7a5d2df8de004efc9bb14c2edadf4ab4", "step": 5, "value": 0.7536959590847341, "stage": "improve", "created_at": 1788848236.8828478}, {"event_id": "8896e21969b1484ab7fd552797964e24", "step": 6, "value": 0.8197592063130709, "stage": "improve", "created_at": 1788848306.2786708}, {"event_id": "176eb71a96294ca199e32cc35fc967c8", "step": 7, "value": 0.638701686156469, "stage": "improve", "created_at": 1788848875.2348897}, {"event_id": "6db48aa5da2f4d75919b4f83a92523d5", "step": 8, "value": 0.8178411213907751, "stage": "debug", "created_at": 1788848112.8691785}, {"event_id": "012b8271b4f3466aa74c7f5eca391527", "step": 11, "value": 0.7535708572521375, "stage": "improve", "created_at": 1788849573.0608776}, {"event_id": "1aaa14ab32db47178ccabb64325b2fa1", "step": 12, "value": 0.5543228200064425, "stage": "debug", "created_at": 1788849452.4133272}, {"event_id": "d58af65c1b2147ada477e45466f01fd9", "step": 13, "value": 0.8354764238693743, "stage": "debug", "created_at": 1788849861.9295573}, {"event_id": "90429c22b6414da59208bc5fc5e772ef", "step": 14, "value": 0.8024314657079975, "stage": "improve", "created_at": 1788850856.6874504}, {"event_id": "9d08050dc85a4e50bc34fd3991e43766", "step": 15, "value": 0.8225620602087504, "stage": "improve", "created_at": 1788850222.454687}, {"event_id": "3b8e07988464402797f5fa93095dfd05", "step": 16, "value": 0.8339616731365157, "stage": "improve", "created_at": 1788850226.6387422}, {"event_id": "fe25d934c4c74333922946d503e12d00", "step": 18, "value": 0.8881537584577474, "stage": "debug", "created_at": 1788852622.2265408}, {"event_id": "72011e69ca634009b9982a8e6888ed46", "step": 19, "value": 0.8473212610131834, "stage": "improve", "created_at": 1788852831.1082253}, {"event_id": "0121fe8b6b724fb88b2cdd0e8de7d824", "step": 20, "value": 0.8781331669924558, "stage": "improve", "created_at": 1788853391.5347173}, {"event_id": "0888a9e1c2c74168be0f8469c70ba809", "step": 21, "value": 0.8600406535419345, "stage": "improve", "created_at": 1788853822.8939583}, {"event_id": "cbb6b92642634a2eaf10ecff659f712d", "step": 22, "value": 0.8833729731033557, "stage": "improve", "created_at": 1788854178.4981568}, {"event_id": "0b9e3c24d3034e1ba0de3d51835a03a8", "step": 23, "value": 0.8841718774455688, "stage": "evolution", "created_at": 1788854880.937829}, {"event_id": "0dfaf7f1aec949a1a433b350fc183b70", "step": 24, "value": 0.6188182517847981, "stage": "evolution", "created_at": 1788854514.5687306}, {"event_id": "079c8830d00d42f49b98816bfc9d2a1a", "step": 25, "value": 0.8800189314137222, "stage": "evolution", "created_at": 1788855529.8231013}, {"event_id": "b13633a0640446a7974000cddf0831ae", "step": 26, "value": 0.826376847263086, "stage": "improve", "created_at": 1788852919.0856228}, {"event_id": "0d304f1a2aa74722a40313514ca3c7db", "step": 27, "value": 0.815180272063287, "stage": "evolution", "created_at": 1788855532.9605255}, {"event_id": "44722e4d8ba24232a237e3ee88721549", "step": 28, "value": 0.8612797815702762, "stage": "evolution", "created_at": 1788856281.4155958}, {"event_id": "313e7a515a0946f19ccaf3aed84a53e1", "step": 30, "value": 0.8800107962317654, "stage": "evolution", "created_at": 1788857087.7896283}, {"event_id": "49c18329020a48e49d6554b87da0f812", "step": 31, "value": 0.6997189685652934, "stage": "debug", "created_at": 1788857223.150976}, {"event_id": "dd3043fe42e74694a146777485f5619f", "step": 32, "value": 0.8494958293212683, "stage": "evolution", "created_at": 1788856191.7916348}, {"event_id": "672f621a98e140a7a531b38829427a46", "step": 33, "value": 0.8462794364166253, "stage": "evolution", "created_at": 1788857829.9023738}, {"event_id": "181627b0475e4706930ae394d70fa769", "step": 35, "value": 0.8705616691394774, "stage": "evolution", "created_at": 1788858149.1621122}, {"event_id": "9148afdfcb9f4650b21777318817c190", "step": 36, "value": 0.8690072388995622, "stage": "debug", "created_at": 1788858264.4544787}, {"event_id": "9b99aeb767dc4ee4b2bddaffcdaa746d", "step": 37, "value": 0.7921664119204139, "stage": "evolution", "created_at": 1788858358.121952}, {"event_id": "f1472f48d79c463482b45ebf4a836261", "step": 38, "value": 0.8390958321298828, "stage": "evolution", "created_at": 1788858804.298039}, {"event_id": "1b2ce0f0471d4ff89391ad5b884737ef", "step": 39, "value": 0.7701244800419547, "stage": "evolution", "created_at": 1788858875.090126}, {"event_id": "94713c289bdc46ae8bea5b2d8fbc6f92", "step": 40, "value": 0.836462703500532, "stage": "evolution", "created_at": 1788858781.2602682}, {"event_id": "d14ded0547f74821a39468a788d9cac9", "step": 42, "value": 0.858480299444562, "stage": "evolution", "created_at": 1788859680.185999}, {"event_id": "ecbd38df4ac34ee6bae3dcec8af429ad", "step": 44, "value": 0.8621716396084816, "stage": "evolution", "created_at": 1788860172.498901}, {"event_id": "48e4dc6732664dc681319fcec00ee9ea", "step": 45, "value": 0.872612072137594, "stage": "debug", "created_at": 1788860139.3710518}, {"event_id": "85462f1ea148416faf814d297e0b8ac1", "step": 47, "value": 0.8446119441219317, "stage": "evolution", "created_at": 1788860934.563002}, {"event_id": "40093e58382545039fd8e2273e65d320", "step": 49, "value": 0.8467586260878235, "stage": "debug", "created_at": 1788861532.6602466}, {"event_id": "6fa7c5a1386e4fcf8aa0905091568b80", "step": 50, "value": 0.8249780514931481, "stage": "evolution", "created_at": 1788860332.4019601}, {"event_id": "35b23b39d60f4cd481db06a54b3c734b", "step": 51, "value": 0.8565647986872066, "stage": "evolution", "created_at": 1788862381.655592}, {"event_id": "f78a51cf00c7497abf55b48848d4d60f", "step": 52, "value": 0.8589050179557827, "stage": "evolution", "created_at": 1788862416.7260168}, {"event_id": "1e1e25afbb8244f8b0c2bf56bb4ff02d", "step": 53, "value": 0.8022665034726406, "stage": "evolution", "created_at": 1788862505.6228561}, {"event_id": "7e6b00edd0c94af8a1d0debbb6c0d4a1", "step": 54, "value": 0.8217784605278574, "stage": "evolution", "created_at": 1788862990.513169}, {"event_id": "ab104f07e33f41fd8f0ae44b16c15714", "step": 55, "value": 0.9021249290084413, "stage": "fusion", "created_at": 1788863326.640581}, {"event_id": "f9054a49978c4c6baa81b43ee6175b84", "step": 56, "value": 0.8848426864053666, "stage": "fusion", "created_at": 1788863212.0949054}, {"event_id": "371b45f2587d40969dcd841f17b936c1", "step": 57, "value": 0.7912228938783342, "stage": "fusion", "created_at": 1788863698.923844}, {"event_id": "5011d53dbdc747af837eb8a18d6bb191", "step": 58, "value": 0.843900748586381, "stage": "improve", "created_at": 1788863974.0973465}, {"event_id": "ddb5d43021b247f5ab327441584326eb", "step": 59, "value": 0.8550318925581754, "stage": "improve", "created_at": 1788864336.7917023}, {"event_id": "f304c8be85d44ffdb6f8e5a9f8f1843e", "step": 60, "value": 0.8125947514872386, "stage": "improve", "created_at": 1788864786.5371733}, {"event_id": "54a0ee028266464393025a6595da9a4b", "step": 61, "value": 0.902013643786819, "stage": "improve", "created_at": 1788865122.03455}, {"event_id": "715030a04e1942bcb70e00bc3966b435", "step": 62, "value": 0.9094267357053211, "stage": "improve", "created_at": 1788865714.7472968}, {"event_id": "3b495299e4004919b08148f15a1b64aa", "step": 63, "value": 0.9050879557198106, "stage": "improve", "created_at": 1788865878.6308649}, {"event_id": "e637f2c622bf404695a1e2ac5856c812", "step": 64, "value": 0.8198091882188685, "stage": "fusion", "created_at": 1788865817.1446471}, {"event_id": "489022e380504796abf1bc2d356d56b5", "step": 65, "value": 0.9079094264345453, "stage": "improve", "created_at": 1788866373.1597834}, {"event_id": "9dd6c14714f14df4915ebe0ee5643bd6", "step": 67, "value": 0.857104834662973, "stage": "improve", "created_at": 1788866634.7057714}, {"event_id": "b074b542a42c4895a3219b2b9ffd66d4", "step": 68, "value": 0.9089276518254087, "stage": "evolution", "created_at": 1788866993.4143286}, {"event_id": "1ece12fdb85a4d8e89c9e36c3cb54890", "step": 69, "value": 0.6027, "stage": "debug", "created_at": 1788867034.596595}, {"event_id": "8cfb2d39377a4e4bb948186ee0b185c4", "step": 70, "value": 0.8903947568784267, "stage": "evolution", "created_at": 1788867749.3799813}, {"event_id": "f88813e10436475386ef7a66ca47bab8", "step": 71, "value": 0.9122121542715097, "stage": "fusion", "created_at": 1788867838.1502032}, {"event_id": "df401e053a4b42a38749cd850fa52801", "step": 72, "value": 0.7621381010183558, "stage": "fusion", "created_at": 1788867795.3399956}, {"event_id": "7029d0960ff646369d18b4d9a87e50c5", "step": 74, "value": 0.8463970152085156, "stage": "evolution", "created_at": 1788868781.843657}, {"event_id": "70fb6fdbca404936adfca1c712c32806", "step": 76, "value": 0.8565534964593304, "stage": "improve", "created_at": 1788869690.1981037}, {"event_id": "1ba3d8cddfbb415c8f569c3222e980a4", "step": 77, "value": 0.9109055956597799, "stage": "improve", "created_at": 1788869606.5942569}, {"event_id": "99d6a77ea438446baba1accb3a5c455e", "step": 78, "value": 0.9633780179931134, "stage": "improve", "created_at": 1788869975.2028012}, {"event_id": "0d3165d03bd547dcaf70c3484d7edfbe", "step": 80, "value": 0.914217689866126, "stage": "improve", "created_at": 1788870881.081807}], "maximize": true, "elapsed_seconds": 28671.702822446823, "node_count": 84, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp6-20260908/xixian.gp6.mlsp-2013-birds.yaml", "note": ""}, {"id": "xixian.gp6.new-york-city-taxi-fare-prediction", "experiment_id": "mlebench-gp6-20260908", "family": "MLEBench", "method": "gp6", "dataset": "new-york-city-taxi-fare-prediction", "status": "archived", "official_score": 5.01424, "medal": "none", "valid_submission": true, "score_maximize": false, "thresholds": {"gold": 2.83377, "silver": 2.88191, "bronze": 2.92371}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp6-gp6-draft-logs-with-private-scores", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp6-gp6-draft-logs-with-private-scores/logs-7b2a3e058322.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp6-gp6-draft-logs-with-private-scores", "member": "gp6_gp6-draft_logs/private_scores/rechecked_private_grades.jsonl:11", "sha256": "7b2a3e05832281a42f745f697155c42c6ef59359301c708d7b3496df1e02188f"}, {"bundle_id": "gp6-gp6-draft-logs-with-private-scores", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp6-gp6-draft-logs-with-private-scores/logs-7b2a3e058322.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp6-gp6-draft-logs-with-private-scores", "member": "gp6_gp6-draft_logs/runs/gp6/11_new-york-city-taxi-fare-prediction/logs/journal.json", "sha256": "7b2a3e05832281a42f745f697155c42c6ef59359301c708d7b3496df1e02188f"}], "alternate_scores": [], "journal_ref": "gp6-gp6-draft-logs-with-private-scores:gp6_gp6-draft_logs/runs/gp6/11_new-york-city-taxi-fare-prediction/logs/journal.json", "metrics": [{"event_id": "6b71f50a21bd4ce1bf9ad9f3af122035", "step": 2, "value": 3.4816947699186604, "stage": "draft", "created_at": 1788846257.496633}, {"event_id": "46446ca4d46549569b04ebc290c5e7b9", "step": 4, "value": 3.922520356570571, "stage": "debug", "created_at": 1788846861.8021727}, {"event_id": "c73cb92dfd4048be854c2c138beb7aef", "step": 5, "value": 3.922520356570571, "stage": "debug", "created_at": 1788846867.0346546}, {"event_id": "c50365f906524daabe20b0d632cf94eb", "step": 6, "value": 4.271696013107669, "stage": "improve", "created_at": 1788848327.8299956}, {"event_id": "a1c26ab753274080a5c0304f299b8d9e", "step": 7, "value": 3.6351945796421723, "stage": "improve", "created_at": 1788848435.361522}, {"event_id": "79a13451024748bcb01ed3cbec042b34", "step": 9, "value": 3.91617386749689, "stage": "debug", "created_at": 1788852105.708124}, {"event_id": "a971671daea74ae38bda0e613bead4b3", "step": 10, "value": 3.100943813784476, "stage": "improve", "created_at": 1788850655.1773975}, {"event_id": "2201aaef34954307a1a3e75f856d1033", "step": 11, "value": 3.027856678119934, "stage": "improve", "created_at": 1788854857.783011}, {"event_id": "7a02da0757f64af48b36597bc1740798", "step": 12, "value": 2.909956909858674, "stage": "improve", "created_at": 1788855644.5224464}, {"event_id": "1e63cdea736e41a69890302077e8b3a3", "step": 13, "value": 2.9670045769136375, "stage": "improve", "created_at": 1788859797.7522845}, {"event_id": "71c5a40fc41249739e6de4b80029935d", "step": 15, "value": 2.8948297299936665, "stage": "improve", "created_at": 1788863901.1357327}, {"event_id": "be5c900bc5d24eb89cb81c588c018b4b", "step": 16, "value": 2.8349356137195234, "stage": "improve", "created_at": 1788864270.8387601}], "maximize": false, "elapsed_seconds": 28688.51359653473, "node_count": 17, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp6-20260908/xixian.gp6.new-york-city-taxi-fare-prediction.yaml", "note": ""}, {"id": "xixian.gp6.nomad2018-predict-transparent-conductors", "experiment_id": "mlebench-gp6-20260908", "family": "MLEBench", "method": "gp6", "dataset": "nomad2018-predict-transparent-conductors", "status": "archived", "official_score": 0.06018, "medal": "silver", "valid_submission": true, "score_maximize": false, "thresholds": {"gold": 0.05589, "silver": 0.06229, "bronze": 0.06582}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp6-gp6-draft-logs-with-private-scores", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp6-gp6-draft-logs-with-private-scores/logs-7b2a3e058322.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp6-gp6-draft-logs-with-private-scores", "member": "gp6_gp6-draft_logs/private_scores/rechecked_private_grades.jsonl:12", "sha256": "7b2a3e05832281a42f745f697155c42c6ef59359301c708d7b3496df1e02188f"}, {"bundle_id": "gp6-gp6-draft-logs-with-private-scores", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp6-gp6-draft-logs-with-private-scores/logs-7b2a3e058322.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp6-gp6-draft-logs-with-private-scores", "member": "gp6_gp6-draft_logs/runs/gp6/12_nomad2018-predict-transparent-conductors/logs/journal.json", "sha256": "7b2a3e05832281a42f745f697155c42c6ef59359301c708d7b3496df1e02188f"}], "alternate_scores": [], "journal_ref": "gp6-gp6-draft-logs-with-private-scores:gp6_gp6-draft_logs/runs/gp6/12_nomad2018-predict-transparent-conductors/logs/journal.json", "metrics": [{"event_id": "2acb02f5666e4365a46859c4921d288c", "step": 2, "value": 0.072606579377168, "stage": "draft", "created_at": 1788846587.2163384}, {"event_id": "5d8a6e15acac450f8723c6fe2d6293cb", "step": 3, "value": 0.061111324360431415, "stage": "debug", "created_at": 1788846763.9366755}, {"event_id": "7dfb7ed88e3b410fa36c500db0621ec2", "step": 4, "value": 0.0597024906037123, "stage": "draft", "created_at": 1788845946.2348866}, {"event_id": "d7d425c8ae0a49d6b6a9a543095b47ac", "step": 5, "value": 0.06017025078244506, "stage": "improve", "created_at": 1788848595.87379}, {"event_id": "506b7131137b4c11bf80b897a04b1c51", "step": 6, "value": 0.060517548123440165, "stage": "improve", "created_at": 1788848640.1245065}, {"event_id": "5ba35cee3f73428b97e8819914aec5ee", "step": 9, "value": 0.05740110823797669, "stage": "improve", "created_at": 1788849421.6812778}, {"event_id": "e033e485573e44268db678e4e90a7e08", "step": 10, "value": 0.06347867095842016, "stage": "improve", "created_at": 1788849164.2411845}, {"event_id": "543a7cb4ce0744d3b2a9bd336e91744c", "step": 11, "value": 0.05944194954452829, "stage": "debug", "created_at": 1788849212.8150563}, {"event_id": "5dd2feee88304d429000835c6c6c4c7f", "step": 12, "value": 0.0576942990049321, "stage": "improve", "created_at": 1788852551.016705}, {"event_id": "befa1c5c66a1424f963c79f3a3d4c197", "step": 13, "value": 0.05777983454699625, "stage": "improve", "created_at": 1788862218.4017558}, {"event_id": "34c39c552f8d4425b18abe861dce1d02", "step": 14, "value": 0.05789136985550018, "stage": "improve", "created_at": 1788860779.5045583}], "maximize": false, "elapsed_seconds": 28733.971845149994, "node_count": 16, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp6-20260908/xixian.gp6.nomad2018-predict-transparent-conductors.yaml", "note": ""}, {"id": "xixian.gp6.plant-pathology-2020-fgvc7", "experiment_id": "mlebench-gp6-20260908", "family": "MLEBench", "method": "gp6", "dataset": "plant-pathology-2020-fgvc7", "status": "archived", "official_score": 0.99645, "medal": "gold", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.97836, "silver": 0.97465, "bronze": 0.97361}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp6-gp6-draft-logs-with-private-scores", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp6-gp6-draft-logs-with-private-scores/logs-7b2a3e058322.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp6-gp6-draft-logs-with-private-scores", "member": "gp6_gp6-draft_logs/private_scores/rechecked_private_grades.jsonl:13", "sha256": "7b2a3e05832281a42f745f697155c42c6ef59359301c708d7b3496df1e02188f"}, {"bundle_id": "gp6-gp6-draft-logs-with-private-scores", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp6-gp6-draft-logs-with-private-scores/logs-7b2a3e058322.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp6-gp6-draft-logs-with-private-scores", "member": "gp6_gp6-draft_logs/runs/gp6/13_plant-pathology-2020-fgvc7/logs/journal.json", "sha256": "7b2a3e05832281a42f745f697155c42c6ef59359301c708d7b3496df1e02188f"}], "alternate_scores": [], "journal_ref": "gp6-gp6-draft-logs-with-private-scores:gp6_gp6-draft_logs/runs/gp6/13_plant-pathology-2020-fgvc7/logs/journal.json", "metrics": [{"event_id": "c9ca70a81ed84e53928913adbbf0986e", "step": 1, "value": 0.9737360379772164, "stage": "draft", "created_at": 1788845206.4718697}, {"event_id": "7e35f8580136475e82dc2f140709bc9e", "step": 3, "value": 0.983048452478838, "stage": "draft", "created_at": 1788845841.3508806}, {"event_id": "b5c4ae2cec104d9b8fc606dfa921a00c", "step": 4, "value": 0.9856897667954589, "stage": "debug", "created_at": 1788846975.9062445}, {"event_id": "ff0f69d94ab6443aa3ff30a81800c23e", "step": 5, "value": 0.987486284525762, "stage": "improve", "created_at": 1788847265.2733076}, {"event_id": "631babce217c459bbc5ffe88afd8dbc8", "step": 6, "value": 0.9879659798828554, "stage": "improve", "created_at": 1788847353.7179735}, {"event_id": "0893b59dddd440ba826da5289f507978", "step": 10, "value": 0.9890354476677238, "stage": "improve", "created_at": 1788848427.4802215}, {"event_id": "f7c0c0e8d5cc46bdb56264fcb5477cc9", "step": 14, "value": 0.9935307827002661, "stage": "improve", "created_at": 1788848405.7159245}, {"event_id": "32513ba7cb9740989cf5adaa98ada0a8", "step": 15, "value": 0.9894792161285879, "stage": "debug", "created_at": 1788849882.1737807}, {"event_id": "de97afe012c14eac99cb6c9cd317deb2", "step": 16, "value": 0.992609875527689, "stage": "debug", "created_at": 1788849686.799287}, {"event_id": "5d9f134a292e4afaad8f0bceade4e53f", "step": 19, "value": 0.9859414140045593, "stage": "improve", "created_at": 1788850893.2142518}, {"event_id": "b9e528b1ff494f16b6d471279067c0a0", "step": 20, "value": 0.9849729079088196, "stage": "debug", "created_at": 1788852005.9022973}, {"event_id": "126f22b38c0648e8846b60f9cce52c56", "step": 21, "value": 0.9835641092326937, "stage": "debug", "created_at": 1788851789.6409376}, {"event_id": "8470f15ca1224fc7af7b0e8e251d9fe2", "step": 22, "value": 0.9915208168698973, "stage": "evolution", "created_at": 1788854839.3831663}, {"event_id": "6dfed97094dd43c4976fe09096a5d4bf", "step": 25, "value": 0.9766961272016189, "stage": "evolution", "created_at": 1788857561.6891055}, {"event_id": "5a82873b49e5439b950a761698ddb389", "step": 26, "value": 0.9820415335914214, "stage": "evolution", "created_at": 1788859017.8747103}, {"event_id": "0bd37d732fe44933b31d6539498b9762", "step": 27, "value": 0.9924742904078703, "stage": "evolution", "created_at": 1788861120.4085252}, {"event_id": "94f213c72a9b427ba4d2d43d822deb64", "step": 28, "value": 0.9892674153544236, "stage": "fusion", "created_at": 1788861092.8563867}, {"event_id": "2902a3b2905445ad89aabf7d833d880d", "step": 29, "value": 0.9958847389533526, "stage": "evolution", "created_at": 1788863449.0280635}, {"event_id": "90636734b7b646cea08cbe0869ac8ece", "step": 30, "value": 0.9885389336937067, "stage": "improve", "created_at": 1788864378.6295762}, {"event_id": "4fc7183c23d44285b7b95791f878d946", "step": 31, "value": 0.9836514226825538, "stage": "improve", "created_at": 1788864314.1490886}, {"event_id": "06b94a5ebe4e46c2b39479a93a9dfd41", "step": 33, "value": 0.9952209564924156, "stage": "improve", "created_at": 1788865650.2487903}, {"event_id": "c14768d88d87429c91999f68532daa43", "step": 37, "value": 0.99433092243918, "stage": "debug", "created_at": 1788869078.4747736}, {"event_id": "57df7fd9f7d04f5e9dd90b9d6c60ec6f", "step": 38, "value": 0.9889892295826644, "stage": "debug", "created_at": 1788869622.9560375}, {"event_id": "14ba724b5bcd41429f7821c17195a22e", "step": 39, "value": 0.9942001354905387, "stage": "debug", "created_at": 1788869592.677381}, {"event_id": "af22d5f205834754bfd547159017ff52", "step": 40, "value": 0.9921850314132247, "stage": "improve", "created_at": 1788870539.4682171}], "maximize": true, "elapsed_seconds": 28726.63468146324, "node_count": 41, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp6-20260908/xixian.gp6.plant-pathology-2020-fgvc7.yaml", "note": ""}, {"id": "xixian.gp6.random-acts-of-pizza", "experiment_id": "mlebench-gp6-20260908", "family": "MLEBench", "method": "gp6", "dataset": "random-acts-of-pizza", "status": "archived", "official_score": 0.69358, "medal": "bronze", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.97908, "silver": 0.76482, "bronze": 0.6921}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp6-gp6-draft-logs-with-private-scores", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp6-gp6-draft-logs-with-private-scores/logs-7b2a3e058322.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp6-gp6-draft-logs-with-private-scores", "member": "gp6_gp6-draft_logs/private_scores/rechecked_private_grades.jsonl:14", "sha256": "7b2a3e05832281a42f745f697155c42c6ef59359301c708d7b3496df1e02188f"}, {"bundle_id": "gp6-gp6-draft-logs-with-private-scores", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp6-gp6-draft-logs-with-private-scores/logs-7b2a3e058322.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp6-gp6-draft-logs-with-private-scores", "member": "gp6_gp6-draft_logs/runs/gp6/14_random-acts-of-pizza/logs/journal.json", "sha256": "7b2a3e05832281a42f745f697155c42c6ef59359301c708d7b3496df1e02188f"}], "alternate_scores": [], "journal_ref": "gp6-gp6-draft-logs-with-private-scores:gp6_gp6-draft_logs/runs/gp6/14_random-acts-of-pizza/logs/journal.json", "metrics": [{"event_id": "58a69d970abe424daecfdc79fde42ddb", "step": 3, "value": 0.6826337634651722, "stage": "debug", "created_at": 1788846951.8786504}, {"event_id": "1d89c3c2a74d4ea684f56064fd84e5ae", "step": 4, "value": 0.6679783713054187, "stage": "draft", "created_at": 1788846187.928671}, {"event_id": "f6ebc74ab62f4bb5bbb4ecfc1ae8e144", "step": 5, "value": 0.7299065420560749, "stage": "debug", "created_at": 1788846968.871254}, {"event_id": "cd7fba95dc13470dada95ff396a0eca3", "step": 6, "value": 0.6906442287504644, "stage": "improve", "created_at": 1788847563.0588417}, {"event_id": "bb313d187b754e5ea7d418e42f9e444c", "step": 7, "value": 0.6774334210823818, "stage": "improve", "created_at": 1788847550.6344082}, {"event_id": "a4fb2a9f109347a3bf7dbebfb8ee4233", "step": 8, "value": 0.7229475197699498, "stage": "improve", "created_at": 1788847744.5602944}, {"event_id": "bcfb2c1137744c0cba63a166460aeaa3", "step": 9, "value": 0.7344356578001436, "stage": "improve", "created_at": 1788848039.8021836}, {"event_id": "e9a8dbd9dd264db8a937ce1da0a510f1", "step": 10, "value": 0.7255930984902947, "stage": "improve", "created_at": 1788848290.6605182}, {"event_id": "6fc80f77577147cbaba1c733c7ed02fb", "step": 13, "value": 0.6743715831094471, "stage": "debug", "created_at": 1788848787.9145339}, {"event_id": "208ba86bfac249d09ce7e494dfcd47fb", "step": 14, "value": 0.7215097052480229, "stage": "debug", "created_at": 1788848907.7770069}, {"event_id": "be563628f9644e169be7e98c7cc6b8a2", "step": 15, "value": 0.7388066139468008, "stage": "improve", "created_at": 1788849136.5705385}, {"event_id": "3a4da8b6d73148a5af78f2b52935532f", "step": 16, "value": 0.7443278217109993, "stage": "evolution", "created_at": 1788849646.3889658}, {"event_id": "342e4ea25b5a4bb4bb90cf465ac219fc", "step": 17, "value": 0.7502228612508988, "stage": "improve", "created_at": 1788850376.5594127}, {"event_id": "bee8c386917b4fbda3960bfbefc82b8e", "step": 18, "value": 0.741624730409777, "stage": "improve", "created_at": 1788851330.623144}, {"event_id": "2d79542f8f3540cda545980ca6082f3f", "step": 19, "value": 0.7565492451473759, "stage": "improve", "created_at": 1788852880.9565525}, {"event_id": "e0dc8a0492a24247a9c72c8f787ac29a", "step": 20, "value": 0.7468008626887132, "stage": "improve", "created_at": 1788853901.2060966}, {"event_id": "c615a28674e84170ad8a1232418b25eb", "step": 21, "value": 0.7686556434219984, "stage": "improve", "created_at": 1788855150.0767045}, {"event_id": "e1034741d38942ada2420d2ffa8cc060", "step": 22, "value": 0.7500790797987059, "stage": "improve", "created_at": 1788859298.8824584}], "maximize": true, "elapsed_seconds": 28736.39585709572, "node_count": 28, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp6-20260908/xixian.gp6.random-acts-of-pizza.yaml", "note": ""}, {"id": "xixian.gp6.ranzcr-clip-catheter-line-classification", "experiment_id": "mlebench-gp6-20260908", "family": "MLEBench", "method": "gp6", "dataset": "ranzcr-clip-catheter-line-classification", "status": "archived", "official_score": 0.89368, "medal": "none", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.97357, "silver": 0.97152, "bronze": 0.9709}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp6-gp6-draft-logs-with-private-scores", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp6-gp6-draft-logs-with-private-scores/logs-7b2a3e058322.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp6-gp6-draft-logs-with-private-scores", "member": "gp6_gp6-draft_logs/private_scores/rechecked_private_grades.jsonl:15", "sha256": "7b2a3e05832281a42f745f697155c42c6ef59359301c708d7b3496df1e02188f"}, {"bundle_id": "gp6-gp6-draft-logs-with-private-scores", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp6-gp6-draft-logs-with-private-scores/logs-7b2a3e058322.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp6-gp6-draft-logs-with-private-scores", "member": "gp6_gp6-draft_logs/runs/gp6/15_ranzcr-clip-catheter-line-classification/logs/journal.json", "sha256": "7b2a3e05832281a42f745f697155c42c6ef59359301c708d7b3496df1e02188f"}], "alternate_scores": [], "journal_ref": "gp6-gp6-draft-logs-with-private-scores:gp6_gp6-draft_logs/runs/gp6/15_ranzcr-clip-catheter-line-classification/logs/journal.json", "metrics": [{"event_id": "327ed06eb6cd4f8ebb34a103ffd036e3", "step": 2, "value": 0.7601330790760482, "stage": "draft", "created_at": 1788845436.3902743}, {"event_id": "1ad3c806c67a4c3d834a1dd542bc836d", "step": 3, "value": 0.6893993522700099, "stage": "debug", "created_at": 1788847959.9345372}, {"event_id": "fe0549c0665f4c6aa252fc38121b2fd9", "step": 4, "value": 0.803015963638756, "stage": "draft", "created_at": 1788846897.9908721}, {"event_id": "70ea1ac8c29e4ff28c8233f8443b83fe", "step": 9, "value": 0.8621482547064984, "stage": "debug", "created_at": 1788857463.4832318}], "maximize": true, "elapsed_seconds": 28692.332401752472, "node_count": 10, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp6-20260908/xixian.gp6.ranzcr-clip-catheter-line-classification.yaml", "note": ""}, {"id": "xixian.gp6.siim-isic-melanoma-classification", "experiment_id": "mlebench-gp6-20260908", "family": "MLEBench", "method": "gp6", "dataset": "siim-isic-melanoma-classification", "status": "archived", "official_score": null, "medal": "none", "valid_submission": false, "score_maximize": true, "thresholds": {"gold": 0.9455, "silver": 0.9401, "bronze": 0.937}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp6-gp6-draft-logs-with-private-scores", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp6-gp6-draft-logs-with-private-scores/logs-7b2a3e058322.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp6-gp6-draft-logs-with-private-scores", "member": "gp6_gp6-draft_logs/private_scores/rechecked_private_grades.jsonl:16", "sha256": "7b2a3e05832281a42f745f697155c42c6ef59359301c708d7b3496df1e02188f"}, {"bundle_id": "gp6-gp6-draft-logs-with-private-scores", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp6-gp6-draft-logs-with-private-scores/logs-7b2a3e058322.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp6-gp6-draft-logs-with-private-scores", "member": "gp6_gp6-draft_logs/runs/gp6/16_siim-isic-melanoma-classification/logs/journal.json", "sha256": "7b2a3e05832281a42f745f697155c42c6ef59359301c708d7b3496df1e02188f"}], "alternate_scores": [], "journal_ref": "gp6-gp6-draft-logs-with-private-scores:gp6_gp6-draft_logs/runs/gp6/16_siim-isic-melanoma-classification/logs/journal.json", "metrics": [], "maximize": null, "elapsed_seconds": 28668.664780139923, "node_count": 9, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp6-20260908/xixian.gp6.siim-isic-melanoma-classification.yaml", "note": ""}, {"id": "xixian.gp6.spooky-author-identification", "experiment_id": "mlebench-gp6-20260908", "family": "MLEBench", "method": "gp6", "dataset": "spooky-author-identification", "status": "archived", "official_score": 0.23971, "medal": "silver", "valid_submission": true, "score_maximize": false, "thresholds": {"gold": 0.16506, "silver": 0.26996, "bronze": 0.29381}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp6-gp6-draft-logs-with-private-scores", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp6-gp6-draft-logs-with-private-scores/logs-7b2a3e058322.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp6-gp6-draft-logs-with-private-scores", "member": "gp6_gp6-draft_logs/private_scores/rechecked_private_grades.jsonl:17", "sha256": "7b2a3e05832281a42f745f697155c42c6ef59359301c708d7b3496df1e02188f"}, {"bundle_id": "gp6-gp6-draft-logs-with-private-scores", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp6-gp6-draft-logs-with-private-scores/logs-7b2a3e058322.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp6-gp6-draft-logs-with-private-scores", "member": "gp6_gp6-draft_logs/runs/gp6/17_spooky-author-identification/logs/journal.json", "sha256": "7b2a3e05832281a42f745f697155c42c6ef59359301c708d7b3496df1e02188f"}], "alternate_scores": [], "journal_ref": "gp6-gp6-draft-logs-with-private-scores:gp6_gp6-draft_logs/runs/gp6/17_spooky-author-identification/logs/journal.json", "metrics": [{"event_id": "43029c6620ca46539f50af38df24063a", "step": 2, "value": 0.4467855494822467, "stage": "draft", "created_at": 1788846382.889679}, {"event_id": "2d35b24162f049998c456d6453256404", "step": 3, "value": 0.2563073694610636, "stage": "draft", "created_at": 1788845345.8467693}, {"event_id": "6be5586b5e584c39b8efcd9f36484541", "step": 6, "value": 0.276634102705609, "stage": "debug", "created_at": 1788846956.1080723}, {"event_id": "63b1e5b5642c4442ab286f922f5bfd56", "step": 7, "value": 0.34424893755520275, "stage": "debug", "created_at": 1788847347.730189}, {"event_id": "6cb36266669a4067a72c5ab09f063c9b", "step": 8, "value": 0.0324903017390478, "stage": "improve", "created_at": 1788848115.0887384}, {"event_id": "b6230428aef24dbf8b0c1e561c17eb6a", "step": 9, "value": 0.3159423739002682, "stage": "improve", "created_at": 1788847949.7399898}, {"event_id": "66335c3fa50547aab3bd4382f0669a2f", "step": 11, "value": 0.3686271548222704, "stage": "improve", "created_at": 1788851257.2151067}, {"event_id": "894c7eb6393f41ec896a80305c3c1847", "step": 12, "value": 0.28842423054706035, "stage": "debug", "created_at": 1788851926.2436166}, {"event_id": "fe2faf044e3d46bf9c61342afa71dfaf", "step": 13, "value": 0.30706298197116594, "stage": "improve", "created_at": 1788857332.9454951}, {"event_id": "d26d6322af4345ecab686f9aabd8eec2", "step": 14, "value": 0.2969716680677689, "stage": "improve", "created_at": 1788863837.6499248}, {"event_id": "b557feaa07f84f92861127baeac4a164", "step": 17, "value": 0.2846757589223744, "stage": "fusion", "created_at": 1788867828.5102177}, {"event_id": "3547c9d8168c47ba8f609ba4b19f8b2b", "step": 18, "value": 0.28404453316940287, "stage": "debug", "created_at": 1788868258.9878826}, {"event_id": "54025e3086554574b93b9fe4fa6887a4", "step": 19, "value": 0.2757235590075401, "stage": "evolution", "created_at": 1788869588.8922439}], "maximize": false, "elapsed_seconds": 28703.23092365265, "node_count": 21, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp6-20260908/xixian.gp6.spooky-author-identification.yaml", "note": ""}, {"id": "xixian.gp6.tabular-playground-series-dec-2021", "experiment_id": "mlebench-gp6-20260908", "family": "MLEBench", "method": "gp6", "dataset": "tabular-playground-series-dec-2021", "status": "archived", "official_score": 0.96326, "medal": "gold", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.9566, "silver": 0.95658, "bronze": 0.95658}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp6-gp6-draft-logs-with-private-scores", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp6-gp6-draft-logs-with-private-scores/logs-7b2a3e058322.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp6-gp6-draft-logs-with-private-scores", "member": "gp6_gp6-draft_logs/private_scores/rechecked_private_grades.jsonl:18", "sha256": "7b2a3e05832281a42f745f697155c42c6ef59359301c708d7b3496df1e02188f"}, {"bundle_id": "gp6-gp6-draft-logs-with-private-scores", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp6-gp6-draft-logs-with-private-scores/logs-7b2a3e058322.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp6-gp6-draft-logs-with-private-scores", "member": "gp6_gp6-draft_logs/runs/gp6/18_tabular-playground-series-dec-2021/logs/journal.json", "sha256": "7b2a3e05832281a42f745f697155c42c6ef59359301c708d7b3496df1e02188f"}], "alternate_scores": [], "journal_ref": "gp6-gp6-draft-logs-with-private-scores:gp6_gp6-draft_logs/runs/gp6/18_tabular-playground-series-dec-2021/logs/journal.json", "metrics": [{"event_id": "263aabdd3c0d4412a8805361f0a92537", "step": 5, "value": 0.9523111111111111, "stage": "debug", "created_at": 1788846336.2107253}, {"event_id": "080e321df9f341eeb028d6dc0205e93e", "step": 6, "value": 0.9429527777777778, "stage": "debug", "created_at": 1788846294.9125757}, {"event_id": "59df44540b86411b9de9bcb05fc015c7", "step": 8, "value": 0.9624592592592592, "stage": "improve", "created_at": 1788846932.7227278}, {"event_id": "e5d042b74ff24a79bea531d937bdaea7", "step": 9, "value": 0.9621776727157575, "stage": "debug", "created_at": 1788846747.6535373}, {"event_id": "8a7e157fd6ac4d949d4a3cf135b42fd8", "step": 11, "value": 0.9623314814814815, "stage": "debug", "created_at": 1788850020.263458}, {"event_id": "8019807da9fb4a4c8c79c120628f5571", "step": 12, "value": 0.9625777777777778, "stage": "improve", "created_at": 1788853808.1345272}, {"event_id": "cebceed118724d1b84471528e6938f97", "step": 13, "value": 0.9626685185185185, "stage": "improve", "created_at": 1788848981.033257}, {"event_id": "342fad8d789f4e53812ffade61041e6a", "step": 14, "value": 0.9621666666666666, "stage": "improve", "created_at": 1788862453.784037}, {"event_id": "30b233e5944b4b198806d123897f2695", "step": 18, "value": 0.9626537037037037, "stage": "debug", "created_at": 1788867388.929}], "maximize": true, "elapsed_seconds": 28727.607109308243, "node_count": 20, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp6-20260908/xixian.gp6.tabular-playground-series-dec-2021.yaml", "note": ""}, {"id": "xixian.gp6.tabular-playground-series-may-2022", "experiment_id": "mlebench-gp6-20260908", "family": "MLEBench", "method": "gp6", "dataset": "tabular-playground-series-may-2022", "status": "archived", "official_score": 0.99338, "medal": "none", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.99823, "silver": 0.99822, "bronze": 0.99818}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp6-gp6-draft-logs-with-private-scores", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp6-gp6-draft-logs-with-private-scores/logs-7b2a3e058322.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp6-gp6-draft-logs-with-private-scores", "member": "gp6_gp6-draft_logs/private_scores/rechecked_private_grades.jsonl:19", "sha256": "7b2a3e05832281a42f745f697155c42c6ef59359301c708d7b3496df1e02188f"}, {"bundle_id": "gp6-gp6-draft-logs-with-private-scores", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp6-gp6-draft-logs-with-private-scores/logs-7b2a3e058322.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp6-gp6-draft-logs-with-private-scores", "member": "gp6_gp6-draft_logs/runs/gp6/19_tabular-playground-series-may-2022/logs/journal.json", "sha256": "7b2a3e05832281a42f745f697155c42c6ef59359301c708d7b3496df1e02188f"}], "alternate_scores": [], "journal_ref": "gp6-gp6-draft-logs-with-private-scores:gp6_gp6-draft_logs/runs/gp6/19_tabular-playground-series-may-2022/logs/journal.json", "metrics": [{"event_id": "a07eacac883c494dbc38a2df3dad6a7a", "step": 1, "value": 0.8046040151170786, "stage": "draft", "created_at": 1788845973.9256656}, {"event_id": "764e72b2093c4a5ca783793f2a36194d", "step": 2, "value": 0.9399955351422578, "stage": "draft", "created_at": 1788845427.2167015}, {"event_id": "338cf453ebb547ba8e9713126013725d", "step": 3, "value": 0.9823937875492655, "stage": "draft", "created_at": 1788846509.5793355}, {"event_id": "ec5654b5d1634eef8e0e5711f280dbe7", "step": 4, "value": 0.759193848047542, "stage": "improve", "created_at": 1788847155.8806846}, {"event_id": "e40ac24e55db4b218abe96fdaed0aa8e", "step": 5, "value": 0.7954180623709259, "stage": "improve", "created_at": 1788847692.6674516}, {"event_id": "26c2ab4325394cf2bb21a02311bdf35e", "step": 6, "value": 0.9847985326588407, "stage": "improve", "created_at": 1788847171.484188}, {"event_id": "90063315e5a448dc98019261c180cc5c", "step": 7, "value": 0.9913577850995501, "stage": "improve", "created_at": 1788847056.688476}, {"event_id": "ed84855925ac458cbb0dfe563822adc3", "step": 8, "value": 0.9912237460177917, "stage": "improve", "created_at": 1788851329.0404482}, {"event_id": "8151a566a0b14ea288f151dffac509cd", "step": 9, "value": 0.9922680866666861, "stage": "improve", "created_at": 1788849318.612772}], "maximize": true, "elapsed_seconds": 28715.952991962433, "node_count": 11, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp6-20260908/xixian.gp6.tabular-playground-series-may-2022.yaml", "note": ""}, {"id": "xixian.gp6.text-normalization-challenge-english-language", "experiment_id": "mlebench-gp6-20260908", "family": "MLEBench", "method": "gp6", "dataset": "text-normalization-challenge-english-language", "status": "archived", "official_score": 0.99045, "medal": "bronze", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.99724, "silver": 0.99135, "bronze": 0.99038}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp6-gp6-draft-logs-with-private-scores", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp6-gp6-draft-logs-with-private-scores/logs-7b2a3e058322.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp6-gp6-draft-logs-with-private-scores", "member": "gp6_gp6-draft_logs/private_scores/rechecked_private_grades.jsonl:20", "sha256": "7b2a3e05832281a42f745f697155c42c6ef59359301c708d7b3496df1e02188f"}, {"bundle_id": "gp6-gp6-draft-logs-with-private-scores", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp6-gp6-draft-logs-with-private-scores/logs-7b2a3e058322.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp6-gp6-draft-logs-with-private-scores", "member": "gp6_gp6-draft_logs/runs/gp6/20_text-normalization-challenge-english-language/logs/journal.json", "sha256": "7b2a3e05832281a42f745f697155c42c6ef59359301c708d7b3496df1e02188f"}], "alternate_scores": [], "journal_ref": "gp6-gp6-draft-logs-with-private-scores:gp6_gp6-draft_logs/runs/gp6/20_text-normalization-challenge-english-language/logs/journal.json", "metrics": [{"event_id": "f7c1564ef5534977927a0f530832961e", "step": 4, "value": 0.9903267797827453, "stage": "draft", "created_at": 1788846170.753872}, {"event_id": "b64fec76af4043c4bc3a603e2b9de9d9", "step": 5, "value": 0.932, "stage": "debug", "created_at": 1788847091.3144321}, {"event_id": "13863f1d539b4997ae73751c52ae5428", "step": 8, "value": 0.932, "stage": "debug", "created_at": 1788852364.6197512}, {"event_id": "32e4f673ffc845a6ab4d046e9774bc86", "step": 9, "value": 0.97465, "stage": "improve", "created_at": 1788857148.9720714}, {"event_id": "e53573ea5a7e45d5ac2e51cd4f2c5705", "step": 10, "value": 0.932, "stage": "debug", "created_at": 1788854277.988098}, {"event_id": "63dda1f783b6471db2bedf7f987ebf55", "step": 11, "value": 0.98955, "stage": "improve", "created_at": 1788861062.8436377}, {"event_id": "daa5200133d74d00a318ec78986943f0", "step": 12, "value": 0.95825, "stage": "improve", "created_at": 1788861379.5126333}, {"event_id": "ec1a1a7123734d459bee4bc0bf56db25", "step": 14, "value": 0.9896, "stage": "improve", "created_at": 1788865216.4457114}, {"event_id": "48d47c18a2b8458d8ec0251032144d56", "step": 15, "value": 0.98965, "stage": "improve", "created_at": 1788865251.6623688}], "maximize": true, "elapsed_seconds": 28717.29037809372, "node_count": 19, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp6-20260908/xixian.gp6.text-normalization-challenge-english-language.yaml", "note": ""}, {"id": "xixian.gp6.text-normalization-challenge-russian-language", "experiment_id": "mlebench-gp6-20260908", "family": "MLEBench", "method": "gp6", "dataset": "text-normalization-challenge-russian-language", "status": "archived", "official_score": 0.98507, "medal": "silver", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.99012, "silver": 0.98232, "bronze": 0.97592}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp6-gp6-draft-logs-with-private-scores", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp6-gp6-draft-logs-with-private-scores/logs-7b2a3e058322.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp6-gp6-draft-logs-with-private-scores", "member": "gp6_gp6-draft_logs/private_scores/rechecked_private_grades.jsonl:21", "sha256": "7b2a3e05832281a42f745f697155c42c6ef59359301c708d7b3496df1e02188f"}, {"bundle_id": "gp6-gp6-draft-logs-with-private-scores", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp6-gp6-draft-logs-with-private-scores/logs-7b2a3e058322.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp6-gp6-draft-logs-with-private-scores", "member": "gp6_gp6-draft_logs/runs/gp6/21_text-normalization-challenge-russian-language/logs/journal.json", "sha256": "7b2a3e05832281a42f745f697155c42c6ef59359301c708d7b3496df1e02188f"}], "alternate_scores": [], "journal_ref": "gp6-gp6-draft-logs-with-private-scores:gp6_gp6-draft_logs/runs/gp6/21_text-normalization-challenge-russian-language/logs/journal.json", "metrics": [{"event_id": "a47a05b613fe455690990cd246f1f922", "step": 6, "value": 0.9826, "stage": "debug", "created_at": 1788847455.5328732}, {"event_id": "5f637e4335ca4ded8face08084896c90", "step": 9, "value": 0.98326, "stage": "improve", "created_at": 1788849091.4287179}, {"event_id": "8809abf64d2343d9bd8d8c04af314e61", "step": 10, "value": 0.98515, "stage": "debug", "created_at": 1788849899.2813737}, {"event_id": "6f5d3eb8586c488a8274c49d39dd5699", "step": 11, "value": 0.98461, "stage": "improve", "created_at": 1788850801.1276782}, {"event_id": "53f0bbac16fd46f793b0736f51f57dda", "step": 12, "value": 0.10498546695311513, "stage": "debug", "created_at": 1788847270.40233}, {"event_id": "9283443dbd484a1f853cf255e66718a7", "step": 13, "value": 0.98542, "stage": "improve", "created_at": 1788852953.6036127}, {"event_id": "2c1156071b7b426a84c85dc90c9b97c0", "step": 14, "value": 0.98537, "stage": "improve", "created_at": 1788854516.6528404}, {"event_id": "7ec371c5d5a34af5b58698d67bcacea7", "step": 15, "value": 0.98524, "stage": "improve", "created_at": 1788854302.160677}, {"event_id": "692763e3b1024b60af9c5c761257f32e", "step": 16, "value": 0.98572, "stage": "improve", "created_at": 1788856700.9533134}, {"event_id": "177dd1842b074b5882e89677bbc86493", "step": 20, "value": 0.98453, "stage": "improve", "created_at": 1788858622.851186}, {"event_id": "1256b0400fa5471ab2e2f75d9ee25f15", "step": 22, "value": 0.98495, "stage": "debug", "created_at": 1788863391.782246}, {"event_id": "d11f04a63abb4ac08c7b0a778437e6fc", "step": 23, "value": 0.87611, "stage": "debug", "created_at": 1788862274.3676434}, {"event_id": "ff53714f57b0496b9758e36f43650ff8", "step": 24, "value": 0.98452, "stage": "improve", "created_at": 1788868250.6076176}], "maximize": true, "elapsed_seconds": 28713.453984737396, "node_count": 25, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp6-20260908/xixian.gp6.text-normalization-challenge-russian-language.yaml", "note": ""}, {"id": "xixian.gp6.the-icml-2013-whale-challenge-right-whale-redux", "experiment_id": "mlebench-gp6-20260908", "family": "MLEBench", "method": "gp6", "dataset": "the-icml-2013-whale-challenge-right-whale-redux", "status": "archived", "official_score": 0.99362, "medal": "gold", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.98961, "silver": 0.95017, "bronze": 0.90521}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp6-gp6-draft-logs-with-private-scores", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp6-gp6-draft-logs-with-private-scores/logs-7b2a3e058322.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp6-gp6-draft-logs-with-private-scores", "member": "gp6_gp6-draft_logs/private_scores/rechecked_private_grades.jsonl:22", "sha256": "7b2a3e05832281a42f745f697155c42c6ef59359301c708d7b3496df1e02188f"}, {"bundle_id": "gp6-gp6-draft-logs-with-private-scores", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp6-gp6-draft-logs-with-private-scores/logs-7b2a3e058322.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp6-gp6-draft-logs-with-private-scores", "member": "gp6_gp6-draft_logs/runs/gp6/22_the-icml-2013-whale-challenge-right-whale-redux/logs/journal.json", "sha256": "7b2a3e05832281a42f745f697155c42c6ef59359301c708d7b3496df1e02188f"}], "alternate_scores": [], "journal_ref": "gp6-gp6-draft-logs-with-private-scores:gp6_gp6-draft_logs/runs/gp6/22_the-icml-2013-whale-challenge-right-whale-redux/logs/journal.json", "metrics": [{"event_id": "2c8e3710e30740f8aa5adfd6be1396a1", "step": 1, "value": 0.8893558453220642, "stage": "draft", "created_at": 1788847267.5354445}, {"event_id": "cb896f76cb294a1a9dd2056ea53a6077", "step": 2, "value": 0.9677985062190463, "stage": "draft", "created_at": 1788846519.1407924}, {"event_id": "6c5028ad220a45e18a451b5561b91dbb", "step": 4, "value": 0.9762549888502587, "stage": "improve", "created_at": 1788849622.5846572}, {"event_id": "3474b02674e34a1486609bc9bcfe065d", "step": 5, "value": 0.936903961876465, "stage": "improve", "created_at": 1788849786.6939595}, {"event_id": "4b684e172c484618a6b41ec19d888bee", "step": 7, "value": 0.9769267923802851, "stage": "improve", "created_at": 1788850701.7788517}, {"event_id": "2b6ea6bb860a41f586e56c6e71253a11", "step": 9, "value": 0.9849411566864701, "stage": "debug", "created_at": 1788851443.337576}, {"event_id": "ff74633a10754384b59876e6d04098a7", "step": 10, "value": 0.9353680858354118, "stage": "improve", "created_at": 1788851689.010882}, {"event_id": "741060deaebe4a36acd5a667ca7fbae9", "step": 12, "value": 0.9623353704497379, "stage": "improve", "created_at": 1788853267.6368299}, {"event_id": "785a76ef7f444177b5ad12c8b8f90f4a", "step": 13, "value": 0.9374969931206516, "stage": "debug", "created_at": 1788851036.1463037}, {"event_id": "9259a4eebaea4c128ab80803123db113", "step": 14, "value": 0.8652174132218902, "stage": "debug", "created_at": 1788854084.7399437}, {"event_id": "6636109db7e24e988119a22045e1840b", "step": 16, "value": 0.9773649953385111, "stage": "improve", "created_at": 1788854701.6662965}, {"event_id": "6659c505438546748c855631f0a33408", "step": 17, "value": 0.8741007197765618, "stage": "improve", "created_at": 1788855009.591905}, {"event_id": "b87692bd16d447159be607411dac414f", "step": 18, "value": 0.9662093567184489, "stage": "debug", "created_at": 1788856184.3770187}, {"event_id": "82019e837aad49db9e04aefa9cb9318d", "step": 19, "value": 0.9867700347363405, "stage": "evolution", "created_at": 1788856398.9840138}, {"event_id": "7c4150a6b5d14fcc92d48a6cc3398726", "step": 20, "value": 0.988419361769076, "stage": "evolution", "created_at": 1788857695.5138922}, {"event_id": "d7864bd05a174568852c674138ca1c24", "step": 21, "value": 0.9913079884773823, "stage": "evolution", "created_at": 1788857976.4777343}, {"event_id": "7ccc8fc3417f4bf0a9d985e14e080972", "step": 24, "value": 0.9894155225331993, "stage": "improve", "created_at": 1788858263.8902946}, {"event_id": "d9d94064587c40af8d255dcfe005beed", "step": 25, "value": 0.9896994671415607, "stage": "debug", "created_at": 1788860438.3903365}, {"event_id": "f1d4615ffd58498ebeca795b0536e1b3", "step": 26, "value": 0.992833515493337, "stage": "debug", "created_at": 1788860888.5927162}, {"event_id": "427b5b12e64446b4bb90ebd1f7271feb", "step": 29, "value": 0.9932158937836786, "stage": "improve", "created_at": 1788863223.297528}, {"event_id": "dc95532c5c9e41778a1377e828c5c05e", "step": 31, "value": 0.9929543313477648, "stage": "debug", "created_at": 1788864515.238072}, {"event_id": "bd1642cbf33744c4833fd0dc8b082517", "step": 32, "value": 0.9917746051469108, "stage": "improve", "created_at": 1788864747.410118}, {"event_id": "7f6753048ebc4492889e7961711c8696", "step": 33, "value": 0.9916783003058681, "stage": "debug", "created_at": 1788865742.9576836}, {"event_id": "feb6920e93564922bc7c471f3c2cbe09", "step": 34, "value": 0.992805201978096, "stage": "improve", "created_at": 1788866677.130662}, {"event_id": "f302a1811e334bdab0a9e641387b2a8b", "step": 36, "value": 0.9918643312276403, "stage": "fusion", "created_at": 1788867536.6126664}, {"event_id": "0ed24a4f3b694e5f902182ad09b6f3f1", "step": 40, "value": 0.8241631644040197, "stage": "debug", "created_at": 1788870780.0032246}, {"event_id": "5441800786c5476d997376052d9bc3dd", "step": 41, "value": 0.9929543313477648, "stage": "debug", "created_at": 1788871121.534562}, {"event_id": "85c8627ce09247edb3f200ac1b792032", "step": 42, "value": 0.9779298795324202, "stage": "debug", "created_at": 1788871231.4034631}], "maximize": true, "elapsed_seconds": 28317.655415296555, "node_count": 43, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp6-20260908/xixian.gp6.the-icml-2013-whale-challenge-right-whale-redux.yaml", "note": ""}, {"id": "xixian.gp6-draft.aerial-cactus-identification", "experiment_id": "mlebench-gp6-20260908", "family": "MLEBench", "method": "gp6_draft", "dataset": "aerial-cactus-identification", "status": "archived", "official_score": 0.99999, "medal": "none", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 1.0, "silver": 1.0, "bronze": 1.0}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp6-gp6-draft-logs-with-private-scores", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp6-gp6-draft-logs-with-private-scores/logs-7b2a3e058322.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp6-gp6-draft-logs-with-private-scores", "member": "gp6_gp6-draft_logs/private_scores/rechecked_private_grades.jsonl:23", "sha256": "7b2a3e05832281a42f745f697155c42c6ef59359301c708d7b3496df1e02188f"}, {"bundle_id": "gp6-gp6-draft-logs-with-private-scores", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp6-gp6-draft-logs-with-private-scores/logs-7b2a3e058322.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp6-gp6-draft-logs-with-private-scores", "member": "gp6_gp6-draft_logs/runs/gp6_draft/01_aerial-cactus-identification/logs/journal.json", "sha256": "7b2a3e05832281a42f745f697155c42c6ef59359301c708d7b3496df1e02188f"}], "alternate_scores": [], "journal_ref": "gp6-gp6-draft-logs-with-private-scores:gp6_gp6-draft_logs/runs/gp6_draft/01_aerial-cactus-identification/logs/journal.json", "metrics": [{"event_id": "b66892c8132548968b92949907e802a2", "step": 3, "value": 0.9999387182690267, "stage": "debug", "created_at": 1788847014.5337555}, {"event_id": "9bb500de375746f385df7f398073ef7f", "step": 4, "value": 0.9994001461333586, "stage": "debug", "created_at": 1788847034.4514966}, {"event_id": "c164a17fa0ac46ca97d9a29de6276def", "step": 6, "value": 0.9999316473000684, "stage": "improve", "created_at": 1788847531.9148784}, {"event_id": "4c8346c54e164bc2bb387e70a580ece2", "step": 7, "value": 0.9998998279397554, "stage": "improve", "created_at": 1788847786.1057262}, {"event_id": "ac743954bc4841cfb96db7a4722c8f27", "step": 8, "value": 0.9998302967449972, "stage": "debug", "created_at": 1788847668.8599048}, {"event_id": "a9c2f93a767e4deb985fcd6f05d2d6e4", "step": 10, "value": 0.999948146227638, "stage": "debug", "created_at": 1788848868.5402305}, {"event_id": "4e8008bfcf364efbb0481e152f844653", "step": 11, "value": 0.999833158768339, "stage": "improve", "created_at": 1788848385.7214475}, {"event_id": "e1f50331937d4f7a800ebdb347f5344d", "step": 13, "value": 0.9991046757563549, "stage": "improve", "created_at": 1788848406.0163548}, {"event_id": "6095c5f6fd1f4a638dde5148669a27fa", "step": 14, "value": 0.9999377677828958, "stage": "evolution", "created_at": 1788850367.1154468}, {"event_id": "166eb720bd534af498838247e55b91cc", "step": 15, "value": 0.9995555144800522, "stage": "evolution", "created_at": 1788849516.400697}, {"event_id": "1d4e4f6663d04ca79ee6bdedc07e7a56", "step": 16, "value": 0.9996068971759307, "stage": "debug", "created_at": 1788849763.4066763}, {"event_id": "09d03c5745694666bd91aff62664eb17", "step": 17, "value": 0.999960395268484, "stage": "evolution", "created_at": 1788851235.5023348}, {"event_id": "ceda38f20ac34c2d806b03a3eb520200", "step": 18, "value": 0.9999457126034511, "stage": "evolution", "created_at": 1788851712.2828846}, {"event_id": "b08841b898fc41f8bb5b1c6cb16491b4", "step": 19, "value": 0.999926533620942, "stage": "evolution", "created_at": 1788851656.6778328}, {"event_id": "639692007862484097609d5b13d89d73", "step": 20, "value": 0.9999787870931247, "stage": "improve", "created_at": 1788852738.536717}, {"event_id": "b30af9b225ce4f19a8bb4d57b1248e6d", "step": 21, "value": 0.999987, "stage": "improve", "created_at": 1788852228.0199351}, {"event_id": "91389a096f8246aeb891340b58385287", "step": 23, "value": 0.9999958617963051, "stage": "improve", "created_at": 1788853656.5929937}, {"event_id": "d5cf511f105d4d3181ec63d0c68caff7", "step": 25, "value": 0.999994986407062, "stage": "debug", "created_at": 1788854714.184764}, {"event_id": "bcdf28f5ef2c44f3b04934fc8f4b8d34", "step": 30, "value": 0.9999853571253873, "stage": "debug", "created_at": 1788857408.706003}, {"event_id": "0536e6780f3044f4adc000a2aaa1bfd1", "step": 31, "value": 0.9999885403589988, "stage": "debug", "created_at": 1788857099.6344864}, {"event_id": "f5190b9414a44cf4ba21d4884281a2ea", "step": 34, "value": 0.9999905033530591, "stage": "improve", "created_at": 1788859690.3952794}, {"event_id": "c824de128e4f420a8c4f762556386f9b", "step": 39, "value": 0.9999884873051051, "stage": "debug", "created_at": 1788863020.7093852}, {"event_id": "e58c267630264707b6ee55317b09ad79", "step": 40, "value": 0.9999927050896403, "stage": "debug", "created_at": 1788862744.431576}, {"event_id": "ef7776f83180411c9cb84e337698e825", "step": 41, "value": 0.9999914848500893, "stage": "fusion", "created_at": 1788865010.3908534}, {"event_id": "802d4ba18a0f4efd97d4a8694c943f8f", "step": 43, "value": 0.9999877976044894, "stage": "evolution", "created_at": 1788865502.2574933}, {"event_id": "02848e6b7b654499ace7001cb8e43d3f", "step": 44, "value": 0.9999968432933353, "stage": "fusion", "created_at": 1788866623.302288}, {"event_id": "efe06e3e5bd94f1896d796730c911ca4", "step": 45, "value": 0.9999956230537842, "stage": "evolution", "created_at": 1788866722.4927962}, {"event_id": "3df8c238587146179587e614bac62cc9", "step": 46, "value": 0.9999970024550159, "stage": "fusion", "created_at": 1788868207.2479506}, {"event_id": "7e2b11a7a5f44934922a1bbb20db1b20", "step": 47, "value": 0.9995780988521461, "stage": "fusion_draft", "created_at": 1788870603.016301}, {"event_id": "5afa3e3a25e246c889c9500a0dfbb23e", "step": 48, "value": 0.9999847470056118, "stage": "improve", "created_at": 1788869358.0096586}, {"event_id": "f096956baded4f4a9a9bcf47a75e2f68", "step": 53, "value": 0.9983756224150154, "stage": "debug", "created_at": 1788872275.1817322}, {"event_id": "3481b1b84a634db797c287a8486bbebd", "step": 54, "value": 0.9999021849294082, "stage": "improve", "created_at": 1788872757.6902628}, {"event_id": "7f5efee542934150b8bbd5b6ceef7744", "step": 55, "value": 0.9999964645155208, "stage": "improve", "created_at": 1788873123.6666098}], "maximize": true, "elapsed_seconds": 28662.23260641098, "node_count": 56, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp6-20260908/xixian.gp6-draft.aerial-cactus-identification.yaml", "note": ""}, {"id": "xixian.gp6-draft.aptos2019-blindness-detection", "experiment_id": "mlebench-gp6-20260908", "family": "MLEBench", "method": "gp6_draft", "dataset": "aptos2019-blindness-detection", "status": "archived", "official_score": 0.91039, "medal": "none", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.930508, "silver": 0.919654, "bronze": 0.914492}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp6-gp6-draft-logs-with-private-scores", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp6-gp6-draft-logs-with-private-scores/logs-7b2a3e058322.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp6-gp6-draft-logs-with-private-scores", "member": "gp6_gp6-draft_logs/private_scores/rechecked_private_grades.jsonl:24", "sha256": "7b2a3e05832281a42f745f697155c42c6ef59359301c708d7b3496df1e02188f"}, {"bundle_id": "gp6-gp6-draft-logs-with-private-scores", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp6-gp6-draft-logs-with-private-scores/logs-7b2a3e058322.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp6-gp6-draft-logs-with-private-scores", "member": "gp6_gp6-draft_logs/runs/gp6_draft/02_aptos2019-blindness-detection/logs/journal.json", "sha256": "7b2a3e05832281a42f745f697155c42c6ef59359301c708d7b3496df1e02188f"}], "alternate_scores": [], "journal_ref": "gp6-gp6-draft-logs-with-private-scores:gp6_gp6-draft_logs/runs/gp6_draft/02_aptos2019-blindness-detection/logs/journal.json", "metrics": [{"event_id": "e977fbf1e0fe462280ea800b5b93a43a", "step": 2, "value": 0.915277934015781, "stage": "draft", "created_at": 1788847027.1373882}, {"event_id": "8f1a6dced22d48efa21057bc4687848c", "step": 3, "value": 0.9176555221944467, "stage": "debug", "created_at": 1788847212.8697417}, {"event_id": "398006f7c4b54492bd823372b18025a4", "step": 4, "value": 0.8827376569193623, "stage": "draft", "created_at": 1788845613.9389706}, {"event_id": "431f07be737e45679ff23aadf3046cf5", "step": 6, "value": 0.9144569540271804, "stage": "improve", "created_at": 1788848386.7315838}, {"event_id": "8c62e47c88a74668a6e83c648e0fdaa0", "step": 7, "value": 0.91134314126084, "stage": "improve", "created_at": 1788848323.4061494}, {"event_id": "0e00db3f99b74b88bb3a94dd65aabb8d", "step": 8, "value": 0.9286164806928154, "stage": "debug", "created_at": 1788849308.0548148}, {"event_id": "b051ae5002a64439b24df0342a61393e", "step": 12, "value": 0.9119001802750714, "stage": "debug", "created_at": 1788850844.3562086}, {"event_id": "461a195834b64a5f84a770247ab48976", "step": 13, "value": 0.9091149490731955, "stage": "improve", "created_at": 1788854294.8301573}, {"event_id": "df611ee42e3e4785b79a33e268638c16", "step": 15, "value": 0.9138286929442131, "stage": "improve", "created_at": 1788855758.2226393}, {"event_id": "42a928887997475aa216c5feee6bc513", "step": 17, "value": 0.9164185699016597, "stage": "debug", "created_at": 1788858220.9058788}, {"event_id": "06c3ee768fce4d248a898961b0846f7b", "step": 19, "value": 0.9209011771614805, "stage": "improve", "created_at": 1788861933.2743952}, {"event_id": "e1b30bc520b44102b57bbcaff51ace83", "step": 20, "value": 0.9162387034857815, "stage": "improve", "created_at": 1788862107.913855}, {"event_id": "164b73d20c324820baaae1583c023c6a", "step": 21, "value": 0.9186207059633396, "stage": "debug", "created_at": 1788853992.1427336}, {"event_id": "c6c16a0182684a3dadc0cc5a4b3ec5e8", "step": 23, "value": 0.9135643883184532, "stage": "evolution", "created_at": 1788862438.3146043}, {"event_id": "4f96275b3a8840f8ba6813971e0eca20", "step": 27, "value": 0.9287223775292864, "stage": "fusion", "created_at": 1788864555.549764}, {"event_id": "8f8ad663b43a4c418cefdfa2ffe1bf75", "step": 28, "value": 0.9086494065201065, "stage": "debug", "created_at": 1788865500.4936724}, {"event_id": "7be42bf183c840acb99a90ef03278a51", "step": 30, "value": 0.9117467537574088, "stage": "debug", "created_at": 1788866641.9013822}, {"event_id": "c7591bab34c04ba8b498397a22d20e0b", "step": 31, "value": 0.9126804405722128, "stage": "improve", "created_at": 1788866029.5367284}, {"event_id": "99450069b665415ba7ae1e2eb62d8413", "step": 32, "value": 0.9132105033587271, "stage": "improve", "created_at": 1788866563.0495768}, {"event_id": "ede701b1e0a24538a4e0b7185416a46c", "step": 33, "value": 0.9225390421050618, "stage": "improve", "created_at": 1788867992.744371}, {"event_id": "d0e7d9722b7f4c83b2ad10ea5a8fad40", "step": 34, "value": 0.9077467188238744, "stage": "improve", "created_at": 1788868696.8631425}, {"event_id": "c59ce036344c4aa5801aa29615defd1d", "step": 36, "value": 0.9263677561006038, "stage": "improve", "created_at": 1788869045.563686}, {"event_id": "ce0faa248bf44a55b2e123de45fc827d", "step": 37, "value": 0.9225659243065992, "stage": "evolution", "created_at": 1788869983.6407065}, {"event_id": "3a3e2c394c7749dfa60b6cc620d079ba", "step": 39, "value": 0.9220004816044776, "stage": "evolution", "created_at": 1788870152.8280568}, {"event_id": "0dff8ae4d0154b3095680c72ed9e30c8", "step": 42, "value": 0.9161882819159965, "stage": "debug", "created_at": 1788871576.7478473}, {"event_id": "400f47bbfb23437d851090a6189ffa52", "step": 43, "value": 0.9288521043700741, "stage": "evolution", "created_at": 1788871085.8476605}, {"event_id": "d80ea2d4a79a41e09c6b8e5c5c60ee7e", "step": 45, "value": 0.9259675335617592, "stage": "improve", "created_at": 1788872768.4499624}, {"event_id": "1949b7a402aa42a28e1f6af9045ab1e1", "step": 46, "value": 0.9204159198012399, "stage": "evolution", "created_at": 1788872660.9094653}], "maximize": true, "elapsed_seconds": 28681.23322725296, "node_count": 47, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp6-20260908/xixian.gp6-draft.aptos2019-blindness-detection.yaml", "note": ""}, {"id": "xixian.gp6-draft.denoising-dirty-documents", "experiment_id": "mlebench-gp6-20260908", "family": "MLEBench", "method": "gp6_draft", "dataset": "denoising-dirty-documents", "status": "archived", "official_score": 0.0122, "medal": "gold", "valid_submission": true, "score_maximize": false, "thresholds": {"gold": 0.01794, "silver": 0.02609, "bronze": 0.04517}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp6-gp6-draft-logs-with-private-scores", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp6-gp6-draft-logs-with-private-scores/logs-7b2a3e058322.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp6-gp6-draft-logs-with-private-scores", "member": "gp6_gp6-draft_logs/private_scores/rechecked_private_grades.jsonl:25", "sha256": "7b2a3e05832281a42f745f697155c42c6ef59359301c708d7b3496df1e02188f"}, {"bundle_id": "gp6-gp6-draft-logs-with-private-scores", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp6-gp6-draft-logs-with-private-scores/logs-7b2a3e058322.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp6-gp6-draft-logs-with-private-scores", "member": "gp6_gp6-draft_logs/runs/gp6_draft/03_denoising-dirty-documents/logs/journal.json", "sha256": "7b2a3e05832281a42f745f697155c42c6ef59359301c708d7b3496df1e02188f"}], "alternate_scores": [], "journal_ref": "gp6-gp6-draft-logs-with-private-scores:gp6_gp6-draft_logs/runs/gp6_draft/03_denoising-dirty-documents/logs/journal.json", "metrics": [{"event_id": "b6ee1548f26e4b2296fb00cbae0b7682", "step": 1, "value": 0.022177848809213113, "stage": "draft", "created_at": 1788845741.0669167}, {"event_id": "591f1b28b5a1491a80cb32577c6b9324", "step": 2, "value": 0.015742634741331772, "stage": "draft", "created_at": 1788847169.2320125}, {"event_id": "b9fa142e2eed47b59fe19350438e2249", "step": 3, "value": 0.03058180011609633, "stage": "draft", "created_at": 1788846437.082453}, {"event_id": "927635bbb37e4311aa27d12dd747f764", "step": 5, "value": 0.39530403298120126, "stage": "improve", "created_at": 1788848009.0521626}, {"event_id": "3fe82f5a6abc49379a4bf4cef20f6703", "step": 7, "value": 0.016538258265727974, "stage": "debug", "created_at": 1788848206.9529083}, {"event_id": "e4b3063c75a5467d999770f7a6145b56", "step": 12, "value": 0.1052079180064139, "stage": "debug", "created_at": 1788849101.0935879}, {"event_id": "82728c8cec8a488287f8b39c69e38272", "step": 13, "value": 0.01414706165128663, "stage": "improve", "created_at": 1788849100.931357}, {"event_id": "f752c5dadbd84612981f7a09c2dab884", "step": 14, "value": 0.016387181289267402, "stage": "debug", "created_at": 1788849232.312702}, {"event_id": "278a207744bf4eb9be8ee2d2e2510b75", "step": 15, "value": 0.015426005531724313, "stage": "improve", "created_at": 1788849804.118163}, {"event_id": "a1096867155348dd958ded022445e6ad", "step": 16, "value": 0.014112725473697728, "stage": "improve", "created_at": 1788850493.382879}, {"event_id": "7751b51bdf274b86bc4ded1f8b899b65", "step": 17, "value": 0.16709726916904546, "stage": "improve", "created_at": 1788850862.6136363}, {"event_id": "a0b6230c6d87411abcc1795f17ab385e", "step": 18, "value": 0.012043742178136606, "stage": "improve", "created_at": 1788851968.144067}, {"event_id": "6bca979c68714ecbb9c4a17f6e6c4a1e", "step": 19, "value": 0.016438687263804097, "stage": "improve", "created_at": 1788850737.0753403}, {"event_id": "ceb10d82e9d449128f29b4527fa5768b", "step": 20, "value": 0.03805588853845721, "stage": "improve", "created_at": 1788853189.1035929}, {"event_id": "8afb10bdfbbb45b9824f2db62b02a2b5", "step": 23, "value": 0.013069337051189671, "stage": "debug", "created_at": 1788854090.353629}, {"event_id": "b1b9a3404e874f15bbbd7a251073ebae", "step": 24, "value": 0.015450707603272532, "stage": "improve", "created_at": 1788854414.5842173}, {"event_id": "72b3b96fc68245c09e98b2bc356849ca", "step": 26, "value": 0.01386352727500405, "stage": "improve", "created_at": 1788855620.883395}, {"event_id": "cca21dae0aba4ca5894586ad1999c305", "step": 28, "value": 0.01622473740837648, "stage": "debug", "created_at": 1788855597.0507522}, {"event_id": "68d4c885221c404489839ed7bff5036d", "step": 29, "value": 0.012204816232920858, "stage": "improve", "created_at": 1788855980.545929}, {"event_id": "8b8ff631ec9d44418f092e224ee3ad1c", "step": 31, "value": 0.015313408990423445, "stage": "evolution", "created_at": 1788858115.9150424}, {"event_id": "03bccf6044c04799b275be1f969e834e", "step": 32, "value": 0.014816896398137613, "stage": "evolution", "created_at": 1788858302.2289975}, {"event_id": "d70fa12842834ed892cc1f38b8ab0822", "step": 33, "value": 0.01634721776981433, "stage": "debug", "created_at": 1788859349.3928437}, {"event_id": "d9bac6508e2643ea9a886ac5c939e961", "step": 34, "value": 0.01678437478360088, "stage": "evolution", "created_at": 1788859906.9954636}, {"event_id": "499c7105bcd3490bb6389026614f22cd", "step": 35, "value": 0.012095819456173787, "stage": "fusion", "created_at": 1788860370.4635894}, {"event_id": "0f277e7018b14623bd9b5befc69897a8", "step": 36, "value": 0.0123869483122498, "stage": "fusion", "created_at": 1788862049.182248}, {"event_id": "5cf9587221ec4265b13125fb6237ee74", "step": 37, "value": 0.026587192850977017, "stage": "evolution", "created_at": 1788859889.6850548}, {"event_id": "b91e321f4ab64e6cb16db9ab57b4756a", "step": 38, "value": 0.01237091985304118, "stage": "fusion", "created_at": 1788862024.4601789}, {"event_id": "5eb6a978837641bbaf99fa7329d5c312", "step": 39, "value": 0.015847011469119335, "stage": "fusion", "created_at": 1788863618.1659362}, {"event_id": "7b3362cd9a2b45f3a41c8e08e0ba3301", "step": 41, "value": 0.06536135866672908, "stage": "evolution", "created_at": 1788863794.2195241}, {"event_id": "a48c941408c44fd6ad0ce9b17fb3a743", "step": 42, "value": 0.016177978162317627, "stage": "evolution", "created_at": 1788865373.9631088}, {"event_id": "6bf0b544ac074a63a49a03b5fb31c392", "step": 43, "value": 0.013740484144200257, "stage": "improve", "created_at": 1788865988.5371485}, {"event_id": "d9b949d35244477a8f12cb5cc028b0eb", "step": 44, "value": 0.024595132579856457, "stage": "debug", "created_at": 1788865591.86262}, {"event_id": "0cc52f6be68e428e977f288bfa7b7f7e", "step": 45, "value": 0.016275973547275967, "stage": "fusion", "created_at": 1788867129.816767}, {"event_id": "1325ccfa8ab54aa68a68b09fbc33fbc2", "step": 46, "value": 0.18666726593481342, "stage": "fusion_draft", "created_at": 1788867748.2967916}, {"event_id": "3353edbe18fa42cab46ec472264a5534", "step": 47, "value": 0.014389473118166752, "stage": "fusion", "created_at": 1788867603.6329439}, {"event_id": "5a4ed7da0b014139bb8cda7889e5c9f9", "step": 48, "value": 0.08863911032676697, "stage": "fusion_draft", "created_at": 1788868700.231606}, {"event_id": "e48e4436482e449f9b6cf73da9688399", "step": 50, "value": 0.016051484501195385, "stage": "evolution", "created_at": 1788868678.0263033}, {"event_id": "6d07bc0c964a428abe935fb77075ef6b", "step": 51, "value": 0.016602401085042958, "stage": "debug", "created_at": 1788869484.8532403}, {"event_id": "5d267fa9d24949f5b518c0320c8e5f9d", "step": 52, "value": 0.017257640633275385, "stage": "evolution", "created_at": 1788870345.2346056}], "maximize": false, "elapsed_seconds": 28720.6819126606, "node_count": 55, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp6-20260908/xixian.gp6-draft.denoising-dirty-documents.yaml", "note": ""}, {"id": "xixian.gp6-draft.detecting-insults-in-social-commentary", "experiment_id": "mlebench-gp6-20260908", "family": "MLEBench", "method": "gp6_draft", "dataset": "detecting-insults-in-social-commentary", "status": "archived", "official_score": 0.95466, "medal": "gold", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.83321, "silver": 0.82307, "bronze": 0.79111}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp6-gp6-draft-logs-with-private-scores", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp6-gp6-draft-logs-with-private-scores/logs-7b2a3e058322.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp6-gp6-draft-logs-with-private-scores", "member": "gp6_gp6-draft_logs/private_scores/rechecked_private_grades.jsonl:26", "sha256": "7b2a3e05832281a42f745f697155c42c6ef59359301c708d7b3496df1e02188f"}, {"bundle_id": "gp6-gp6-draft-logs-with-private-scores", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp6-gp6-draft-logs-with-private-scores/logs-7b2a3e058322.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp6-gp6-draft-logs-with-private-scores", "member": "gp6_gp6-draft_logs/runs/gp6_draft/04_detecting-insults-in-social-commentary/logs/journal.json", "sha256": "7b2a3e05832281a42f745f697155c42c6ef59359301c708d7b3496df1e02188f"}], "alternate_scores": [], "journal_ref": "gp6-gp6-draft-logs-with-private-scores:gp6_gp6-draft_logs/runs/gp6_draft/04_detecting-insults-in-social-commentary/logs/journal.json", "metrics": [{"event_id": "d68b3d9258fc4c338ec1feb7f9234662", "step": 3, "value": 0.9466681216353849, "stage": "draft", "created_at": 1788845642.8403459}, {"event_id": "b265523f112b49199f6d4543c3a7f4c7", "step": 7, "value": 0.8535646733595228, "stage": "improve", "created_at": 1788847546.5011342}, {"event_id": "f55d207221a745f8be64cb999d4495f5", "step": 8, "value": 0.8797077302231942, "stage": "debug", "created_at": 1788847142.8560574}, {"event_id": "4524656588c848ae959ba72ac7657dcd", "step": 10, "value": 0.9448149341795374, "stage": "debug", "created_at": 1788849020.7565525}, {"event_id": "f39ec61f355843f6bb784aade6177f65", "step": 11, "value": 0.958162374508948, "stage": "improve", "created_at": 1788849454.0695782}, {"event_id": "ade68ac138ab46ab997c21161f1e1854", "step": 12, "value": 0.9502691692128619, "stage": "improve", "created_at": 1788849777.5482466}, {"event_id": "3318674ce005452aa57f997f8d05a3c7", "step": 13, "value": 0.8841117415975557, "stage": "improve", "created_at": 1788849313.3011043}, {"event_id": "ea2d13d7fa7f4ff0a531ea1b13348f50", "step": 15, "value": 0.9613196566273825, "stage": "debug", "created_at": 1788855158.6254864}, {"event_id": "3e2b1040ef734ddaa4ddaebe576e47aa", "step": 16, "value": 0.9569838498472283, "stage": "improve", "created_at": 1788854072.5842566}, {"event_id": "8465c130340a438bade0153d0a4ba64f", "step": 18, "value": 0.9564964353266405, "stage": "improve", "created_at": 1788859374.9771497}, {"event_id": "35ca7e2716b446a2a2a83b0c735c938e", "step": 19, "value": 0.9134584606430962, "stage": "debug", "created_at": 1788860873.1765394}], "maximize": true, "elapsed_seconds": 28691.86981844902, "node_count": 20, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp6-20260908/xixian.gp6-draft.detecting-insults-in-social-commentary.yaml", "note": ""}, {"id": "xixian.gp6-draft.dog-breed-identification", "experiment_id": "mlebench-gp6-20260908", "family": "MLEBench", "method": "gp6_draft", "dataset": "dog-breed-identification", "status": "archived", "official_score": 0.25681, "medal": "none", "valid_submission": true, "score_maximize": false, "thresholds": {"gold": 0.0005, "silver": 0.00539, "bronze": 0.04598}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp6-gp6-draft-logs-with-private-scores", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp6-gp6-draft-logs-with-private-scores/logs-7b2a3e058322.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp6-gp6-draft-logs-with-private-scores", "member": "gp6_gp6-draft_logs/private_scores/rechecked_private_grades.jsonl:27", "sha256": "7b2a3e05832281a42f745f697155c42c6ef59359301c708d7b3496df1e02188f"}, {"bundle_id": "gp6-gp6-draft-logs-with-private-scores", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp6-gp6-draft-logs-with-private-scores/logs-7b2a3e058322.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp6-gp6-draft-logs-with-private-scores", "member": "gp6_gp6-draft_logs/runs/gp6_draft/05_dog-breed-identification/logs/journal.json", "sha256": "7b2a3e05832281a42f745f697155c42c6ef59359301c708d7b3496df1e02188f"}], "alternate_scores": [], "journal_ref": "gp6-gp6-draft-logs-with-private-scores:gp6_gp6-draft_logs/runs/gp6_draft/05_dog-breed-identification/logs/journal.json", "metrics": [{"event_id": "7a3be4c3ddbc49faa1008ba6fb2ac119", "step": 3, "value": 0.19441127316954263, "stage": "debug", "created_at": 1788846972.455268}, {"event_id": "ceb66428e43e4eef89d9d84e185d6f1b", "step": 4, "value": 0.3103472885576004, "stage": "draft", "created_at": 1788846099.9441395}, {"event_id": "65f817b2ff084df39c36360938bb1bf1", "step": 5, "value": 0.6214025414938534, "stage": "debug", "created_at": 1788846947.708268}, {"event_id": "3e01d496ec7646b48015dcb1c342797d", "step": 8, "value": 0.1955331894189862, "stage": "improve", "created_at": 1788849091.0308826}, {"event_id": "7b72601922b74fd0bfda175f90f42013", "step": 10, "value": 0.19396676021815415, "stage": "debug", "created_at": 1788849187.2465553}, {"event_id": "21b236161773458783e9f9ccf658c5e2", "step": 11, "value": 0.4013812767857492, "stage": "debug", "created_at": 1788849042.2670255}, {"event_id": "628a4d75fccf41e6ad68e8326f54baf0", "step": 12, "value": 0.18358393349540889, "stage": "debug", "created_at": 1788851637.3106496}, {"event_id": "123fcd053633418c8f984b1357d0c2bf", "step": 13, "value": 0.18225835926295525, "stage": "improve", "created_at": 1788852165.9497964}, {"event_id": "951783ecf8c14f9d8df6e0d4563b8775", "step": 16, "value": 0.18075372243245824, "stage": "improve", "created_at": 1788854392.9922836}, {"event_id": "839eb977f77c48eba8e9fd680aaa3af2", "step": 17, "value": 0.18199669105499836, "stage": "improve", "created_at": 1788854953.7947934}, {"event_id": "8951dd7b61954ea9a4a2bacfa184fd2e", "step": 25, "value": 0.1973925438246746, "stage": "debug", "created_at": 1788860212.859558}, {"event_id": "39a748c17cd54fd08c89288e48aef3d3", "step": 30, "value": 0.2112883022659003, "stage": "debug", "created_at": 1788866833.6068118}, {"event_id": "3f0fa162608d4b40ad4d73baf275817c", "step": 31, "value": 0.20462792237357688, "stage": "improve", "created_at": 1788866604.4825683}], "maximize": false, "elapsed_seconds": 28753.955464601517, "node_count": 34, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp6-20260908/xixian.gp6-draft.dog-breed-identification.yaml", "note": ""}, {"id": "xixian.gp6-draft.dogs-vs-cats-redux-kernels-edition", "experiment_id": "mlebench-gp6-20260908", "family": "MLEBench", "method": "gp6_draft", "dataset": "dogs-vs-cats-redux-kernels-edition", "status": "archived", "official_score": 0.00344, "medal": "gold", "valid_submission": true, "score_maximize": false, "thresholds": {"gold": 0.03882, "silver": 0.05038, "bronze": 0.06127}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp6-gp6-draft-logs-with-private-scores", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp6-gp6-draft-logs-with-private-scores/logs-7b2a3e058322.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp6-gp6-draft-logs-with-private-scores", "member": "gp6_gp6-draft_logs/private_scores/rechecked_private_grades.jsonl:28", "sha256": "7b2a3e05832281a42f745f697155c42c6ef59359301c708d7b3496df1e02188f"}, {"bundle_id": "gp6-gp6-draft-logs-with-private-scores", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp6-gp6-draft-logs-with-private-scores/logs-7b2a3e058322.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp6-gp6-draft-logs-with-private-scores", "member": "gp6_gp6-draft_logs/runs/gp6_draft/06_dogs-vs-cats-redux-kernels-edition/logs/journal.json", "sha256": "7b2a3e05832281a42f745f697155c42c6ef59359301c708d7b3496df1e02188f"}], "alternate_scores": [], "journal_ref": "gp6-gp6-draft-logs-with-private-scores:gp6_gp6-draft_logs/runs/gp6_draft/06_dogs-vs-cats-redux-kernels-edition/logs/journal.json", "metrics": [{"event_id": "a12f8eab773b4095b42c42fe6deea566", "step": 2, "value": 0.042081403774484404, "stage": "draft", "created_at": 1788846116.653117}, {"event_id": "29abf2fc381d464490e66765a24a4697", "step": 3, "value": 0.006680378757995629, "stage": "draft", "created_at": 1788845616.395012}, {"event_id": "3a5cdbcb337c46538dbb12b1a70109d6", "step": 5, "value": 0.0076856445089379605, "stage": "debug", "created_at": 1788846965.0246112}, {"event_id": "7b875d67bb7d4d7c9c05edd798f6670c", "step": 6, "value": 0.012951813638728207, "stage": "draft", "created_at": 1788847701.2246678}, {"event_id": "4c2b63be5dda4875bc8f4235ea43c148", "step": 7, "value": 0.014386730439489667, "stage": "debug", "created_at": 1788847525.248807}, {"event_id": "e6e5de9d07114b9996f8ae9efc5334fd", "step": 8, "value": 0.006098348250910467, "stage": "improve", "created_at": 1788848776.4132943}, {"event_id": "7ab605cdbe8b48998e4fba60d134fa47", "step": 9, "value": 0.00831575243844921, "stage": "improve", "created_at": 1788848643.4723496}, {"event_id": "29facd9c2c69488582619408da91e057", "step": 10, "value": 0.005924891444141434, "stage": "improve", "created_at": 1788850961.3595562}, {"event_id": "5d8f145c2f2b47f0831fbd7f9729655c", "step": 11, "value": 0.008284707259915224, "stage": "improve", "created_at": 1788848401.3921392}, {"event_id": "f4eadc2835044f51b03b1d3b533c22b8", "step": 12, "value": 0.0050649539753564515, "stage": "improve", "created_at": 1788851729.6948097}, {"event_id": "82a84eabb34d40a1ad5bc6aa975a80cd", "step": 13, "value": 0.0045657779528125355, "stage": "improve", "created_at": 1788852369.4745052}, {"event_id": "880166b4449e4c118f1839bbd4491ee9", "step": 16, "value": 0.0035816360255242993, "stage": "improve", "created_at": 1788853246.1881442}, {"event_id": "eff641058f804ec382df681fa2515642", "step": 18, "value": 0.020430516483637404, "stage": "improve", "created_at": 1788855756.4125333}, {"event_id": "52631e6eb0464344822ed5348e4588e0", "step": 19, "value": 0.005719387269639721, "stage": "improve", "created_at": 1788851366.3321712}, {"event_id": "809c7466e92944c1865f3c0fc8e45322", "step": 21, "value": 0.009034493229105161, "stage": "debug", "created_at": 1788856711.4854822}, {"event_id": "775fe7c72b884129a58a7a00eb115f80", "step": 24, "value": 0.0037196709643026234, "stage": "improve", "created_at": 1788857617.1211505}, {"event_id": "43d562606b4641fbae4de395cbc2b41b", "step": 26, "value": 0.004866727194941891, "stage": "debug", "created_at": 1788860463.0182996}, {"event_id": "8317bc93f7e04fae9a916d8c27700410", "step": 27, "value": 0.0019465961399219263, "stage": "fusion", "created_at": 1788860821.9447103}, {"event_id": "7c597cb67a094e63b22d2e6a4d2afcfe", "step": 31, "value": 0.007443389137580182, "stage": "debug", "created_at": 1788862966.1820695}, {"event_id": "b571390e3c304349911c768571941f11", "step": 34, "value": 0.0059944288680831076, "stage": "fusion_draft", "created_at": 1788869627.2332194}], "maximize": false, "elapsed_seconds": 28707.909589767456, "node_count": 37, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp6-20260908/xixian.gp6-draft.dogs-vs-cats-redux-kernels-edition.yaml", "note": ""}, {"id": "xixian.gp6-draft.histopathologic-cancer-detection", "experiment_id": "mlebench-gp6-20260908", "family": "MLEBench", "method": "gp6_draft", "dataset": "histopathologic-cancer-detection", "status": "archived", "official_score": 0.99742, "medal": "gold", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.9835, "silver": 0.9798, "bronze": 0.9738}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp6-gp6-draft-logs-with-private-scores", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp6-gp6-draft-logs-with-private-scores/logs-7b2a3e058322.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp6-gp6-draft-logs-with-private-scores", "member": "gp6_gp6-draft_logs/private_scores/rechecked_private_grades.jsonl:29", "sha256": "7b2a3e05832281a42f745f697155c42c6ef59359301c708d7b3496df1e02188f"}, {"bundle_id": "gp6-gp6-draft-logs-with-private-scores", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp6-gp6-draft-logs-with-private-scores/logs-7b2a3e058322.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp6-gp6-draft-logs-with-private-scores", "member": "gp6_gp6-draft_logs/runs/gp6_draft/07_histopathologic-cancer-detection/logs/journal.json", "sha256": "7b2a3e05832281a42f745f697155c42c6ef59359301c708d7b3496df1e02188f"}], "alternate_scores": [], "journal_ref": "gp6-gp6-draft-logs-with-private-scores:gp6_gp6-draft_logs/runs/gp6_draft/07_histopathologic-cancer-detection/logs/journal.json", "metrics": [{"event_id": "712f6a11a5ee4e809c8afe9278251d51", "step": 2, "value": 0.9900376898804657, "stage": "debug", "created_at": 1788848087.2454438}, {"event_id": "650e24eebf0a4968a978db28d66dbba2", "step": 3, "value": 0.9981250909941473, "stage": "draft", "created_at": 1788846496.6244009}, {"event_id": "4759b3207ec4477ab31d0c3f2a0b591c", "step": 4, "value": 0.9824540782642671, "stage": "draft", "created_at": 1788845902.2745144}], "maximize": true, "elapsed_seconds": 28686.476960659027, "node_count": 6, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp6-20260908/xixian.gp6-draft.histopathologic-cancer-detection.yaml", "note": ""}, {"id": "xixian.gp6-draft.jigsaw-toxic-comment-classification-challenge", "experiment_id": "mlebench-gp6-20260908", "family": "MLEBench", "method": "gp6_draft", "dataset": "jigsaw-toxic-comment-classification-challenge", "status": "archived", "official_score": 0.98733, "medal": "silver", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.9874, "silver": 0.98668, "bronze": 0.98639}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp6-gp6-draft-logs-with-private-scores", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp6-gp6-draft-logs-with-private-scores/logs-7b2a3e058322.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp6-gp6-draft-logs-with-private-scores", "member": "gp6_gp6-draft_logs/private_scores/rechecked_private_grades.jsonl:30", "sha256": "7b2a3e05832281a42f745f697155c42c6ef59359301c708d7b3496df1e02188f"}, {"bundle_id": "gp6-gp6-draft-logs-with-private-scores", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp6-gp6-draft-logs-with-private-scores/logs-7b2a3e058322.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp6-gp6-draft-logs-with-private-scores", "member": "gp6_gp6-draft_logs/runs/gp6_draft/08_jigsaw-toxic-comment-classification-challenge/logs/journal.json", "sha256": "7b2a3e05832281a42f745f697155c42c6ef59359301c708d7b3496df1e02188f"}], "alternate_scores": [], "journal_ref": "gp6-gp6-draft-logs-with-private-scores:gp6_gp6-draft_logs/runs/gp6_draft/08_jigsaw-toxic-comment-classification-challenge/logs/journal.json", "metrics": [{"event_id": "c63ffc7ae01a40adac5c6e3f7f397d86", "step": 8, "value": 0.9913102602736706, "stage": "debug", "created_at": 1788847911.841934}, {"event_id": "2cbc05f410414b3a9e127eb91e5b45ea", "step": 9, "value": 0.9910163175197727, "stage": "debug", "created_at": 1788847001.7548165}, {"event_id": "ad46b6f6dbcf4054b3598b98fc6aceb1", "step": 10, "value": 0.9918164980803518, "stage": "improve", "created_at": 1788852771.3439524}, {"event_id": "fa2278fe67a24d6983dce625b6a06916", "step": 12, "value": 0.9916796976724513, "stage": "debug", "created_at": 1788861174.963812}], "maximize": true, "elapsed_seconds": 28706.460527658463, "node_count": 14, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp6-20260908/xixian.gp6-draft.jigsaw-toxic-comment-classification-challenge.yaml", "note": ""}, {"id": "xixian.gp6-draft.leaf-classification", "experiment_id": "mlebench-gp6-20260908", "family": "MLEBench", "method": "gp6_draft", "dataset": "leaf-classification", "status": "archived", "official_score": 0.02129, "medal": "none", "valid_submission": true, "score_maximize": false, "thresholds": {"gold": 0.0, "silver": 0.00791, "bronze": 0.01526}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp6-gp6-draft-logs-with-private-scores", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp6-gp6-draft-logs-with-private-scores/logs-7b2a3e058322.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp6-gp6-draft-logs-with-private-scores", "member": "gp6_gp6-draft_logs/private_scores/rechecked_private_grades.jsonl:31", "sha256": "7b2a3e05832281a42f745f697155c42c6ef59359301c708d7b3496df1e02188f"}, {"bundle_id": "gp6-gp6-draft-logs-with-private-scores", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp6-gp6-draft-logs-with-private-scores/logs-7b2a3e058322.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp6-gp6-draft-logs-with-private-scores", "member": "gp6_gp6-draft_logs/runs/gp6_draft/09_leaf-classification/logs/journal.json", "sha256": "7b2a3e05832281a42f745f697155c42c6ef59359301c708d7b3496df1e02188f"}], "alternate_scores": [], "journal_ref": "gp6-gp6-draft-logs-with-private-scores:gp6_gp6-draft_logs/runs/gp6_draft/09_leaf-classification/logs/journal.json", "metrics": [{"event_id": "0ff538b287464e898f04c705844a7d31", "step": 4, "value": 0.0012412568179257706, "stage": "draft", "created_at": 1788847659.851388}, {"event_id": "9c5be6b4ebc04c6691599f5d87129af1", "step": 5, "value": 0.009743669619433156, "stage": "debug", "created_at": 1788847617.5007935}, {"event_id": "2be3a68ebc1f4323a94406e684f121ae", "step": 6, "value": 0.03154123651736869, "stage": "debug", "created_at": 1788847186.473139}, {"event_id": "de453355f2d9447a9ca90e2ec9f986b2", "step": 7, "value": 0.006841375318890339, "stage": "improve", "created_at": 1788848113.4367032}, {"event_id": "b484b058ccfe404cb19031c5bca1f706", "step": 8, "value": 0.0017689088715964847, "stage": "draft", "created_at": 1788848822.7652779}, {"event_id": "ac8dd0bc2d7e4b05b553c7cf33582f94", "step": 9, "value": 0.0016892438750616267, "stage": "improve", "created_at": 1788848767.9405358}, {"event_id": "81f874c62927491888624da409006039", "step": 10, "value": 0.02515111211844136, "stage": "improve", "created_at": 1788849020.435247}, {"event_id": "fa9e6237871d4f44a7844dce5f5ae54a", "step": 11, "value": 0.00031205003495087745, "stage": "improve", "created_at": 1788849670.5466511}, {"event_id": "f6ff1db516c04dc3942473830b9a7dfe", "step": 12, "value": 0.004114849829926352, "stage": "improve", "created_at": 1788850479.403508}, {"event_id": "4df0044a3f734432b69c425a63133494", "step": 15, "value": 0.016478513980134942, "stage": "debug", "created_at": 1788854890.2261298}, {"event_id": "238cb1813b60465ab04d24162f0bf7c9", "step": 16, "value": 0.0017876379162826074, "stage": "improve", "created_at": 1788851324.6199408}, {"event_id": "02f61a32e2dc44479b314cec1f2a3c0c", "step": 17, "value": 0.05755420076714583, "stage": "improve", "created_at": 1788856093.640263}, {"event_id": "36c028524a8c48c8ad3e17bdbea0f02d", "step": 18, "value": 0.0009001018942520378, "stage": "improve", "created_at": 1788860161.3961487}, {"event_id": "6ef67c0ff7c84403a707d2b900b3ae88", "step": 19, "value": 0.0007922112174362696, "stage": "improve", "created_at": 1788862863.4055517}], "maximize": false, "elapsed_seconds": 28757.523383140564, "node_count": 21, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp6-20260908/xixian.gp6-draft.leaf-classification.yaml", "note": ""}, {"id": "xixian.gp6-draft.mlsp-2013-birds", "experiment_id": "mlebench-gp6-20260908", "family": "MLEBench", "method": "gp6_draft", "dataset": "mlsp-2013-birds", "status": "archived", "official_score": 0.82808, "medal": "none", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.93527, "silver": 0.90038, "bronze": 0.87372}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp6-gp6-draft-logs-with-private-scores", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp6-gp6-draft-logs-with-private-scores/logs-7b2a3e058322.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp6-gp6-draft-logs-with-private-scores", "member": "gp6_gp6-draft_logs/private_scores/rechecked_private_grades.jsonl:32", "sha256": "7b2a3e05832281a42f745f697155c42c6ef59359301c708d7b3496df1e02188f"}, {"bundle_id": "gp6-gp6-draft-logs-with-private-scores", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp6-gp6-draft-logs-with-private-scores/logs-7b2a3e058322.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp6-gp6-draft-logs-with-private-scores", "member": "gp6_gp6-draft_logs/runs/gp6_draft/10_mlsp-2013-birds/logs/journal.json", "sha256": "7b2a3e05832281a42f745f697155c42c6ef59359301c708d7b3496df1e02188f"}], "alternate_scores": [], "journal_ref": "gp6-gp6-draft-logs-with-private-scores:gp6_gp6-draft_logs/runs/gp6_draft/10_mlsp-2013-birds/logs/journal.json", "metrics": [{"event_id": "ea73ff531435433396d61b0cd866a063", "step": 4, "value": 0.7691961110260606, "stage": "debug", "created_at": 1788847684.0147219}, {"event_id": "2c6118fcd92a4f8886ba36d52682f6b1", "step": 5, "value": 0.6041299937160105, "stage": "debug", "created_at": 1788847656.6062126}, {"event_id": "8db0de62ff95479593ced8400d813108", "step": 7, "value": 0.7834427704984618, "stage": "improve", "created_at": 1788848181.404944}, {"event_id": "6bc40290b3c7494c88aeebd90d4acfc0", "step": 8, "value": 0.7856826846128748, "stage": "debug", "created_at": 1788848099.2374692}, {"event_id": "57d48b7eba49419aba23bde7f76ce9f4", "step": 10, "value": 0.8269669567076745, "stage": "improve", "created_at": 1788848650.4982672}, {"event_id": "f3b1db04ecca486a867bfd28b0bbe335", "step": 11, "value": 0.5460907994241738, "stage": "debug", "created_at": 1788848769.3949878}, {"event_id": "6b279bd39a11458fa91bbdf139d9fc73", "step": 12, "value": 0.756613266140246, "stage": "improve", "created_at": 1788848927.7775903}, {"event_id": "4141fe233f0c4b8ebc1d83549810546d", "step": 13, "value": 0.7584678898405015, "stage": "improve", "created_at": 1788849423.7976954}, {"event_id": "0e2d279b7db74cca98a9f19e510e441d", "step": 14, "value": 0.8102060801622719, "stage": "improve", "created_at": 1788849526.2652597}, {"event_id": "0326f3a008e344229c20e2ef88b90cd4", "step": 15, "value": 0.8170355343191694, "stage": "improve", "created_at": 1788849696.009653}, {"event_id": "d0c86c08188142eb802e94024fcabd66", "step": 16, "value": 0.8514195663349149, "stage": "evolution", "created_at": 1788850020.8746712}, {"event_id": "34fcef0101ef4f49aeb82bfd799eb36d", "step": 18, "value": 0.8278428708107262, "stage": "evolution", "created_at": 1788850484.1762912}, {"event_id": "81c46d7b9a304506a9f6008a9061e35b", "step": 19, "value": 0.8143853975412895, "stage": "debug", "created_at": 1788850495.516417}, {"event_id": "f52768efdc83407083327b485028e65c", "step": 20, "value": 0.6957939711620302, "stage": "improve", "created_at": 1788850895.4636204}, {"event_id": "4aa0b86af6c64a38b2521b8a327d37d9", "step": 23, "value": 0.8247255546396751, "stage": "evolution", "created_at": 1788851531.9063737}, {"event_id": "86cd87ac97fb449a9c9fa30d755c997a", "step": 24, "value": 0.7434246563798319, "stage": "debug", "created_at": 1788851890.198529}, {"event_id": "2c05599311bd43d1b67a4167f347341f", "step": 25, "value": 0.800334228874816, "stage": "debug", "created_at": 1788851929.6992135}, {"event_id": "2fe621b260de48b7b8e3fa8fb81674dc", "step": 26, "value": 0.8345109640254242, "stage": "evolution", "created_at": 1788852582.1051874}, {"event_id": "5f6232f71fc2470b883e0f8a9f7be7c5", "step": 27, "value": 0.7867082322898359, "stage": "evolution", "created_at": 1788852335.8957617}, {"event_id": "4ad679f1d4b54f0ca765da397cfffeb0", "step": 28, "value": 0.8276787405158964, "stage": "evolution", "created_at": 1788852578.867763}, {"event_id": "45d8c46578cf494199f3153450f43361", "step": 29, "value": 0.8623391189988071, "stage": "evolution", "created_at": 1788853482.9484725}, {"event_id": "eb1421f16e804f4b96b0a014ee584a8a", "step": 30, "value": 0.7322581437709154, "stage": "evolution", "created_at": 1788853452.5610366}, {"event_id": "d484eb5fce294e2c96e963bfcae5db33", "step": 31, "value": 0.8316988057095656, "stage": "evolution", "created_at": 1788853599.5004609}, {"event_id": "6e20c46aff4e45d8808cc1a853ade713", "step": 32, "value": 0.851936280953834, "stage": "improve", "created_at": 1788854269.912933}, {"event_id": "7a2d071d198d4ba7b606439c717f5e28", "step": 34, "value": 0.7025350296302669, "stage": "improve", "created_at": 1788854494.9840333}, {"event_id": "86975b2e91a54bdea70f86e9f9db2b78", "step": 35, "value": 0.8542286104172829, "stage": "debug", "created_at": 1788854856.680097}, {"event_id": "f9870b1553c3484b84bf594e02264c80", "step": 36, "value": 0.8480210219080705, "stage": "evolution", "created_at": 1788854976.4764652}, {"event_id": "a28d60c2e36845c4a6ca14ee1c950529", "step": 37, "value": 0.8633546457303494, "stage": "evolution", "created_at": 1788855737.8969438}, {"event_id": "1f237eb445084fa0980e4fcbce3375e2", "step": 38, "value": 0.8565199941778185, "stage": "evolution", "created_at": 1788855828.5655007}, {"event_id": "9fc6c57345cc4b50b775e5b94051f963", "step": 39, "value": 0.8590074960048967, "stage": "evolution", "created_at": 1788855981.4912891}, {"event_id": "a0e495e4544647799d41024665fd55ac", "step": 40, "value": 0.8355695191882276, "stage": "improve", "created_at": 1788856585.503471}, {"event_id": "41c5129d086c4dea8891f522eb6b0b96", "step": 42, "value": 0.8335591577691082, "stage": "evolution", "created_at": 1788857275.8290641}, {"event_id": "d8c7609fd9cf41ab8c167f0cfc9fce4e", "step": 43, "value": 0.8618846135482446, "stage": "improve", "created_at": 1788857052.9935002}, {"event_id": "8a512efa92eb46f8a28b7a8a52c13ea8", "step": 44, "value": 0.8621785744076886, "stage": "debug", "created_at": 1788857772.1784797}, {"event_id": "4a542c04af6f4f60b31538198f87f51c", "step": 45, "value": 0.8611830260214569, "stage": "evolution", "created_at": 1788858347.8417807}, {"event_id": "e504d2a791a94ca095c924379156cfae", "step": 46, "value": 0.6883875570121595, "stage": "evolution", "created_at": 1788858532.059316}, {"event_id": "9ee385bdcc684759aae98225bbfe4b08", "step": 47, "value": 0.7518074745730186, "stage": "evolution", "created_at": 1788859104.4677308}, {"event_id": "59b753ed4a67477691e41a1690173c48", "step": 48, "value": 0.8734796118141975, "stage": "evolution", "created_at": 1788859492.331608}, {"event_id": "955993d363384fcd9b9a63a4a3084dd4", "step": 49, "value": 0.8611509618383446, "stage": "evolution", "created_at": 1788859699.0560231}, {"event_id": "d2ddf1c56f92400493a919138677b489", "step": 50, "value": 0.7916772381802106, "stage": "evolution", "created_at": 1788860380.072475}, {"event_id": "6c025725749e41f38049cd1ed89277fa", "step": 51, "value": 0.8787772148098846, "stage": "improve", "created_at": 1788860385.6814709}, {"event_id": "8e384c4d2d404bab81f8bc359a46bedc", "step": 52, "value": 0.8597263947700144, "stage": "improve", "created_at": 1788861048.804842}, {"event_id": "739793d0f15b4969815b5efaf6efa8a0", "step": 53, "value": 0.800711635642551, "stage": "improve", "created_at": 1788861521.1165082}, {"event_id": "798a1a386bbb473a88a34baaaae8f925", "step": 54, "value": 0.8691368791189763, "stage": "improve", "created_at": 1788862082.7409678}, {"event_id": "fd6fcfdcdc3446d8acbc33a9ad9c9693", "step": 56, "value": 0.840274738396215, "stage": "improve", "created_at": 1788862585.1927965}, {"event_id": "e3c44eeb594c4b17b0a04ac179fa5e16", "step": 57, "value": 0.8830702156882813, "stage": "improve", "created_at": 1788862599.9031997}, {"event_id": "93386d3f128446eabda931bae3221303", "step": 59, "value": 0.7223981317597472, "stage": "evolution", "created_at": 1788863961.2812293}, {"event_id": "74a058636713496c810d47befd6293f4", "step": 60, "value": 0.8726206752207429, "stage": "improve", "created_at": 1788864065.7649283}, {"event_id": "ab1ae784f6384be48a68f2b19877c8ed", "step": 62, "value": 0.8617255722369462, "stage": "improve", "created_at": 1788864692.3543975}, {"event_id": "d1cee0cc320942c2bf9a4c2a30870818", "step": 63, "value": 0.8742553711885228, "stage": "debug", "created_at": 1788865138.9583805}, {"event_id": "b8dfa39ec3344cec916e3776012004ea", "step": 64, "value": 0.86529156466529, "stage": "evolution", "created_at": 1788865527.5647936}, {"event_id": "788681b25b7544c2b2c6b27a7a7fc2b3", "step": 65, "value": 0.8803530442595094, "stage": "improve", "created_at": 1788865391.6141255}, {"event_id": "c311b48165ef46eba6ccfa52edc5c975", "step": 66, "value": 0.8387711844698015, "stage": "evolution", "created_at": 1788866256.0958664}, {"event_id": "85e11dbf4d0f416aa9a4b329e7dfd8de", "step": 67, "value": 0.875075849054878, "stage": "evolution", "created_at": 1788866953.3256392}, {"event_id": "79f73e76a72d4d1ba6c96310549f07e8", "step": 68, "value": 0.852201861602178, "stage": "evolution", "created_at": 1788867123.5118291}, {"event_id": "195ddd96d0c442928803a0438caabbb8", "step": 69, "value": 0.8693059852420348, "stage": "evolution", "created_at": 1788867563.7992055}, {"event_id": "f1fa995e6db14542b6185e97098e3090", "step": 70, "value": 0.8792977380529667, "stage": "evolution", "created_at": 1788867857.4678752}, {"event_id": "25391c1ab32746e7a021b46373d24e2f", "step": 71, "value": 0.8566201688182239, "stage": "evolution", "created_at": 1788869312.6016295}, {"event_id": "350b7fbc13f94c87b713e359d0399f09", "step": 72, "value": 0.8560686988305184, "stage": "evolution", "created_at": 1788869178.921094}, {"event_id": "66eed2a753f74382a68b5f08b04a9df8", "step": 73, "value": 0.8756652693871998, "stage": "evolution", "created_at": 1788869609.3565292}, {"event_id": "00eabcdf45cc405aa66632acca2a331d", "step": 74, "value": 0.8457247216290013, "stage": "fusion", "created_at": 1788870729.5099666}, {"event_id": "f8b128d569ff4f9aa82ab97fb73674a6", "step": 75, "value": 0.8673820102299186, "stage": "fusion", "created_at": 1788870539.345858}, {"event_id": "3ec2bcd4ecef4b14b35e09c363550bec", "step": 76, "value": 0.8767433082271969, "stage": "fusion", "created_at": 1788871489.0403237}, {"event_id": "603837a514a74d90bc7648bec19f1af5", "step": 77, "value": 0.8662860284166264, "stage": "fusion", "created_at": 1788871764.1848662}, {"event_id": "aade920fa5624aea96046930e00dd3bf", "step": 78, "value": 0.8109501602769399, "stage": "evolution", "created_at": 1788872028.8771126}, {"event_id": "943d4d0a8ecc48fa97c03dbdedc5a38d", "step": 79, "value": 0.8727741524840684, "stage": "evolution", "created_at": 1788872552.181848}], "maximize": true, "elapsed_seconds": 28694.653610229492, "node_count": 80, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp6-20260908/xixian.gp6-draft.mlsp-2013-birds.yaml", "note": ""}, {"id": "xixian.gp6-draft.new-york-city-taxi-fare-prediction", "experiment_id": "mlebench-gp6-20260908", "family": "MLEBench", "method": "gp6_draft", "dataset": "new-york-city-taxi-fare-prediction", "status": "archived", "official_score": 4.98928, "medal": "none", "valid_submission": true, "score_maximize": false, "thresholds": {"gold": 2.83377, "silver": 2.88191, "bronze": 2.92371}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp6-gp6-draft-logs-with-private-scores", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp6-gp6-draft-logs-with-private-scores/logs-7b2a3e058322.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp6-gp6-draft-logs-with-private-scores", "member": "gp6_gp6-draft_logs/private_scores/rechecked_private_grades.jsonl:33", "sha256": "7b2a3e05832281a42f745f697155c42c6ef59359301c708d7b3496df1e02188f"}, {"bundle_id": "gp6-gp6-draft-logs-with-private-scores", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp6-gp6-draft-logs-with-private-scores/logs-7b2a3e058322.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp6-gp6-draft-logs-with-private-scores", "member": "gp6_gp6-draft_logs/runs/gp6_draft/11_new-york-city-taxi-fare-prediction/logs/journal.json", "sha256": "7b2a3e05832281a42f745f697155c42c6ef59359301c708d7b3496df1e02188f"}], "alternate_scores": [], "journal_ref": "gp6-gp6-draft-logs-with-private-scores:gp6_gp6-draft_logs/runs/gp6_draft/11_new-york-city-taxi-fare-prediction/logs/journal.json", "metrics": [{"event_id": "0c871545948b478abd17c2accf003009", "step": 3, "value": 3.8781694026838665, "stage": "draft", "created_at": 1788847125.4846032}, {"event_id": "5d758d91eebc4bc0aadb1bcd9ed339e5", "step": 4, "value": 3.3502689082027652, "stage": "debug", "created_at": 1788847390.2171495}, {"event_id": "db3a53ca1d854c549941c92421e09063", "step": 5, "value": 2.8232378590645735, "stage": "improve", "created_at": 1788848013.3852093}, {"event_id": "1da7f639807b4129ab4098590aa31e6b", "step": 6, "value": 2.974121903010205, "stage": "improve", "created_at": 1788848159.1325474}, {"event_id": "1c99363294b14b8088f4252a89a1358a", "step": 7, "value": 3.6003263858654635, "stage": "debug", "created_at": 1788847475.5768025}, {"event_id": "717a3bd673754cc8ac3ec8131efbc564", "step": 9, "value": 2.855642532390727, "stage": "improve", "created_at": 1788849294.6373842}, {"event_id": "a91602e1fee74aa6a82f06c5c0a559c1", "step": 12, "value": 2.9226076871054776, "stage": "debug", "created_at": 1788854403.1204026}, {"event_id": "127c59b5905f460a86283062231ec07d", "step": 13, "value": 2.7636344620531856, "stage": "debug", "created_at": 1788854109.9152215}, {"event_id": "2b4702b437a54beebd2893ad0fdc830c", "step": 14, "value": 2.8981535823986535, "stage": "improve", "created_at": 1788857884.1471622}, {"event_id": "7bc379acf0384256a5903ccad1468577", "step": 15, "value": 2.8333152777041106, "stage": "improve", "created_at": 1788854312.0502515}, {"event_id": "1a31582e41fb4eb28bddf833e920d9a9", "step": 16, "value": 3.18401644018431, "stage": "improve", "created_at": 1788858769.3456466}, {"event_id": "10c462c3c565453c814fd6abbdd95d83", "step": 17, "value": 2.7823454907154495, "stage": "improve", "created_at": 1788860225.412251}, {"event_id": "473813a341df4707ae92156843aa5795", "step": 18, "value": 3.0384505840993508, "stage": "evolution", "created_at": 1788865119.6504307}, {"event_id": "3dfeead158c247ecb3e8da08b4c8b06d", "step": 19, "value": 2.7630144435591912, "stage": "evolution", "created_at": 1788865627.9703999}, {"event_id": "b93c0f0e9a38474d8738a42a5c18d216", "step": 20, "value": 3.097621189668567, "stage": "improve", "created_at": 1788862950.7698421}, {"event_id": "8ff5059afde44a96bae6c22cbcf77b3e", "step": 21, "value": 3.6604700403141237, "stage": "fusion_draft", "created_at": 1788872449.3494005}], "maximize": false, "elapsed_seconds": 28663.226336479187, "node_count": 22, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp6-20260908/xixian.gp6-draft.new-york-city-taxi-fare-prediction.yaml", "note": ""}, {"id": "xixian.gp6-draft.nomad2018-predict-transparent-conductors", "experiment_id": "mlebench-gp6-20260908", "family": "MLEBench", "method": "gp6_draft", "dataset": "nomad2018-predict-transparent-conductors", "status": "archived", "official_score": 0.06064, "medal": "silver", "valid_submission": true, "score_maximize": false, "thresholds": {"gold": 0.05589, "silver": 0.06229, "bronze": 0.06582}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp6-gp6-draft-logs-with-private-scores", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp6-gp6-draft-logs-with-private-scores/logs-7b2a3e058322.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp6-gp6-draft-logs-with-private-scores", "member": "gp6_gp6-draft_logs/private_scores/rechecked_private_grades.jsonl:34", "sha256": "7b2a3e05832281a42f745f697155c42c6ef59359301c708d7b3496df1e02188f"}, {"bundle_id": "gp6-gp6-draft-logs-with-private-scores", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp6-gp6-draft-logs-with-private-scores/logs-7b2a3e058322.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp6-gp6-draft-logs-with-private-scores", "member": "gp6_gp6-draft_logs/runs/gp6_draft/12_nomad2018-predict-transparent-conductors/logs/journal.json", "sha256": "7b2a3e05832281a42f745f697155c42c6ef59359301c708d7b3496df1e02188f"}], "alternate_scores": [], "journal_ref": "gp6-gp6-draft-logs-with-private-scores:gp6_gp6-draft_logs/runs/gp6_draft/12_nomad2018-predict-transparent-conductors/logs/journal.json", "metrics": [{"event_id": "b89e9da5bb89495aa94e3a2e12959d2b", "step": 1, "value": 0.055799304014670426, "stage": "draft", "created_at": 1788846192.5890527}, {"event_id": "ab7fc385e73f477bbc7337c44858a978", "step": 2, "value": 0.0567933743959355, "stage": "draft", "created_at": 1788845642.572122}, {"event_id": "aa8e80ca6b1145d0951e08f3d8b19d46", "step": 3, "value": 0.09353827798445569, "stage": "draft", "created_at": 1788846769.09167}, {"event_id": "a238c49c7c5d4a3d83319ef2cdf10231", "step": 4, "value": 0.055799304014670426, "stage": "improve", "created_at": 1788851069.6043203}, {"event_id": "4d685462153141dab5ced7a41a604b6b", "step": 7, "value": 0.05576129816454463, "stage": "debug", "created_at": 1788853567.7634423}, {"event_id": "84c915f40c8f4922b2ff83922aca1e75", "step": 8, "value": 0.05525436192359284, "stage": "improve", "created_at": 1788856391.4283488}, {"event_id": "2e49d9b9739d4b42b91608d69eee4321", "step": 10, "value": 0.05776708471896698, "stage": "improve", "created_at": 1788861365.0549023}], "maximize": false, "elapsed_seconds": 28714.455404996872, "node_count": 12, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp6-20260908/xixian.gp6-draft.nomad2018-predict-transparent-conductors.yaml", "note": ""}, {"id": "xixian.gp6-draft.plant-pathology-2020-fgvc7", "experiment_id": "mlebench-gp6-20260908", "family": "MLEBench", "method": "gp6_draft", "dataset": "plant-pathology-2020-fgvc7", "status": "archived", "official_score": 0.99441, "medal": "gold", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.97836, "silver": 0.97465, "bronze": 0.97361}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp6-gp6-draft-logs-with-private-scores", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp6-gp6-draft-logs-with-private-scores/logs-7b2a3e058322.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp6-gp6-draft-logs-with-private-scores", "member": "gp6_gp6-draft_logs/private_scores/rechecked_private_grades.jsonl:35", "sha256": "7b2a3e05832281a42f745f697155c42c6ef59359301c708d7b3496df1e02188f"}, {"bundle_id": "gp6-gp6-draft-logs-with-private-scores", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp6-gp6-draft-logs-with-private-scores/logs-7b2a3e058322.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp6-gp6-draft-logs-with-private-scores", "member": "gp6_gp6-draft_logs/runs/gp6_draft/13_plant-pathology-2020-fgvc7/logs/journal.json", "sha256": "7b2a3e05832281a42f745f697155c42c6ef59359301c708d7b3496df1e02188f"}], "alternate_scores": [], "journal_ref": "gp6-gp6-draft-logs-with-private-scores:gp6_gp6-draft_logs/runs/gp6_draft/13_plant-pathology-2020-fgvc7/logs/journal.json", "metrics": [{"event_id": "25339fa27c444a6b81833f5ea939be99", "step": 1, "value": 0.9916160912054038, "stage": "draft", "created_at": 1788846280.7349513}, {"event_id": "22a0184521944d72849477dc1cf173ad", "step": 2, "value": 0.9748258445367369, "stage": "draft", "created_at": 1788845601.1282716}, {"event_id": "644413041d624afda60f602746b80617", "step": 3, "value": 0.9958240915095532, "stage": "draft", "created_at": 1788846989.2212412}, {"event_id": "5fdcb0a38b634730a5e5162133ac268c", "step": 4, "value": 0.9866348521257959, "stage": "improve", "created_at": 1788847747.029386}, {"event_id": "5f9bcbe3ee1041068e6c102461e609a4", "step": 6, "value": 0.9963274063972958, "stage": "improve", "created_at": 1788848038.1136696}, {"event_id": "2ec178a1f169406ca4eea7674bbe5435", "step": 7, "value": 0.9899264273807796, "stage": "debug", "created_at": 1788848822.317259}, {"event_id": "2cce77cc77e64e55bc33318ae19a48f5", "step": 9, "value": 0.9902731564230616, "stage": "improve", "created_at": 1788848961.016218}, {"event_id": "990aa953de724661a1d0f09a3c521a37", "step": 11, "value": 0.9897293096871135, "stage": "debug", "created_at": 1788850140.7178183}, {"event_id": "79558f5c0a1949968e57b30ed659c90b", "step": 13, "value": 0.9900058591829123, "stage": "improve", "created_at": 1788849536.8564622}, {"event_id": "5857f24c661144649abff90f3a27f912", "step": 14, "value": 0.9965282618961014, "stage": "debug", "created_at": 1788851398.1874197}, {"event_id": "99ee7b090e3e46f19fbfbc5c52807ab8", "step": 15, "value": 0.9941790496337153, "stage": "debug", "created_at": 1788850900.7045755}, {"event_id": "b59b549df59849189b79f4f3779d4dbf", "step": 16, "value": 0.9919909063367367, "stage": "improve", "created_at": 1788853009.840991}, {"event_id": "a4fd43e4ddcc4991a4294b9472aab818", "step": 17, "value": 0.9944459468179744, "stage": "improve", "created_at": 1788852987.684388}, {"event_id": "d4bdd990d292444aa6c6ede5abadd49f", "step": 21, "value": 0.9925017163203815, "stage": "debug", "created_at": 1788855140.2541926}, {"event_id": "62d4f0ded42342c1be0da695ff9fb6bf", "step": 24, "value": 0.9937539833957552, "stage": "evolution", "created_at": 1788856895.7820756}, {"event_id": "957d59ca96c3406ea4c836892798b881", "step": 25, "value": 0.9970646424153293, "stage": "debug", "created_at": 1788855783.60977}, {"event_id": "e5438279bfc043609e76ac25c802c848", "step": 26, "value": 0.9802051726145438, "stage": "debug", "created_at": 1788856827.2201567}, {"event_id": "365b842ea4114477a74b0c8b18959edf", "step": 29, "value": 0.9964889877296288, "stage": "evolution", "created_at": 1788858372.1299298}, {"event_id": "2f9b6ba055714ad3ab1e13e5f7f3af74", "step": 30, "value": 0.9852553009016127, "stage": "improve", "created_at": 1788860260.0920966}, {"event_id": "2c456c082cc94205a7fdc97a4e06adce", "step": 31, "value": 0.9844584217213235, "stage": "debug", "created_at": 1788859748.1729684}, {"event_id": "613d69fb1c4f4d4e9452c02c2b8b12de", "step": 33, "value": 0.9797183219814567, "stage": "debug", "created_at": 1788860027.7677453}, {"event_id": "da6c059ed76a4cccb630c1a2d976b183", "step": 34, "value": 0.9972213697447975, "stage": "evolution", "created_at": 1788864163.5756762}, {"event_id": "87c18454d58b42f3a003aed808756eab", "step": 37, "value": 0.9954756807783902, "stage": "improve", "created_at": 1788865619.0510821}, {"event_id": "a4f38d32ccbf426a89e5e9352779fe83", "step": 38, "value": 0.9420637027091261, "stage": "debug", "created_at": 1788867932.5465536}, {"event_id": "ca3aa53ac1264245aaebce3755e9cc6d", "step": 39, "value": 0.9950344770946753, "stage": "debug", "created_at": 1788867974.8183851}, {"event_id": "bcfe43885b5641ec890022ff20d4d23e", "step": 40, "value": 0.9905262160776186, "stage": "fusion_draft", "created_at": 1788869665.3401818}, {"event_id": "23523244bf994953b434dde5a2485559", "step": 41, "value": 0.9959671647536952, "stage": "improve", "created_at": 1788871114.6579103}, {"event_id": "89dfa4bc78834a0fa621cb1043797ebb", "step": 44, "value": 0.9954843271679404, "stage": "evolution", "created_at": 1788872580.1152666}], "maximize": true, "elapsed_seconds": 28713.7074072361, "node_count": 45, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp6-20260908/xixian.gp6-draft.plant-pathology-2020-fgvc7.yaml", "note": ""}, {"id": "xixian.gp6-draft.random-acts-of-pizza", "experiment_id": "mlebench-gp6-20260908", "family": "MLEBench", "method": "gp6_draft", "dataset": "random-acts-of-pizza", "status": "archived", "official_score": 0.68939, "medal": "none", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.97908, "silver": 0.76482, "bronze": 0.6921}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp6-gp6-draft-logs-with-private-scores", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp6-gp6-draft-logs-with-private-scores/logs-7b2a3e058322.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp6-gp6-draft-logs-with-private-scores", "member": "gp6_gp6-draft_logs/private_scores/rechecked_private_grades.jsonl:36", "sha256": "7b2a3e05832281a42f745f697155c42c6ef59359301c708d7b3496df1e02188f"}, {"bundle_id": "gp6-gp6-draft-logs-with-private-scores", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp6-gp6-draft-logs-with-private-scores/logs-7b2a3e058322.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp6-gp6-draft-logs-with-private-scores", "member": "gp6_gp6-draft_logs/runs/gp6_draft/14_random-acts-of-pizza/logs/journal.json", "sha256": "7b2a3e05832281a42f745f697155c42c6ef59359301c708d7b3496df1e02188f"}], "alternate_scores": [], "journal_ref": "gp6-gp6-draft-logs-with-private-scores:gp6_gp6-draft_logs/runs/gp6_draft/14_random-acts-of-pizza/logs/journal.json", "metrics": [{"event_id": "8c1e4c496a06403680cfbbdf8fdcb1ff", "step": 4, "value": 0.6045911834644229, "stage": "debug", "created_at": 1788847147.48642}, {"event_id": "bd4ce8c6f435490194cde2cee4441bb0", "step": 5, "value": 0.6657730260501622, "stage": "debug", "created_at": 1788847270.5648224}, {"event_id": "3d51bc0f3ec04b9ba7cfb1d57d33b96a", "step": 7, "value": 0.6690515027697475, "stage": "improve", "created_at": 1788847721.2392557}, {"event_id": "33abb9f7c8154e2eb1f05a6100cd64fc", "step": 8, "value": 0.654003394014193, "stage": "draft", "created_at": 1788847735.5375593}, {"event_id": "5cd04da7b99d408a91bcab2dee6854ed", "step": 9, "value": 0.6920008398068445, "stage": "improve", "created_at": 1788848565.423585}, {"event_id": "ca8a09ed87624a0a97c4d2316f4b6a92", "step": 10, "value": 0.6714255721184128, "stage": "improve", "created_at": 1788848598.8921554}, {"event_id": "4357c18b62634cefa6d33081f3fff4d0", "step": 11, "value": 0.6505944759465887, "stage": "debug", "created_at": 1788847686.2321484}, {"event_id": "6a37c37262fe43c6851d6b75f9a54b84", "step": 13, "value": 0.6887062129556355, "stage": "improve", "created_at": 1788850726.2985523}, {"event_id": "e890f8f934dc4d3cae266d04c2f95b83", "step": 14, "value": 0.6922592419128215, "stage": "improve", "created_at": 1788850268.5964353}, {"event_id": "8e2fd9b970814e308ab882a570eebbce", "step": 15, "value": 0.690918780988065, "stage": "debug", "created_at": 1788852054.6663458}, {"event_id": "1c79be6daf3c4336b3d03aac99aae178", "step": 16, "value": 0.7011095140425394, "stage": "improve", "created_at": 1788852802.0313172}, {"event_id": "5a976c04194c41d098c2a96ce8292c92", "step": 17, "value": 0.6877372050582212, "stage": "improve", "created_at": 1788853902.7155678}, {"event_id": "adce8976768d4f3c984fb98406f2e716", "step": 18, "value": 0.7125017377444562, "stage": "improve", "created_at": 1788852492.816292}, {"event_id": "fc3d4008e4644ac09201abf63816c49b", "step": 20, "value": 0.6949781609975785, "stage": "improve", "created_at": 1788853315.4330862}, {"event_id": "73c266eaaebf4eec99970dbb877b4b76", "step": 21, "value": 0.690014373617145, "stage": "debug", "created_at": 1788861740.779431}, {"event_id": "f844bf3c4ec74ab2b54d82b03da59e77", "step": 22, "value": 0.7071026061317324, "stage": "improve", "created_at": 1788864255.1747108}], "maximize": true, "elapsed_seconds": 28713.290636062622, "node_count": 24, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp6-20260908/xixian.gp6-draft.random-acts-of-pizza.yaml", "note": ""}, {"id": "xixian.gp6-draft.ranzcr-clip-catheter-line-classification", "experiment_id": "mlebench-gp6-20260908", "family": "MLEBench", "method": "gp6_draft", "dataset": "ranzcr-clip-catheter-line-classification", "status": "archived", "official_score": 0.85394, "medal": "none", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.97357, "silver": 0.97152, "bronze": 0.9709}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp6-gp6-draft-logs-with-private-scores", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp6-gp6-draft-logs-with-private-scores/logs-7b2a3e058322.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp6-gp6-draft-logs-with-private-scores", "member": "gp6_gp6-draft_logs/private_scores/rechecked_private_grades.jsonl:37", "sha256": "7b2a3e05832281a42f745f697155c42c6ef59359301c708d7b3496df1e02188f"}, {"bundle_id": "gp6-gp6-draft-logs-with-private-scores", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp6-gp6-draft-logs-with-private-scores/logs-7b2a3e058322.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp6-gp6-draft-logs-with-private-scores", "member": "gp6_gp6-draft_logs/runs/gp6_draft/15_ranzcr-clip-catheter-line-classification/logs/journal.json", "sha256": "7b2a3e05832281a42f745f697155c42c6ef59359301c708d7b3496df1e02188f"}], "alternate_scores": [], "journal_ref": "gp6-gp6-draft-logs-with-private-scores:gp6_gp6-draft_logs/runs/gp6_draft/15_ranzcr-clip-catheter-line-classification/logs/journal.json", "metrics": [{"event_id": "e13dd737420a45189bc01e1ddf1ffb79", "step": 2, "value": 0.8199618295494217, "stage": "draft", "created_at": 1788847268.2797713}, {"event_id": "77b2d9ea7ed045f0aec64275a54cb12a", "step": 3, "value": 0.9321887648206659, "stage": "debug", "created_at": 1788847607.6365182}, {"event_id": "3ae66691e7d2474784aaffa59d68642c", "step": 5, "value": 0.8185272848808486, "stage": "improve", "created_at": 1788850822.3555748}], "maximize": true, "elapsed_seconds": 28652.11025118828, "node_count": 8, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp6-20260908/xixian.gp6-draft.ranzcr-clip-catheter-line-classification.yaml", "note": ""}, {"id": "xixian.gp6-draft.siim-isic-melanoma-classification", "experiment_id": "mlebench-gp6-20260908", "family": "MLEBench", "method": "gp6_draft", "dataset": "siim-isic-melanoma-classification", "status": "archived", "official_score": 0.89125, "medal": "none", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.9455, "silver": 0.9401, "bronze": 0.937}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp6-gp6-draft-logs-with-private-scores", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp6-gp6-draft-logs-with-private-scores/logs-7b2a3e058322.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp6-gp6-draft-logs-with-private-scores", "member": "gp6_gp6-draft_logs/private_scores/rechecked_private_grades.jsonl:38", "sha256": "7b2a3e05832281a42f745f697155c42c6ef59359301c708d7b3496df1e02188f"}, {"bundle_id": "gp6-gp6-draft-logs-with-private-scores", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp6-gp6-draft-logs-with-private-scores/logs-7b2a3e058322.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp6-gp6-draft-logs-with-private-scores", "member": "gp6_gp6-draft_logs/runs/gp6_draft/16_siim-isic-melanoma-classification/logs/journal.json", "sha256": "7b2a3e05832281a42f745f697155c42c6ef59359301c708d7b3496df1e02188f"}], "alternate_scores": [], "journal_ref": "gp6-gp6-draft-logs-with-private-scores:gp6_gp6-draft_logs/runs/gp6_draft/16_siim-isic-melanoma-classification/logs/journal.json", "metrics": [{"event_id": "e706705eb24e410e881acc133b0e2a3e", "step": 1, "value": 0.8925141733194494, "stage": "draft", "created_at": 1788846416.5031989}, {"event_id": "4653a7dc8eaa4b4398b5299a82569658", "step": 2, "value": 0.8489090838969353, "stage": "draft", "created_at": 1788845726.3177989}, {"event_id": "bd9831948b374cc1a2dd85d7a66cc1ba", "step": 4, "value": 0.8979731364320049, "stage": "improve", "created_at": 1788869204.1805341}, {"event_id": "fb456bf5a2f04c698dcbd0076f6a7a81", "step": 5, "value": 0.8720895171780282, "stage": "improve", "created_at": 1788869814.993387}, {"event_id": "a4c2fbf27e8248ea97e506b4a69503a3", "step": 6, "value": 0.8994719846854522, "stage": "improve", "created_at": 1788870435.4805892}, {"event_id": "04c1ff8800a140d5ad0a52cde8e76e48", "step": 7, "value": 0.8978662010595366, "stage": "improve", "created_at": 1788871832.7129292}, {"event_id": "d34b95769db14b838a276a580e0714a9", "step": 8, "value": 0.898790052556106, "stage": "improve", "created_at": 1788873614.5195858}], "maximize": true, "elapsed_seconds": 28709.547056674957, "node_count": 9, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp6-20260908/xixian.gp6-draft.siim-isic-melanoma-classification.yaml", "note": ""}, {"id": "xixian.gp6-draft.spooky-author-identification", "experiment_id": "mlebench-gp6-20260908", "family": "MLEBench", "method": "gp6_draft", "dataset": "spooky-author-identification", "status": "archived", "official_score": 0.19753, "medal": "silver", "valid_submission": true, "score_maximize": false, "thresholds": {"gold": 0.16506, "silver": 0.26996, "bronze": 0.29381}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp6-gp6-draft-logs-with-private-scores", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp6-gp6-draft-logs-with-private-scores/logs-7b2a3e058322.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp6-gp6-draft-logs-with-private-scores", "member": "gp6_gp6-draft_logs/private_scores/rechecked_private_grades.jsonl:39", "sha256": "7b2a3e05832281a42f745f697155c42c6ef59359301c708d7b3496df1e02188f"}, {"bundle_id": "gp6-gp6-draft-logs-with-private-scores", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp6-gp6-draft-logs-with-private-scores/logs-7b2a3e058322.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp6-gp6-draft-logs-with-private-scores", "member": "gp6_gp6-draft_logs/runs/gp6_draft/17_spooky-author-identification/logs/journal.json", "sha256": "7b2a3e05832281a42f745f697155c42c6ef59359301c708d7b3496df1e02188f"}], "alternate_scores": [], "journal_ref": "gp6-gp6-draft-logs-with-private-scores:gp6_gp6-draft_logs/runs/gp6_draft/17_spooky-author-identification/logs/journal.json", "metrics": [{"event_id": "1892576bb12a4e0eb6c6ebbcab43b37a", "step": 4, "value": 0.3324037398945726, "stage": "draft", "created_at": 1788846316.1816595}, {"event_id": "12c92fe2dc2949ca99973d02d777e3b9", "step": 5, "value": 0.541065514087677, "stage": "debug", "created_at": 1788847348.4977393}, {"event_id": "1ffb875ed9454b04ae8f53421438f3c0", "step": 6, "value": 0.3362531833257765, "stage": "debug", "created_at": 1788847116.392777}, {"event_id": "35f7764e06594834be9084951fe62319", "step": 9, "value": 0.29843032667748737, "stage": "improve", "created_at": 1788847860.9100497}, {"event_id": "efc0bb5d12c5431d8c30a61ddae6c42f", "step": 10, "value": 0.34210695089215, "stage": "debug", "created_at": 1788848731.454725}, {"event_id": "577beface2184901a2a4a7f05ea3938d", "step": 11, "value": 0.26548895476148626, "stage": "improve", "created_at": 1788849305.2215357}, {"event_id": "854d437943a44e82b186193ac40803d8", "step": 12, "value": 0.2616659826475432, "stage": "improve", "created_at": 1788849483.87376}, {"event_id": "0747e6162a6e4fb9ad7b10a98e91d069", "step": 13, "value": 0.24718231674091018, "stage": "improve", "created_at": 1788851545.6136312}, {"event_id": "2b8d59a109464a33bc005f363d60c845", "step": 14, "value": 0.2499831839244568, "stage": "improve", "created_at": 1788854445.7248483}, {"event_id": "f058d0bf6fb64e2db65214d0758088f0", "step": 15, "value": 0.23325235736044425, "stage": "improve", "created_at": 1788856143.1395133}, {"event_id": "e37879031cb64b738dd4a52d393a4e5d", "step": 16, "value": 0.21400282162041234, "stage": "improve", "created_at": 1788858304.6750286}, {"event_id": "acf81b6e5c004a2d9d5ec34cc4766519", "step": 17, "value": 0.27128694898371614, "stage": "improve", "created_at": 1788847890.9949389}, {"event_id": "cb0f4c64285c4cb19d8e6d98bb181969", "step": 18, "value": 0.2630216169648728, "stage": "improve", "created_at": 1788854285.3015172}, {"event_id": "aab79d13cac14ca79f6cb52234eedb54", "step": 19, "value": 0.2130957725729961, "stage": "improve", "created_at": 1788861702.5154552}], "maximize": false, "elapsed_seconds": 28715.242591142654, "node_count": 21, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp6-20260908/xixian.gp6-draft.spooky-author-identification.yaml", "note": ""}, {"id": "xixian.gp6-draft.tabular-playground-series-dec-2021", "experiment_id": "mlebench-gp6-20260908", "family": "MLEBench", "method": "gp6_draft", "dataset": "tabular-playground-series-dec-2021", "status": "archived", "official_score": 0.96346, "medal": "gold", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.9566, "silver": 0.95658, "bronze": 0.95658}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp6-gp6-draft-logs-with-private-scores", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp6-gp6-draft-logs-with-private-scores/logs-7b2a3e058322.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp6-gp6-draft-logs-with-private-scores", "member": "gp6_gp6-draft_logs/private_scores/rechecked_private_grades.jsonl:40", "sha256": "7b2a3e05832281a42f745f697155c42c6ef59359301c708d7b3496df1e02188f"}, {"bundle_id": "gp6-gp6-draft-logs-with-private-scores", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp6-gp6-draft-logs-with-private-scores/logs-7b2a3e058322.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp6-gp6-draft-logs-with-private-scores", "member": "gp6_gp6-draft_logs/runs/gp6_draft/18_tabular-playground-series-dec-2021/logs/journal.json", "sha256": "7b2a3e05832281a42f745f697155c42c6ef59359301c708d7b3496df1e02188f"}], "alternate_scores": [], "journal_ref": "gp6-gp6-draft-logs-with-private-scores:gp6_gp6-draft_logs/runs/gp6_draft/18_tabular-playground-series-dec-2021/logs/journal.json", "metrics": [{"event_id": "a2beb25e437f4d30ae88d4b4eb847d1c", "step": 8, "value": 0.9488527777777778, "stage": "debug", "created_at": 1788846754.051583}, {"event_id": "e7691943dd3543aa8e25da3ec07c9497", "step": 9, "value": 0.9507, "stage": "debug", "created_at": 1788847115.4016898}, {"event_id": "949eaa28102a49f9bac62210f72cca0d", "step": 12, "value": 0.9607222222222223, "stage": "debug", "created_at": 1788848487.838116}, {"event_id": "174950b524324af3b94fda4d6561e6d0", "step": 13, "value": 0.9592666666666667, "stage": "improve", "created_at": 1788847737.3017547}, {"event_id": "6909649173e2414f94fa93f29bc106ed", "step": 14, "value": 0.9619333333333333, "stage": "improve", "created_at": 1788849157.1079652}, {"event_id": "d6a8d8ec5f2243329493d95c8be76268", "step": 16, "value": 0.9509055555555556, "stage": "improve", "created_at": 1788848301.656102}, {"event_id": "99a6aa8c6f3c433fb6c55a5995a5725f", "step": 17, "value": 0.9610722222222222, "stage": "improve", "created_at": 1788850830.8700702}, {"event_id": "b382197dc1b545ef8e2393c7b02e4df4", "step": 19, "value": 0.9617611111111111, "stage": "improve", "created_at": 1788855822.0852273}, {"event_id": "e771f0cf71a94b669019cdc3021bc8a3", "step": 20, "value": 0.9623722222222222, "stage": "debug", "created_at": 1788850768.0901349}, {"event_id": "9498ea5ccaf7496db50ebd805494d6fb", "step": 21, "value": 0.9622361111111111, "stage": "improve", "created_at": 1788857167.6898332}, {"event_id": "2f319dfb60484d84be9f7ad8c430ec1f", "step": 23, "value": 0.9622638888888889, "stage": "improve", "created_at": 1788857719.2238686}, {"event_id": "354eac6c4e13407cbfddfb26e8dbb010", "step": 24, "value": 0.962575, "stage": "improve", "created_at": 1788859247.2194066}, {"event_id": "7c4d272fe6c1446cbc88d2e429af995c", "step": 25, "value": 0.9624833333333334, "stage": "debug", "created_at": 1788864109.4171312}, {"event_id": "0a5eca58b414419f996c022c77f16b25", "step": 31, "value": 0.9629277777777778, "stage": "improve", "created_at": 1788866387.694283}], "maximize": true, "elapsed_seconds": 28728.08117580414, "node_count": 32, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp6-20260908/xixian.gp6-draft.tabular-playground-series-dec-2021.yaml", "note": ""}, {"id": "xixian.gp6-draft.tabular-playground-series-may-2022", "experiment_id": "mlebench-gp6-20260908", "family": "MLEBench", "method": "gp6_draft", "dataset": "tabular-playground-series-may-2022", "status": "archived", "official_score": 0.99308, "medal": "none", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.99823, "silver": 0.99822, "bronze": 0.99818}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp6-gp6-draft-logs-with-private-scores", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp6-gp6-draft-logs-with-private-scores/logs-7b2a3e058322.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp6-gp6-draft-logs-with-private-scores", "member": "gp6_gp6-draft_logs/private_scores/rechecked_private_grades.jsonl:41", "sha256": "7b2a3e05832281a42f745f697155c42c6ef59359301c708d7b3496df1e02188f"}, {"bundle_id": "gp6-gp6-draft-logs-with-private-scores", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp6-gp6-draft-logs-with-private-scores/logs-7b2a3e058322.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp6-gp6-draft-logs-with-private-scores", "member": "gp6_gp6-draft_logs/runs/gp6_draft/19_tabular-playground-series-may-2022/logs/journal.json", "sha256": "7b2a3e05832281a42f745f697155c42c6ef59359301c708d7b3496df1e02188f"}], "alternate_scores": [], "journal_ref": "gp6-gp6-draft-logs-with-private-scores:gp6_gp6-draft_logs/runs/gp6_draft/19_tabular-playground-series-may-2022/logs/journal.json", "metrics": [{"event_id": "21e6a91a5513465cbd6bcaa02952292f", "step": 2, "value": 0.9845187070168153, "stage": "draft", "created_at": 1788847014.5179262}, {"event_id": "19d73b4146a94144b267daaded760d1a", "step": 3, "value": 0.9864290593408923, "stage": "draft", "created_at": 1788846302.2582908}, {"event_id": "20c92a5bdea5456ab5254d9c2d50b8f1", "step": 4, "value": 0.9681333529320232, "stage": "debug", "created_at": 1788847156.973866}, {"event_id": "37612f9771c447e3972c01a69a9b9172", "step": 5, "value": 0.9805178228847047, "stage": "improve", "created_at": 1788847739.271254}, {"event_id": "7415176caeb241c38cb42ff16bbdda34", "step": 6, "value": 0.9873210241437279, "stage": "improve", "created_at": 1788847659.8785546}, {"event_id": "e8d9d79c962c41ff888bf005570679b6", "step": 8, "value": 0.9872465982187193, "stage": "debug", "created_at": 1788848932.7797544}, {"event_id": "32a9e1bf55344a11b5a72845f1d3a239", "step": 9, "value": 0.9741091533372598, "stage": "improve", "created_at": 1788848418.1739492}, {"event_id": "47715191aab6431a99d93cc3ffb76efe", "step": 10, "value": 0.9911989792448705, "stage": "improve", "created_at": 1788847664.2148736}, {"event_id": "1d14db67d59f4ff58234ed10e88a0d08", "step": 11, "value": 0.9918424326902037, "stage": "improve", "created_at": 1788851809.3231814}, {"event_id": "f4bbafa624fb4176b815771a76bd9f68", "step": 12, "value": 0.9806701606079994, "stage": "improve", "created_at": 1788855082.1424158}, {"event_id": "bdc36a4545b241b9b129ee173c1139ab", "step": 14, "value": 0.9919195524902393, "stage": "improve", "created_at": 1788856312.8001764}, {"event_id": "90e6ddeafd12437093473ef802c29b68", "step": 15, "value": 0.9912175044222227, "stage": "improve", "created_at": 1788862701.5608606}], "maximize": true, "elapsed_seconds": 28712.1106069088, "node_count": 19, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp6-20260908/xixian.gp6-draft.tabular-playground-series-may-2022.yaml", "note": ""}, {"id": "xixian.gp6-draft.text-normalization-challenge-english-language", "experiment_id": "mlebench-gp6-20260908", "family": "MLEBench", "method": "gp6_draft", "dataset": "text-normalization-challenge-english-language", "status": "archived", "official_score": 0.996, "medal": "silver", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.99724, "silver": 0.99135, "bronze": 0.99038}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp6-gp6-draft-logs-with-private-scores", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp6-gp6-draft-logs-with-private-scores/logs-7b2a3e058322.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp6-gp6-draft-logs-with-private-scores", "member": "gp6_gp6-draft_logs/private_scores/rechecked_private_grades.jsonl:42", "sha256": "7b2a3e05832281a42f745f697155c42c6ef59359301c708d7b3496df1e02188f"}, {"bundle_id": "gp6-gp6-draft-logs-with-private-scores", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp6-gp6-draft-logs-with-private-scores/logs-7b2a3e058322.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp6-gp6-draft-logs-with-private-scores", "member": "gp6_gp6-draft_logs/runs/gp6_draft/20_text-normalization-challenge-english-language/logs/journal.json", "sha256": "7b2a3e05832281a42f745f697155c42c6ef59359301c708d7b3496df1e02188f"}], "alternate_scores": [], "journal_ref": "gp6-gp6-draft-logs-with-private-scores:gp6_gp6-draft_logs/runs/gp6_draft/20_text-normalization-challenge-english-language/logs/journal.json", "metrics": [{"event_id": "1b2dcbac1cc94977be107d854192a2d1", "step": 5, "value": 0.931011171390424, "stage": "debug", "created_at": 1788847666.1070454}, {"event_id": "115405ef168e4730a2a71c30ee423302", "step": 10, "value": 0.9903775476110925, "stage": "debug", "created_at": 1788848299.8329785}, {"event_id": "cee17575110b4a3cb44ad79dd8e2bdf4", "step": 11, "value": 0.9886370678339446, "stage": "debug", "created_at": 1788849873.918814}, {"event_id": "ce51e92e8cd2439c9c832d9662ab1478", "step": 12, "value": 0.994783304320393, "stage": "improve", "created_at": 1788851246.1739283}, {"event_id": "3c0c7863ff0843eda2aa33f8c321b96c", "step": 15, "value": 0.9954029981916206, "stage": "improve", "created_at": 1788868926.9873607}, {"event_id": "e196f026a0384f69b57bb4ecfc64aae7", "step": 16, "value": 0.9963381725791095, "stage": "debug", "created_at": 1788853833.859265}, {"event_id": "289538d7def04d2fa8a8c90fbc4bfff9", "step": 18, "value": 0.9943269842879435, "stage": "improve", "created_at": 1788872555.5790715}, {"event_id": "5e3905d663c1490da9cd92dc0683dfec", "step": 19, "value": 0.9872925715558526, "stage": "improve", "created_at": 1788870597.6926568}], "maximize": true, "elapsed_seconds": 28737.804578781128, "node_count": 20, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp6-20260908/xixian.gp6-draft.text-normalization-challenge-english-language.yaml", "note": ""}, {"id": "xixian.gp6-draft.text-normalization-challenge-russian-language", "experiment_id": "mlebench-gp6-20260908", "family": "MLEBench", "method": "gp6_draft", "dataset": "text-normalization-challenge-russian-language", "status": "archived", "official_score": 0.9809, "medal": "bronze", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.99012, "silver": 0.98232, "bronze": 0.97592}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp6-gp6-draft-logs-with-private-scores", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp6-gp6-draft-logs-with-private-scores/logs-7b2a3e058322.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp6-gp6-draft-logs-with-private-scores", "member": "gp6_gp6-draft_logs/private_scores/rechecked_private_grades.jsonl:43", "sha256": "7b2a3e05832281a42f745f697155c42c6ef59359301c708d7b3496df1e02188f"}, {"bundle_id": "gp6-gp6-draft-logs-with-private-scores", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp6-gp6-draft-logs-with-private-scores/logs-7b2a3e058322.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp6-gp6-draft-logs-with-private-scores", "member": "gp6_gp6-draft_logs/runs/gp6_draft/21_text-normalization-challenge-russian-language/logs/journal.json", "sha256": "7b2a3e05832281a42f745f697155c42c6ef59359301c708d7b3496df1e02188f"}], "alternate_scores": [], "journal_ref": "gp6-gp6-draft-logs-with-private-scores:gp6_gp6-draft_logs/runs/gp6_draft/21_text-normalization-challenge-russian-language/logs/journal.json", "metrics": [{"event_id": "8a8b4833f8e443fda73618ad3eaa0f26", "step": 5, "value": 0.9739787835852499, "stage": "debug", "created_at": 1788847855.9464998}, {"event_id": "03cfb8aee37f4942a9757ca47f96de5c", "step": 6, "value": 0.9072239330360177, "stage": "improve", "created_at": 1788848987.240025}, {"event_id": "77a4c389d92f4b538efd787de6f5da74", "step": 7, "value": 0.8761018916460144, "stage": "debug", "created_at": 1788848248.235151}, {"event_id": "f89781a405e546149c89beae60a5de0e", "step": 8, "value": 0.9580950771339775, "stage": "debug", "created_at": 1788847591.5101168}, {"event_id": "eeaf08bcf05a43539f722304870dd253", "step": 9, "value": 0.976760235691468, "stage": "improve", "created_at": 1788852470.07159}, {"event_id": "2b9b6c2e131245daa53448d396ebd20a", "step": 10, "value": 0.9358436112868399, "stage": "improve", "created_at": 1788854556.9021466}, {"event_id": "b7c45ef514024f3db5f65c325f65b966", "step": 11, "value": 0.9554392550727517, "stage": "improve", "created_at": 1788854916.2278237}, {"event_id": "d198800c1bea4014b426465cf1cccad7", "step": 12, "value": 0.9802213659439423, "stage": "improve", "created_at": 1788855349.3204684}, {"event_id": "aa0a2e9d25694bc8af2117e8a21e12a5", "step": 13, "value": 0.9772203255135491, "stage": "improve", "created_at": 1788855960.8044074}, {"event_id": "5bd57ceacdf3434a8b43455c180378df", "step": 14, "value": 0.9739787835852499, "stage": "improve", "created_at": 1788857298.7443528}, {"event_id": "7a81ec715d8f498890e15bcbcacff2eb", "step": 15, "value": 0.9808853592099003, "stage": "improve", "created_at": 1788857784.43021}, {"event_id": "d20e4606842547059c0a7adb450a584d", "step": 16, "value": 0.9450924623693581, "stage": "improve", "created_at": 1788858975.032817}, {"event_id": "0d613f212def4e4aaa01ecbe889ae440", "step": 17, "value": 0.981293166097654, "stage": "improve", "created_at": 1788859630.0257068}, {"event_id": "31e6e9ee342440dd960ddbcc48775141", "step": 18, "value": 0.9826054677492719, "stage": "improve", "created_at": 1788862588.7198753}, {"event_id": "0f8d091de976434180bc9585403c10c1", "step": 20, "value": 0.9718717813318555, "stage": "improve", "created_at": 1788866330.4105954}, {"event_id": "57db26653e8e41a58eaad63bc20c997c", "step": 21, "value": 0.9762426346416266, "stage": "improve", "created_at": 1788860290.2626183}], "maximize": true, "elapsed_seconds": 28727.437332868576, "node_count": 22, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp6-20260908/xixian.gp6-draft.text-normalization-challenge-russian-language.yaml", "note": ""}, {"id": "xixian.gp6-draft.the-icml-2013-whale-challenge-right-whale-redux", "experiment_id": "mlebench-gp6-20260908", "family": "MLEBench", "method": "gp6_draft", "dataset": "the-icml-2013-whale-challenge-right-whale-redux", "status": "archived", "official_score": 0.98979, "medal": "gold", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.98961, "silver": 0.95017, "bronze": 0.90521}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp6-gp6-draft-logs-with-private-scores", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp6-gp6-draft-logs-with-private-scores/logs-7b2a3e058322.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp6-gp6-draft-logs-with-private-scores", "member": "gp6_gp6-draft_logs/private_scores/rechecked_private_grades.jsonl:44", "sha256": "7b2a3e05832281a42f745f697155c42c6ef59359301c708d7b3496df1e02188f"}, {"bundle_id": "gp6-gp6-draft-logs-with-private-scores", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp6-gp6-draft-logs-with-private-scores/logs-7b2a3e058322.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp6-gp6-draft-logs-with-private-scores", "member": "gp6_gp6-draft_logs/runs/gp6_draft/22_the-icml-2013-whale-challenge-right-whale-redux/logs/journal.json", "sha256": "7b2a3e05832281a42f745f697155c42c6ef59359301c708d7b3496df1e02188f"}], "alternate_scores": [], "journal_ref": "gp6-gp6-draft-logs-with-private-scores:gp6_gp6-draft_logs/runs/gp6_draft/22_the-icml-2013-whale-challenge-right-whale-redux/logs/journal.json", "metrics": [{"event_id": "e8e08cbf050649ad889c37413e95f350", "step": 3, "value": 0.9941862538209943, "stage": "draft", "created_at": 1788846212.319742}, {"event_id": "c350b95581ba40c0ad7f6f06313c5eaa", "step": 4, "value": 0.7537785914487648, "stage": "debug", "created_at": 1788850805.3308299}, {"event_id": "ed4b9188b6664a82a786f5ef0e43adec", "step": 5, "value": 0.7940145049212354, "stage": "improve", "created_at": 1788851340.656478}, {"event_id": "7bfc99eadd1f47539dc3358158b3e646", "step": 6, "value": 0.988388921586895, "stage": "improve", "created_at": 1788854596.0440896}, {"event_id": "c250856ef3f54baaa9a52367f6390913", "step": 8, "value": 0.9907162637910824, "stage": "improve", "created_at": 1788856673.0244288}, {"event_id": "ad1dd23966dc483bad0ac435fba8e25d", "step": 10, "value": 0.8463655037013266, "stage": "improve", "created_at": 1788855783.120161}, {"event_id": "d0d240aae5514984a920442fb7e5a442", "step": 13, "value": 0.9377635797246614, "stage": "improve", "created_at": 1788864460.791962}, {"event_id": "c0a532dacd654c3b9fe72851bd3b88b8", "step": 14, "value": 0.8342828342537627, "stage": "debug", "created_at": 1788870778.3254168}], "maximize": true, "elapsed_seconds": 28332.263018846512, "node_count": 15, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp6-20260908/xixian.gp6-draft.the-icml-2013-whale-challenge-right-whale-redux.yaml", "note": ""}, {"id": "xixian.gp7-ancestry-logei.aptos2019-blindness-detection", "experiment_id": "mlebench-gp7-recovery-20260913", "family": "MLEBench", "method": "gp7_ancestry_logei", "dataset": "aptos2019-blindness-detection", "status": "archived", "official_score": 0.89305, "medal": "none", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.930508, "silver": 0.919654, "bronze": 0.914492}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7/logs-31ca423ebfab.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7", "member": "graph-selectors-recovery-44-runs/results/private_grades.jsonl:1", "sha256": "31ca423ebfabbe5e7b019284026d4b5e56ffcf69cd0b4e76caf8bb4a870dae41"}, {"bundle_id": "gp7", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7/logs-31ca423ebfab.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7", "member": "graph-selectors-recovery-44-runs/runs/gp7_ancestry_logei/02_aptos2019-blindness-detection/logs/journal.json", "sha256": "31ca423ebfabbe5e7b019284026d4b5e56ffcf69cd0b4e76caf8bb4a870dae41"}], "alternate_scores": [], "journal_ref": "gp7:graph-selectors-recovery-44-runs/runs/gp7_ancestry_logei/02_aptos2019-blindness-detection/logs/journal.json", "metrics": [{"event_id": "78faad31ce9d4e63a0a56816c1621444", "step": 2, "value": 0.894650143997205, "stage": "draft", "created_at": 1789264510.4610703}, {"event_id": "dc78c78f913c44e1b14dd199c1cc471a", "step": 3, "value": 0.894752672670181, "stage": "debug", "created_at": 1789265447.6569746}, {"event_id": "b7b07119591e4a7cabec72298ffbb708", "step": 4, "value": 0.8949829954815798, "stage": "draft", "created_at": 1789264257.8952768}, {"event_id": "3c44735e5e5543009436078d024082de", "step": 6, "value": 0.9075730178073037, "stage": "improve", "created_at": 1789269922.0179422}, {"event_id": "32eeb954040b46fc8eecff7cecf5ce4b", "step": 7, "value": 0.9075730178073037, "stage": "improve", "created_at": 1789269941.1478064}, {"event_id": "267350af861c4d83a717c8a102f881c1", "step": 10, "value": 0.9166758426390349, "stage": "improve", "created_at": 1789272759.5849426}, {"event_id": "764db210be7f4b4f83f24dc89ab0342b", "step": 11, "value": 0.9155966051803608, "stage": "debug", "created_at": 1789270766.363272}, {"event_id": "4acca27b03b74881b8bbf00cf343b193", "step": 13, "value": 0.9117556874499355, "stage": "improve", "created_at": 1789276324.0724614}, {"event_id": "fa425bcaaad743deb54866e8727f802d", "step": 14, "value": 0.9170346684417923, "stage": "debug", "created_at": 1789279432.6533482}, {"event_id": "05ee2602cf964f618115c307615f0299", "step": 15, "value": 0.9194828717919272, "stage": "improve", "created_at": 1789278311.4658377}, {"event_id": "8d423c628e3d4e449ea69e414f8e910e", "step": 16, "value": 0.9200536794562038, "stage": "improve", "created_at": 1789279830.072899}, {"event_id": "fc92998171b840ad9cab33d241cacd3e", "step": 17, "value": 0.9235947261593732, "stage": "improve", "created_at": 1789283551.2896395}, {"event_id": "fe8432554bc3409db0da280e797121f5", "step": 18, "value": 0.91226826580294, "stage": "improve", "created_at": 1789286987.3203537}], "maximize": true, "elapsed_seconds": 28743.38888812065, "node_count": 19, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-recovery-20260913/xixian.gp7-ancestry-logei.aptos2019-blindness-detection.yaml", "note": ""}, {"id": "xixian.gp7-ancestry-logei.denoising-dirty-documents", "experiment_id": "mlebench-gp7-recovery-20260913", "family": "MLEBench", "method": "gp7_ancestry_logei", "dataset": "denoising-dirty-documents", "status": "archived", "official_score": 0.01646, "medal": "gold", "valid_submission": true, "score_maximize": false, "thresholds": {"gold": 0.01794, "silver": 0.02609, "bronze": 0.04517}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7/logs-31ca423ebfab.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7", "member": "graph-selectors-recovery-44-runs/results/private_grades.jsonl:2", "sha256": "31ca423ebfabbe5e7b019284026d4b5e56ffcf69cd0b4e76caf8bb4a870dae41"}, {"bundle_id": "gp7", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7/logs-31ca423ebfab.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7", "member": "graph-selectors-recovery-44-runs/runs/gp7_ancestry_logei/03_denoising-dirty-documents/logs/journal.json", "sha256": "31ca423ebfabbe5e7b019284026d4b5e56ffcf69cd0b4e76caf8bb4a870dae41"}], "alternate_scores": [], "journal_ref": "gp7:graph-selectors-recovery-44-runs/runs/gp7_ancestry_logei/03_denoising-dirty-documents/logs/journal.json", "metrics": [{"event_id": "f607f895f2ff4f338e9409ebfb416671", "step": 4, "value": 0.34703616850023156, "stage": "draft", "created_at": 1789264682.272417}, {"event_id": "bfa89a1e084f4a6290a27922fd824b35", "step": 5, "value": 0.021176809316611096, "stage": "debug", "created_at": 1789264840.1649437}, {"event_id": "88f402f205244644b1d889ddbea0ed1e", "step": 7, "value": 0.022768066291977015, "stage": "improve", "created_at": 1789265060.1785762}, {"event_id": "eda0c5e647274219b838a781888bf174", "step": 8, "value": 0.020910664491055497, "stage": "debug", "created_at": 1789264944.6617057}, {"event_id": "5c94c325ce2a45d69c1c6af43bf0ef26", "step": 11, "value": 0.019206613159029946, "stage": "improve", "created_at": 1789265419.72195}, {"event_id": "29fd9d18d95349458d02a6623ac3d843", "step": 12, "value": 0.019286437416620252, "stage": "debug", "created_at": 1789265599.9028218}, {"event_id": "940ec5698b2e4ea0bb736acf856fe4a9", "step": 13, "value": 0.019301179210466708, "stage": "improve", "created_at": 1789265460.874423}, {"event_id": "4725f4e605cd498d8552ef67df40c7d5", "step": 14, "value": 0.0184894465725952, "stage": "improve", "created_at": 1789265778.8759677}, {"event_id": "1bf669dd161c441d933ec7db440b4c81", "step": 15, "value": 0.43573309723702913, "stage": "improve", "created_at": 1789265953.2499707}, {"event_id": "fdcd868a2a8c42c791ca246a3c4f492a", "step": 16, "value": 0.017955895181267823, "stage": "improve", "created_at": 1789266000.6616287}, {"event_id": "9b3b376fc942493abc71448e19dd42ed", "step": 20, "value": 0.017034399657001233, "stage": "debug", "created_at": 1789266351.7378304}, {"event_id": "82446048e3a142c2a638cff3c0a743f4", "step": 21, "value": 0.01763151144808532, "stage": "debug", "created_at": 1789266443.7675688}, {"event_id": "a27440da6898417e9a754e64e4946d6b", "step": 22, "value": 0.016946534075509365, "stage": "debug", "created_at": 1789266534.874962}, {"event_id": "eddf9e54fc394c01b166a5a18b9c7d45", "step": 23, "value": 0.020450916549499164, "stage": "improve", "created_at": 1789266760.9597769}, {"event_id": "16e8b882ae9b46658dac7fe12a98fddd", "step": 24, "value": 0.02210954669347577, "stage": "improve", "created_at": 1789266804.027883}, {"event_id": "0cf8932629b64598a619c26d39e33c68", "step": 25, "value": 0.13362889860289065, "stage": "improve", "created_at": 1789266905.4419844}, {"event_id": "e1d5e9a2c2544a52ba9408bc0c74e847", "step": 27, "value": 0.01816271642711534, "stage": "improve", "created_at": 1789267139.167642}, {"event_id": "330a3b68f5354de8976a7cb4d7d8b215", "step": 28, "value": 0.15181435587970107, "stage": "improve", "created_at": 1789267280.8274283}, {"event_id": "b1c2e389afc64c27976da2c1799ce936", "step": 29, "value": 0.021971620002951473, "stage": "debug", "created_at": 1789267370.5948675}, {"event_id": "381d5eda3b174e7dafd4f018b8a5532e", "step": 31, "value": 0.01615342679321729, "stage": "evolution", "created_at": 1789267701.5802357}, {"event_id": "b6c1ff5e16db45d0b3f0c87ac8e005cf", "step": 32, "value": 0.015745591040123495, "stage": "evolution", "created_at": 1789267584.6376095}, {"event_id": "e806a49a2f704268bb817e57fa3411ff", "step": 33, "value": 0.015591714161895543, "stage": "improve", "created_at": 1789268180.7532213}, {"event_id": "0c2a58591edf4951a88fc6b046cc1591", "step": 34, "value": 0.01925844670390857, "stage": "improve", "created_at": 1789268585.5901015}, {"event_id": "412d83eb65a04904b879b8a6c374abb5", "step": 35, "value": 0.01716447480664118, "stage": "improve", "created_at": 1789268330.414413}, {"event_id": "f058346a7a214e8a906f091fa262fddf", "step": 36, "value": 0.03771183813344409, "stage": "debug", "created_at": 1789267675.2972639}, {"event_id": "0bdbb1475eb1409ab43b4baa1a172537", "step": 37, "value": 0.021883781678223208, "stage": "improve", "created_at": 1789269090.979786}, {"event_id": "4f7e8b843ec042d4aafde8ea80d9792b", "step": 38, "value": 0.022421588745554243, "stage": "improve", "created_at": 1789269163.3354425}, {"event_id": "b1a7fc4badd14261a4c019767091440c", "step": 39, "value": 0.4999425302761099, "stage": "evolution", "created_at": 1789269529.5428681}, {"event_id": "52cf3495917a4debb9ac599a71742e14", "step": 42, "value": 0.01765522179462477, "stage": "evolution", "created_at": 1789270078.3380215}, {"event_id": "c8394a86d8734a57bd9236a700ae07eb", "step": 45, "value": 0.019002385060292937, "stage": "evolution", "created_at": 1789270672.3254702}, {"event_id": "6343011d2d8e4534ac19bc577627640e", "step": 46, "value": 0.08917326065948565, "stage": "debug", "created_at": 1789270672.9301863}, {"event_id": "bca46b56aab141ceac01dee67c704988", "step": 47, "value": 0.034017277077513404, "stage": "evolution", "created_at": 1789271354.9769285}, {"event_id": "77268f9e4fba4b01bf6d88174187539d", "step": 48, "value": 0.1636305864302822, "stage": "debug", "created_at": 1789270858.2223284}, {"event_id": "d936d194ffd44bb0b167bfeb3d1b20ee", "step": 49, "value": 0.21908913122275248, "stage": "improve", "created_at": 1789272205.0442724}, {"event_id": "d31ff9739a36413f86a535724ec2e75d", "step": 50, "value": 0.017102785930589063, "stage": "improve", "created_at": 1789272325.4869153}, {"event_id": "4b169fa33d63451292737502a5ea3a9c", "step": 53, "value": 0.031616067205028506, "stage": "evolution", "created_at": 1789272652.2936165}, {"event_id": "69626b3757574bb6b9b11704393ef12e", "step": 55, "value": 0.02844556196130442, "stage": "debug", "created_at": 1789272831.283701}, {"event_id": "7b91ee7b8bfd4c3b87806ec0870a608d", "step": 56, "value": 0.021971620002951473, "stage": "debug", "created_at": 1789272903.3614883}, {"event_id": "a2b32ceacaf34fdfbeef5dcda10f7409", "step": 57, "value": 0.018532835008159165, "stage": "debug", "created_at": 1789273181.3150976}, {"event_id": "ba504276072d421aa8d33159ddadd1c9", "step": 58, "value": 0.023813344448520245, "stage": "evolution", "created_at": 1789273531.037302}, {"event_id": "e0785dee5e2c472bbbcb44195fa6aff5", "step": 60, "value": 0.016989539172922116, "stage": "evolution", "created_at": 1789273448.3425875}, {"event_id": "e1f70a02f0ab4222aa9632e430943ea6", "step": 65, "value": 0.4549844123570524, "stage": "evolution", "created_at": 1789273901.6800933}, {"event_id": "03eb3ed8d50140bfac9fc53270e60382", "step": 66, "value": 0.016397894709548624, "stage": "evolution", "created_at": 1789275160.5213666}, {"event_id": "cec394b823804445bf40baa9147cf231", "step": 67, "value": 0.061989515092245304, "stage": "debug", "created_at": 1789274318.366168}, {"event_id": "d2f67df0044f4695ab27b9f6e427bac2", "step": 68, "value": 0.01955939810998187, "stage": "evolution", "created_at": 1789275622.2175484}, {"event_id": "0ed1ca5e46ab4b988c0c38ebff597666", "step": 70, "value": 0.025945240877767378, "stage": "evolution", "created_at": 1789275655.8842626}, {"event_id": "ea417c2f31ec411a95a0b67be433d710", "step": 71, "value": 0.026742126659716547, "stage": "evolution", "created_at": 1789276354.0221765}, {"event_id": "6e351c92fdd842e69099e8c18d791034", "step": 72, "value": 0.500137552020337, "stage": "evolution", "created_at": 1789276377.7742808}, {"event_id": "5059f502042546039c25f7d6d90f4d8e", "step": 73, "value": 0.3666730756075435, "stage": "evolution", "created_at": 1789276467.3008235}, {"event_id": "2d3a74251ca54e83a7642e5856368848", "step": 75, "value": 0.0184808264333004, "stage": "improve", "created_at": 1789276898.383781}, {"event_id": "060735fd1a014e83b9743cda691c31be", "step": 76, "value": 0.015571782128038876, "stage": "evolution", "created_at": 1789277359.244096}, {"event_id": "9573f46b86a64d8b940c3b5087a1ca7c", "step": 78, "value": 0.016145332455365664, "stage": "debug", "created_at": 1789278212.636235}, {"event_id": "5fa9fb3c90464611ab6afb282fe22f62", "step": 79, "value": 0.02051245070038468, "stage": "improve", "created_at": 1789278176.7589138}, {"event_id": "fc56dffcbc914b32b9dfd91ed7e70549", "step": 80, "value": 0.10340669903570726, "stage": "improve", "created_at": 1789278947.0819528}, {"event_id": "188fa95e07e24a64ab6398d3e70d0226", "step": 82, "value": 0.046194729823974684, "stage": "improve", "created_at": 1789279288.928523}, {"event_id": "4f095fefa6f642938eadf0af4dcef75f", "step": 83, "value": 0.018975902090493303, "stage": "fusion", "created_at": 1789279699.8596349}, {"event_id": "93c0f2a2edf441959ecab0d3d1999e7c", "step": 85, "value": 0.01534601303257998, "stage": "evolution", "created_at": 1789280555.1034749}, {"event_id": "f15a636e6626402a87e5c76630e7a98f", "step": 86, "value": 0.02088575088563304, "stage": "improve", "created_at": 1789281393.2523813}, {"event_id": "1e5fb585dfcc434db1307627d5b5c66e", "step": 87, "value": 0.0334890305555967, "stage": "improve", "created_at": 1789282359.096427}, {"event_id": "a699432a9db740dca401952edf62d89a", "step": 88, "value": 0.23040510280257503, "stage": "debug", "created_at": 1789279933.605269}, {"event_id": "3ffb4c099f80418d9874300dfe91b5b3", "step": 89, "value": 0.016175235219118112, "stage": "evolution", "created_at": 1789281126.467735}, {"event_id": "a66ec148ea7246b2817cc7ad85634474", "step": 90, "value": 0.02039429521003605, "stage": "improve", "created_at": 1789282801.3300653}, {"event_id": "dfd394e682614044ada25733a83016da", "step": 91, "value": 0.5000326636971045, "stage": "evolution", "created_at": 1789282797.9974902}, {"event_id": "57822030ad8a49d78240f97b3e2f2302", "step": 93, "value": 0.01688482800355468, "stage": "evolution", "created_at": 1789283009.2994123}, {"event_id": "a576f8d342cc4b5aaa4109cdac0d0486", "step": 94, "value": 0.01760570810099194, "stage": "evolution", "created_at": 1789283973.0086174}, {"event_id": "24312ef040b2418dbeba30d23d7addda", "step": 95, "value": 0.018864915190020478, "stage": "evolution", "created_at": 1789284883.1490812}, {"event_id": "0ab86fa9365c4bbf98e38cb9b8ae9e65", "step": 96, "value": 0.016038111311845214, "stage": "debug", "created_at": 1789284541.6505537}, {"event_id": "acec5c567abb489ba9c9ea7a719708b6", "step": 97, "value": 0.09101011421501128, "stage": "evolution", "created_at": 1789284828.5720909}, {"event_id": "dcc9d4b92923468ebf6df53bc84754c9", "step": 98, "value": 0.061327609178445, "stage": "evolution", "created_at": 1789285555.0101385}, {"event_id": "312dab936e8b428a9b8d59b633b28664", "step": 99, "value": 0.45415750472726185, "stage": "evolution", "created_at": 1789286062.1375473}, {"event_id": "6b250b4ebc5f45d493aa23a59e269068", "step": 100, "value": 0.03569595470736847, "stage": "evolution", "created_at": 1789286487.984568}, {"event_id": "ac1e10b0e2bd4fc3b57fcc57efb46628", "step": 101, "value": 0.016065015848563936, "stage": "fusion", "created_at": 1789287321.3942337}, {"event_id": "eea210f95ec44a6681d7558664ac036a", "step": 103, "value": 0.01806965176569809, "stage": "fusion", "created_at": 1789287925.3631248}, {"event_id": "a54658d6cccf4c7b88e3cf89ee62fcdc", "step": 104, "value": 0.01852364453950858, "stage": "fusion_draft", "created_at": 1789288556.1057863}, {"event_id": "0a4532f12a9e4c59a55d2ebf6f1f9e54", "step": 105, "value": 0.015347386103578185, "stage": "fusion", "created_at": 1789288650.0475721}, {"event_id": "2a03590768554fc092adf729e44e266a", "step": 106, "value": 0.02062022002639999, "stage": "improve", "created_at": 1789289107.0303798}, {"event_id": "1eac9f45a40b4828a8918f428f26d371", "step": 107, "value": 0.030836809755614775, "stage": "fusion", "created_at": 1789289563.988763}, {"event_id": "32b94a2e09ae4fdebd65a9935f8d2e60", "step": 109, "value": 0.015320439044587554, "stage": "evolution", "created_at": 1789289738.843194}, {"event_id": "74c7369779864f13a4a8ff136b42e0b9", "step": 113, "value": 0.07065498901857703, "stage": "debug", "created_at": 1789291321.3660958}, {"event_id": "4482b0eb51c14cb8a51f63c15c59f543", "step": 114, "value": 0.016767505479525765, "stage": "evolution", "created_at": 1789290734.0206277}, {"event_id": "b3cd6811e2d149c49f46880fffa56b34", "step": 115, "value": 0.024068187947741786, "stage": "debug", "created_at": 1789291447.2999203}, {"event_id": "53dc09c5735e426dbead5cbdb0827361", "step": 116, "value": 0.10286344740078691, "stage": "improve", "created_at": 1789291868.2250488}, {"event_id": "76831a66f98c4466880434783669e02d", "step": 117, "value": 0.039252676174566264, "stage": "improve", "created_at": 1789292001.8343034}], "maximize": false, "elapsed_seconds": 28735.664974689484, "node_count": 119, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-recovery-20260913/xixian.gp7-ancestry-logei.denoising-dirty-documents.yaml", "note": ""}, {"id": "xixian.gp7-ancestry-logei.detecting-insults-in-social-commentary", "experiment_id": "mlebench-gp7-recovery-20260913", "family": "MLEBench", "method": "gp7_ancestry_logei", "dataset": "detecting-insults-in-social-commentary", "status": "archived", "official_score": 0.9552, "medal": "gold", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.83321, "silver": 0.82307, "bronze": 0.79111}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7/logs-31ca423ebfab.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7", "member": "graph-selectors-recovery-44-runs/results/private_grades.jsonl:3", "sha256": "31ca423ebfabbe5e7b019284026d4b5e56ffcf69cd0b4e76caf8bb4a870dae41"}, {"bundle_id": "gp7", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7/logs-31ca423ebfab.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7", "member": "graph-selectors-recovery-44-runs/runs/gp7_ancestry_logei/04_detecting-insults-in-social-commentary/logs/journal.json", "sha256": "31ca423ebfabbe5e7b019284026d4b5e56ffcf69cd0b4e76caf8bb4a870dae41"}], "alternate_scores": [], "journal_ref": "gp7:graph-selectors-recovery-44-runs/runs/gp7_ancestry_logei/04_detecting-insults-in-social-commentary/logs/journal.json", "metrics": [{"event_id": "f5582b6661194a59afe42658b9b83765", "step": 5, "value": 0.9367015859159029, "stage": "debug", "created_at": 1789264743.2739131}, {"event_id": "555845d2151d4e9596c9c3f91e3d50b4", "step": 6, "value": 0.8929586307163627, "stage": "debug", "created_at": 1789264793.0214522}, {"event_id": "14c094dc246a496ca7c8a84cfac2499b", "step": 7, "value": 0.8699403462825549, "stage": "debug", "created_at": 1789264869.3168652}, {"event_id": "805cab39e85e404e94ca48c04835c571", "step": 8, "value": 0.9443110723119453, "stage": "improve", "created_at": 1789265007.6372926}, {"event_id": "4571f518d3b94ee493ff82392e618b08", "step": 9, "value": 0.8543940055288812, "stage": "improve", "created_at": 1789265079.5056021}, {"event_id": "96c50234bbb141099f7d0bf55d024527", "step": 10, "value": 0.9524734468208933, "stage": "improve", "created_at": 1789265121.7951365}, {"event_id": "740f47cfcff34fdb85ed138189a7c6dc", "step": 11, "value": 0.9489524225229157, "stage": "improve", "created_at": 1789265455.2642255}, {"event_id": "2ce16f03d8874b65b7cade3e091cdf1f", "step": 13, "value": 0.9479557689509676, "stage": "improve", "created_at": 1789265782.9721997}, {"event_id": "c7c8d1532e854fbc906b28fdb0306e96", "step": 14, "value": 0.9489596973665066, "stage": "debug", "created_at": 1789265742.1435}, {"event_id": "46f5c066508147f4a5fbbbfbed704c35", "step": 15, "value": 0.929266695766041, "stage": "improve", "created_at": 1789265282.0799866}, {"event_id": "a9776edfa366489596d467ff2d58d115", "step": 16, "value": 0.9417025054588779, "stage": "evolution", "created_at": 1789266263.4748619}, {"event_id": "68394f8b029c4a278281b09d429b3165", "step": 17, "value": 0.9368158310422163, "stage": "evolution", "created_at": 1789266381.772588}, {"event_id": "3c61c93adcf3494ba005cb0eecf6f707", "step": 18, "value": 0.9410332624781167, "stage": "improve", "created_at": 1789266147.2524498}, {"event_id": "e509e49b573b4f58bf8c4fcde717941a", "step": 22, "value": 0.9378395145792666, "stage": "debug", "created_at": 1789267918.8363466}, {"event_id": "60815d124ac44eb4bdd02986dfb870d9", "step": 23, "value": 0.9508447691810729, "stage": "debug", "created_at": 1789267558.172594}, {"event_id": "b32a2e48a1b9414b95142fc7734c8229", "step": 24, "value": 0.936918298080067, "stage": "evolution", "created_at": 1789268938.4477563}, {"event_id": "87d87c3ee08c477aa88733924b1c87df", "step": 25, "value": 0.9544148326218207, "stage": "evolution", "created_at": 1789269647.853015}, {"event_id": "4f004379e1724ad6a634edc0213a5c56", "step": 26, "value": 0.9527529916098739, "stage": "evolution", "created_at": 1789269602.1051943}, {"event_id": "38938117201f4b71a4212716710816c0", "step": 27, "value": 0.9528128599915395, "stage": "debug", "created_at": 1789267885.4162076}, {"event_id": "7d89b13daa6048b899cea5bbe5dadf6f", "step": 28, "value": 0.9537932869781006, "stage": "improve", "created_at": 1789271667.7103543}, {"event_id": "990ce9448f47412d9111e4830022ef0f", "step": 29, "value": 0.9481079288763625, "stage": "improve", "created_at": 1789271697.3160963}, {"event_id": "3181026ac5ea4946b5d6a329717e6a77", "step": 30, "value": 0.9554015096042701, "stage": "improve", "created_at": 1789272185.8400588}, {"event_id": "8bd4800c7a2c49a497e9a1b6221495ab", "step": 31, "value": 0.9551483847707996, "stage": "evolution", "created_at": 1789273357.0962305}, {"event_id": "a355c6f58ab3437d8713b92bbcae63bc", "step": 32, "value": 0.9566913113872952, "stage": "evolution", "created_at": 1789273670.0821245}, {"event_id": "e980c24f20fb4dccb3def290ffef6091", "step": 33, "value": 0.9523707550192402, "stage": "improve", "created_at": 1789273826.9717066}, {"event_id": "6a27817103e149d9a77f1ca7e94b3a88", "step": 34, "value": 0.9552311149795296, "stage": "improve", "created_at": 1789275115.7055273}, {"event_id": "7ec8846b13c14803abd148139f09e779", "step": 35, "value": 0.9561158183448565, "stage": "improve", "created_at": 1789275374.7600043}, {"event_id": "1eafb93c1105418695fa829650235849", "step": 36, "value": 0.9571043045366419, "stage": "improve", "created_at": 1789275606.174007}, {"event_id": "7d9e6cc83a66443fbd8d7cf7f0610699", "step": 37, "value": 0.9566913113872952, "stage": "improve", "created_at": 1789276712.1266122}, {"event_id": "0af6d7cec2194b2786b2c4e41328cff5", "step": 38, "value": 0.9575664752852138, "stage": "improve", "created_at": 1789277449.9988658}, {"event_id": "55ba229c0c6c4906bfbfac1aff34902e", "step": 39, "value": 0.9596445989180271, "stage": "evolution", "created_at": 1789277142.8177757}, {"event_id": "b39e4e4b91ea4169aafef006d563f65a", "step": 40, "value": 0.9599141711090979, "stage": "improve", "created_at": 1789278909.8251934}, {"event_id": "aff2214e51f7455daa55059896ab8956", "step": 41, "value": 0.962401669472586, "stage": "improve", "created_at": 1789278348.153416}, {"event_id": "affe9b76c6204418857cc5f071e064df", "step": 42, "value": 0.9580681196920264, "stage": "improve", "created_at": 1789279366.6513302}, {"event_id": "82f15379def0444db523e183f4114b71", "step": 43, "value": 0.9508658217988014, "stage": "improve", "created_at": 1789281266.6719217}, {"event_id": "39cfe43a06df45f988cc8dca0b231b04", "step": 44, "value": 0.9588033165767654, "stage": "improve", "created_at": 1789281381.5982876}, {"event_id": "f99e0e127bf64c1bb46e2b46e02bb1b8", "step": 45, "value": 0.9548615428542481, "stage": "improve", "created_at": 1789281867.738572}, {"event_id": "0b405d96575047178edebc2f1017712b", "step": 46, "value": 0.9592115399924078, "stage": "improve", "created_at": 1789283597.71842}, {"event_id": "c0f617c975684f0483d55df822a9489d", "step": 47, "value": 0.9577469027980903, "stage": "fusion", "created_at": 1789285265.3337562}, {"event_id": "7059aadd2fde4466bd6fd26c5bdd3e68", "step": 48, "value": 0.9571427913534266, "stage": "improve", "created_at": 1789285759.768351}, {"event_id": "9ca86de9e3e843fc8f1337bc0e03bb35", "step": 49, "value": 0.9605460785881061, "stage": "improve", "created_at": 1789286039.6545916}, {"event_id": "d643880871ae4dd8b583bf313b11a78b", "step": 50, "value": 0.9589404875391528, "stage": "evolution", "created_at": 1789287579.9797132}, {"event_id": "7985adb8f11441f99f5c75e3d10df8ca", "step": 52, "value": 0.9597325922811893, "stage": "evolution", "created_at": 1789287387.3594875}, {"event_id": "3698126c3af44ad7bd45fac54b361eed", "step": 53, "value": 0.9476276660344303, "stage": "evolution", "created_at": 1789288904.4979022}, {"event_id": "24e56d1645d34e078c7df50dec85bf37", "step": 57, "value": 0.9504733878464554, "stage": "evolution", "created_at": 1789291917.4802918}], "maximize": true, "elapsed_seconds": 28726.521535873413, "node_count": 58, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-recovery-20260913/xixian.gp7-ancestry-logei.detecting-insults-in-social-commentary.yaml", "note": ""}, {"id": "xixian.gp7-ancestry-logei.dog-breed-identification", "experiment_id": "mlebench-gp7-recovery-20260913", "family": "MLEBench", "method": "gp7_ancestry_logei", "dataset": "dog-breed-identification", "status": "archived", "official_score": 0.33666, "medal": "none", "valid_submission": true, "score_maximize": false, "thresholds": {"gold": 0.0005, "silver": 0.00539, "bronze": 0.04598}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7/logs-31ca423ebfab.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7", "member": "graph-selectors-recovery-44-runs/results/private_grades.jsonl:4", "sha256": "31ca423ebfabbe5e7b019284026d4b5e56ffcf69cd0b4e76caf8bb4a870dae41"}, {"bundle_id": "gp7", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7/logs-31ca423ebfab.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7", "member": "graph-selectors-recovery-44-runs/runs/gp7_ancestry_logei/05_dog-breed-identification/logs/journal.json", "sha256": "31ca423ebfabbe5e7b019284026d4b5e56ffcf69cd0b4e76caf8bb4a870dae41"}], "alternate_scores": [], "journal_ref": "gp7:graph-selectors-recovery-44-runs/runs/gp7_ancestry_logei/05_dog-breed-identification/logs/journal.json", "metrics": [{"event_id": "2954e7eea979421f92e5bfffddf82375", "step": 3, "value": 0.6204499240682969, "stage": "draft", "created_at": 1789264378.9093866}, {"event_id": "fea826b3112a4f26b18232124a92dcae", "step": 4, "value": 0.5588371403833335, "stage": "draft", "created_at": 1789264186.9539707}, {"event_id": "ad253e172cfe44dfb2eb3ccf1c36f32c", "step": 6, "value": 0.5809859715341871, "stage": "debug", "created_at": 1789264870.8460958}, {"event_id": "f23588ac652743599adefb31aafbf571", "step": 8, "value": 0.47828261614246853, "stage": "debug", "created_at": 1789265401.2541664}, {"event_id": "f136256fb89b461aae4fd9c429045cca", "step": 9, "value": 0.4706823247937886, "stage": "improve", "created_at": 1789266377.7569642}, {"event_id": "78213d3e85f74a1e9ab1819d44f79b21", "step": 10, "value": 0.5997814725597965, "stage": "debug", "created_at": 1789265862.0322556}, {"event_id": "52e49299b8c541c89dec167b5569f207", "step": 11, "value": 0.4874001854839168, "stage": "improve", "created_at": 1789267688.1829238}, {"event_id": "c8a24517fb9d4a2a8e1a5e78af0368e1", "step": 12, "value": 0.8061994849664083, "stage": "improve", "created_at": 1789269529.9874377}, {"event_id": "5a09ab5ec4484dfebeb4e05ed5301e58", "step": 13, "value": 0.46902436809112047, "stage": "improve", "created_at": 1789269363.4265366}, {"event_id": "7a8be9afbccc4393b931c2f6852d311c", "step": 14, "value": 0.3178471575921952, "stage": "improve", "created_at": 1789271291.5037184}, {"event_id": "8bf0c501cd8343d182e9341d4e6985d7", "step": 15, "value": 0.5091146554096149, "stage": "improve", "created_at": 1789265247.3487747}, {"event_id": "09458a988cee4fb5ae9df7bdf7ae72ae", "step": 17, "value": 0.3541691311102154, "stage": "debug", "created_at": 1789272248.5003295}, {"event_id": "cf8784e94fae4b409a1e0576ef04e604", "step": 18, "value": 0.2934315592092848, "stage": "improve", "created_at": 1789272303.9044228}, {"event_id": "e6afd709e763412a8a0fbba65ecff690", "step": 21, "value": 0.3207126568724531, "stage": "debug", "created_at": 1789274313.422217}, {"event_id": "af73f0b0424448c1b10e91ba8cdc0bf4", "step": 22, "value": 0.39766030838005806, "stage": "improve", "created_at": 1789273331.982425}, {"event_id": "a2daca30b0384481af6c7553c6fa136f", "step": 23, "value": 0.24571328992345146, "stage": "improve", "created_at": 1789278537.5497575}, {"event_id": "382c4e32f9a941ad85ff79212580292f", "step": 24, "value": 0.28448957760079924, "stage": "improve", "created_at": 1789276356.786371}, {"event_id": "aa786d837cd045ff9ae29c30712c3b5d", "step": 25, "value": 0.27531994520439623, "stage": "improve", "created_at": 1789280923.5355678}, {"event_id": "d5d97c066b42412685e416827456bdf1", "step": 26, "value": 0.27747216380008743, "stage": "improve", "created_at": 1789280343.1615353}, {"event_id": "fe35b789a0794a3e878fbc67248dc2c5", "step": 27, "value": 0.2839526290398401, "stage": "debug", "created_at": 1789275505.068794}, {"event_id": "0eaf4a676e1e46d8993c54b32b85237b", "step": 29, "value": 0.011930973414924294, "stage": "evolution", "created_at": 1789285623.532425}, {"event_id": "71e903b8addf4539a0847678e735a337", "step": 31, "value": 0.29699451111279607, "stage": "improve", "created_at": 1789283112.1264505}, {"event_id": "d1003902f7fd40c195c3b110486d4460", "step": 32, "value": 0.24510472635577923, "stage": "debug", "created_at": 1789286569.2632434}, {"event_id": "6fa80cc27a7644e28a8c892723d50d0f", "step": 33, "value": 0.10118159874054711, "stage": "improve", "created_at": 1789288866.6247911}, {"event_id": "e8cadaaef3d14ec58bbca6c0437401b7", "step": 34, "value": 0.09761072453920155, "stage": "improve", "created_at": 1789288831.2527459}], "maximize": false, "elapsed_seconds": 28749.72744679451, "node_count": 36, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-recovery-20260913/xixian.gp7-ancestry-logei.dog-breed-identification.yaml", "note": ""}, {"id": "xixian.gp7-ancestry-logei.dogs-vs-cats-redux-kernels-edition", "experiment_id": "mlebench-gp7-recovery-20260913", "family": "MLEBench", "method": "gp7_ancestry_logei", "dataset": "dogs-vs-cats-redux-kernels-edition", "status": "archived", "official_score": 0.00285, "medal": "gold", "valid_submission": true, "score_maximize": false, "thresholds": {"gold": 0.03882, "silver": 0.05038, "bronze": 0.06127}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7/logs-31ca423ebfab.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7", "member": "graph-selectors-recovery-44-runs/results/private_grades.jsonl:5", "sha256": "31ca423ebfabbe5e7b019284026d4b5e56ffcf69cd0b4e76caf8bb4a870dae41"}, {"bundle_id": "gp7", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7/logs-31ca423ebfab.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7", "member": "graph-selectors-recovery-44-runs/runs/gp7_ancestry_logei/06_dogs-vs-cats-redux-kernels-edition/logs/journal.json", "sha256": "31ca423ebfabbe5e7b019284026d4b5e56ffcf69cd0b4e76caf8bb4a870dae41"}], "alternate_scores": [], "journal_ref": "gp7:graph-selectors-recovery-44-runs/runs/gp7_ancestry_logei/06_dogs-vs-cats-redux-kernels-edition/logs/journal.json", "metrics": [{"event_id": "4824d659ac4640b2b7f8ae6e9ff8c368", "step": 2, "value": 0.014315651025476758, "stage": "draft", "created_at": 1789264443.3978753}, {"event_id": "d065f7ee4c66480fb175dfe31610f89e", "step": 3, "value": 0.0017955662040244284, "stage": "draft", "created_at": 1789264259.3745494}, {"event_id": "56240ed57bca4b3a8fbea1726b8ea03d", "step": 4, "value": 0.010828722928178335, "stage": "debug", "created_at": 1789264774.9606066}, {"event_id": "be77675d345641a3bee65fc4ea37736a", "step": 7, "value": 0.0009796233386749876, "stage": "improve", "created_at": 1789265264.0957587}, {"event_id": "250e09d7cb404b238a69e7abd511df49", "step": 8, "value": 0.0030355052006449056, "stage": "improve", "created_at": 1789265254.0942996}, {"event_id": "566204aee524459996f0fbd77ea4c033", "step": 9, "value": 0.006737765875079762, "stage": "improve", "created_at": 1789266051.231217}, {"event_id": "3bcef7cbe61c41d58a06e4ffb96cc672", "step": 10, "value": 0.009746876647117864, "stage": "debug", "created_at": 1789265965.6769447}, {"event_id": "4268abf5c49a4384b9324b02938cd1b7", "step": 11, "value": 0.008007519402087066, "stage": "improve", "created_at": 1789266100.6339066}, {"event_id": "7ff47964047f45919767e8fff1a742e4", "step": 12, "value": 0.004539035446161699, "stage": "improve", "created_at": 1789266790.721602}, {"event_id": "0c3e6b8c1d7c4d3ebf3cb9ea9fe0ef6b", "step": 13, "value": 0.005370033233290433, "stage": "improve", "created_at": 1789267119.9120486}, {"event_id": "439a610495794a11b538e016aa3826fc", "step": 14, "value": 0.0014818962768869573, "stage": "improve", "created_at": 1789267230.6646566}, {"event_id": "8b295dae89eb474899bc55aa0dad37f9", "step": 16, "value": 0.0049866963939022325, "stage": "evolution", "created_at": 1789268057.3024192}, {"event_id": "3ec0c5788d0b438dbac06412adf5c77e", "step": 17, "value": 0.004349876269855206, "stage": "debug", "created_at": 1789268742.3581786}, {"event_id": "0a0c3e432192446f867ab58a904afb8d", "step": 19, "value": 0.002329138031572854, "stage": "improve", "created_at": 1789268264.0733051}, {"event_id": "36a9f0ce0af04ffa8acfc4a49ab7f13f", "step": 20, "value": 0.004721467247177026, "stage": "debug", "created_at": 1789270703.935693}, {"event_id": "6d73b10329e94d29a6b5b6e58bc82d02", "step": 21, "value": 0.004533091133212382, "stage": "improve", "created_at": 1789269383.9643393}, {"event_id": "4e1a08be67db4ecba33f6ea2f0377d21", "step": 23, "value": 0.0027402750363307734, "stage": "evolution", "created_at": 1789272618.9343402}, {"event_id": "fca3c32b47b04076b97371d74f4a2b52", "step": 25, "value": 0.003490802652552964, "stage": "evolution", "created_at": 1789273360.2622414}, {"event_id": "82a600589a2e462ebce8fea8b922a96b", "step": 26, "value": 0.004015315764564764, "stage": "debug", "created_at": 1789273049.9127822}, {"event_id": "d11d39bbc524499daeb0da4a7debbf19", "step": 27, "value": 0.0012903173470356247, "stage": "debug", "created_at": 1789273846.9338038}, {"event_id": "f08ab69e42d84221b2351c3b3b0e4e04", "step": 29, "value": 0.002167242128831833, "stage": "debug", "created_at": 1789275978.641702}, {"event_id": "da2521fcfd83496f9990ba0dcd23795b", "step": 30, "value": 0.004342596670743349, "stage": "improve", "created_at": 1789274231.891478}, {"event_id": "005219244fb640bb8007879427214ac4", "step": 31, "value": 3.0, "stage": "evolution", "created_at": 1789275616.9070592}, {"event_id": "28716093985f4011b9fd2afb85de8224", "step": 32, "value": 0.002790217531585912, "stage": "evolution", "created_at": 1789277085.4053454}, {"event_id": "c0e9a2e891ec4edea46530fd305eaeb7", "step": 33, "value": 0.006091351510387387, "stage": "evolution", "created_at": 1789278125.6415248}, {"event_id": "e10247e266c3447483aec8dd12b097e7", "step": 34, "value": 0.00892110138556938, "stage": "fusion", "created_at": 1789278997.2082279}, {"event_id": "39626666ca7c44c58c0f0b969072ca58", "step": 35, "value": 0.004407851538508781, "stage": "evolution", "created_at": 1789277676.2015378}, {"event_id": "4b9d8df554e64287b0f8bac453243002", "step": 36, "value": 0.005086227053193605, "stage": "evolution", "created_at": 1789280594.0526345}, {"event_id": "74ab959e32d143a88d84cc72355579f3", "step": 38, "value": 0.006165421247976858, "stage": "improve", "created_at": 1789280615.490924}, {"event_id": "e499188f9cc54848a19511abfbd06b6f", "step": 39, "value": 0.0021841711623810903, "stage": "evolution", "created_at": 1789281619.3120615}, {"event_id": "fd156e8a87db492896e7e029d028fc98", "step": 40, "value": 0.002015294114747445, "stage": "evolution", "created_at": 1789282779.5526066}, {"event_id": "487273c5966f4ee2bbbc831ca02e3ca0", "step": 41, "value": 0.00191, "stage": "evolution", "created_at": 1789282818.9080184}, {"event_id": "95e7a89ee9ab43188a446f688cab3f5d", "step": 42, "value": 0.00264538091716657, "stage": "evolution", "created_at": 1789284178.7247417}, {"event_id": "9d47e23d9bbc4f36b49828c52a2d5377", "step": 43, "value": 0.06041986531994737, "stage": "evolution", "created_at": 1789282879.7011487}, {"event_id": "b10357bb84fa43ee8856035fb349195a", "step": 44, "value": 0.0017195341936943759, "stage": "evolution", "created_at": 1789284975.8011506}, {"event_id": "05ce7874d068438182f78527f9e47f4f", "step": 45, "value": 0.002263791686457592, "stage": "evolution", "created_at": 1789285701.3221457}, {"event_id": "9db547d23b104004988947821f1493e3", "step": 46, "value": 0.012956189718583424, "stage": "improve", "created_at": 1789286868.20892}, {"event_id": "0b7c765fc1b5439287cf15eae775ba0f", "step": 47, "value": 0.0013263922588987213, "stage": "improve", "created_at": 1789286970.2131379}, {"event_id": "387026540b104e569411ad5f549be631", "step": 48, "value": 0.002191749108661858, "stage": "improve", "created_at": 1789286181.9188862}, {"event_id": "f443958d905949088edd7cbae8ecdf85", "step": 49, "value": 0.0032887966639233665, "stage": "improve", "created_at": 1789289073.504868}, {"event_id": "ae359743fc4145afbe33b5cfb050d548", "step": 51, "value": 0.004603369277644501, "stage": "improve", "created_at": 1789289113.9503195}], "maximize": false, "elapsed_seconds": 28739.302051782608, "node_count": 52, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-recovery-20260913/xixian.gp7-ancestry-logei.dogs-vs-cats-redux-kernels-edition.yaml", "note": ""}, {"id": "xixian.gp7-ancestry-logei.histopathologic-cancer-detection", "experiment_id": "mlebench-gp7-recovery-20260913", "family": "MLEBench", "method": "gp7_ancestry_logei", "dataset": "histopathologic-cancer-detection", "status": "archived", "official_score": 0.99734, "medal": "gold", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.9835, "silver": 0.9798, "bronze": 0.9738}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7/logs-31ca423ebfab.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7", "member": "graph-selectors-recovery-44-runs/results/private_grades.jsonl:6", "sha256": "31ca423ebfabbe5e7b019284026d4b5e56ffcf69cd0b4e76caf8bb4a870dae41"}, {"bundle_id": "gp7", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7/logs-31ca423ebfab.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7", "member": "graph-selectors-recovery-44-runs/runs/gp7_ancestry_logei/07_histopathologic-cancer-detection/logs/journal.json", "sha256": "31ca423ebfabbe5e7b019284026d4b5e56ffcf69cd0b4e76caf8bb4a870dae41"}], "alternate_scores": [], "journal_ref": "gp7:graph-selectors-recovery-44-runs/runs/gp7_ancestry_logei/07_histopathologic-cancer-detection/logs/journal.json", "metrics": [{"event_id": "ae19e2a208cf408a808bd9c9ec9e5682", "step": 4, "value": 0.9846493848767313, "stage": "debug", "created_at": 1789266031.3042963}, {"event_id": "cb027619909c4f12a82511093132385e", "step": 5, "value": 0.9937115979821729, "stage": "draft", "created_at": 1789264685.0631037}, {"event_id": "fedb37ecb5d245009066832b9ec4cafb", "step": 6, "value": 0.9978648698717927, "stage": "draft", "created_at": 1789264470.851108}, {"event_id": "3abb95010ff24e20a98747aa0144b2c8", "step": 7, "value": 0.992009144791703, "stage": "improve", "created_at": 1789273589.4797463}, {"event_id": "5ec5c1798bea4384aa065b2824ec7f61", "step": 8, "value": 0.9938996394617465, "stage": "improve", "created_at": 1789273577.214529}, {"event_id": "2d59578d23fb488085ddfc17c6d9b82e", "step": 10, "value": 0.9976532894915171, "stage": "improve", "created_at": 1789273584.4398668}], "maximize": true, "elapsed_seconds": 28731.880487203598, "node_count": 11, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-recovery-20260913/xixian.gp7-ancestry-logei.histopathologic-cancer-detection.yaml", "note": ""}, {"id": "xixian.gp7-ancestry-logei.jigsaw-toxic-comment-classification-challenge", "experiment_id": "mlebench-gp7-recovery-20260913", "family": "MLEBench", "method": "gp7_ancestry_logei", "dataset": "jigsaw-toxic-comment-classification-challenge", "status": "archived", "official_score": 0.98729, "medal": "silver", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.9874, "silver": 0.98668, "bronze": 0.98639}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7/logs-31ca423ebfab.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7", "member": "graph-selectors-recovery-44-runs/results/private_grades.jsonl:7", "sha256": "31ca423ebfabbe5e7b019284026d4b5e56ffcf69cd0b4e76caf8bb4a870dae41"}, {"bundle_id": "gp7", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7/logs-31ca423ebfab.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7", "member": "graph-selectors-recovery-44-runs/runs/gp7_ancestry_logei/08_jigsaw-toxic-comment-classification-challenge/logs/journal.json", "sha256": "31ca423ebfabbe5e7b019284026d4b5e56ffcf69cd0b4e76caf8bb4a870dae41"}], "alternate_scores": [], "journal_ref": "gp7:graph-selectors-recovery-44-runs/runs/gp7_ancestry_logei/08_jigsaw-toxic-comment-classification-challenge/logs/journal.json", "metrics": [{"event_id": "2fcaaab7e96d451b83d79aaf9d0ae1d3", "step": 4, "value": 0.9925426585292856, "stage": "debug", "created_at": 1789264798.9835303}, {"event_id": "cebea354bde6453b9b41959131d84339", "step": 5, "value": 0.9913205102144568, "stage": "debug", "created_at": 1789264806.3545702}, {"event_id": "62f97124c68646009f8ff6063c3e61da", "step": 6, "value": 0.9900170371392202, "stage": "debug", "created_at": 1789264968.5668406}, {"event_id": "7d3bdf3031d6457d961862326da4c659", "step": 7, "value": 0.9929896242645738, "stage": "improve", "created_at": 1789272597.3207624}, {"event_id": "a562c8a72479403fa1f5661ef77f01d4", "step": 9, "value": 0.9926170692045386, "stage": "improve", "created_at": 1789269575.1274896}, {"event_id": "9e443dc259cf45599fdf4460e0f328da", "step": 10, "value": 0.9915838733622285, "stage": "debug", "created_at": 1789284328.8532593}, {"event_id": "daba03dc7d7b4c2d98929c4d77c28491", "step": 11, "value": 0.99267223139212, "stage": "improve", "created_at": 1789269980.8476694}], "maximize": true, "elapsed_seconds": 28737.25516986847, "node_count": 12, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-recovery-20260913/xixian.gp7-ancestry-logei.jigsaw-toxic-comment-classification-challenge.yaml", "note": ""}, {"id": "xixian.gp7-ancestry-logei.leaf-classification", "experiment_id": "mlebench-gp7-recovery-20260913", "family": "MLEBench", "method": "gp7_ancestry_logei", "dataset": "leaf-classification", "status": "archived", "official_score": 1e-05, "medal": "silver", "valid_submission": true, "score_maximize": false, "thresholds": {"gold": 0.0, "silver": 0.00791, "bronze": 0.01526}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7/logs-31ca423ebfab.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7", "member": "graph-selectors-recovery-44-runs/results/private_grades.jsonl:8", "sha256": "31ca423ebfabbe5e7b019284026d4b5e56ffcf69cd0b4e76caf8bb4a870dae41"}, {"bundle_id": "gp7", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7/logs-31ca423ebfab.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7", "member": "graph-selectors-recovery-44-runs/runs/gp7_ancestry_logei/09_leaf-classification/logs/journal.json", "sha256": "31ca423ebfabbe5e7b019284026d4b5e56ffcf69cd0b4e76caf8bb4a870dae41"}], "alternate_scores": [], "journal_ref": "gp7:graph-selectors-recovery-44-runs/runs/gp7_ancestry_logei/09_leaf-classification/logs/journal.json", "metrics": [{"event_id": "bfbfaba9542b43cc9fdbc3958143871f", "step": 3, "value": 9.693026337893151e-08, "stage": "draft", "created_at": 1789264711.5024612}, {"event_id": "a36d56484a0c4df58611ef092ae8f71c", "step": 6, "value": 0.004936094032766754, "stage": "draft", "created_at": 1789264241.9601936}, {"event_id": "726c20c60ce145f293acbebbb95a17f9", "step": 7, "value": 0.014076438584739078, "stage": "debug", "created_at": 1789265359.3165634}, {"event_id": "aca8847a634b43fd914c9269d582f2fd", "step": 9, "value": 2.3029659201028683e-07, "stage": "improve", "created_at": 1789265434.5607407}, {"event_id": "fe2b421d2ff44b7aa12b318f3b58062e", "step": 10, "value": 0.00046879638146206794, "stage": "debug", "created_at": 1789265519.4079437}, {"event_id": "ba6694898c404e2d9492660606c13d93", "step": 11, "value": 0.006856539145426087, "stage": "improve", "created_at": 1789265857.3946745}, {"event_id": "4b8dabff50bb4a3fb2ee14c11db002ce", "step": 12, "value": 0.00046879638146206794, "stage": "improve", "created_at": 1789266269.0336113}, {"event_id": "4d73e7cf48ae45ceb0be118d27182404", "step": 13, "value": 0.6958352567469894, "stage": "improve", "created_at": 1789267350.2421868}, {"event_id": "913aa3ceb66f4acabe308760d46db918", "step": 14, "value": 0.0365100465563989, "stage": "improve", "created_at": 1789267345.1958404}, {"event_id": "59542857ae344e46935369fea1062c41", "step": 15, "value": 0.017520634444728657, "stage": "improve", "created_at": 1789268883.2255526}, {"event_id": "8d6972df47eb4ea1af4b54b76bd292cc", "step": 16, "value": 0.01593830957268738, "stage": "improve", "created_at": 1789270784.9375525}, {"event_id": "9cb20055053a4378a860e6203cca8b27", "step": 17, "value": 0.014076438584739078, "stage": "improve", "created_at": 1789265549.7978933}, {"event_id": "fa12d22e38544520b904fab6bc70d4bb", "step": 18, "value": 0.11247097834939328, "stage": "fusion", "created_at": 1789284283.4646072}, {"event_id": "7035f5d0cf664e67881042d3b0a85aab", "step": 19, "value": 0.018073085187003183, "stage": "evolution", "created_at": 1789286171.4263642}, {"event_id": "0b8cbad1aa2943b59b7c0242867ed0e9", "step": 20, "value": 0.05297703452509625, "stage": "evolution", "created_at": 1789287458.0597315}], "maximize": false, "elapsed_seconds": 28739.886773109436, "node_count": 21, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-recovery-20260913/xixian.gp7-ancestry-logei.leaf-classification.yaml", "note": ""}, {"id": "xixian.gp7-ancestry-logei.mlsp-2013-birds", "experiment_id": "mlebench-gp7-recovery-20260913", "family": "MLEBench", "method": "gp7_ancestry_logei", "dataset": "mlsp-2013-birds", "status": "archived", "official_score": 0.89955, "medal": "bronze", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.93527, "silver": 0.90038, "bronze": 0.87372}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7/logs-31ca423ebfab.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7", "member": "graph-selectors-recovery-44-runs/results/private_grades.jsonl:9", "sha256": "31ca423ebfabbe5e7b019284026d4b5e56ffcf69cd0b4e76caf8bb4a870dae41"}, {"bundle_id": "gp7", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7/logs-31ca423ebfab.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7", "member": "graph-selectors-recovery-44-runs/runs/gp7_ancestry_logei/10_mlsp-2013-birds/logs/journal.json", "sha256": "31ca423ebfabbe5e7b019284026d4b5e56ffcf69cd0b4e76caf8bb4a870dae41"}], "alternate_scores": [], "journal_ref": "gp7:graph-selectors-recovery-44-runs/runs/gp7_ancestry_logei/10_mlsp-2013-birds/logs/journal.json", "metrics": [{"event_id": "ca948588c4894f01aab70cd664c25f2d", "step": 8, "value": 0.8530269385191666, "stage": "debug", "created_at": 1789265118.6728249}, {"event_id": "103f301fb9ed4521872c6a2253376b5b", "step": 10, "value": 0.7696541082679698, "stage": "debug", "created_at": 1789265235.45971}, {"event_id": "2e625e3deaf1493198c050bfde8d7ad1", "step": 11, "value": 0.6438807681284037, "stage": "debug", "created_at": 1789265360.5469718}, {"event_id": "597b67cc8d724ab2bb240c2a73c0b141", "step": 13, "value": 0.8170266693582755, "stage": "debug", "created_at": 1789265726.2987115}, {"event_id": "26452ec1e00c45a09f87adecb491fa7d", "step": 14, "value": 0.8813841598815693, "stage": "improve", "created_at": 1789265669.4639103}, {"event_id": "091c84a5cac9472582c16df9231a02aa", "step": 15, "value": 0.8432249960747371, "stage": "improve", "created_at": 1789265663.2168903}, {"event_id": "d3fdc7598c8d447b9da69e085b92962d", "step": 16, "value": 0.8573110826996838, "stage": "improve", "created_at": 1789266067.0353687}, {"event_id": "9da47959fae947fb8dbeba53a3a13a51", "step": 17, "value": 0.8744027992732656, "stage": "improve", "created_at": 1789266083.8645785}, {"event_id": "d19a30232c5b4d738aa1a55694d37d68", "step": 18, "value": 0.8908552587309064, "stage": "improve", "created_at": 1789266110.8738732}, {"event_id": "7bc26a71feb94f53a03049d2c09afb96", "step": 19, "value": 0.8869748558867729, "stage": "improve", "created_at": 1789266551.9232316}, {"event_id": "472aeea99a91440884a16c2c9b7a45db", "step": 20, "value": 0.8765392638449634, "stage": "improve", "created_at": 1789266412.6757703}, {"event_id": "9037eb3dc6b3441fa486ed5b05f21185", "step": 21, "value": 0.8916515263665523, "stage": "improve", "created_at": 1789267062.5550008}, {"event_id": "f3d3a288188843a5be46ecd2f399fcd7", "step": 22, "value": 0.8445543881532656, "stage": "evolution", "created_at": 1789266475.1699538}, {"event_id": "6302fa1b52ff4055a458c2a89d096ff1", "step": 24, "value": 0.8837449251957025, "stage": "improve", "created_at": 1789267497.599942}, {"event_id": "50f9907d02cc4725bba782bec21ba2bf", "step": 27, "value": 0.8638161261434146, "stage": "improve", "created_at": 1789267257.1686707}, {"event_id": "28488ae1333d4246bdc21cd789caae34", "step": 28, "value": 0.8781037615234505, "stage": "debug", "created_at": 1789268158.7996905}, {"event_id": "249f613cb9054fdd946521c056e11f85", "step": 29, "value": 0.8731393526514425, "stage": "improve", "created_at": 1789268102.1559355}, {"event_id": "a48e01f182094db49f29974b3f05b53a", "step": 30, "value": 0.8553388665003518, "stage": "evolution", "created_at": 1789268508.418498}, {"event_id": "ab36c17136594294893030babd534de1", "step": 31, "value": 0.8618323418409773, "stage": "evolution", "created_at": 1789268609.0565226}, {"event_id": "bf4ce442ead2485b9623aa50be936e07", "step": 32, "value": 0.8579679204247426, "stage": "evolution", "created_at": 1789270034.1179037}, {"event_id": "cc063c13f55c4cfeacec98e9a68ac53b", "step": 33, "value": 0.8628766071771252, "stage": "evolution", "created_at": 1789269894.6971188}, {"event_id": "3c074e8c6c9545a688d2cf4f9d195d0e", "step": 34, "value": 0.8615836691613894, "stage": "evolution", "created_at": 1789270193.3643632}, {"event_id": "e50943a1eaa34f83bd004d890a18a365", "step": 35, "value": 0.8103758875455767, "stage": "evolution", "created_at": 1789271163.9260855}, {"event_id": "2cd56ee27a3547efb68e59ea485526b4", "step": 36, "value": 0.8186948282479369, "stage": "evolution", "created_at": 1789271551.0189905}, {"event_id": "4bb43db7c651485eacfbe5ebd5571b40", "step": 37, "value": 0.6573986119107016, "stage": "evolution", "created_at": 1789271908.2224627}, {"event_id": "49144fe0efba40d28003867683a435e9", "step": 38, "value": 0.8949936074288406, "stage": "evolution", "created_at": 1789272488.2130263}, {"event_id": "65ecf42ed59345ab9859c8be9e29074a", "step": 39, "value": 0.8237142582997505, "stage": "evolution", "created_at": 1789271591.339303}, {"event_id": "b475e050eb9f42c796f0e9a2bb4e0060", "step": 40, "value": 0.93610793351726, "stage": "improve", "created_at": 1789272969.545004}, {"event_id": "47cc56ffa43d4120a3a1a9e8775fa80f", "step": 41, "value": 0.8820738846645582, "stage": "improve", "created_at": 1789273652.1781049}, {"event_id": "fab0ea0bef17473dae70c550b4bee830", "step": 42, "value": 0.8649779312991749, "stage": "improve", "created_at": 1789273987.9198596}, {"event_id": "5f2b30d5c4184a36947e1105c6cb63c8", "step": 43, "value": 0.8758387705494787, "stage": "improve", "created_at": 1789274167.1699157}, {"event_id": "041121ad46944b889d99aabc33e0fa8e", "step": 45, "value": 0.8968665186281766, "stage": "evolution", "created_at": 1789275476.6818595}, {"event_id": "486d14ac9b184290a8c26d6c7b46eca8", "step": 46, "value": 0.8691917738118083, "stage": "evolution", "created_at": 1789272815.4252055}, {"event_id": "b584439f311f4ce6a064ed0ee4f8efb0", "step": 47, "value": 0.9398313258416885, "stage": "debug", "created_at": 1789275447.0178742}, {"event_id": "a42c66afa5f645569332e7c9a804303d", "step": 48, "value": 0.9052665814323845, "stage": "evolution", "created_at": 1789276134.0946956}, {"event_id": "4d289dadc24245b3884bf476fbf1af34", "step": 50, "value": 0.8226907823194524, "stage": "improve", "created_at": 1789276434.0723803}, {"event_id": "71b2a60c47184886ac4523feb4c978f0", "step": 51, "value": 0.8320228043241861, "stage": "evolution", "created_at": 1789275981.179271}, {"event_id": "99203ea2fedf4295af16f64094a7b4f9", "step": 52, "value": 0.9269340331516497, "stage": "debug", "created_at": 1789276886.3915951}, {"event_id": "f0dbd34419f54018bef8b31afd5c60e8", "step": 53, "value": 0.9283134827176278, "stage": "evolution", "created_at": 1789277730.8713877}, {"event_id": "b3da2dfc8a824aa3b1d35b923fa4d5a4", "step": 54, "value": 0.9440930399479622, "stage": "improve", "created_at": 1789277617.8225493}, {"event_id": "68d1b834b586458cb343a49f37230af3", "step": 55, "value": 0.9235246618666308, "stage": "evolution", "created_at": 1789277814.9307227}, {"event_id": "b6d3223debfe428f910c60e8fbe766c5", "step": 56, "value": 0.8892551013880893, "stage": "evolution", "created_at": 1789278241.9196517}, {"event_id": "3398ff7f040e4a608711ab040c8dd32c", "step": 57, "value": 0.9488145705762288, "stage": "improve", "created_at": 1789278896.065345}, {"event_id": "970446b02a4144c4a747ba3244884570", "step": 58, "value": 0.9436220083888478, "stage": "improve", "created_at": 1789278920.020397}, {"event_id": "e386582cc1a7412a8809a02b372e9b2b", "step": 59, "value": 0.9347172689141601, "stage": "improve", "created_at": 1789280174.740897}, {"event_id": "8bad45e5c96d48a98c9e0ce8a033a278", "step": 60, "value": 0.5, "stage": "improve", "created_at": 1789279979.4128065}, {"event_id": "ce958660fedf41508e6b8c9d49a4ba8c", "step": 61, "value": 0.9371060718210977, "stage": "improve", "created_at": 1789280268.6413379}, {"event_id": "4d8a28d66c264685affa696611735c99", "step": 62, "value": 0.9325639817867797, "stage": "improve", "created_at": 1789281328.7711415}, {"event_id": "6d4f068c687b4c2f95c98b570290ef89", "step": 63, "value": 0.875381404720783, "stage": "fusion", "created_at": 1789281443.455704}, {"event_id": "04a4527701e54075b3666ce579f5deba", "step": 64, "value": 0.8913156463890487, "stage": "evolution", "created_at": 1789281467.1503828}, {"event_id": "f58fa27687f84e0fb575e7fc26ac91af", "step": 65, "value": 0.7327520309601485, "stage": "evolution", "created_at": 1789282396.491909}, {"event_id": "9d49c5e516e043e3931cc3fca72ef875", "step": 66, "value": 0.9024475468560097, "stage": "evolution", "created_at": 1789282528.6980186}, {"event_id": "a02fe9f73ec64e20bcc8fa941b310e29", "step": 67, "value": 0.9308368660700267, "stage": "evolution", "created_at": 1789283410.4287045}, {"event_id": "38f4656fcefb413c888025c6ac0ff68c", "step": 68, "value": 0.8828056035309921, "stage": "evolution", "created_at": 1789283745.5288982}, {"event_id": "c83834608af74db7a05fd3541825b263", "step": 69, "value": 0.9003246337875008, "stage": "evolution", "created_at": 1789282647.8502033}, {"event_id": "f911411bf6c94d92af1184362ad0114f", "step": 70, "value": 0.9400780566583675, "stage": "evolution", "created_at": 1789284456.3516905}, {"event_id": "55005c2f743b40f798e57ee68ba7ba08", "step": 71, "value": 0.9394051544310612, "stage": "evolution", "created_at": 1789284983.646543}, {"event_id": "2373206d51be45239a4fa7f294c5b513", "step": 72, "value": 0.9320929502276653, "stage": "evolution", "created_at": 1789285046.724403}, {"event_id": "fe663b28ed8d4dc6a5713b62a2915d54", "step": 73, "value": 0.8605985735303525, "stage": "evolution", "created_at": 1789286118.160831}, {"event_id": "c61b071114d549f09465b128f7c025e2", "step": 74, "value": 0.8729162668713618, "stage": "evolution", "created_at": 1789285645.3237686}, {"event_id": "87693f3dda7d4d2d988118c0d4052362", "step": 75, "value": 0.890512057826393, "stage": "evolution", "created_at": 1789286369.5363805}, {"event_id": "617b90e5a3ed47fb8e47a7b16259d613", "step": 76, "value": 0.8210508219791467, "stage": "fusion", "created_at": 1789287679.8627877}, {"event_id": "5f98a82853384015ae519adea6ac9d74", "step": 77, "value": 0.9276517955274433, "stage": "fusion", "created_at": 1789287794.640206}, {"event_id": "62435ce2c6494466a531930c11203964", "step": 78, "value": 0.9447890679971854, "stage": "evolution", "created_at": 1789287661.3216703}, {"event_id": "e9a5300b1e12422887e30c8fc17e2caa", "step": 79, "value": 0.8865980617923623, "stage": "fusion", "created_at": 1789288881.6183667}, {"event_id": "0ada3d2895fc458eaf10a5bf8f0a128b", "step": 80, "value": 0.8865980617923623, "stage": "fusion", "created_at": 1789288959.6073954}, {"event_id": "875bba1497454294ba5efc3acf35ad0e", "step": 83, "value": 0.7702688223629501, "stage": "fusion", "created_at": 1789290132.5119061}], "maximize": true, "elapsed_seconds": 28755.116966962814, "node_count": 84, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-recovery-20260913/xixian.gp7-ancestry-logei.mlsp-2013-birds.yaml", "note": ""}, {"id": "xixian.gp7-ancestry-logei.new-york-city-taxi-fare-prediction", "experiment_id": "mlebench-gp7-recovery-20260913", "family": "MLEBench", "method": "gp7_ancestry_logei", "dataset": "new-york-city-taxi-fare-prediction", "status": "archived", "official_score": 10.69648, "medal": "none", "valid_submission": true, "score_maximize": false, "thresholds": {"gold": 2.83377, "silver": 2.88191, "bronze": 2.92371}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7/logs-31ca423ebfab.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7", "member": "graph-selectors-recovery-44-runs/results/private_grades.jsonl:10", "sha256": "31ca423ebfabbe5e7b019284026d4b5e56ffcf69cd0b4e76caf8bb4a870dae41"}, {"bundle_id": "gp7", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7/logs-31ca423ebfab.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7", "member": "graph-selectors-recovery-44-runs/runs/gp7_ancestry_logei/11_new-york-city-taxi-fare-prediction/logs/journal.json", "sha256": "31ca423ebfabbe5e7b019284026d4b5e56ffcf69cd0b4e76caf8bb4a870dae41"}], "alternate_scores": [], "journal_ref": "gp7:graph-selectors-recovery-44-runs/runs/gp7_ancestry_logei/11_new-york-city-taxi-fare-prediction/logs/journal.json", "metrics": [{"event_id": "abac4f4aaab14f3bb835a57eca3acc51", "step": 2, "value": 3.7439890928470136, "stage": "draft", "created_at": 1789264631.171925}, {"event_id": "9b63e07d0282417a8ada0ba1d1ada1eb", "step": 3, "value": 3.4301836490631104, "stage": "draft", "created_at": 1789265145.4784973}, {"event_id": "41090c7f2b86403eadbbc31ae9dc184e", "step": 4, "value": 3.8128275089973207, "stage": "improve", "created_at": 1789265726.2885551}, {"event_id": "4a1290461f8348898376f3d0f616adae", "step": 5, "value": 3.178069363810046, "stage": "improve", "created_at": 1789265677.4319205}, {"event_id": "ff8e322dda4e42b78008f6eced4d3879", "step": 6, "value": 3.1725136822810702, "stage": "improve", "created_at": 1789266404.7036932}, {"event_id": "782feabde20f44cfae85c728445b818c", "step": 7, "value": 3.6466529030944463, "stage": "improve", "created_at": 1789266356.4657152}, {"event_id": "a9176d85956a4607913ee5e783c18a46", "step": 8, "value": 3.192705502111208, "stage": "improve", "created_at": 1789267417.2432103}, {"event_id": "317a7c6313c741dfa71664cd1603b754", "step": 9, "value": 3.139476669302747, "stage": "improve", "created_at": 1789268367.9507344}, {"event_id": "9e155deb970c44b2928a41223f759deb", "step": 11, "value": 3.1454565721044094, "stage": "debug", "created_at": 1789269303.9541187}, {"event_id": "9997f9cd3dce44e98b800db7c81acb4d", "step": 12, "value": 3.115141198717174, "stage": "improve", "created_at": 1789267308.6861267}, {"event_id": "67d5d6556c39403a8f5bf58893dbef43", "step": 13, "value": 3.0675763077962688, "stage": "improve", "created_at": 1789270532.3038085}, {"event_id": "a200c5e473c04a73afc8d94f15c1d148", "step": 14, "value": 3.2229122807108075, "stage": "improve", "created_at": 1789270146.0062883}, {"event_id": "dfb1668b7f8c4fa399e7d0f529bd8243", "step": 15, "value": 3.116036419611321, "stage": "improve", "created_at": 1789274753.7048063}, {"event_id": "15ea7d41637749aa94d4be558b3f6175", "step": 16, "value": 3.107993518379812, "stage": "improve", "created_at": 1789274004.603913}, {"event_id": "2f0a0cfeffb94762ab3940f7612130bd", "step": 17, "value": 3.0675703068080766, "stage": "fusion", "created_at": 1789279177.353158}, {"event_id": "735c45e52048449694032f8c107d95e9", "step": 19, "value": 3.2537090919498075, "stage": "improve", "created_at": 1789282894.3419745}, {"event_id": "5a71102de2ac474592432a61e76342b1", "step": 20, "value": 3.967049794109011, "stage": "debug", "created_at": 1789287029.2137587}, {"event_id": "136da1d82e9348428c54fb0dc7cc7a6d", "step": 21, "value": 3.086174694453059, "stage": "improve", "created_at": 1789288533.895061}], "maximize": false, "elapsed_seconds": 28752.43256163597, "node_count": 22, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-recovery-20260913/xixian.gp7-ancestry-logei.new-york-city-taxi-fare-prediction.yaml", "note": ""}, {"id": "xixian.gp7-ancestry-logei.nomad2018-predict-transparent-conductors", "experiment_id": "mlebench-gp7-recovery-20260913", "family": "MLEBench", "method": "gp7_ancestry_logei", "dataset": "nomad2018-predict-transparent-conductors", "status": "archived", "official_score": 0.05951, "medal": "silver", "valid_submission": true, "score_maximize": false, "thresholds": {"gold": 0.05589, "silver": 0.06229, "bronze": 0.06582}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7/logs-31ca423ebfab.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7", "member": "graph-selectors-recovery-44-runs/results/private_grades.jsonl:11", "sha256": "31ca423ebfabbe5e7b019284026d4b5e56ffcf69cd0b4e76caf8bb4a870dae41"}, {"bundle_id": "gp7", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7/logs-31ca423ebfab.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7", "member": "graph-selectors-recovery-44-runs/runs/gp7_ancestry_logei/12_nomad2018-predict-transparent-conductors/logs/journal.json", "sha256": "31ca423ebfabbe5e7b019284026d4b5e56ffcf69cd0b4e76caf8bb4a870dae41"}], "alternate_scores": [], "journal_ref": "gp7:graph-selectors-recovery-44-runs/runs/gp7_ancestry_logei/12_nomad2018-predict-transparent-conductors/logs/journal.json", "metrics": [{"event_id": "4495c86737a34be893da5bee5286b18e", "step": 2, "value": 0.06583349844048876, "stage": "draft", "created_at": 1789264552.1248496}, {"event_id": "ddeb9f59eeb54ec9a2928fade734925d", "step": 4, "value": 0.05993855106394076, "stage": "debug", "created_at": 1789265091.6343825}, {"event_id": "74371bfa8686420aaedb199b0162c0f4", "step": 5, "value": 0.24700007158322942, "stage": "draft", "created_at": 1789264814.2847037}, {"event_id": "327b3dd6bd7547d89281f82b42d38ad7", "step": 6, "value": 0.05951698502218107, "stage": "improve", "created_at": 1789270773.094702}, {"event_id": "c3cf0e4ad9c5460d8b8218928d587530", "step": 7, "value": 0.06590417886226296, "stage": "improve", "created_at": 1789273706.5580084}, {"event_id": "877f165445e84ee7b23bc281918583b6", "step": 8, "value": 0.06590417886226296, "stage": "improve", "created_at": 1789273931.4854562}, {"event_id": "6c0629705f834a1ab91637b7b2c61e33", "step": 9, "value": 0.11070308310021051, "stage": "improve", "created_at": 1789270787.070446}, {"event_id": "0932264bae0e4f52af095e40824a1224", "step": 10, "value": 0.059919361470672644, "stage": "improve", "created_at": 1789270844.4278533}, {"event_id": "e7e69a359e2f48ac80a8424f49daa90d", "step": 11, "value": 0.05976056039776924, "stage": "improve", "created_at": 1789274164.48806}, {"event_id": "f997a921175247b68c687f25fe1c55cb", "step": 12, "value": 0.05987575021055326, "stage": "improve", "created_at": 1789275729.2344596}, {"event_id": "8da86b088e994a80903f3a74b0cb5dd8", "step": 13, "value": 0.05976056039776924, "stage": "fusion", "created_at": 1789278565.130726}, {"event_id": "d61975c970cf41a0805582a9df3deef7", "step": 15, "value": 0.05914657178259046, "stage": "evolution", "created_at": 1789278898.6390452}, {"event_id": "121e925a7b00476bafafce7c467f45aa", "step": 16, "value": 0.05954422082617177, "stage": "evolution", "created_at": 1789282074.5508382}], "maximize": false, "elapsed_seconds": 28765.010415315628, "node_count": 17, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-recovery-20260913/xixian.gp7-ancestry-logei.nomad2018-predict-transparent-conductors.yaml", "note": ""}, {"id": "xixian.gp7-ancestry-logei.plant-pathology-2020-fgvc7", "experiment_id": "mlebench-gp7-recovery-20260913", "family": "MLEBench", "method": "gp7_ancestry_logei", "dataset": "plant-pathology-2020-fgvc7", "status": "archived", "official_score": 0.99654, "medal": "gold", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.97836, "silver": 0.97465, "bronze": 0.97361}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7/logs-31ca423ebfab.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7", "member": "graph-selectors-recovery-44-runs/results/private_grades.jsonl:12", "sha256": "31ca423ebfabbe5e7b019284026d4b5e56ffcf69cd0b4e76caf8bb4a870dae41"}, {"bundle_id": "gp7", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7/logs-31ca423ebfab.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7", "member": "graph-selectors-recovery-44-runs/runs/gp7_ancestry_logei/13_plant-pathology-2020-fgvc7/logs/journal.json", "sha256": "31ca423ebfabbe5e7b019284026d4b5e56ffcf69cd0b4e76caf8bb4a870dae41"}], "alternate_scores": [], "journal_ref": "gp7:graph-selectors-recovery-44-runs/runs/gp7_ancestry_logei/13_plant-pathology-2020-fgvc7/logs/journal.json", "metrics": [{"event_id": "17f97c0f7809409e8be0669fa35998d4", "step": 1, "value": 0.99059793658804, "stage": "draft", "created_at": 1789264188.3751163}, {"event_id": "bc513a1718d842099d34ceec998cf129", "step": 2, "value": 0.9798012459549078, "stage": "draft", "created_at": 1789264396.7466104}, {"event_id": "f15244ca6cea46988f9c7aef28527f6b", "step": 6, "value": 0.9830030981868124, "stage": "debug", "created_at": 1789265575.9452088}, {"event_id": "5f0fe5bebe45498c92dbe9cde4a6a283", "step": 9, "value": 0.9893750764364994, "stage": "debug", "created_at": 1789265845.0627658}, {"event_id": "ae068d2951f24f7ba5dfaa6f15350f33", "step": 10, "value": 0.9818188002419996, "stage": "debug", "created_at": 1789266159.0059261}, {"event_id": "a3c15b87edd941fba4fc549c6c4d1ee7", "step": 11, "value": 0.9863479541906734, "stage": "debug", "created_at": 1789266206.6700335}, {"event_id": "8e07d156f6ec4d878216694f4b531ac2", "step": 12, "value": 0.9842159217197384, "stage": "improve", "created_at": 1789266743.216811}, {"event_id": "6c989598a94f4b4385d4590895c7c419", "step": 14, "value": 0.9840865154448133, "stage": "improve", "created_at": 1789268608.25945}, {"event_id": "37af3cf980244a33b9ec928f148ac889", "step": 15, "value": 0.9634143004339746, "stage": "improve", "created_at": 1789266717.0422602}, {"event_id": "491d80d0b056408081241febd858b9e4", "step": 16, "value": 0.9865907248694624, "stage": "improve", "created_at": 1789270533.4734225}, {"event_id": "88b4620664254b508b33b353c574ea3c", "step": 18, "value": 0.9942102086262355, "stage": "evolution", "created_at": 1789273775.269374}, {"event_id": "987f70c1ae02439e9b3f39895ad3dd4a", "step": 19, "value": 0.9913098226387611, "stage": "evolution", "created_at": 1789273640.7115202}, {"event_id": "6379a121aa8343c9a40a2b63f6416f37", "step": 20, "value": 0.9923106348216997, "stage": "improve", "created_at": 1789274638.5791717}, {"event_id": "64a5a6164f704937b63ebde2faafc64c", "step": 24, "value": 0.994772399779353, "stage": "improve", "created_at": 1789275752.90895}, {"event_id": "a4b07d5eba9546d8868c385a7f6d6518", "step": 25, "value": 0.9583283490411029, "stage": "improve", "created_at": 1789276707.576158}, {"event_id": "71b07459408947f6aa673cdb125f30ab", "step": 26, "value": 0.993851565925811, "stage": "improve", "created_at": 1789277368.100897}, {"event_id": "3ee02df990a247c3a26455afb9d2c1cb", "step": 27, "value": 0.9901376618363541, "stage": "debug", "created_at": 1789277186.524641}, {"event_id": "2f21b80017c24607bc36ea5807ef0b92", "step": 29, "value": 0.994727652144399, "stage": "improve", "created_at": 1789278844.1539338}, {"event_id": "84891756454e44d2b6c3f100fb852ac5", "step": 30, "value": 0.9937240628068472, "stage": "improve", "created_at": 1789279436.547279}, {"event_id": "9ab5ab32b1fa4e4999cec6d873ef9a40", "step": 33, "value": 0.9945903081521019, "stage": "evolution", "created_at": 1789280826.882485}, {"event_id": "78c656b179a444189100db728e88dc86", "step": 35, "value": 0.975130301072523, "stage": "debug", "created_at": 1789281403.2422287}, {"event_id": "8bf08e6fd44f46eaaf762aa2bf40e9a4", "step": 36, "value": 0.9941989993478008, "stage": "evolution", "created_at": 1789282459.1341457}, {"event_id": "e06945bb8d994d4c8333953bbfe44574", "step": 39, "value": 0.9973599002068965, "stage": "evolution", "created_at": 1789284133.9857156}, {"event_id": "4afc723e3a1049c58392be6c6fbbaeff", "step": 43, "value": 0.9915998429163907, "stage": "debug", "created_at": 1789285707.1630554}, {"event_id": "2c472a34003348c19cf7797bea223e11", "step": 46, "value": 0.9940145099831224, "stage": "debug", "created_at": 1789285867.2133768}, {"event_id": "e4003134cc564870828fa3f2931c3d8e", "step": 47, "value": 0.6221926867596379, "stage": "debug", "created_at": 1789287205.7858338}, {"event_id": "98cf0804134d445e9961cb77ee5e8e7e", "step": 48, "value": 0.9944776061138803, "stage": "improve", "created_at": 1789287138.0239892}, {"event_id": "8f57b848a588475a81082212d112f773", "step": 49, "value": 0.9905039407267171, "stage": "improve", "created_at": 1789287826.4568772}, {"event_id": "7a2583813f6b470397218a79da5dcf8f", "step": 52, "value": 0.9944913287167498, "stage": "evolution", "created_at": 1789288757.5500846}, {"event_id": "dec2c1b1fb604aefad307c2c2f6c47fd", "step": 54, "value": 0.9955190677470535, "stage": "evolution", "created_at": 1789289505.173776}], "maximize": true, "elapsed_seconds": 28757.814412355423, "node_count": 55, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-recovery-20260913/xixian.gp7-ancestry-logei.plant-pathology-2020-fgvc7.yaml", "note": ""}, {"id": "xixian.gp7-ancestry-logei.random-acts-of-pizza", "experiment_id": "mlebench-gp7-recovery-20260913", "family": "MLEBench", "method": "gp7_ancestry_logei", "dataset": "random-acts-of-pizza", "status": "archived", "official_score": 0.70229, "medal": "bronze", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.97908, "silver": 0.76482, "bronze": 0.6921}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7/logs-31ca423ebfab.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7", "member": "graph-selectors-recovery-44-runs/results/private_grades.jsonl:13", "sha256": "31ca423ebfabbe5e7b019284026d4b5e56ffcf69cd0b4e76caf8bb4a870dae41"}, {"bundle_id": "gp7", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7/logs-31ca423ebfab.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7", "member": "graph-selectors-recovery-44-runs/runs/gp7_ancestry_logei/14_random-acts-of-pizza/logs/journal.json", "sha256": "31ca423ebfabbe5e7b019284026d4b5e56ffcf69cd0b4e76caf8bb4a870dae41"}], "alternate_scores": [], "journal_ref": "gp7:graph-selectors-recovery-44-runs/runs/gp7_ancestry_logei/14_random-acts-of-pizza/logs/journal.json", "metrics": [{"event_id": "3733c43533444a1f9637b729f7019476", "step": 2, "value": 0.6815240833932422, "stage": "draft", "created_at": 1789264416.749497}, {"event_id": "48a0d461dfd548d1952d6eb61d98e110", "step": 4, "value": 0.5946369518332135, "stage": "draft", "created_at": 1789264657.7693236}, {"event_id": "c3b7a74c19194584b4e732edc3aec73f", "step": 5, "value": 0.6482242990654205, "stage": "debug", "created_at": 1789264859.1087706}, {"event_id": "5b41b172fd754dba9f2962184d0e9d24", "step": 6, "value": 0.6640977713874909, "stage": "improve", "created_at": 1789265023.9434195}, {"event_id": "be2939bbe25048ef9f5c015185e7e078", "step": 7, "value": 0.5978720345075486, "stage": "improve", "created_at": 1789265027.0728767}, {"event_id": "4cb9aa3199ea4e97bdc1fdf4d304a4c4", "step": 8, "value": 0.7261826024442847, "stage": "improve", "created_at": 1789265169.8606005}, {"event_id": "e0e9a83d2b3d4fe8bdf63038a7e76041", "step": 10, "value": 0.6927102803738316, "stage": "debug", "created_at": 1789265753.7493296}, {"event_id": "ee37fff1433049ffbf433568ba224f88", "step": 11, "value": 0.6878217109992811, "stage": "improve", "created_at": 1789266055.1768284}, {"event_id": "eb963cbadcdf4480a39353082e72b878", "step": 12, "value": 0.6888569374550684, "stage": "improve", "created_at": 1789266449.493759}, {"event_id": "fd02d8eaaf6d4ade9c87f29bf31ae182", "step": 13, "value": 0.6625161754133717, "stage": "evolution", "created_at": 1789267356.3319454}, {"event_id": "366ef643619b4ffabdde0a445542ecad", "step": 14, "value": 0.6640977713874909, "stage": "improve", "created_at": 1789265416.7726765}, {"event_id": "d216da6da6f54e918372671cee661219", "step": 15, "value": 0.6879367361610352, "stage": "improve", "created_at": 1789265431.8640225}, {"event_id": "2644d8985ca740d6ae9476109d6c3fda", "step": 16, "value": 0.7054205607476636, "stage": "improve", "created_at": 1789267759.4923172}, {"event_id": "d3b0e642c5ca44b5ace19ee5798e986b", "step": 17, "value": 0.6542056074766355, "stage": "improve", "created_at": 1789270040.165907}, {"event_id": "4d1fefc402cd40c995efe1e2245e6cf0", "step": 18, "value": 0.6763767074047446, "stage": "evolution", "created_at": 1789267758.0727215}, {"event_id": "635c81b760734f6494212da21deeede0", "step": 20, "value": 0.6828181164629763, "stage": "debug", "created_at": 1789279150.7595208}, {"event_id": "f463803dedc042449a34953926dc87f5", "step": 21, "value": 0.6959309849029475, "stage": "improve", "created_at": 1789274490.682275}, {"event_id": "8b7a7cc67b724479934676f8bac3025f", "step": 22, "value": 0.6901273483797756, "stage": "improve", "created_at": 1789285657.6842248}, {"event_id": "39daad36389141dcb3574ef52f961a9e", "step": 23, "value": 0.6859897384169229, "stage": "improve", "created_at": 1789285854.1454089}, {"event_id": "7adf6630b1a54af0b3aaf1273403582f", "step": 24, "value": 0.46530553558590937, "stage": "fusion", "created_at": 1789287279.8490975}, {"event_id": "7103597e2b354a27aed54b89850e9b8f", "step": 25, "value": 0.6775844716031633, "stage": "improve", "created_at": 1789274403.7867482}], "maximize": true, "elapsed_seconds": 28759.676570892334, "node_count": 26, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-recovery-20260913/xixian.gp7-ancestry-logei.random-acts-of-pizza.yaml", "note": ""}, {"id": "xixian.gp7-ancestry-logei.ranzcr-clip-catheter-line-classification", "experiment_id": "mlebench-gp7-recovery-20260913", "family": "MLEBench", "method": "gp7_ancestry_logei", "dataset": "ranzcr-clip-catheter-line-classification", "status": "archived", "official_score": 0.89007, "medal": "none", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.97357, "silver": 0.97152, "bronze": 0.9709}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7/logs-31ca423ebfab.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7", "member": "graph-selectors-recovery-44-runs/results/private_grades.jsonl:14", "sha256": "31ca423ebfabbe5e7b019284026d4b5e56ffcf69cd0b4e76caf8bb4a870dae41"}, {"bundle_id": "gp7", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7/logs-31ca423ebfab.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7", "member": "graph-selectors-recovery-44-runs/runs/gp7_ancestry_logei/15_ranzcr-clip-catheter-line-classification/logs/journal.json", "sha256": "31ca423ebfabbe5e7b019284026d4b5e56ffcf69cd0b4e76caf8bb4a870dae41"}], "alternate_scores": [], "journal_ref": "gp7:graph-selectors-recovery-44-runs/runs/gp7_ancestry_logei/15_ranzcr-clip-catheter-line-classification/logs/journal.json", "metrics": [{"event_id": "1684170eca914591ba137ab136e26fc5", "step": 2, "value": 0.9198600636819078, "stage": "draft", "created_at": 1789264304.0171084}, {"event_id": "883b2b3934be499abc8b7266ce9ee84d", "step": 6, "value": 0.693381050892172, "stage": "debug", "created_at": 1789268234.6341145}, {"event_id": "62a798fc2ae04979b1b069805fc451b4", "step": 9, "value": 0.8189878933949583, "stage": "debug", "created_at": 1789268590.5306294}, {"event_id": "184d03a51f4543609444e8db31e1fc2a", "step": 10, "value": 0.8203731504957648, "stage": "improve", "created_at": 1789272771.3050396}, {"event_id": "5c154ecad1134caba78c2a8354785a83", "step": 13, "value": 0.8638273354915131, "stage": "debug", "created_at": 1789277502.868493}, {"event_id": "5c26823522f9461e9bf6438f28bee5e7", "step": 14, "value": 0.7962751656731767, "stage": "debug", "created_at": 1789265021.4997594}, {"event_id": "6b10a7763a6d4c73b9cd5a92d73d4b92", "step": 15, "value": 0.9240516643075611, "stage": "fusion", "created_at": 1789282267.532179}, {"event_id": "1a1a7b7d1cc34e44a6777d92f7794c49", "step": 17, "value": 0.8863920021044401, "stage": "evolution", "created_at": 1789284116.3279526}], "maximize": true, "elapsed_seconds": 28742.254819869995, "node_count": 19, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-recovery-20260913/xixian.gp7-ancestry-logei.ranzcr-clip-catheter-line-classification.yaml", "note": ""}, {"id": "xixian.gp7-ancestry-logei.siim-isic-melanoma-classification", "experiment_id": "mlebench-gp7-recovery-20260913", "family": "MLEBench", "method": "gp7_ancestry_logei", "dataset": "siim-isic-melanoma-classification", "status": "archived", "official_score": 0.88264, "medal": "none", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.9455, "silver": 0.9401, "bronze": 0.937}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7/logs-31ca423ebfab.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7", "member": "graph-selectors-recovery-44-runs/results/private_grades.jsonl:15", "sha256": "31ca423ebfabbe5e7b019284026d4b5e56ffcf69cd0b4e76caf8bb4a870dae41"}, {"bundle_id": "gp7", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7/logs-31ca423ebfab.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7", "member": "graph-selectors-recovery-44-runs/runs/gp7_ancestry_logei/16_siim-isic-melanoma-classification/logs/journal.json", "sha256": "31ca423ebfabbe5e7b019284026d4b5e56ffcf69cd0b4e76caf8bb4a870dae41"}], "alternate_scores": [], "journal_ref": "gp7:graph-selectors-recovery-44-runs/runs/gp7_ancestry_logei/16_siim-isic-melanoma-classification/logs/journal.json", "metrics": [{"event_id": "f62cc787fef34040ad536122e8ffa4cc", "step": 6, "value": 0.8942459434305831, "stage": "debug", "created_at": 1789265057.8425562}, {"event_id": "7076d67cc8754dbfaa6c3bd46c49414e", "step": 7, "value": 0.8535975864160523, "stage": "debug", "created_at": 1789266200.018185}, {"event_id": "23a0545c4d21463aa02d8c2346ff4696", "step": 9, "value": 0.6868268152315811, "stage": "debug", "created_at": 1789271260.387072}, {"event_id": "68978937b5da4814b2f77a98f32c2f19", "step": 11, "value": 0.8840627728166777, "stage": "debug", "created_at": 1789277576.6672857}], "maximize": true, "elapsed_seconds": 28759.37921476364, "node_count": 12, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-recovery-20260913/xixian.gp7-ancestry-logei.siim-isic-melanoma-classification.yaml", "note": ""}, {"id": "xixian.gp7-ancestry-logei.spooky-author-identification", "experiment_id": "mlebench-gp7-recovery-20260913", "family": "MLEBench", "method": "gp7_ancestry_logei", "dataset": "spooky-author-identification", "status": "archived", "official_score": 0.2278, "medal": "silver", "valid_submission": true, "score_maximize": false, "thresholds": {"gold": 0.16506, "silver": 0.26996, "bronze": 0.29381}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7/logs-31ca423ebfab.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7", "member": "graph-selectors-recovery-44-runs/results/private_grades.jsonl:16", "sha256": "31ca423ebfabbe5e7b019284026d4b5e56ffcf69cd0b4e76caf8bb4a870dae41"}, {"bundle_id": "gp7", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7/logs-31ca423ebfab.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7", "member": "graph-selectors-recovery-44-runs/runs/gp7_ancestry_logei/17_spooky-author-identification/logs/journal.json", "sha256": "31ca423ebfabbe5e7b019284026d4b5e56ffcf69cd0b4e76caf8bb4a870dae41"}], "alternate_scores": [], "journal_ref": "gp7:graph-selectors-recovery-44-runs/runs/gp7_ancestry_logei/17_spooky-author-identification/logs/journal.json", "metrics": [{"event_id": "9762cc31a08743cc88425481de00baad", "step": 7, "value": 0.35910943150520325, "stage": "draft", "created_at": 1789264245.6627307}, {"event_id": "68760bc210fc455284b61ad1f6628327", "step": 8, "value": 0.4475047843470357, "stage": "debug", "created_at": 1789265074.4626644}, {"event_id": "a3a78b3c97924f6c84b19f83ee129bf3", "step": 9, "value": 0.5101989414200363, "stage": "debug", "created_at": 1789265415.4483202}, {"event_id": "e70e237066064ef5abaccd1672292b64", "step": 10, "value": 0.3242208819628049, "stage": "improve", "created_at": 1789265753.7440975}, {"event_id": "276dc2b86bc74df2850c3966eb2e14ec", "step": 11, "value": 0.32374425105417554, "stage": "improve", "created_at": 1789265828.9209225}, {"event_id": "07e1d50593bf4e33af4f05249f4e35fe", "step": 12, "value": 0.33650538798579055, "stage": "improve", "created_at": 1789265488.6777632}, {"event_id": "e6fa92bcfc254def971ade67d34186a5", "step": 13, "value": 0.33234907260083646, "stage": "improve", "created_at": 1789266579.441779}, {"event_id": "25cb49ccb5bb4b2d82f12a28ad940108", "step": 14, "value": 0.3330306411044959, "stage": "improve", "created_at": 1789267414.2795336}, {"event_id": "3aec4c3b7e9d4d8ebc4ac5168928de5d", "step": 15, "value": 0.2674014142484045, "stage": "improve", "created_at": 1789266646.9564118}, {"event_id": "04605f52c59c4e70959e61861f06d3f9", "step": 16, "value": 0.26358560604757747, "stage": "improve", "created_at": 1789267064.3895032}, {"event_id": "73b3d7b4e6c64b53a18b1de4b83c1b1e", "step": 17, "value": 0.25104436003727526, "stage": "improve", "created_at": 1789269448.4821265}, {"event_id": "22817735631947bd9b240759de4acc71", "step": 19, "value": 0.27197583487974397, "stage": "improve", "created_at": 1789273874.7460883}, {"event_id": "37c54c2be13e475c8f3656aa86ebaed8", "step": 20, "value": 0.28162496784032404, "stage": "improve", "created_at": 1789278009.5908556}, {"event_id": "7ccdf0f0405f40c8973b7307d6781123", "step": 21, "value": 0.25120058506681414, "stage": "improve", "created_at": 1789281271.8164554}], "maximize": false, "elapsed_seconds": 28748.690499782562, "node_count": 23, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-recovery-20260913/xixian.gp7-ancestry-logei.spooky-author-identification.yaml", "note": ""}, {"id": "xixian.gp7-ancestry-logei.tabular-playground-series-dec-2021", "experiment_id": "mlebench-gp7-recovery-20260913", "family": "MLEBench", "method": "gp7_ancestry_logei", "dataset": "tabular-playground-series-dec-2021", "status": "archived", "official_score": 0.96325, "medal": "gold", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.9566, "silver": 0.95658, "bronze": 0.95658}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7/logs-31ca423ebfab.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7", "member": "graph-selectors-recovery-44-runs/results/private_grades.jsonl:17", "sha256": "31ca423ebfabbe5e7b019284026d4b5e56ffcf69cd0b4e76caf8bb4a870dae41"}, {"bundle_id": "gp7", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7/logs-31ca423ebfab.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7", "member": "graph-selectors-recovery-44-runs/runs/gp7_ancestry_logei/18_tabular-playground-series-dec-2021/logs/journal.json", "sha256": "31ca423ebfabbe5e7b019284026d4b5e56ffcf69cd0b4e76caf8bb4a870dae41"}], "alternate_scores": [], "journal_ref": "gp7:graph-selectors-recovery-44-runs/runs/gp7_ancestry_logei/18_tabular-playground-series-dec-2021/logs/journal.json", "metrics": [{"event_id": "048020501b6648818175204473337fad", "step": 7, "value": 0.9607277777777777, "stage": "debug", "created_at": 1789265366.075179}, {"event_id": "e4f9d39815844c5b9456fe2fdc8e661a", "step": 8, "value": 0.948175, "stage": "debug", "created_at": 1789265458.594416}, {"event_id": "3f3e0e343fb349f2bf74667faf3aff85", "step": 9, "value": 0.9622388888888889, "stage": "debug", "created_at": 1789265692.7385378}, {"event_id": "d80335735c0c4cb490aa5eddbd8144b6", "step": 10, "value": 0.9622583333333333, "stage": "improve", "created_at": 1789267429.4028132}, {"event_id": "e8dd140d646648c3891b5f295497730d", "step": 11, "value": 0.9623805555555556, "stage": "improve", "created_at": 1789268890.595194}, {"event_id": "07d1b940780a4576a4d27b4ba3fa501c", "step": 12, "value": 0.9622861111111111, "stage": "improve", "created_at": 1789265832.7052953}], "maximize": true, "elapsed_seconds": 28759.424073934555, "node_count": 14, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-recovery-20260913/xixian.gp7-ancestry-logei.tabular-playground-series-dec-2021.yaml", "note": ""}, {"id": "xixian.gp7-ancestry-logei.tabular-playground-series-may-2022", "experiment_id": "mlebench-gp7-recovery-20260913", "family": "MLEBench", "method": "gp7_ancestry_logei", "dataset": "tabular-playground-series-may-2022", "status": "archived", "official_score": 0.99219, "medal": "none", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.99823, "silver": 0.99822, "bronze": 0.99818}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7/logs-31ca423ebfab.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7", "member": "graph-selectors-recovery-44-runs/results/private_grades.jsonl:18", "sha256": "31ca423ebfabbe5e7b019284026d4b5e56ffcf69cd0b4e76caf8bb4a870dae41"}, {"bundle_id": "gp7", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7/logs-31ca423ebfab.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7", "member": "graph-selectors-recovery-44-runs/runs/gp7_ancestry_logei/19_tabular-playground-series-may-2022/logs/journal.json", "sha256": "31ca423ebfabbe5e7b019284026d4b5e56ffcf69cd0b4e76caf8bb4a870dae41"}], "alternate_scores": [], "journal_ref": "gp7:graph-selectors-recovery-44-runs/runs/gp7_ancestry_logei/19_tabular-playground-series-may-2022/logs/journal.json", "metrics": [{"event_id": "b1755aa51bf44b91a82261f4aba59a66", "step": 2, "value": 0.9060135391953745, "stage": "draft", "created_at": 1789264811.010293}, {"event_id": "ecb6eac80e8c4994816a4e340491f213", "step": 3, "value": 0.6774628111028638, "stage": "draft", "created_at": 1789265223.172008}, {"event_id": "eca07335326f44429aacddd70d809bb3", "step": 4, "value": 0.815363320422972, "stage": "debug", "created_at": 1789265321.4458218}, {"event_id": "33621b636df444528afe644a39e48a2d", "step": 5, "value": 0.9058716662348378, "stage": "improve", "created_at": 1789265607.9640882}, {"event_id": "b172ca6bf81844e9ad0dfc9f395da82b", "step": 6, "value": 0.9897739474514159, "stage": "improve", "created_at": 1789265543.7107687}, {"event_id": "bae2fc218ef94b92b4b99143a663d6ee", "step": 7, "value": 0.9510235258837375, "stage": "improve", "created_at": 1789265615.4279683}, {"event_id": "cbc06258a5d74db4a5056eb6d03090fb", "step": 8, "value": 0.8987584168127676, "stage": "improve", "created_at": 1789265860.0248487}, {"event_id": "c06212928c28480894147de1412a65ab", "step": 10, "value": 0.9919041461332192, "stage": "improve", "created_at": 1789266946.4416416}, {"event_id": "9383812535eb468c9dd1d68efb7c4e6c", "step": 11, "value": 0.9901107020877464, "stage": "debug", "created_at": 1789268321.5358083}, {"event_id": "819b864cc0ce4afb9caff668e9fd672f", "step": 12, "value": 0.9915828844997322, "stage": "improve", "created_at": 1789267631.5205376}, {"event_id": "3f8e88635bc34db3a3ad08be7c5a8370", "step": 13, "value": 0.9916855803145016, "stage": "improve", "created_at": 1789270960.1234305}, {"event_id": "2067a67104d1405283e765a621a9dc0e", "step": 14, "value": 0.9923434151948894, "stage": "improve", "created_at": 1789269578.2482247}], "maximize": true, "elapsed_seconds": 28764.50138449669, "node_count": 15, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-recovery-20260913/xixian.gp7-ancestry-logei.tabular-playground-series-may-2022.yaml", "note": ""}, {"id": "xixian.gp7-ancestry-logei.text-normalization-challenge-english-language", "experiment_id": "mlebench-gp7-recovery-20260913", "family": "MLEBench", "method": "gp7_ancestry_logei", "dataset": "text-normalization-challenge-english-language", "status": "archived", "official_score": 0.99346, "medal": "silver", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.99724, "silver": 0.99135, "bronze": 0.99038}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7/logs-31ca423ebfab.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7", "member": "graph-selectors-recovery-44-runs/results/private_grades.jsonl:19", "sha256": "31ca423ebfabbe5e7b019284026d4b5e56ffcf69cd0b4e76caf8bb4a870dae41"}, {"bundle_id": "gp7", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7/logs-31ca423ebfab.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7", "member": "graph-selectors-recovery-44-runs/runs/gp7_ancestry_logei/20_text-normalization-challenge-english-language/logs/journal.json", "sha256": "31ca423ebfabbe5e7b019284026d4b5e56ffcf69cd0b4e76caf8bb4a870dae41"}], "alternate_scores": [], "journal_ref": "gp7:graph-selectors-recovery-44-runs/runs/gp7_ancestry_logei/20_text-normalization-challenge-english-language/logs/journal.json", "metrics": [{"event_id": "c1514010659d4f15ad0810d0dc185757", "step": 6, "value": 0.9398623212392211, "stage": "debug", "created_at": 1789266213.6996996}, {"event_id": "12af9f013e0e418c8bb430433c7c349b", "step": 7, "value": 0.9684099447679205, "stage": "debug", "created_at": 1789265777.263467}, {"event_id": "7eafa167513e408d828cf80deee7ea88", "step": 8, "value": 0.9336123563041051, "stage": "improve", "created_at": 1789268186.5780785}, {"event_id": "23ce80b5f48746b0b91cdaa7814c8a2d", "step": 10, "value": 0.9787827987247227, "stage": "improve", "created_at": 1789270290.2110415}, {"event_id": "3efeb048a23f4f1ab4467ea541543a1d", "step": 11, "value": 0.9906599410259097, "stage": "debug", "created_at": 1789272010.1705647}, {"event_id": "9a56ddef18ce467486672a44b4b572df", "step": 12, "value": 0.9912212426469488, "stage": "improve", "created_at": 1789274699.975858}, {"event_id": "5ccd796a012d404388519af9a3065d00", "step": 14, "value": 0.9627379028638118, "stage": "debug", "created_at": 1789287277.9145343}], "maximize": true, "elapsed_seconds": 28770.668658018112, "node_count": 15, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-recovery-20260913/xixian.gp7-ancestry-logei.text-normalization-challenge-english-language.yaml", "note": ""}, {"id": "xixian.gp7-ancestry-logei.text-normalization-challenge-russian-language", "experiment_id": "mlebench-gp7-recovery-20260913", "family": "MLEBench", "method": "gp7_ancestry_logei", "dataset": "text-normalization-challenge-russian-language", "status": "archived", "official_score": 0.9824, "medal": "silver", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.99012, "silver": 0.98232, "bronze": 0.97592}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7/logs-31ca423ebfab.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7", "member": "graph-selectors-recovery-44-runs/results/private_grades.jsonl:20", "sha256": "31ca423ebfabbe5e7b019284026d4b5e56ffcf69cd0b4e76caf8bb4a870dae41"}, {"bundle_id": "gp7", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7/logs-31ca423ebfab.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7", "member": "graph-selectors-recovery-44-runs/runs/gp7_ancestry_logei/21_text-normalization-challenge-russian-language/logs/journal.json", "sha256": "31ca423ebfabbe5e7b019284026d4b5e56ffcf69cd0b4e76caf8bb4a870dae41"}], "alternate_scores": [], "journal_ref": "gp7:graph-selectors-recovery-44-runs/runs/gp7_ancestry_logei/21_text-normalization-challenge-russian-language/logs/journal.json", "metrics": [{"event_id": "12796532640a486d8640db365fa4ccf8", "step": 4, "value": 0.9518408459939453, "stage": "debug", "created_at": 1789265968.4504874}, {"event_id": "1606c5128032425898174cad2ab62e64", "step": 5, "value": 0.7049360648975663, "stage": "draft", "created_at": 1789265482.0219643}, {"event_id": "644f1f60ebc94e88bdb851737ef8e0cc", "step": 7, "value": 0.9523361095997434, "stage": "improve", "created_at": 1789269033.1896298}, {"event_id": "06db6906330d4ff495e05437adf8d671", "step": 8, "value": 0.9351869554529811, "stage": "debug", "created_at": 1789265793.6125405}, {"event_id": "f1e2d3170aec4fe8af7ca9db63bf8f9c", "step": 9, "value": 0.9807509870394397, "stage": "debug", "created_at": 1789269288.9017897}, {"event_id": "67ba5df5e48143a49c05d915d9e9b9f5", "step": 10, "value": 0.9766214651432079, "stage": "improve", "created_at": 1789270485.7752953}, {"event_id": "ff93f05085044afca539c7d87db9a5b0", "step": 11, "value": 0.9674835028390463, "stage": "improve", "created_at": 1789271228.283256}, {"event_id": "5af3fae662c64cf5ad856b05c1894be9", "step": 12, "value": 0.9826483349377084, "stage": "improve", "created_at": 1789273425.6313841}, {"event_id": "5ec119c6d9fc40c6afdf1d5ffa4bcb16", "step": 16, "value": 0.9712991252668145, "stage": "improve", "created_at": 1789277498.3944364}], "maximize": true, "elapsed_seconds": 28763.514688014984, "node_count": 18, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-recovery-20260913/xixian.gp7-ancestry-logei.text-normalization-challenge-russian-language.yaml", "note": ""}, {"id": "xixian.gp7-ancestry-logei.the-icml-2013-whale-challenge-right-whale-redux", "experiment_id": "mlebench-gp7-recovery-20260913", "family": "MLEBench", "method": "gp7_ancestry_logei", "dataset": "the-icml-2013-whale-challenge-right-whale-redux", "status": "archived", "official_score": 0.99106, "medal": "gold", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.98961, "silver": 0.95017, "bronze": 0.90521}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7/logs-31ca423ebfab.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7", "member": "graph-selectors-recovery-44-runs/results/private_grades.jsonl:21", "sha256": "31ca423ebfabbe5e7b019284026d4b5e56ffcf69cd0b4e76caf8bb4a870dae41"}, {"bundle_id": "gp7", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7/logs-31ca423ebfab.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7", "member": "graph-selectors-recovery-44-runs/runs/gp7_ancestry_logei/22_the-icml-2013-whale-challenge-right-whale-redux/logs/journal.json", "sha256": "31ca423ebfabbe5e7b019284026d4b5e56ffcf69cd0b4e76caf8bb4a870dae41"}], "alternate_scores": [], "journal_ref": "gp7:graph-selectors-recovery-44-runs/runs/gp7_ancestry_logei/22_the-icml-2013-whale-challenge-right-whale-redux/logs/journal.json", "metrics": [{"event_id": "22951ec333fd481f96b3b3c4551638a7", "step": 2, "value": 0.983512145688058, "stage": "draft", "created_at": 1789265609.5287287}, {"event_id": "2fca433b433a4c36bce2629c614d6a86", "step": 3, "value": 0.6578895154944034, "stage": "debug", "created_at": 1789266133.9373145}, {"event_id": "802192b6716d44cf8438b5e0ac2734c4", "step": 4, "value": 0.7979458811148793, "stage": "draft", "created_at": 1789265389.7110794}, {"event_id": "e6135f76ab5a4967b42cd043666b8a0e", "step": 5, "value": 0.9868057032994748, "stage": "improve", "created_at": 1789267036.2941623}, {"event_id": "b685a5f0fae3492cbbbf36860b0af972", "step": 6, "value": 0.6717599470994791, "stage": "improve", "created_at": 1789267067.319023}, {"event_id": "68aaad2162e242c592eb01b0a49bc786", "step": 7, "value": 0.8767638054487517, "stage": "improve", "created_at": 1789267468.682155}, {"event_id": "39728c8360cc4ddcb7897389bf99e2d0", "step": 8, "value": 0.9865807654767231, "stage": "improve", "created_at": 1789267683.7970605}, {"event_id": "82536bca0a4e4c1fa64901ac4a372340", "step": 9, "value": 0.8291909976124583, "stage": "improve", "created_at": 1789267057.379975}, {"event_id": "b9b373bb1a0f40479fe8200f60aaacbd", "step": 10, "value": 0.9869994405430261, "stage": "improve", "created_at": 1789267826.9946175}, {"event_id": "47895795c26747828ef7bbd058938d1b", "step": 12, "value": 0.9870150530681475, "stage": "improve", "created_at": 1789268335.9532213}, {"event_id": "94b71511571442518c10387056fb650e", "step": 13, "value": 0.9887951990555353, "stage": "improve", "created_at": 1789268084.8293781}, {"event_id": "154397704bd64896a2967eb061e06ba6", "step": 14, "value": 0.9868767427358811, "stage": "debug", "created_at": 1789268580.9463782}, {"event_id": "1af37db1dc114831a8961e1616a612b4", "step": 16, "value": 0.986040493800188, "stage": "improve", "created_at": 1789268851.7976446}, {"event_id": "cc241959d2cc40d2a11e5ab068af2a1d", "step": 17, "value": 0.9864928165499423, "stage": "improve", "created_at": 1789268925.1749964}, {"event_id": "110962995d2f4aa08edce40082332614", "step": 18, "value": 0.9865376474998204, "stage": "debug", "created_at": 1789269175.126527}, {"event_id": "ca54a1826fc64198bb5b1f1851c44724", "step": 21, "value": 0.9928403427125787, "stage": "improve", "created_at": 1789269331.5690491}, {"event_id": "a8e52bc2b7864d2fafd360e234a036bb", "step": 22, "value": 0.9963564902527617, "stage": "debug", "created_at": 1789270061.318409}, {"event_id": "f396c678ff9e49c9b2db23f44a3cb11c", "step": 23, "value": 0.9885879789607572, "stage": "debug", "created_at": 1789270143.4144018}, {"event_id": "649fd33c94954827921565252a1e2194", "step": 25, "value": 0.9928808631229826, "stage": "improve", "created_at": 1789270295.744167}, {"event_id": "de318371902c4be5bd5070aaea7389b2", "step": 26, "value": 0.9970097859977881, "stage": "improve", "created_at": 1789270908.8008366}, {"event_id": "10f57f36706d42f49c8b1b305ddb8f85", "step": 28, "value": 0.9978790465641415, "stage": "debug", "created_at": 1789271275.4236329}, {"event_id": "a51711cc32654369a980e98ca8ca8329", "step": 29, "value": 0.9988538481621255, "stage": "improve", "created_at": 1789271569.3448248}, {"event_id": "7e70c80a8de1467b84ab4edd603c6f7c", "step": 30, "value": 0.991231906032574, "stage": "debug", "created_at": 1789271835.5796754}, {"event_id": "6b3e94893a674e989ebcd1f72efd7fcf", "step": 31, "value": 0.9080800161329783, "stage": "improve", "created_at": 1789272328.2989585}, {"event_id": "dace7c2131d3402c86688f3341c10c76", "step": 32, "value": 0.9890941330075398, "stage": "improve", "created_at": 1789272532.3069258}, {"event_id": "95474d6a2c9d4f02a699e3dceb50e140", "step": 33, "value": 0.9980810112649982, "stage": "improve", "created_at": 1789272219.1534142}, {"event_id": "7842d08bf43740f7894b66e151d1caf9", "step": 35, "value": 0.9972111025449194, "stage": "evolution", "created_at": 1789273267.9392414}, {"event_id": "6016efaf4e7043e8808ad641b204e53d", "step": 36, "value": 0.9941532645040168, "stage": "improve", "created_at": 1789273175.1863184}, {"event_id": "a0a254361cc44f9ab5896e2376edb73d", "step": 37, "value": 0.9949969013930897, "stage": "debug", "created_at": 1789273613.403059}, {"event_id": "5efb914e49e5475fa5c921318af0e238", "step": 38, "value": 0.9980810112649982, "stage": "evolution", "created_at": 1789274082.0677304}, {"event_id": "28f9e5eca89a4250913531132b90e23d", "step": 39, "value": 0.9940276307068964, "stage": "evolution", "created_at": 1789274427.1184027}, {"event_id": "a00c0ed497194e279e957c65e86a870c", "step": 41, "value": 0.9977574637278052, "stage": "evolution", "created_at": 1789275534.7324386}, {"event_id": "602866086dca4770862df43ddcf53377", "step": 42, "value": 0.9984682399057186, "stage": "evolution", "created_at": 1789275810.375721}, {"event_id": "dd083eb789f74690b388bc5e897f5c03", "step": 43, "value": 0.9981457834272969, "stage": "debug", "created_at": 1789276458.937905}, {"event_id": "51c75d9c34ea4856a0fad3ec7ded1a57", "step": 44, "value": 0.9991566007672931, "stage": "evolution", "created_at": 1789277355.0107672}, {"event_id": "7fc735ada77e42dcaf881b07c5e86f92", "step": 45, "value": 0.9959356872490619, "stage": "evolution", "created_at": 1789277497.860441}, {"event_id": "6bbd90e1230e47d6b60cd1a280c943d9", "step": 46, "value": 0.9993424264403854, "stage": "evolution", "created_at": 1789278669.0108268}, {"event_id": "15c78219740e4597a313d39509661e1f", "step": 47, "value": 0.9981703916637404, "stage": "improve", "created_at": 1789279004.8519154}, {"event_id": "e821f8aacdf440359748519ec6742f94", "step": 48, "value": 0.9969019116127456, "stage": "improve", "created_at": 1789279368.4819372}, {"event_id": "bdac5f58fafa449790512755a881a855", "step": 49, "value": 0.9984682399057186, "stage": "improve", "created_at": 1789281217.4960265}, {"event_id": "c0114a4aef3741c89d946dab03c60394", "step": 50, "value": 0.9982202562903535, "stage": "improve", "created_at": 1789281753.6559489}, {"event_id": "b60bf050df2a48d9b09829694d49ec16", "step": 51, "value": 0.9874352159548828, "stage": "improve", "created_at": 1789281896.4953554}, {"event_id": "96a565babbd94f80a3bd36a46afe94c2", "step": 52, "value": 0.9994220413229976, "stage": "fusion", "created_at": 1789282749.1198187}, {"event_id": "011a61cbbe2f4e78bce57f0384a72738", "step": 53, "value": 0.9999657342730468, "stage": "evolution", "created_at": 1789284390.7023995}, {"event_id": "78c2e519032344a39bcde7661c94b69f", "step": 54, "value": 0.9995002302674135, "stage": "evolution", "created_at": 1789283747.7832131}, {"event_id": "d735c3e4d6a341fe8585adb9bca80b1f", "step": 55, "value": 0.9994768751281724, "stage": "improve", "created_at": 1789285485.6885855}, {"event_id": "dadd7e413caa4570a311badcb7d5607f", "step": 56, "value": 0.9986302567319623, "stage": "improve", "created_at": 1789286775.9906454}, {"event_id": "f9699c19fb334b3e86492697c47e9f65", "step": 57, "value": 0.9877268851313449, "stage": "improve", "created_at": 1789286436.1720686}, {"event_id": "167808b01f1142508e8f237644e118ed", "step": 58, "value": 0.9967601928006714, "stage": "improve", "created_at": 1789288078.4847274}, {"event_id": "2c8512b5845140e8b7e29b10ebdcef6e", "step": 59, "value": 0.997252627593598, "stage": "evolution", "created_at": 1789288643.7827337}, {"event_id": "4205dc4e494a46dd81a1d7e0c3d2549a", "step": 60, "value": 0.9991858757105601, "stage": "evolution", "created_at": 1789288832.6494296}, {"event_id": "bdbf30a624d14ff2804edcb3d2c36354", "step": 61, "value": 0.9951715788221043, "stage": "evolution", "created_at": 1789289673.8989441}], "maximize": true, "elapsed_seconds": 28341.973992824554, "node_count": 62, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-recovery-20260913/xixian.gp7-ancestry-logei.the-icml-2013-whale-challenge-right-whale-redux.yaml", "note": ""}, {"id": "xixian.laplacian-anchor-logei.aerial-cactus-identification", "experiment_id": "mlebench-gp7-recovery-20260913", "family": "MLEBench", "method": "laplacian_anchor_logei", "dataset": "aerial-cactus-identification", "status": "archived", "official_score": 1.0, "medal": "gold", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 1.0, "silver": 1.0, "bronze": 1.0}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7/logs-31ca423ebfab.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7", "member": "graph-selectors-recovery-44-runs/results/private_grades.jsonl:22", "sha256": "31ca423ebfabbe5e7b019284026d4b5e56ffcf69cd0b4e76caf8bb4a870dae41"}, {"bundle_id": "gp7", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7/logs-31ca423ebfab.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7", "member": "graph-selectors-recovery-44-runs/runs/laplacian_anchor_logei/01_aerial-cactus-identification/logs/journal.json", "sha256": "31ca423ebfabbe5e7b019284026d4b5e56ffcf69cd0b4e76caf8bb4a870dae41"}], "alternate_scores": [], "journal_ref": "gp7:graph-selectors-recovery-44-runs/runs/laplacian_anchor_logei/01_aerial-cactus-identification/logs/journal.json", "metrics": [{"event_id": "7c6e7f08f53f4925b2844e4b3bb8aa69", "step": 2, "value": 0.9998750795484007, "stage": "draft", "created_at": 1789264466.9623113}, {"event_id": "8c040062b877441fa03b63f6a2be3818", "step": 3, "value": 0.9999446107431589, "stage": "draft", "created_at": 1789264263.8469002}, {"event_id": "7703b9d1ab164e44bdd86ad2c33d0534", "step": 4, "value": 0.9999446107431588, "stage": "improve", "created_at": 1789265108.1185846}, {"event_id": "6b0d64da696b4292b29d179d27978122", "step": 5, "value": 0.9999787704649401, "stage": "debug", "created_at": 1789264832.3339329}, {"event_id": "bd4a51499e184e9e9fc24a371c051537", "step": 6, "value": 0.9999599311759022, "stage": "improve", "created_at": 1789265110.25783}, {"event_id": "c0ad6801f5614205a2cae0764ab4c17e", "step": 7, "value": 0.9999493247224644, "stage": "improve", "created_at": 1789266168.8971782}, {"event_id": "0fa449566d9743b788afb649d4919461", "step": 8, "value": 0.9999960194621762, "stage": "improve", "created_at": 1789266259.9990685}, {"event_id": "71be24296eb54cbc8913dc7b8b1eb321", "step": 9, "value": 0.9999814241568226, "stage": "improve", "created_at": 1789267663.4096894}, {"event_id": "058565d8033d4c9ba26ccc38cbdbf165", "step": 10, "value": 0.9997837241115771, "stage": "improve", "created_at": 1789270850.8911536}, {"event_id": "56cd19ba81534dd39c98be5e091592bc", "step": 12, "value": 0.9999960194621762, "stage": "improve", "created_at": 1789270398.965741}, {"event_id": "15b004c262a0404899db92204acabd2f", "step": 17, "value": 0.9999147501482751, "stage": "improve", "created_at": 1789283294.1099713}, {"event_id": "6d1bdf87c913465b9216ffb76634883c", "step": 18, "value": 1.0, "stage": "improve", "created_at": 1789285621.2581933}, {"event_id": "11fe68a754174285857801c69b0a4f74", "step": 22, "value": 0.9999988215051736, "stage": "fusion_draft", "created_at": 1789286279.5683887}, {"event_id": "8ef8d9593fca48cca2dbf7a1ae2e19aa", "step": 24, "value": 1.0, "stage": "debug", "created_at": 1789286725.0558946}, {"event_id": "1166fb41cfc64f099e46f0f5d7eb2f8b", "step": 26, "value": 0.982587149692413, "stage": "debug", "created_at": 1789287285.74273}, {"event_id": "cac0fc2b34a44fe39e42018e7e97f617", "step": 27, "value": 0.9999827510027639, "stage": "debug", "created_at": 1789281175.7667127}, {"event_id": "1855c2b7d16345af882bda640ab8354f", "step": 28, "value": 0.9999952860206943, "stage": "improve", "created_at": 1789288352.9426572}], "maximize": true, "elapsed_seconds": 28694.14228606224, "node_count": 30, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-recovery-20260913/xixian.laplacian-anchor-logei.aerial-cactus-identification.yaml", "note": ""}, {"id": "xixian.laplacian-anchor-logei.aptos2019-blindness-detection", "experiment_id": "mlebench-gp7-recovery-20260913", "family": "MLEBench", "method": "laplacian_anchor_logei", "dataset": "aptos2019-blindness-detection", "status": "archived", "official_score": 0.89544, "medal": "none", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.930508, "silver": 0.919654, "bronze": 0.914492}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7/logs-31ca423ebfab.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7", "member": "graph-selectors-recovery-44-runs/results/private_grades.jsonl:23", "sha256": "31ca423ebfabbe5e7b019284026d4b5e56ffcf69cd0b4e76caf8bb4a870dae41"}, {"bundle_id": "gp7", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7/logs-31ca423ebfab.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7", "member": "graph-selectors-recovery-44-runs/runs/laplacian_anchor_logei/02_aptos2019-blindness-detection/logs/journal.json", "sha256": "31ca423ebfabbe5e7b019284026d4b5e56ffcf69cd0b4e76caf8bb4a870dae41"}], "alternate_scores": [], "journal_ref": "gp7:graph-selectors-recovery-44-runs/runs/laplacian_anchor_logei/02_aptos2019-blindness-detection/logs/journal.json", "metrics": [{"event_id": "a6fbf8e50cb543ccaebea2bd67786772", "step": 2, "value": 0.904437998149685, "stage": "debug", "created_at": 1789265425.9891157}, {"event_id": "a2d9201c2c024fcb915b7d208bf56ed5", "step": 3, "value": 0.8932069569805348, "stage": "draft", "created_at": 1789264248.8620534}, {"event_id": "d26103fd6f7a47c5a83015df9787dc50", "step": 4, "value": 0.8793974366825142, "stage": "draft", "created_at": 1789264851.1153815}, {"event_id": "964a61517f884dbd813b92ed60403114", "step": 7, "value": 0.8953434774672321, "stage": "improve", "created_at": 1789268206.288106}, {"event_id": "2b3027e3f12e4e4b8e78593734970945", "step": 9, "value": 0.9103888953394734, "stage": "debug", "created_at": 1789268762.627282}, {"event_id": "dd9f9472419f43c5aea1ab9957b7800c", "step": 10, "value": 0.9001617215089607, "stage": "debug", "created_at": 1789269143.8690999}, {"event_id": "2fb24ecc0fd3488ebb7fce571cf2d7d8", "step": 11, "value": 0.9084281628430597, "stage": "improve", "created_at": 1789269548.552896}, {"event_id": "52152c83a99e4f5ea865ad954c576d54", "step": 12, "value": 0.9019517463813523, "stage": "debug", "created_at": 1789268763.4573195}, {"event_id": "625759668f8f4b45adc8221544f48ad7", "step": 13, "value": 0.9050712015585385, "stage": "improve", "created_at": 1789269843.596604}, {"event_id": "b8467ecde9164f7a9fca5c402cfec59a", "step": 14, "value": 0.9027215740991741, "stage": "evolution", "created_at": 1789271061.917563}, {"event_id": "bad0f1fcd1c145e0ab30a286cc911fc7", "step": 15, "value": 0.909024247810651, "stage": "evolution", "created_at": 1789270337.0607078}, {"event_id": "924b43d8f1d8493683b80f4a25bda58d", "step": 16, "value": 0.923692407452438, "stage": "evolution", "created_at": 1789272620.9203923}, {"event_id": "18c44d2ec49c4e518526e7c8622399f9", "step": 17, "value": 0.9137394878527876, "stage": "improve", "created_at": 1789270311.6177967}, {"event_id": "0c8a323e82e94e8283362a4df3e43ce8", "step": 18, "value": 0.9082328942615102, "stage": "improve", "created_at": 1789273394.842283}, {"event_id": "e4980ce497d54c06a89d1afca6197d2a", "step": 19, "value": 0.8538059395468591, "stage": "evolution", "created_at": 1789272980.992167}, {"event_id": "e6a63d970e224ac983d6763d5b72a31b", "step": 20, "value": 0.8908407686159343, "stage": "evolution", "created_at": 1789277135.9932284}, {"event_id": "1b115874859945bcadae26794cdee91b", "step": 21, "value": 0.9087024974674842, "stage": "improve", "created_at": 1789276414.6254723}, {"event_id": "2842f66732a9445781a2006cd41751d9", "step": 22, "value": 0.9049888179063941, "stage": "improve", "created_at": 1789273659.6332762}, {"event_id": "4c7653fc7de748cb9f6549bd10318e23", "step": 23, "value": 0.9237223563931355, "stage": "evolution", "created_at": 1789279275.8669362}, {"event_id": "78c611454c00409382ade98efe1f17b5", "step": 25, "value": 0.8869584162827036, "stage": "fusion", "created_at": 1789279063.987151}, {"event_id": "574123aa23b24861b21b4841e36e55a5", "step": 26, "value": 0.9082898141554155, "stage": "debug", "created_at": 1789282315.9455693}, {"event_id": "e892f3ad94c644e5ad9bbe457e909d0f", "step": 27, "value": 0.9304943841964648, "stage": "improve", "created_at": 1789280343.2224112}, {"event_id": "7d62edca71884f1199f7d68ff5dc9615", "step": 28, "value": 0.9170027433075577, "stage": "improve", "created_at": 1789285586.2198105}, {"event_id": "916fde8533ea47afbaa0be8a8de1d8e4", "step": 29, "value": 0.9184992617458134, "stage": "improve", "created_at": 1789283697.2580543}], "maximize": true, "elapsed_seconds": 28729.040051221848, "node_count": 30, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-recovery-20260913/xixian.laplacian-anchor-logei.aptos2019-blindness-detection.yaml", "note": ""}, {"id": "xixian.laplacian-anchor-logei.denoising-dirty-documents", "experiment_id": "mlebench-gp7-recovery-20260913", "family": "MLEBench", "method": "laplacian_anchor_logei", "dataset": "denoising-dirty-documents", "status": "archived", "official_score": 0.01464, "medal": "gold", "valid_submission": true, "score_maximize": false, "thresholds": {"gold": 0.01794, "silver": 0.02609, "bronze": 0.04517}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7/logs-31ca423ebfab.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7", "member": "graph-selectors-recovery-44-runs/results/private_grades.jsonl:24", "sha256": "31ca423ebfabbe5e7b019284026d4b5e56ffcf69cd0b4e76caf8bb4a870dae41"}, {"bundle_id": "gp7", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7/logs-31ca423ebfab.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7", "member": "graph-selectors-recovery-44-runs/runs/laplacian_anchor_logei/03_denoising-dirty-documents/logs/journal.json", "sha256": "31ca423ebfabbe5e7b019284026d4b5e56ffcf69cd0b4e76caf8bb4a870dae41"}], "alternate_scores": [], "journal_ref": "gp7:graph-selectors-recovery-44-runs/runs/laplacian_anchor_logei/03_denoising-dirty-documents/logs/journal.json", "metrics": [{"event_id": "8f6b49f73a9f4854acca1480f3b38afe", "step": 7, "value": 0.027196900063574374, "stage": "debug", "created_at": 1789265043.5816474}, {"event_id": "bb7970818c314f39af5e1fca046c9836", "step": 8, "value": 0.3453295157207539, "stage": "debug", "created_at": 1789264962.6938457}, {"event_id": "1e2f0abe12c04f9e89fb0c41a37685d1", "step": 9, "value": 0.5474909313253431, "stage": "debug", "created_at": 1789265361.5122092}, {"event_id": "77bd18afc58841b384d8ebf4b9cf0b4a", "step": 10, "value": 0.02136383855023188, "stage": "improve", "created_at": 1789265513.6653106}, {"event_id": "86122b8360164f30abc7fea4d321df27", "step": 13, "value": 0.019422112247082204, "stage": "improve", "created_at": 1789265506.9683626}, {"event_id": "de44e070e9924b6d9ca70d6ef54cbc29", "step": 15, "value": 0.020165125654809476, "stage": "improve", "created_at": 1789265947.661063}, {"event_id": "c28f6522354a480aa6236fa3a4817951", "step": 17, "value": 0.028304077262583775, "stage": "improve", "created_at": 1789266110.8830125}, {"event_id": "42d0ea39d1d84248a448e047bcf1a6af", "step": 18, "value": 0.026519650522765906, "stage": "improve", "created_at": 1789266339.5960965}, {"event_id": "6a1c81c261f9417a9adb511da72037e8", "step": 19, "value": 0.019184288523442766, "stage": "improve", "created_at": 1789266322.7393575}, {"event_id": "611b84783177473481186e9db5c29b3b", "step": 20, "value": 0.12389883466242048, "stage": "improve", "created_at": 1789266453.136534}, {"event_id": "9693f769dbfc4223ac7895142daf7d91", "step": 22, "value": 0.021957225134938047, "stage": "improve", "created_at": 1789266735.660947}, {"event_id": "75ac8236a6714733978d40bef3393e15", "step": 23, "value": 0.02879791583994481, "stage": "debug", "created_at": 1789266813.5166323}, {"event_id": "7f37ec9dc03b408e9710ed959c11d0dc", "step": 24, "value": 0.02190591413104897, "stage": "improve", "created_at": 1789266864.8123534}, {"event_id": "f81cd5c589914fd7b3a01be0ed3b451d", "step": 26, "value": 0.03783744438961042, "stage": "improve", "created_at": 1789267120.5400956}, {"event_id": "8bca0dcda04f4d08ba1a85bcd13d2c23", "step": 28, "value": 0.022571482805833893, "stage": "evolution", "created_at": 1789267243.4070754}, {"event_id": "76c771d5eb8743a4a2d727364c10d7b6", "step": 29, "value": 0.020700646349467194, "stage": "evolution", "created_at": 1789267465.457134}, {"event_id": "19bc8c0baba543409acb29b3e1e6d07c", "step": 30, "value": 0.017129438448764196, "stage": "debug", "created_at": 1789267438.8677664}, {"event_id": "75f0bf241349450499060ae1f57895e9", "step": 31, "value": 0.014336161243898507, "stage": "improve", "created_at": 1789268177.4530053}, {"event_id": "022b552737f34dd3b6d050789fe87702", "step": 32, "value": 0.018753525463528025, "stage": "evolution", "created_at": 1789268129.5132475}, {"event_id": "b7530fd250574ed7a4bd21c173db3055", "step": 33, "value": 0.04116883881596608, "stage": "evolution", "created_at": 1789268167.140805}, {"event_id": "bbedc318ac88455ea6d6789feaeaacf9", "step": 34, "value": 0.015121728188075109, "stage": "improve", "created_at": 1789268982.7105103}, {"event_id": "39dcc9373abb4ae6969e605caf37cd17", "step": 35, "value": 0.01600367064496314, "stage": "improve", "created_at": 1789269114.849576}, {"event_id": "6ff36d62d94248d6b4e0d2b5eb45dad0", "step": 36, "value": 0.015920233115266035, "stage": "improve", "created_at": 1789269259.133443}, {"event_id": "d9bb661b40d1411fa8c225552bb7deb1", "step": 37, "value": 0.02298634613508189, "stage": "evolution", "created_at": 1789269540.3222713}, {"event_id": "24e2c6f1e760440f8695e572e43c4240", "step": 38, "value": 0.014463619667616796, "stage": "evolution", "created_at": 1789269914.5724192}, {"event_id": "291023377e284568b3cbb3302a7dbee8", "step": 40, "value": 0.017462259253260674, "stage": "evolution", "created_at": 1789269839.0889332}, {"event_id": "b084f666e6da46b29d33e9f8a0f90f4f", "step": 41, "value": 0.019060289660422867, "stage": "debug", "created_at": 1789271533.0509129}, {"event_id": "31e317ce85f24191a2cbebb0d26e5d52", "step": 42, "value": 0.015108982992207184, "stage": "evolution", "created_at": 1789271199.7207835}, {"event_id": "286f3efa01bd43aa946b7cc2b055002c", "step": 43, "value": 0.01957455136094132, "stage": "evolution", "created_at": 1789271919.780261}, {"event_id": "0e7758df2c5e4b10be5aebf73cb33416", "step": 45, "value": 0.016186704924022004, "stage": "evolution", "created_at": 1789274651.1029143}, {"event_id": "4248835607b846f89e04861146083220", "step": 46, "value": 0.01877115394043, "stage": "debug", "created_at": 1789275439.1695485}, {"event_id": "5e5790c9fc4a4e52ac6d26e5e44e2027", "step": 47, "value": 0.014993858803084981, "stage": "evolution", "created_at": 1789272777.8177488}, {"event_id": "4220cac2086242b5a977b9a648bed818", "step": 48, "value": 0.01498377299467433, "stage": "fusion", "created_at": 1789278778.9160812}, {"event_id": "4d22c35d661248fdbaacbeab1b1771e6", "step": 49, "value": 0.015019910392648573, "stage": "evolution", "created_at": 1789280914.8926136}, {"event_id": "7f5b7648fb974ba4a4545d20467f458d", "step": 50, "value": 0.016021940070381314, "stage": "evolution", "created_at": 1789277151.5032635}, {"event_id": "3ec8e097077a49da837bbe5cd7c13774", "step": 51, "value": 0.11481757127759713, "stage": "evolution", "created_at": 1789278895.7492929}, {"event_id": "83f731b6835044c5a28f836b7c6d2229", "step": 52, "value": 0.014575128504037122, "stage": "evolution", "created_at": 1789283285.9256434}, {"event_id": "e25f3bd8c05d48bb884a0fc0f585c5b9", "step": 53, "value": 0.015329154999980783, "stage": "evolution", "created_at": 1789288234.2059634}], "maximize": false, "elapsed_seconds": 28769.586877822876, "node_count": 54, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-recovery-20260913/xixian.laplacian-anchor-logei.denoising-dirty-documents.yaml", "note": ""}, {"id": "xixian.laplacian-anchor-logei.detecting-insults-in-social-commentary", "experiment_id": "mlebench-gp7-recovery-20260913", "family": "MLEBench", "method": "laplacian_anchor_logei", "dataset": "detecting-insults-in-social-commentary", "status": "archived", "official_score": 0.95916, "medal": "gold", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.83321, "silver": 0.82307, "bronze": 0.79111}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7/logs-31ca423ebfab.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7", "member": "graph-selectors-recovery-44-runs/results/private_grades.jsonl:25", "sha256": "31ca423ebfabbe5e7b019284026d4b5e56ffcf69cd0b4e76caf8bb4a870dae41"}, {"bundle_id": "gp7", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7/logs-31ca423ebfab.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7", "member": "graph-selectors-recovery-44-runs/runs/laplacian_anchor_logei/04_detecting-insults-in-social-commentary/logs/journal.json", "sha256": "31ca423ebfabbe5e7b019284026d4b5e56ffcf69cd0b4e76caf8bb4a870dae41"}], "alternate_scores": [], "journal_ref": "gp7:graph-selectors-recovery-44-runs/runs/laplacian_anchor_logei/04_detecting-insults-in-social-commentary/logs/journal.json", "metrics": [{"event_id": "b5f98e0b5efb453fa402f3d569e98def", "step": 3, "value": 0.9557826487625065, "stage": "draft", "created_at": 1789264429.9979126}, {"event_id": "f1b9bad2eca342d69700053d93bf9c80", "step": 5, "value": 0.9566201076676851, "stage": "debug", "created_at": 1789264762.2445467}, {"event_id": "2f7c319e9f714779a21037edc5403202", "step": 6, "value": 0.9141179078014183, "stage": "debug", "created_at": 1789264953.0779681}, {"event_id": "2550dfde6f7c4006a7ca81ee100fe7f2", "step": 7, "value": 0.9529810097419694, "stage": "improve", "created_at": 1789264937.4416566}, {"event_id": "9fc1c67bceb44414b1ae3ba1936906d1", "step": 8, "value": 0.9416921286192346, "stage": "improve", "created_at": 1789265194.4140475}, {"event_id": "addbef1040f94c91bbcfd0abd50c35b1", "step": 9, "value": 0.9542994325622, "stage": "improve", "created_at": 1789265276.331965}, {"event_id": "53e98bf292a043f594f558fe68a3f61d", "step": 11, "value": 0.9500410509031199, "stage": "debug", "created_at": 1789265794.929128}, {"event_id": "346122cc6c634cca879fa153bfc4c5cf", "step": 12, "value": 0.9489651651544966, "stage": "improve", "created_at": 1789265576.878701}, {"event_id": "f8abb7163b25404fae90e87bc70550c2", "step": 13, "value": 0.9548086716135603, "stage": "evolution", "created_at": 1789266673.7316928}, {"event_id": "8e0b4add43794aa9a984d002b40444cc", "step": 14, "value": 0.953397351956933, "stage": "evolution", "created_at": 1789266362.6161056}, {"event_id": "f7d79ae71f6340bd922ec63cfcea8555", "step": 15, "value": 0.9406608943020432, "stage": "evolution", "created_at": 1789267115.0193348}, {"event_id": "f971063aac1f4a72bac19d3931083c7a", "step": 16, "value": 0.9369497125330839, "stage": "evolution", "created_at": 1789268467.3536744}, {"event_id": "c362c4c701164a9b84a14dea731fe9d0", "step": 17, "value": 0.9457799698815987, "stage": "evolution", "created_at": 1789268190.9202085}, {"event_id": "fdb62af282c04c9299081d084103d9b1", "step": 18, "value": 0.9497453804743197, "stage": "improve", "created_at": 1789265133.1649387}, {"event_id": "a0c693c4b74f48b7a10df95c8a674e02", "step": 20, "value": 0.943533918727685, "stage": "improve", "created_at": 1789269405.67588}, {"event_id": "12ba68ab8db840c0bed7ba474c3665ac", "step": 21, "value": 0.9470888505994404, "stage": "improve", "created_at": 1789269378.7480047}, {"event_id": "383e6c34bcd34ba392d9a677ed6b85d5", "step": 24, "value": 0.9585390337019484, "stage": "debug", "created_at": 1789270852.9096656}, {"event_id": "7db201f1db5c495daa0b1765ef483bc5", "step": 26, "value": 0.9625131648235913, "stage": "debug", "created_at": 1789271248.3373232}, {"event_id": "41f88f389ce544f5b384b88d5c24be58", "step": 27, "value": 0.9614599789362822, "stage": "improve", "created_at": 1789271344.0525777}, {"event_id": "95ad778ea3cf4b1892135ef7c1351216", "step": 28, "value": 0.9636239468141128, "stage": "improve", "created_at": 1789271877.7464087}, {"event_id": "65f0249587c44171883ed7f29deda3a5", "step": 29, "value": 0.9663145076355977, "stage": "improve", "created_at": 1789271861.453409}, {"event_id": "711d058450e74a00b59ef78463ca6da9", "step": 30, "value": 0.9593700631911533, "stage": "improve", "created_at": 1789272671.8830252}, {"event_id": "923e1096683b492592a54d393e8a2cf2", "step": 31, "value": 0.9615010121703869, "stage": "improve", "created_at": 1789272781.9478877}, {"event_id": "ae450b50bb2243acb6e81c58f857e635", "step": 33, "value": 0.9608368678704816, "stage": "improve", "created_at": 1789273555.630624}, {"event_id": "0f312232c1a2489591b44888edcfb4eb", "step": 36, "value": 0.5, "stage": "debug", "created_at": 1789277806.7747617}, {"event_id": "c21885a976794782899ed545b263aa13", "step": 37, "value": 0.9637144549763033, "stage": "evolution", "created_at": 1789278112.983008}, {"event_id": "0e102085b41444ee9bd86f587cce1351", "step": 38, "value": 0.9426418439716312, "stage": "fusion", "created_at": 1789278641.057088}, {"event_id": "94c55555dcac4d1a9e3b7f144e8fd7e0", "step": 40, "value": 0.9602414735253464, "stage": "evolution", "created_at": 1789279038.8932796}, {"event_id": "28f76da144594b49902983209914266f", "step": 41, "value": 0.9609750256743252, "stage": "debug", "created_at": 1789279833.1672132}, {"event_id": "2ef673663ce54ee1a16e95200091188b", "step": 43, "value": 0.9605194338687935, "stage": "evolution", "created_at": 1789282761.2389262}, {"event_id": "66a69676d94c42af8783b397e80b29a5", "step": 44, "value": 0.6319995842107999, "stage": "evolution", "created_at": 1789286457.0958433}, {"event_id": "52951e2495644b079903591fb9d35bd6", "step": 45, "value": 0.957901014538806, "stage": "evolution", "created_at": 1789287760.2535093}, {"event_id": "4588e0203aa74ff8b71b067d75e77138", "step": 46, "value": 0.9594270003769733, "stage": "evolution", "created_at": 1789284319.0023177}, {"event_id": "35c13b1b312d4c30b597721d3b7940c7", "step": 48, "value": 0.9468339165566338, "stage": "debug", "created_at": 1789290330.7983854}], "maximize": true, "elapsed_seconds": 28766.369040727615, "node_count": 49, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-recovery-20260913/xixian.laplacian-anchor-logei.detecting-insults-in-social-commentary.yaml", "note": ""}, {"id": "xixian.laplacian-anchor-logei.dog-breed-identification", "experiment_id": "mlebench-gp7-recovery-20260913", "family": "MLEBench", "method": "laplacian_anchor_logei", "dataset": "dog-breed-identification", "status": "archived", "official_score": 0.27908, "medal": "none", "valid_submission": true, "score_maximize": false, "thresholds": {"gold": 0.0005, "silver": 0.00539, "bronze": 0.04598}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7/logs-31ca423ebfab.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7", "member": "graph-selectors-recovery-44-runs/results/private_grades.jsonl:26", "sha256": "31ca423ebfabbe5e7b019284026d4b5e56ffcf69cd0b4e76caf8bb4a870dae41"}, {"bundle_id": "gp7", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7/logs-31ca423ebfab.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7", "member": "graph-selectors-recovery-44-runs/runs/laplacian_anchor_logei/05_dog-breed-identification/logs/journal.json", "sha256": "31ca423ebfabbe5e7b019284026d4b5e56ffcf69cd0b4e76caf8bb4a870dae41"}], "alternate_scores": [], "journal_ref": "gp7:graph-selectors-recovery-44-runs/runs/laplacian_anchor_logei/05_dog-breed-identification/logs/journal.json", "metrics": [{"event_id": "f58e5120def74c1c80aed8af1a9a3114", "step": 1, "value": 0.4880139950459244, "stage": "draft", "created_at": 1789264492.3419907}, {"event_id": "7def882f0dbc487e93760ce9b8ded440", "step": 3, "value": 0.46156357409394616, "stage": "draft", "created_at": 1789264221.0495992}, {"event_id": "4806910720a64a48ba8d4ef2916f8205", "step": 4, "value": 0.3987435647484071, "stage": "debug", "created_at": 1789265410.2427726}, {"event_id": "818e2e6ecc35448e9a08623fd07701e6", "step": 7, "value": 0.3887116107397087, "stage": "improve", "created_at": 1789265762.778469}, {"event_id": "b705402c4fa743c786b54538bd73e478", "step": 8, "value": 0.40121055658236826, "stage": "debug", "created_at": 1789266290.2984407}, {"event_id": "d20bca7c819748899cd1b693b22e1ce6", "step": 9, "value": 0.419860234069412, "stage": "debug", "created_at": 1789266454.939699}, {"event_id": "abba40c093154676af2a88ffc7ca4f05", "step": 10, "value": 0.3769173427889765, "stage": "improve", "created_at": 1789267279.2136326}, {"event_id": "45fa2c096f204932b0f08bc832a75eae", "step": 14, "value": 0.3887116107397087, "stage": "debug", "created_at": 1789268622.3559647}, {"event_id": "37fe391d994d4f42a9a35466c7d8092d", "step": 16, "value": 0.3878582453931324, "stage": "debug", "created_at": 1789268638.1985142}, {"event_id": "f4254b3ba8124898b4addf109f7eb012", "step": 17, "value": 0.40415379873614343, "stage": "debug", "created_at": 1789269926.1841843}, {"event_id": "2b386d8440384ed69ff2588cc8af75d1", "step": 18, "value": 0.247828017372333, "stage": "improve", "created_at": 1789270316.7238877}, {"event_id": "923d5c37d45841209523887ef7e27bc2", "step": 21, "value": 0.25090464597445733, "stage": "debug", "created_at": 1789271958.0854394}, {"event_id": "0ed529daff7343b8aa69d3a11b48174e", "step": 29, "value": 0.3831603152228424, "stage": "debug", "created_at": 1789275829.6464598}, {"event_id": "30d57330c6474c53adc3afcb23c6e84c", "step": 30, "value": 0.2577941719440947, "stage": "debug", "created_at": 1789276669.600079}, {"event_id": "3f9dcd19362b44018916d0b3144cfe53", "step": 32, "value": 0.2453752652602886, "stage": "improve", "created_at": 1789278418.5176544}, {"event_id": "e544dabb06cf4af5ba1b44ae87149273", "step": 34, "value": 0.13097768166875215, "stage": "debug", "created_at": 1789279022.7088332}, {"event_id": "4f09699cba9a466cb057062cdda15e5c", "step": 35, "value": 0.24657099456654114, "stage": "improve", "created_at": 1789280676.2616932}, {"event_id": "1496a7e5ca32435aa14c707520478ff9", "step": 36, "value": 0.2896791483592887, "stage": "fusion", "created_at": 1789278820.6243062}, {"event_id": "72a69814053140f0871788c34accb5df", "step": 37, "value": 0.10345464241356919, "stage": "improve", "created_at": 1789280806.993883}, {"event_id": "acb27b6abc524d139c91a043003e4f73", "step": 38, "value": 0.12227294937662188, "stage": "improve", "created_at": 1789282142.83248}, {"event_id": "00b004de988144878541beb4c389f4bb", "step": 39, "value": 0.12754487702212702, "stage": "improve", "created_at": 1789282878.4203055}, {"event_id": "906dcedfcc0744c99a79b1eadeaa4771", "step": 40, "value": 0.12756368090842418, "stage": "improve", "created_at": 1789284329.033523}, {"event_id": "4e4bff987c2743dfb68cc0fa6b4ac616", "step": 41, "value": 0.11331697948037597, "stage": "improve", "created_at": 1789282222.5758338}, {"event_id": "fc2a9d5c239e46cca90dd40ed2dbc3b1", "step": 45, "value": 0.14995899371187382, "stage": "debug", "created_at": 1789289174.0950406}, {"event_id": "acbeb1471fed4f0797bed66e50b776c7", "step": 47, "value": 0.14756266949276725, "stage": "debug", "created_at": 1789290705.564981}], "maximize": false, "elapsed_seconds": 28746.344382047653, "node_count": 50, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-recovery-20260913/xixian.laplacian-anchor-logei.dog-breed-identification.yaml", "note": ""}, {"id": "xixian.laplacian-anchor-logei.dogs-vs-cats-redux-kernels-edition", "experiment_id": "mlebench-gp7-recovery-20260913", "family": "MLEBench", "method": "laplacian_anchor_logei", "dataset": "dogs-vs-cats-redux-kernels-edition", "status": "archived", "official_score": 0.00144, "medal": "gold", "valid_submission": true, "score_maximize": false, "thresholds": {"gold": 0.03882, "silver": 0.05038, "bronze": 0.06127}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7/logs-31ca423ebfab.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7", "member": "graph-selectors-recovery-44-runs/results/private_grades.jsonl:27", "sha256": "31ca423ebfabbe5e7b019284026d4b5e56ffcf69cd0b4e76caf8bb4a870dae41"}, {"bundle_id": "gp7", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7/logs-31ca423ebfab.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7", "member": "graph-selectors-recovery-44-runs/runs/laplacian_anchor_logei/06_dogs-vs-cats-redux-kernels-edition/logs/journal.json", "sha256": "31ca423ebfabbe5e7b019284026d4b5e56ffcf69cd0b4e76caf8bb4a870dae41"}], "alternate_scores": [], "journal_ref": "gp7:graph-selectors-recovery-44-runs/runs/laplacian_anchor_logei/06_dogs-vs-cats-redux-kernels-edition/logs/journal.json", "metrics": [{"event_id": "de4797fb43c04f299d6c6a02dcb61c63", "step": 2, "value": 0.0026429401523943995, "stage": "draft", "created_at": 1789264407.29844}, {"event_id": "d3966bb829fd475997c7a919d415bb67", "step": 3, "value": 0.005499536712875831, "stage": "draft", "created_at": 1789264215.2643547}, {"event_id": "d84d4dca01a64ebf84249f23b386582f", "step": 4, "value": 0.09094397285036589, "stage": "debug", "created_at": 1789264754.4774244}, {"event_id": "b40fc2b5008447cc8d29bc586f5a22b8", "step": 6, "value": 0.002539861024115793, "stage": "improve", "created_at": 1789265077.5845208}, {"event_id": "dfe0c853bb5449a283430576a632caf3", "step": 7, "value": 0.01575488469055664, "stage": "debug", "created_at": 1789265224.7714798}, {"event_id": "734735c37f81481a9dadccf8ff25b747", "step": 8, "value": 0.0018323114233575208, "stage": "improve", "created_at": 1789265633.5331097}, {"event_id": "1645bca96eb740bbac1d4551b0f12055", "step": 9, "value": 0.013788457624622748, "stage": "improve", "created_at": 1789265284.7045455}, {"event_id": "e6a5460461d84d47a0a67a7569fbba4a", "step": 10, "value": 0.0012616651777242664, "stage": "improve", "created_at": 1789266092.704131}, {"event_id": "edbbaa37c4624b82a6ffd72c15a42cf4", "step": 11, "value": 0.001470877228282062, "stage": "improve", "created_at": 1789266741.879471}, {"event_id": "0bb1b414ff9743069508060953fd8b67", "step": 12, "value": 0.0015404554739179498, "stage": "improve", "created_at": 1789267025.670934}, {"event_id": "8511341a19774cde8a282660d4538c3c", "step": 19, "value": 0.0020903787695654677, "stage": "improve", "created_at": 1789277196.6171532}, {"event_id": "c833014d519f4f7aa15522727ea81d73", "step": 20, "value": 0.001253736032277085, "stage": "debug", "created_at": 1789274986.0204976}, {"event_id": "aef21eff0f4d4367abbe39b8d939d5dd", "step": 24, "value": 0.0031455901783145513, "stage": "improve", "created_at": 1789279690.0016778}, {"event_id": "98e3078f149e43a5a8caf4bbd0d7434f", "step": 29, "value": 0.001465867082689968, "stage": "debug", "created_at": 1789282122.830588}, {"event_id": "7eacdf2c016146508c4ea84773b736c7", "step": 30, "value": 0.018318290075534635, "stage": "fusion_draft", "created_at": 1789287131.1858335}], "maximize": false, "elapsed_seconds": 28744.773550987244, "node_count": 33, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-recovery-20260913/xixian.laplacian-anchor-logei.dogs-vs-cats-redux-kernels-edition.yaml", "note": ""}, {"id": "xixian.laplacian-anchor-logei.histopathologic-cancer-detection", "experiment_id": "mlebench-gp7-recovery-20260913", "family": "MLEBench", "method": "laplacian_anchor_logei", "dataset": "histopathologic-cancer-detection", "status": "archived", "official_score": 0.99403, "medal": "gold", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.9835, "silver": 0.9798, "bronze": 0.9738}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7/logs-31ca423ebfab.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7", "member": "graph-selectors-recovery-44-runs/results/private_grades.jsonl:28", "sha256": "31ca423ebfabbe5e7b019284026d4b5e56ffcf69cd0b4e76caf8bb4a870dae41"}, {"bundle_id": "gp7", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7/logs-31ca423ebfab.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7", "member": "graph-selectors-recovery-44-runs/runs/laplacian_anchor_logei/07_histopathologic-cancer-detection/logs/journal.json", "sha256": "31ca423ebfabbe5e7b019284026d4b5e56ffcf69cd0b4e76caf8bb4a870dae41"}], "alternate_scores": [], "journal_ref": "gp7:graph-selectors-recovery-44-runs/runs/laplacian_anchor_logei/07_histopathologic-cancer-detection/logs/journal.json", "metrics": [{"event_id": "bda17ff9d9114016a5ac63c35957d8d1", "step": 4, "value": 0.9820763348214452, "stage": "debug", "created_at": 1789266324.638688}, {"event_id": "8a39d9bba3ae4b17855391c1c0ba2432", "step": 5, "value": 0.989804237052975, "stage": "debug", "created_at": 1789264995.5201051}, {"event_id": "ad82a05970454a4b9630118b4a307b29", "step": 6, "value": 0.990290980816987, "stage": "draft", "created_at": 1789264890.3318853}, {"event_id": "a2cd65921acf48809bd31bd710204fc0", "step": 9, "value": 0.9935383247610152, "stage": "improve", "created_at": 1789271153.1312907}, {"event_id": "5a978e6331674f888d01ee96c9f1b4b2", "step": 10, "value": 0.9926411679587358, "stage": "debug", "created_at": 1789271633.3270333}], "maximize": true, "elapsed_seconds": 28742.790957689285, "node_count": 11, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-recovery-20260913/xixian.laplacian-anchor-logei.histopathologic-cancer-detection.yaml", "note": ""}, {"id": "xixian.laplacian-anchor-logei.jigsaw-toxic-comment-classification-challenge", "experiment_id": "mlebench-gp7-recovery-20260913", "family": "MLEBench", "method": "laplacian_anchor_logei", "dataset": "jigsaw-toxic-comment-classification-challenge", "status": "archived", "official_score": 0.98567, "medal": "none", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.9874, "silver": 0.98668, "bronze": 0.98639}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7/logs-31ca423ebfab.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7", "member": "graph-selectors-recovery-44-runs/results/private_grades.jsonl:29", "sha256": "31ca423ebfabbe5e7b019284026d4b5e56ffcf69cd0b4e76caf8bb4a870dae41"}, {"bundle_id": "gp7", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7/logs-31ca423ebfab.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7", "member": "graph-selectors-recovery-44-runs/runs/laplacian_anchor_logei/08_jigsaw-toxic-comment-classification-challenge/logs/journal.json", "sha256": "31ca423ebfabbe5e7b019284026d4b5e56ffcf69cd0b4e76caf8bb4a870dae41"}], "alternate_scores": [], "journal_ref": "gp7:graph-selectors-recovery-44-runs/runs/laplacian_anchor_logei/08_jigsaw-toxic-comment-classification-challenge/logs/journal.json", "metrics": [{"event_id": "2a2cab4830854e9db416562950867551", "step": 5, "value": 0.9442259928507618, "stage": "debug", "created_at": 1789265737.134101}, {"event_id": "ac61f1a375bb4fe0b772017ca19f3bea", "step": 6, "value": 0.9856925145795238, "stage": "draft", "created_at": 1789264489.2294583}, {"event_id": "5ee38d421b7b4a6b82d315515092955b", "step": 7, "value": 0.9592081148366197, "stage": "improve", "created_at": 1789270561.1799214}, {"event_id": "738a9a8a200143129b1a3b27ba84041f", "step": 10, "value": 0.9931918124130968, "stage": "debug", "created_at": 1789267683.5967803}, {"event_id": "45197285a5da418b8851a5f99e9f586b", "step": 12, "value": 0.9457603703827, "stage": "debug", "created_at": 1789277807.2824345}, {"event_id": "fccd2f93e66d495b8bf554f1a07dffe8", "step": 13, "value": 0.9928945360066214, "stage": "improve", "created_at": 1789284408.5072057}], "maximize": true, "elapsed_seconds": 28737.271633148193, "node_count": 15, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-recovery-20260913/xixian.laplacian-anchor-logei.jigsaw-toxic-comment-classification-challenge.yaml", "note": ""}, {"id": "xixian.laplacian-anchor-logei.leaf-classification", "experiment_id": "mlebench-gp7-recovery-20260913", "family": "MLEBench", "method": "laplacian_anchor_logei", "dataset": "leaf-classification", "status": "archived", "official_score": 0.00239, "medal": "silver", "valid_submission": true, "score_maximize": false, "thresholds": {"gold": 0.0, "silver": 0.00791, "bronze": 0.01526}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7/logs-31ca423ebfab.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7", "member": "graph-selectors-recovery-44-runs/results/private_grades.jsonl:30", "sha256": "31ca423ebfabbe5e7b019284026d4b5e56ffcf69cd0b4e76caf8bb4a870dae41"}, {"bundle_id": "gp7", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7/logs-31ca423ebfab.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7", "member": "graph-selectors-recovery-44-runs/runs/laplacian_anchor_logei/09_leaf-classification/logs/journal.json", "sha256": "31ca423ebfabbe5e7b019284026d4b5e56ffcf69cd0b4e76caf8bb4a870dae41"}], "alternate_scores": [], "journal_ref": "gp7:graph-selectors-recovery-44-runs/runs/laplacian_anchor_logei/09_leaf-classification/logs/journal.json", "metrics": [{"event_id": "4871c160bf1e49aba58f93377371e9c1", "step": 5, "value": 0.13737602974701443, "stage": "debug", "created_at": 1789264841.5033197}, {"event_id": "ca5a6571f6e744a896d0e4860944fe0d", "step": 7, "value": 0.09704806747550619, "stage": "debug", "created_at": 1789264886.2982392}, {"event_id": "ffe5e8bd6fec471cbc7d585a90d00f2e", "step": 8, "value": 0.0002506078993170581, "stage": "debug", "created_at": 1789265196.0459433}, {"event_id": "b2856929d1834439bed42466e9a26649", "step": 9, "value": 0.11158607412378989, "stage": "improve", "created_at": 1789265121.9485643}, {"event_id": "a9f172aaecde48b885a4beb9bb92cb3c", "step": 10, "value": 0.08724859712424698, "stage": "improve", "created_at": 1789265405.8361685}, {"event_id": "43273a811f3e4249be56f8bea7c13aa1", "step": 11, "value": 0.017341104918082866, "stage": "improve", "created_at": 1789265531.5336177}, {"event_id": "d3cfcc258b5440fdb714db0e8a1e0c01", "step": 12, "value": 2.1941703169450085e-05, "stage": "improve", "created_at": 1789265640.7738488}, {"event_id": "b2a1df69e01a49cdb19da6fd3d9d548e", "step": 13, "value": 0.20065420123640365, "stage": "improve", "created_at": 1789265316.2497602}, {"event_id": "d7634dfc748c40e084a5669ec50984f9", "step": 14, "value": 3.384862113254758e-05, "stage": "improve", "created_at": 1789265926.8951461}, {"event_id": "a8846c2dc00b43508d4ed88a01f5dee3", "step": 15, "value": 0.00029529301342691417, "stage": "improve", "created_at": 1789266100.0601234}, {"event_id": "b33e1db75890477d9b97dce40614a678", "step": 16, "value": 0.00956861637108312, "stage": "improve", "created_at": 1789266342.5853906}, {"event_id": "632eae49e88349fe8ce592cdc21ade24", "step": 18, "value": 0.010241631015749528, "stage": "improve", "created_at": 1789266701.9024987}, {"event_id": "6dcc6268226b4bd6a6910b67520bbd33", "step": 20, "value": 0.00018509937092799577, "stage": "evolution", "created_at": 1789268407.578283}, {"event_id": "686d937c791548dabdf2137fababf219", "step": 23, "value": 0.026026730808784856, "stage": "debug", "created_at": 1789269015.8863304}, {"event_id": "24a0b0d2a46847faa03a47c466ce4882", "step": 25, "value": 0.016810296215574876, "stage": "debug", "created_at": 1789271006.944694}, {"event_id": "7753c8e2f0b44611860619b6aa9eb807", "step": 28, "value": 1.2492673213790761, "stage": "fusion_draft", "created_at": 1789287664.8397417}, {"event_id": "af18aa4a3cb34a159dd8fef341b16097", "step": 30, "value": 0.03643309161619934, "stage": "debug", "created_at": 1789288164.9958606}], "maximize": false, "elapsed_seconds": 28767.24168944359, "node_count": 32, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-recovery-20260913/xixian.laplacian-anchor-logei.leaf-classification.yaml", "note": ""}, {"id": "xixian.laplacian-anchor-logei.mlsp-2013-birds", "experiment_id": "mlebench-gp7-recovery-20260913", "family": "MLEBench", "method": "laplacian_anchor_logei", "dataset": "mlsp-2013-birds", "status": "archived", "official_score": 0.91179, "medal": "silver", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.93527, "silver": 0.90038, "bronze": 0.87372}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7/logs-31ca423ebfab.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7", "member": "graph-selectors-recovery-44-runs/results/private_grades.jsonl:31", "sha256": "31ca423ebfabbe5e7b019284026d4b5e56ffcf69cd0b4e76caf8bb4a870dae41"}, {"bundle_id": "gp7", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7/logs-31ca423ebfab.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7", "member": "graph-selectors-recovery-44-runs/runs/laplacian_anchor_logei/10_mlsp-2013-birds/logs/journal.json", "sha256": "31ca423ebfabbe5e7b019284026d4b5e56ffcf69cd0b4e76caf8bb4a870dae41"}], "alternate_scores": [], "journal_ref": "gp7:graph-selectors-recovery-44-runs/runs/laplacian_anchor_logei/10_mlsp-2013-birds/logs/journal.json", "metrics": [{"event_id": "00b010447e804014961e33b7a30309b2", "step": 8, "value": 0.8134579046819231, "stage": "debug", "created_at": 1789265191.4174507}, {"event_id": "80c416e892484fa2b178050a05c29753", "step": 9, "value": 0.793525614108755, "stage": "improve", "created_at": 1789265416.739157}, {"event_id": "d59c52ed606348438883d458ff7ae81c", "step": 10, "value": 0.7623434037815998, "stage": "debug", "created_at": 1789265384.5361032}, {"event_id": "cbc565f1eaad43c28bfdf65cc33f9341", "step": 11, "value": 0.7925458394569249, "stage": "improve", "created_at": 1789265615.561909}, {"event_id": "a9ea4d84b6b84331ab0a5418cd6bcb10", "step": 12, "value": 0.8171364336202673, "stage": "improve", "created_at": 1789265660.305396}, {"event_id": "1a65e324e34c4fe3aa7ec29deca572db", "step": 15, "value": 0.7970772972216391, "stage": "debug", "created_at": 1789265988.4724326}, {"event_id": "65c8273f36d646f893128dc6c81167e0", "step": 16, "value": 0.7698929246273356, "stage": "debug", "created_at": 1789266042.8499978}, {"event_id": "0c4583a303d04452ba2f032c0137ca5a", "step": 17, "value": 0.7802155504234027, "stage": "improve", "created_at": 1789266219.7525167}, {"event_id": "880c29de5a284304aee23ac9a07be2b4", "step": 18, "value": 0.8217936416554723, "stage": "improve", "created_at": 1789266361.7060823}, {"event_id": "f64baf6c745244c8b2669e4a286e5bc1", "step": 19, "value": 0.8370946075609289, "stage": "evolution", "created_at": 1789266461.3233132}, {"event_id": "278e26e20d7f4e2cb1e1de2353135246", "step": 20, "value": 0.8409502334804579, "stage": "improve", "created_at": 1789266844.809863}, {"event_id": "39f5b2eb39a8405b9e87c0407d5aa8e6", "step": 21, "value": 0.8220519094223757, "stage": "improve", "created_at": 1789266786.1618724}, {"event_id": "14a5f57a28834919b80dbd10d872879b", "step": 23, "value": 0.8391399603403058, "stage": "improve", "created_at": 1789267327.138858}, {"event_id": "64fdf3c5bbf24e4b9f6822aea217e387", "step": 24, "value": 0.8344775474956823, "stage": "improve", "created_at": 1789267315.6507804}, {"event_id": "e4f59f4faee8485492d16d85c082f1b5", "step": 25, "value": 0.8407167530224525, "stage": "evolution", "created_at": 1789267857.9324117}, {"event_id": "0b7476d0d37a418588e8321ae3c928e4", "step": 26, "value": 0.8446515384123329, "stage": "improve", "created_at": 1789267909.5679348}, {"event_id": "d347f5a1be704a829c5f5f8cbbe943ba", "step": 28, "value": 0.8520653425446172, "stage": "improve", "created_at": 1789268498.6166832}, {"event_id": "f308aca557c8437bbcbff30eae772d73", "step": 29, "value": 0.8550346222733961, "stage": "evolution", "created_at": 1789268299.7339365}, {"event_id": "e20b3fa0e40940a787fcd174b754e42c", "step": 31, "value": 0.8582089969935394, "stage": "improve", "created_at": 1789269033.570799}, {"event_id": "3b162051a8d14abbb55dc5965eff113e", "step": 32, "value": 0.840911453335892, "stage": "debug", "created_at": 1789269254.4618104}, {"event_id": "17311ad6a2c24c3c88639cada813a10a", "step": 33, "value": 0.8684068406840684, "stage": "debug", "created_at": 1789268840.162627}, {"event_id": "876e21ea172c4c469732dadc21bd5f78", "step": 34, "value": 0.8418129917482249, "stage": "improve", "created_at": 1789269619.4972672}, {"event_id": "a84ab2c384854e248c6f35483c9c190d", "step": 35, "value": 0.8000783598797415, "stage": "improve", "created_at": 1789269942.7606}, {"event_id": "4abb2b8551f2485990c723930d200bf8", "step": 36, "value": 0.8000085722858, "stage": "improve", "created_at": 1789270277.3199255}, {"event_id": "b88c0e77f602487daa248bd0886f5c8e", "step": 38, "value": 0.8665723715228666, "stage": "improve", "created_at": 1789270706.892599}, {"event_id": "959a93c02c03497393c2ad1a26d0b4ef", "step": 39, "value": 0.8672924435300673, "stage": "improve", "created_at": 1789270279.8346303}, {"event_id": "9411372737104f23a64e43f3e76c2fbe", "step": 40, "value": 0.8446319484423975, "stage": "debug", "created_at": 1789271817.3986049}, {"event_id": "53ac8d632a1d4599812ae79ef3b0c7d4", "step": 41, "value": 0.8573914534310574, "stage": "improve", "created_at": 1789272083.3923092}, {"event_id": "87378bfa3e9d45cd84d90d39f906cd1e", "step": 42, "value": 0.8476172199833685, "stage": "evolution", "created_at": 1789272360.8596673}, {"event_id": "f6e8c2413cbc46a7b80bfbcc67f2c137", "step": 43, "value": 0.8108759935065073, "stage": "evolution", "created_at": 1789274893.5086312}, {"event_id": "767511eb32254cfeb8c2fe7ee5fd0f93", "step": 44, "value": 0.8780335176374781, "stage": "evolution", "created_at": 1789273642.9493382}, {"event_id": "2c9e6811d1ce403aaa79ab286a24fb26", "step": 45, "value": 0.8625887545576665, "stage": "evolution", "created_at": 1789276263.7802522}, {"event_id": "545bb1fe5428418d85c9b5b144923f37", "step": 46, "value": 0.8805451973768805, "stage": "evolution", "created_at": 1789272644.5211153}, {"event_id": "782fcc79d1f84765ba9f522c35e69fc5", "step": 47, "value": 0.8546568942608548, "stage": "improve", "created_at": 1789276744.9203565}, {"event_id": "7e9c5416ee9d4c55a81754cc5dfdc365", "step": 49, "value": 0.8355921306416356, "stage": "improve", "created_at": 1789278515.7180505}, {"event_id": "e247ea1bacd54ea8b3963f54956c0e14", "step": 50, "value": 0.888971754318289, "stage": "improve", "created_at": 1789279521.7169695}, {"event_id": "141ab52472a44393a70de2ae03647d7a", "step": 51, "value": 0.9238095238095237, "stage": "debug", "created_at": 1789280896.540625}, {"event_id": "dc689946e54b4a6e9e259e0630e4d3f5", "step": 52, "value": 0.8405897732630405, "stage": "improve", "created_at": 1789281071.3385382}], "maximize": true, "elapsed_seconds": 28745.719119787216, "node_count": 53, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-recovery-20260913/xixian.laplacian-anchor-logei.mlsp-2013-birds.yaml", "note": ""}, {"id": "xixian.laplacian-anchor-logei.new-york-city-taxi-fare-prediction", "experiment_id": "mlebench-gp7-recovery-20260913", "family": "MLEBench", "method": "laplacian_anchor_logei", "dataset": "new-york-city-taxi-fare-prediction", "status": "archived", "official_score": 6.89406, "medal": "none", "valid_submission": true, "score_maximize": false, "thresholds": {"gold": 2.83377, "silver": 2.88191, "bronze": 2.92371}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7/logs-31ca423ebfab.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7", "member": "graph-selectors-recovery-44-runs/results/private_grades.jsonl:32", "sha256": "31ca423ebfabbe5e7b019284026d4b5e56ffcf69cd0b4e76caf8bb4a870dae41"}, {"bundle_id": "gp7", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7/logs-31ca423ebfab.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7", "member": "graph-selectors-recovery-44-runs/runs/laplacian_anchor_logei/11_new-york-city-taxi-fare-prediction/logs/journal.json", "sha256": "31ca423ebfabbe5e7b019284026d4b5e56ffcf69cd0b4e76caf8bb4a870dae41"}], "alternate_scores": [], "journal_ref": "gp7:graph-selectors-recovery-44-runs/runs/laplacian_anchor_logei/11_new-york-city-taxi-fare-prediction/logs/journal.json", "metrics": [{"event_id": "ff3261cf8cb9458e868f39886c56cc9e", "step": 2, "value": 4.111221550170269, "stage": "draft", "created_at": 1789265136.633503}, {"event_id": "c15e7292591241a5834ef645a693aacf", "step": 3, "value": 3.6896681783349004, "stage": "draft", "created_at": 1789264644.9055912}, {"event_id": "150ddfdbdd204b7e99739dc527b4891d", "step": 5, "value": 3.6654531873671266, "stage": "improve", "created_at": 1789265891.797645}, {"event_id": "1ef460b9fa2e4a5dbad222c91d088d98", "step": 6, "value": 2.753649313872973, "stage": "improve", "created_at": 1789265897.9222407}, {"event_id": "dc2138acf0ce4f94ab3c35fc8ab05f27", "step": 7, "value": 3.830401850344957, "stage": "improve", "created_at": 1789266808.2558413}, {"event_id": "6330c85cbeb0451badc11b727949bec5", "step": 9, "value": 2.744537377070921, "stage": "improve", "created_at": 1789267153.3805637}, {"event_id": "c263d60fcfb0436a931d72ad45d54e05", "step": 11, "value": 2.7575897237888376, "stage": "debug", "created_at": 1789268150.1113799}, {"event_id": "e20ee08f69304f50b6745eff8daf6ad2", "step": 12, "value": 2.8770584597765287, "stage": "debug", "created_at": 1789268706.8803577}, {"event_id": "e94e2996483945e8b4b5ed7146bf568f", "step": 13, "value": 2.7257573578824874, "stage": "improve", "created_at": 1789269543.9231138}, {"event_id": "f1e2648b43d7427eb0e0103892c3bae7", "step": 14, "value": 2.7256981209017077, "stage": "improve", "created_at": 1789271335.0664542}, {"event_id": "e307236319e74bb79ac3ca990c309d5b", "step": 17, "value": 3.0413197528845766, "stage": "improve", "created_at": 1789275614.773235}, {"event_id": "b1758fb8125749558362e49769d71b35", "step": 18, "value": 3.1785816688728477, "stage": "debug", "created_at": 1789277703.5755663}, {"event_id": "de7537db1df447fb90eba57ca9f3cd91", "step": 19, "value": 2.7349245806819154, "stage": "improve", "created_at": 1789280033.5380747}, {"event_id": "a5a839df3619462b844158c8f1178043", "step": 21, "value": 2.919450753383286, "stage": "fusion", "created_at": 1789285182.4024177}, {"event_id": "9389e088b31d40be954b89bf99bca816", "step": 23, "value": 3.0374119897631893, "stage": "evolution", "created_at": 1789289734.4037473}], "maximize": false, "elapsed_seconds": 28754.76269865036, "node_count": 24, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-recovery-20260913/xixian.laplacian-anchor-logei.new-york-city-taxi-fare-prediction.yaml", "note": ""}, {"id": "xixian.laplacian-anchor-logei.nomad2018-predict-transparent-conductors", "experiment_id": "mlebench-gp7-recovery-20260913", "family": "MLEBench", "method": "laplacian_anchor_logei", "dataset": "nomad2018-predict-transparent-conductors", "status": "archived", "official_score": 0.05895, "medal": "silver", "valid_submission": true, "score_maximize": false, "thresholds": {"gold": 0.05589, "silver": 0.06229, "bronze": 0.06582}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7/logs-31ca423ebfab.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7", "member": "graph-selectors-recovery-44-runs/results/private_grades.jsonl:33", "sha256": "31ca423ebfabbe5e7b019284026d4b5e56ffcf69cd0b4e76caf8bb4a870dae41"}, {"bundle_id": "gp7", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7/logs-31ca423ebfab.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7", "member": "graph-selectors-recovery-44-runs/runs/laplacian_anchor_logei/12_nomad2018-predict-transparent-conductors/logs/journal.json", "sha256": "31ca423ebfabbe5e7b019284026d4b5e56ffcf69cd0b4e76caf8bb4a870dae41"}], "alternate_scores": [], "journal_ref": "gp7:graph-selectors-recovery-44-runs/runs/laplacian_anchor_logei/12_nomad2018-predict-transparent-conductors/logs/journal.json", "metrics": [{"event_id": "45d8f787c4bd43eaafde563092b0dccc", "step": 2, "value": 0.0609931801819702, "stage": "draft", "created_at": 1789264249.0616586}, {"event_id": "f35d2af93cf948f9bee108a74a84f48e", "step": 3, "value": 0.055839043869800625, "stage": "debug", "created_at": 1789265009.67375}, {"event_id": "8d6224848bc64ce5bccc16c160345104", "step": 4, "value": 0.9077475513749378, "stage": "draft", "created_at": 1789264458.4651604}, {"event_id": "383952a05c9c44f1a2a4ab35956472f1", "step": 5, "value": 0.054515963735926376, "stage": "improve", "created_at": 1789265337.602615}, {"event_id": "9eb51d34b9914b708de7076fd17314b3", "step": 6, "value": 0.05743828733588158, "stage": "improve", "created_at": 1789265414.428292}, {"event_id": "25b9de098e4d471ea90e28f37c8db5bf", "step": 8, "value": 0.05271364660266327, "stage": "improve", "created_at": 1789265684.1256728}, {"event_id": "281e3f3e24de422fbc332d60a0f5e61b", "step": 9, "value": 0.05917007827674291, "stage": "debug", "created_at": 1789265851.1379333}, {"event_id": "e32a8c6c6a3449e19b22dc76757b418f", "step": 10, "value": 0.05330185501639005, "stage": "improve", "created_at": 1789265931.568203}, {"event_id": "8fed5a7a861c4f07902d30e6680146cf", "step": 11, "value": 0.05335156153540128, "stage": "improve", "created_at": 1789266093.0053065}, {"event_id": "473d8d8a1ad84b44a787ecf225bea5de", "step": 12, "value": 0.05318217291761724, "stage": "improve", "created_at": 1789266180.9623609}, {"event_id": "a7e615c9384a4a078ae92709bf72ba67", "step": 13, "value": 0.05982627975660382, "stage": "evolution", "created_at": 1789266458.6998231}, {"event_id": "c6313d512b0b4a8588e664d995d6cb3e", "step": 15, "value": 0.05357762731110178, "stage": "improve", "created_at": 1789265325.9343247}, {"event_id": "a0f4005a164f4f0a836cb14849ebb1a8", "step": 17, "value": 0.056365877367993346, "stage": "debug", "created_at": 1789267675.7253647}, {"event_id": "e062c5d8144041b49b641fb33275dab3", "step": 18, "value": 0.060250019313480285, "stage": "evolution", "created_at": 1789266297.1038425}, {"event_id": "e4ea742c24804a33ad49a5c464f18984", "step": 19, "value": 0.059512758210713626, "stage": "debug", "created_at": 1789267001.5259771}, {"event_id": "837000702c2d4ed7895384d89a1c6061", "step": 20, "value": 0.06045089226512371, "stage": "evolution", "created_at": 1789268294.6803703}], "maximize": false, "elapsed_seconds": 28749.123953342438, "node_count": 23, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-recovery-20260913/xixian.laplacian-anchor-logei.nomad2018-predict-transparent-conductors.yaml", "note": ""}, {"id": "xixian.laplacian-anchor-logei.plant-pathology-2020-fgvc7", "experiment_id": "mlebench-gp7-recovery-20260913", "family": "MLEBench", "method": "laplacian_anchor_logei", "dataset": "plant-pathology-2020-fgvc7", "status": "archived", "official_score": 0.9989, "medal": "gold", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.97836, "silver": 0.97465, "bronze": 0.97361}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7/logs-31ca423ebfab.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7", "member": "graph-selectors-recovery-44-runs/results/private_grades.jsonl:34", "sha256": "31ca423ebfabbe5e7b019284026d4b5e56ffcf69cd0b4e76caf8bb4a870dae41"}, {"bundle_id": "gp7", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7/logs-31ca423ebfab.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7", "member": "graph-selectors-recovery-44-runs/runs/laplacian_anchor_logei/13_plant-pathology-2020-fgvc7/logs/journal.json", "sha256": "31ca423ebfabbe5e7b019284026d4b5e56ffcf69cd0b4e76caf8bb4a870dae41"}], "alternate_scores": [], "journal_ref": "gp7:graph-selectors-recovery-44-runs/runs/laplacian_anchor_logei/13_plant-pathology-2020-fgvc7/logs/journal.json", "metrics": [{"event_id": "f124f6ec5ef74784baddd3a0acddded0", "step": 3, "value": 0.9905805099128581, "stage": "debug", "created_at": 1789264956.041182}, {"event_id": "d6492a8df2304f35b8afb04a9966875e", "step": 5, "value": 0.9881405335223166, "stage": "debug", "created_at": 1789265181.5725722}, {"event_id": "27576304b3ab4cffb7795fee38cd9b2f", "step": 6, "value": 0.9816510697702104, "stage": "improve", "created_at": 1789265479.9791858}, {"event_id": "4bc6dd157fff4b93a6ae524f3a527716", "step": 8, "value": 0.9910519041250787, "stage": "debug", "created_at": 1789266001.2083569}, {"event_id": "45fe75433ccc47af8e99a8fb4b971762", "step": 9, "value": 0.9903400622534524, "stage": "debug", "created_at": 1789265367.3174007}, {"event_id": "9834a590de804ddd88c925c4dda02aa5", "step": 11, "value": 0.9927939364227035, "stage": "improve", "created_at": 1789265946.7411978}, {"event_id": "ead98560808c48f896913a931821f0bd", "step": 12, "value": 0.9859830240665275, "stage": "debug", "created_at": 1789266585.2218485}, {"event_id": "7182344981c745b9be0b382fa875533b", "step": 14, "value": 0.99512733801162, "stage": "improve", "created_at": 1789266781.0054395}, {"event_id": "d62c7f9b538149a2a853e54992295458", "step": 18, "value": 0.9932852472118325, "stage": "debug", "created_at": 1789267979.963489}, {"event_id": "8942f9c885284c19b7c6280b5f8ca116", "step": 19, "value": 0.9809472936907119, "stage": "debug", "created_at": 1789268509.104428}, {"event_id": "9bb400c255784ae5a8bd5ca97db8f0e5", "step": 24, "value": 0.9960254200948597, "stage": "debug", "created_at": 1789270610.9929757}, {"event_id": "92fee7336c4a4149929317079f69e388", "step": 27, "value": 0.9950898935121888, "stage": "debug", "created_at": 1789272294.6984372}, {"event_id": "b0ba93324c414d4eb8cbed729032b6ed", "step": 28, "value": 0.9980460646195872, "stage": "improve", "created_at": 1789272284.3845499}, {"event_id": "ecf75a901fa2460a8260bc350cc74c2d", "step": 29, "value": 0.9920230633572364, "stage": "debug", "created_at": 1789272431.03092}, {"event_id": "5c211f8e4234410fa81ebdef1e8654bd", "step": 30, "value": 0.9961366359170748, "stage": "improve", "created_at": 1789274380.8868723}, {"event_id": "6683ba157ad0469da449bf8bde295a06", "step": 32, "value": 0.998593612208641, "stage": "improve", "created_at": 1789274397.3987734}, {"event_id": "8ef4cfc90a4b4466b2bf3d0ad1f74ef7", "step": 34, "value": 0.9984488376249759, "stage": "improve", "created_at": 1789277787.4900117}, {"event_id": "7c9aa02d862744c2b9236129ccb989c8", "step": 35, "value": 0.9960254200948597, "stage": "debug", "created_at": 1789276962.8481874}, {"event_id": "330617a1928f48aaa4cb62ac2e60b6a5", "step": 36, "value": 0.9978807620726424, "stage": "improve", "created_at": 1789276769.4394746}, {"event_id": "d77458c2108d4d16bb426c2760567498", "step": 39, "value": 0.998308497660781, "stage": "fusion", "created_at": 1789281027.90157}, {"event_id": "9022e6feafce408a8540fd9e7643c239", "step": 42, "value": 0.9986324875771754, "stage": "debug", "created_at": 1789281425.5141943}, {"event_id": "d286c2cb144e4370b232f4eaf8f5e928", "step": 44, "value": 0.8180849145253077, "stage": "evolution", "created_at": 1789283515.7679162}, {"event_id": "1dbcbca26b824784b93191a84a00c140", "step": 45, "value": 0.9988352311347303, "stage": "debug", "created_at": 1789283957.562781}, {"event_id": "e6f05bae80c942c4a7fd03876050a234", "step": 46, "value": 0.9973516882784791, "stage": "debug", "created_at": 1789285729.7304776}, {"event_id": "fbffe2f7e72e4c97976e585a6695dad0", "step": 47, "value": 0.997711414725296, "stage": "improve", "created_at": 1789286348.27968}, {"event_id": "5f006b2ab0f0417b845baaf3ed0f0387", "step": 48, "value": 0.9985894377457498, "stage": "improve", "created_at": 1789287639.8503578}, {"event_id": "864c93b6ddb94b01babb66411c22fae6", "step": 49, "value": 0.9987157775585487, "stage": "improve", "created_at": 1789289890.9869525}], "maximize": true, "elapsed_seconds": 28753.266843557358, "node_count": 50, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-recovery-20260913/xixian.laplacian-anchor-logei.plant-pathology-2020-fgvc7.yaml", "note": ""}, {"id": "xixian.laplacian-anchor-logei.random-acts-of-pizza", "experiment_id": "mlebench-gp7-recovery-20260913", "family": "MLEBench", "method": "laplacian_anchor_logei", "dataset": "random-acts-of-pizza", "status": "archived", "official_score": 0.67159, "medal": "none", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.97908, "silver": 0.76482, "bronze": 0.6921}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7/logs-31ca423ebfab.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7", "member": "graph-selectors-recovery-44-runs/results/private_grades.jsonl:35", "sha256": "31ca423ebfabbe5e7b019284026d4b5e56ffcf69cd0b4e76caf8bb4a870dae41"}, {"bundle_id": "gp7", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7/logs-31ca423ebfab.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7", "member": "graph-selectors-recovery-44-runs/runs/laplacian_anchor_logei/14_random-acts-of-pizza/logs/journal.json", "sha256": "31ca423ebfabbe5e7b019284026d4b5e56ffcf69cd0b4e76caf8bb4a870dae41"}], "alternate_scores": [], "journal_ref": "gp7:graph-selectors-recovery-44-runs/runs/laplacian_anchor_logei/14_random-acts-of-pizza/logs/journal.json", "metrics": [{"event_id": "02bcec8a468c482a898676f944221b2d", "step": 3, "value": 0.6789935298346514, "stage": "draft", "created_at": 1789264461.5553305}, {"event_id": "038ad932b6614731ba05f902475d4f28", "step": 4, "value": 0.655902228612509, "stage": "debug", "created_at": 1789264830.193288}, {"event_id": "55f47ebbc65b432d8ac94e189f6a8533", "step": 5, "value": 0.6213246613300494, "stage": "debug", "created_at": 1789264838.7277849}, {"event_id": "1cf00d2e209d4f1b9715170b3c2baf0f", "step": 6, "value": 0.6750251617541336, "stage": "improve", "created_at": 1789265250.7452374}, {"event_id": "cd30695539234dd38303ad22bd2ec191", "step": 7, "value": 0.690999281092739, "stage": "improve", "created_at": 1789265002.0552135}, {"event_id": "b2743ffa9d2b4307828faac723e26cc8", "step": 8, "value": 0.672293314162473, "stage": "improve", "created_at": 1789265677.4737086}, {"event_id": "067e37c7eb664613959027c719bdc76b", "step": 9, "value": 0.6596117900790799, "stage": "improve", "created_at": 1789265323.322764}, {"event_id": "1de2ae146339486ba46e510689053890", "step": 10, "value": 0.7013371675053918, "stage": "improve", "created_at": 1789265767.7897341}, {"event_id": "2e7c0a67ad7c431484063b17ed3d9cf3", "step": 11, "value": 0.7003019410496046, "stage": "improve", "created_at": 1789266069.3291628}, {"event_id": "3b4ad4c54e054d6098a349e7d66fca58", "step": 12, "value": 0.7040115025161753, "stage": "improve", "created_at": 1789266141.8964212}, {"event_id": "89dde9ce5e2245a8aaf28ae5d8ee0624", "step": 13, "value": 0.7123220704529115, "stage": "improve", "created_at": 1789266543.3468602}, {"event_id": "57fd5ea799e1474787ff93f944afbd7b", "step": 14, "value": 0.7030050323508267, "stage": "improve", "created_at": 1789266552.8095744}, {"event_id": "190fb927e0b54cfa895a9d155490add3", "step": 15, "value": 0.7334004313443565, "stage": "improve", "created_at": 1789267582.8685324}, {"event_id": "f641695f7dca445b95624f703dd2a03b", "step": 16, "value": 0.7038389647735441, "stage": "improve", "created_at": 1789267754.4100106}, {"event_id": "2136a74cc37d463f89525a423b64da01", "step": 17, "value": 0.7011071171818835, "stage": "improve", "created_at": 1789266199.0378978}, {"event_id": "12f8ed0c07ea49abb1db0bc391279e6e", "step": 18, "value": 0.7233357296908698, "stage": "improve", "created_at": 1789268144.7356944}, {"event_id": "1640abfa188a40d08c24c162493e4987", "step": 19, "value": 0.719137311286844, "stage": "improve", "created_at": 1789268413.6716256}, {"event_id": "cfe1014757e149bab9377aff4ab41412", "step": 20, "value": 0.6253492465963597, "stage": "improve", "created_at": 1789270211.4770937}, {"event_id": "2c045b5986f2486a82f04a52b928128c", "step": 21, "value": 0.6624029981100737, "stage": "evolution", "created_at": 1789270900.5303378}, {"event_id": "be81b37071104604a61ed462530d578f", "step": 22, "value": 0.6349908751756327, "stage": "evolution", "created_at": 1789270487.1042428}, {"event_id": "96ee91c94e804b2aa2e55f8e62e568b6", "step": 23, "value": 0.7216391085549965, "stage": "evolution", "created_at": 1789270265.1877887}, {"event_id": "195f1debe0af4f749cf04d9c0f5b773e", "step": 24, "value": 0.7608914450035946, "stage": "evolution", "created_at": 1789275158.2552173}, {"event_id": "71daf4280a2f49c28504562ac7dfcb1e", "step": 25, "value": 0.7443514414388201, "stage": "evolution", "created_at": 1789274309.9628575}, {"event_id": "1d6512feb45448318d07840578ac7658", "step": 26, "value": 0.7570668583752694, "stage": "improve", "created_at": 1789277848.381195}, {"event_id": "593b5ad36c1a440f934dd8ba3c5a92e9", "step": 27, "value": 0.6692188070828848, "stage": "improve", "created_at": 1789280527.3931985}, {"event_id": "3b4e0b20e4474efeaf3acd1f087bed25", "step": 28, "value": 0.9575269590222861, "stage": "fusion", "created_at": 1789283219.4873805}, {"event_id": "a11fb372e0b04d56a91ea41bd46efc02", "step": 29, "value": 0.7174406901509706, "stage": "improve", "created_at": 1789285157.1168997}, {"event_id": "c2df6ab291914953a68210c6b7a398d5", "step": 30, "value": 0.7363623292595255, "stage": "improve", "created_at": 1789279664.4564705}, {"event_id": "7f6b9da50edf43b5a21b271f67b1745c", "step": 32, "value": 0.6743637670740474, "stage": "evolution", "created_at": 1789277043.3653142}, {"event_id": "62b2843ecaf440368e18a28abbd4f7a2", "step": 33, "value": 0.6918899870356181, "stage": "improve", "created_at": 1789289416.9901593}], "maximize": true, "elapsed_seconds": 28758.22270345688, "node_count": 35, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-recovery-20260913/xixian.laplacian-anchor-logei.random-acts-of-pizza.yaml", "note": ""}, {"id": "xixian.laplacian-anchor-logei.ranzcr-clip-catheter-line-classification", "experiment_id": "mlebench-gp7-recovery-20260913", "family": "MLEBench", "method": "laplacian_anchor_logei", "dataset": "ranzcr-clip-catheter-line-classification", "status": "archived", "official_score": 0.87985, "medal": "none", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.97357, "silver": 0.97152, "bronze": 0.9709}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7/logs-31ca423ebfab.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7", "member": "graph-selectors-recovery-44-runs/results/private_grades.jsonl:36", "sha256": "31ca423ebfabbe5e7b019284026d4b5e56ffcf69cd0b4e76caf8bb4a870dae41"}, {"bundle_id": "gp7", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7/logs-31ca423ebfab.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7", "member": "graph-selectors-recovery-44-runs/runs/laplacian_anchor_logei/15_ranzcr-clip-catheter-line-classification/logs/journal.json", "sha256": "31ca423ebfabbe5e7b019284026d4b5e56ffcf69cd0b4e76caf8bb4a870dae41"}], "alternate_scores": [], "journal_ref": "gp7:graph-selectors-recovery-44-runs/runs/laplacian_anchor_logei/15_ranzcr-clip-catheter-line-classification/logs/journal.json", "metrics": [{"event_id": "7705842d4d374c28b2c5b6e888ea33f4", "step": 2, "value": 0.8170288128054294, "stage": "draft", "created_at": 1789264315.698241}, {"event_id": "59dceaac5cee44bdb78650e932d19053", "step": 7, "value": 0.8807697366110046, "stage": "debug", "created_at": 1789267844.9259942}, {"event_id": "fc18f1433aec40f498772f7742423543", "step": 9, "value": 0.5260767144892248, "stage": "debug", "created_at": 1789274488.4839048}, {"event_id": "14f528c82fc641d7947043fb917407a9", "step": 11, "value": 0.8411734528681475, "stage": "debug", "created_at": 1789270920.4041977}, {"event_id": "f91c8616ce1c4159a9127d739cf3ffa0", "step": 13, "value": 0.8043785505667863, "stage": "improve", "created_at": 1789278236.286725}, {"event_id": "b7dbe0940a3d4c40b14f117912a91cd5", "step": 15, "value": 0.8400495686321431, "stage": "improve", "created_at": 1789282363.8157961}], "maximize": true, "elapsed_seconds": 28743.733854055405, "node_count": 18, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-recovery-20260913/xixian.laplacian-anchor-logei.ranzcr-clip-catheter-line-classification.yaml", "note": ""}, {"id": "xixian.laplacian-anchor-logei.siim-isic-melanoma-classification", "experiment_id": "mlebench-gp7-recovery-20260913", "family": "MLEBench", "method": "laplacian_anchor_logei", "dataset": "siim-isic-melanoma-classification", "status": "archived", "official_score": 0.89329, "medal": "none", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.9455, "silver": 0.9401, "bronze": 0.937}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7/logs-31ca423ebfab.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7", "member": "graph-selectors-recovery-44-runs/results/private_grades.jsonl:37", "sha256": "31ca423ebfabbe5e7b019284026d4b5e56ffcf69cd0b4e76caf8bb4a870dae41"}, {"bundle_id": "gp7", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7/logs-31ca423ebfab.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7", "member": "graph-selectors-recovery-44-runs/runs/laplacian_anchor_logei/16_siim-isic-melanoma-classification/logs/journal.json", "sha256": "31ca423ebfabbe5e7b019284026d4b5e56ffcf69cd0b4e76caf8bb4a870dae41"}], "alternate_scores": [], "journal_ref": "gp7:graph-selectors-recovery-44-runs/runs/laplacian_anchor_logei/16_siim-isic-melanoma-classification/logs/journal.json", "metrics": [{"event_id": "676c7445bebb475f86a54d97a744293f", "step": 1, "value": 0.4477212837837838, "stage": "draft", "created_at": 1789264711.9647415}, {"event_id": "bf1d74837a9a4c5aa65af1f4a44df547", "step": 2, "value": 0.881042286804175, "stage": "draft", "created_at": 1789264438.576518}, {"event_id": "adcbfff180d748e3918544b5791472ba", "step": 3, "value": 0.8827304632580578, "stage": "draft", "created_at": 1789264225.0819244}, {"event_id": "9ad4e426ff6e41aea4c8a3e9fd36de41", "step": 4, "value": 0.8868553637731007, "stage": "improve", "created_at": 1789266827.4277701}, {"event_id": "93ee08c58e904776a60add3441354490", "step": 5, "value": 0.538161027140548, "stage": "improve", "created_at": 1789267079.1308823}, {"event_id": "336ba0425e70455794500a202099e153", "step": 6, "value": 0.9443074324324324, "stage": "improve", "created_at": 1789266804.9195852}, {"event_id": "8f2aa0a2e20c4754bf083ca01db07bfb", "step": 10, "value": 0.8773538929734694, "stage": "debug", "created_at": 1789289234.831481}], "maximize": true, "elapsed_seconds": 28761.80719590187, "node_count": 11, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-recovery-20260913/xixian.laplacian-anchor-logei.siim-isic-melanoma-classification.yaml", "note": ""}, {"id": "xixian.laplacian-anchor-logei.spooky-author-identification", "experiment_id": "mlebench-gp7-recovery-20260913", "family": "MLEBench", "method": "laplacian_anchor_logei", "dataset": "spooky-author-identification", "status": "archived", "official_score": 0.21696, "medal": "silver", "valid_submission": true, "score_maximize": false, "thresholds": {"gold": 0.16506, "silver": 0.26996, "bronze": 0.29381}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7/logs-31ca423ebfab.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7", "member": "graph-selectors-recovery-44-runs/results/private_grades.jsonl:38", "sha256": "31ca423ebfabbe5e7b019284026d4b5e56ffcf69cd0b4e76caf8bb4a870dae41"}, {"bundle_id": "gp7", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7/logs-31ca423ebfab.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7", "member": "graph-selectors-recovery-44-runs/runs/laplacian_anchor_logei/17_spooky-author-identification/logs/journal.json", "sha256": "31ca423ebfabbe5e7b019284026d4b5e56ffcf69cd0b4e76caf8bb4a870dae41"}], "alternate_scores": [], "journal_ref": "gp7:graph-selectors-recovery-44-runs/runs/laplacian_anchor_logei/17_spooky-author-identification/logs/journal.json", "metrics": [{"event_id": "31d2c53482ab419fb8a5896bd31ac73a", "step": 7, "value": 0.2733444916301622, "stage": "debug", "created_at": 1789265419.4014568}, {"event_id": "d496303a50a74532a8c2c9f43306076e", "step": 8, "value": 0.2606452208732605, "stage": "debug", "created_at": 1789265516.4312317}, {"event_id": "095d2873de204d4dbb8ab3955f14ce5e", "step": 9, "value": 0.2793629536905521, "stage": "debug", "created_at": 1789265700.7201061}, {"event_id": "c36c174ede6a4979975c4866f77790fc", "step": 10, "value": 0.2584536338086539, "stage": "improve", "created_at": 1789266240.4364128}, {"event_id": "9ba8143256a7477182db455545e0da9d", "step": 11, "value": 0.2547495650371482, "stage": "improve", "created_at": 1789266075.4016652}, {"event_id": "5a75918dc5d846a188f81afea223a945", "step": 12, "value": 0.2640422539798077, "stage": "improve", "created_at": 1789265900.5227447}, {"event_id": "c421dec469504b6a8b9b1fd6fdae35f6", "step": 14, "value": 0.2379588985585583, "stage": "improve", "created_at": 1789267653.7359498}, {"event_id": "f763ec5b0e814d1597ca79c60cd73e22", "step": 15, "value": 0.25061325432796033, "stage": "improve", "created_at": 1789269501.0766845}, {"event_id": "16ec57fcfe5e4c8f93125654ec396469", "step": 17, "value": 0.2415621316574907, "stage": "debug", "created_at": 1789269832.4244523}, {"event_id": "d639df0f3da14176b7265dbd2ad1f41e", "step": 22, "value": 0.23323580816524328, "stage": "debug", "created_at": 1789279067.717061}, {"event_id": "63339114b2eb48fbbc3fcbe24bd050c7", "step": 25, "value": 0.3066141572165986, "stage": "debug", "created_at": 1789289141.8329513}, {"event_id": "2afcacd5d5ff43b39c2d10d6453255c4", "step": 26, "value": 0.25887089700494825, "stage": "debug", "created_at": 1789280224.6839225}, {"event_id": "00246eadcc3248eb86b2a73d710e0b7c", "step": 27, "value": 0.25955930236048563, "stage": "improve", "created_at": 1789290724.2911487}], "maximize": false, "elapsed_seconds": 28758.16529607773, "node_count": 28, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-recovery-20260913/xixian.laplacian-anchor-logei.spooky-author-identification.yaml", "note": ""}, {"id": "xixian.laplacian-anchor-logei.tabular-playground-series-dec-2021", "experiment_id": "mlebench-gp7-recovery-20260913", "family": "MLEBench", "method": "laplacian_anchor_logei", "dataset": "tabular-playground-series-dec-2021", "status": "archived", "official_score": 0.96298, "medal": "gold", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.9566, "silver": 0.95658, "bronze": 0.95658}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7/logs-31ca423ebfab.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7", "member": "graph-selectors-recovery-44-runs/results/private_grades.jsonl:39", "sha256": "31ca423ebfabbe5e7b019284026d4b5e56ffcf69cd0b4e76caf8bb4a870dae41"}, {"bundle_id": "gp7", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7/logs-31ca423ebfab.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7", "member": "graph-selectors-recovery-44-runs/runs/laplacian_anchor_logei/18_tabular-playground-series-dec-2021/logs/journal.json", "sha256": "31ca423ebfabbe5e7b019284026d4b5e56ffcf69cd0b4e76caf8bb4a870dae41"}], "alternate_scores": [], "journal_ref": "gp7:graph-selectors-recovery-44-runs/runs/laplacian_anchor_logei/18_tabular-playground-series-dec-2021/logs/journal.json", "metrics": [{"event_id": "d9db889598cd407abc823e420e37ba2e", "step": 6, "value": 0.9595583333333333, "stage": "debug", "created_at": 1789265810.6366613}, {"event_id": "855cbac2301f4779b38b23a9e36822d6", "step": 7, "value": 0.9159361111111111, "stage": "debug", "created_at": 1789265750.79467}, {"event_id": "82b555210dd24b039e485694d096d579", "step": 9, "value": 0.9621166666666666, "stage": "improve", "created_at": 1789266510.1281521}, {"event_id": "7fa0c6eb1427422fb726ca376f248996", "step": 10, "value": 0.9623805555555556, "stage": "improve", "created_at": 1789270790.1318846}, {"event_id": "4bc6132eb96d4a1291380d00a34a4226", "step": 13, "value": 0.9618527777777778, "stage": "debug", "created_at": 1789287208.4253914}], "maximize": true, "elapsed_seconds": 28770.583965539932, "node_count": 14, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-recovery-20260913/xixian.laplacian-anchor-logei.tabular-playground-series-dec-2021.yaml", "note": ""}, {"id": "xixian.laplacian-anchor-logei.tabular-playground-series-may-2022", "experiment_id": "mlebench-gp7-recovery-20260913", "family": "MLEBench", "method": "laplacian_anchor_logei", "dataset": "tabular-playground-series-may-2022", "status": "archived", "official_score": 0.99293, "medal": "none", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.99823, "silver": 0.99822, "bronze": 0.99818}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7/logs-31ca423ebfab.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7", "member": "graph-selectors-recovery-44-runs/results/private_grades.jsonl:40", "sha256": "31ca423ebfabbe5e7b019284026d4b5e56ffcf69cd0b4e76caf8bb4a870dae41"}, {"bundle_id": "gp7", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7/logs-31ca423ebfab.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7", "member": "graph-selectors-recovery-44-runs/runs/laplacian_anchor_logei/19_tabular-playground-series-may-2022/logs/journal.json", "sha256": "31ca423ebfabbe5e7b019284026d4b5e56ffcf69cd0b4e76caf8bb4a870dae41"}], "alternate_scores": [], "journal_ref": "gp7:graph-selectors-recovery-44-runs/runs/laplacian_anchor_logei/19_tabular-playground-series-may-2022/logs/journal.json", "metrics": [{"event_id": "9f29bb9d0a4d44d396fdf257381ee45a", "step": 2, "value": 0.9878271173768416, "stage": "draft", "created_at": 1789264770.5461051}, {"event_id": "dd42274b452c4c418875ea857525278a", "step": 3, "value": 0.9860963901687951, "stage": "debug", "created_at": 1789265445.5874374}, {"event_id": "e216fe7627dd4721aa44a21477b9d935", "step": 4, "value": 0.8360224472646652, "stage": "draft", "created_at": 1789265182.4276407}, {"event_id": "e61a3bc3fe594900bde7fd6bfff039f6", "step": 5, "value": 0.9866608383084249, "stage": "improve", "created_at": 1789267854.953893}, {"event_id": "ad564f2aa50e471db7c984a02cbb2689", "step": 6, "value": 0.9909650098920673, "stage": "improve", "created_at": 1789267852.0236282}, {"event_id": "470da00e618b4e658b9a3d0ac6f65fb6", "step": 7, "value": 0.9722770741210001, "stage": "improve", "created_at": 1789267830.8862922}, {"event_id": "120f8015d093459e946583d186e2852b", "step": 8, "value": 0.9898770188047274, "stage": "improve", "created_at": 1789268278.5988157}, {"event_id": "895fcc5e50e6485982a36891e703f31a", "step": 9, "value": 0.9874169009920721, "stage": "improve", "created_at": 1789268898.7198749}, {"event_id": "b45b79c7d2514705802e3be3d75c13f8", "step": 10, "value": 0.988489610056316, "stage": "improve", "created_at": 1789268140.8603892}, {"event_id": "aac777a598db4642898b995c3838a9ba", "step": 12, "value": 0.9911611190179894, "stage": "evolution", "created_at": 1789269790.9114912}, {"event_id": "cad81d5d29ec42f5a33172355ab843ec", "step": 13, "value": 0.9918538206052214, "stage": "improve", "created_at": 1789272517.6928372}, {"event_id": "11957d9747544c53b6316e317da26df3", "step": 14, "value": 0.9916130081097849, "stage": "improve", "created_at": 1789275234.759642}, {"event_id": "2fae9535355849aba0291f22ea7881a5", "step": 15, "value": 0.9902485204473458, "stage": "improve", "created_at": 1789277963.9634364}], "maximize": true, "elapsed_seconds": 28763.04858803749, "node_count": 18, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-recovery-20260913/xixian.laplacian-anchor-logei.tabular-playground-series-may-2022.yaml", "note": ""}, {"id": "xixian.laplacian-anchor-logei.text-normalization-challenge-english-language", "experiment_id": "mlebench-gp7-recovery-20260913", "family": "MLEBench", "method": "laplacian_anchor_logei", "dataset": "text-normalization-challenge-english-language", "status": "archived", "official_score": 0.99375, "medal": "silver", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.99724, "silver": 0.99135, "bronze": 0.99038}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7/logs-31ca423ebfab.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7", "member": "graph-selectors-recovery-44-runs/results/private_grades.jsonl:41", "sha256": "31ca423ebfabbe5e7b019284026d4b5e56ffcf69cd0b4e76caf8bb4a870dae41"}, {"bundle_id": "gp7", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7/logs-31ca423ebfab.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7", "member": "graph-selectors-recovery-44-runs/runs/laplacian_anchor_logei/20_text-normalization-challenge-english-language/logs/journal.json", "sha256": "31ca423ebfabbe5e7b019284026d4b5e56ffcf69cd0b4e76caf8bb4a870dae41"}], "alternate_scores": [], "journal_ref": "gp7:graph-selectors-recovery-44-runs/runs/laplacian_anchor_logei/20_text-normalization-challenge-english-language/logs/journal.json", "metrics": [{"event_id": "6343f8eda6a84a7197b3d738efc0e402", "step": 4, "value": 0.931648722796663, "stage": "debug", "created_at": 1789265994.8421023}, {"event_id": "48b9a693f6e446d0b3819bf42c4ccfb0", "step": 5, "value": 0.973277753154437, "stage": "debug", "created_at": 1789265779.8132787}, {"event_id": "7160ae896d27418c9297f5e0a49c9a59", "step": 7, "value": 0.9805263659876235, "stage": "debug", "created_at": 1789269638.5985124}, {"event_id": "0ed15a12eee64d9c9de3e1acd5d8b42e", "step": 8, "value": 0.9812052221430535, "stage": "improve", "created_at": 1789273719.36232}, {"event_id": "1a15ec65ac8a4087a5faf3dfd6c1cb0f", "step": 9, "value": 0.9324678384883388, "stage": "improve", "created_at": 1789269204.004932}, {"event_id": "4cde3e4be7d3463ea6f04db799c18966", "step": 10, "value": 0.9837747768470778, "stage": "improve", "created_at": 1789277864.8217092}, {"event_id": "208a7f1b61564c0ca429e0a75cbc0f74", "step": 11, "value": 0.9654288295061181, "stage": "improve", "created_at": 1789282386.7881718}, {"event_id": "52a6b2bab9004e10948097c652835d4a", "step": 12, "value": 0.9751277414411826, "stage": "debug", "created_at": 1789265783.7496974}, {"event_id": "9ba7617a584241d3846b8677c2e1f0db", "step": 13, "value": 0.994327904354217, "stage": "improve", "created_at": 1789283327.969028}, {"event_id": "e8e5ba96a78a4ad5b3805ab03fa9a6ae", "step": 16, "value": 0.9623, "stage": "debug", "created_at": 1789292608.4308603}], "maximize": true, "elapsed_seconds": 28734.64798784256, "node_count": 17, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-recovery-20260913/xixian.laplacian-anchor-logei.text-normalization-challenge-english-language.yaml", "note": ""}, {"id": "xixian.laplacian-anchor-logei.text-normalization-challenge-russian-language", "experiment_id": "mlebench-gp7-recovery-20260913", "family": "MLEBench", "method": "laplacian_anchor_logei", "dataset": "text-normalization-challenge-russian-language", "status": "archived", "official_score": 0.97808, "medal": "bronze", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.99012, "silver": 0.98232, "bronze": 0.97592}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7/logs-31ca423ebfab.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7", "member": "graph-selectors-recovery-44-runs/results/private_grades.jsonl:42", "sha256": "31ca423ebfabbe5e7b019284026d4b5e56ffcf69cd0b4e76caf8bb4a870dae41"}, {"bundle_id": "gp7", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7/logs-31ca423ebfab.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7", "member": "graph-selectors-recovery-44-runs/runs/laplacian_anchor_logei/21_text-normalization-challenge-russian-language/logs/journal.json", "sha256": "31ca423ebfabbe5e7b019284026d4b5e56ffcf69cd0b4e76caf8bb4a870dae41"}], "alternate_scores": [], "journal_ref": "gp7:graph-selectors-recovery-44-runs/runs/laplacian_anchor_logei/21_text-normalization-challenge-russian-language/logs/journal.json", "metrics": [{"event_id": "3a6c683be1e24afd87fcc485abc36b0f", "step": 2, "value": 0.9403540692871558, "stage": "draft", "created_at": 1789265124.4026814}, {"event_id": "d44742bbc3e54ea5b38469844d2ac0a5", "step": 3, "value": 0.8115879895643263, "stage": "draft", "created_at": 1789264857.992056}, {"event_id": "d5f91701552b4c09a5ee4fafe25a4551", "step": 8, "value": 0.8365530907056627, "stage": "debug", "created_at": 1789266759.2979693}, {"event_id": "935cba75db6549bc9ab6987e35e2a80c", "step": 9, "value": 0.8835524045550083, "stage": "debug", "created_at": 1789266895.3607984}, {"event_id": "c57394742092487d825883d9bb45bcc0", "step": 10, "value": 0.9431512793968483, "stage": "improve", "created_at": 1789267688.1439178}, {"event_id": "fa947d0fef3c4d12a06967fc5bf1806b", "step": 11, "value": 0.8688430309462688, "stage": "improve", "created_at": 1789267360.3241506}, {"event_id": "335bc01740f74cb9a18c8cb0e9fe7c55", "step": 13, "value": 0.9438466606016878, "stage": "improve", "created_at": 1789268258.0145333}, {"event_id": "2b301e7d64384a23b9f56be12c500430", "step": 14, "value": 0.8910373310448402, "stage": "debug", "created_at": 1789266609.0028124}, {"event_id": "d3ff2a004aca4e3bb8e49ce6b755d42d", "step": 16, "value": 0.941237673976012, "stage": "improve", "created_at": 1789269471.8260608}, {"event_id": "bd73894955914e7f813e3bc8dcff019e", "step": 17, "value": 0.9437839194403489, "stage": "improve", "created_at": 1789269285.5923634}, {"event_id": "921bf67575c64702a3fa0d6ca30e2c30", "step": 18, "value": 0.939282241114283, "stage": "improve", "created_at": 1789270723.2681415}, {"event_id": "41250f87e8f340a6a6b0d42a67c24db1", "step": 19, "value": 0.9432401627087451, "stage": "improve", "created_at": 1789271125.532056}, {"event_id": "44539eca3f1d4340a749123e5b21567a", "step": 21, "value": 0.9374052347042278, "stage": "evolution", "created_at": 1789271579.5447738}, {"event_id": "8f7ab61f800d4a3192b1dc93d12793ac", "step": 23, "value": 0.9406782319540735, "stage": "evolution", "created_at": 1789273000.7067237}, {"event_id": "6f07b8f1586d4053acde79910bf40b67", "step": 25, "value": 0.9432401627087451, "stage": "evolution", "created_at": 1789273888.6545174}, {"event_id": "452bbb5670c8453e99c7321f069b389f", "step": 26, "value": 0.9782392738756261, "stage": "debug", "created_at": 1789269597.0333865}, {"event_id": "678eb2a764c24642b9456e4aae985c7e", "step": 28, "value": 0.9471092009913104, "stage": "evolution", "created_at": 1789274565.6705976}, {"event_id": "bfe4259e893e45e2b6ce82c66d7c93ca", "step": 29, "value": 0.9767543997239388, "stage": "improve", "created_at": 1789275899.1563761}, {"event_id": "7fc9463d57164be1818d2ea0a6bcfa19", "step": 30, "value": 0.9782392738756261, "stage": "improve", "created_at": 1789274660.6194184}, {"event_id": "c243d14b1a51438eaefe7c5c2e72c2ab", "step": 31, "value": 0.9772092731436459, "stage": "improve", "created_at": 1789282464.0420878}, {"event_id": "318b2ad171d74dd190a1d54397c4ea76", "step": 32, "value": 0.9756564294005082, "stage": "improve", "created_at": 1789282688.4800844}, {"event_id": "2d8b72006b8e45198b86493c8e70d8b0", "step": 35, "value": 0.942884629461158, "stage": "improve", "created_at": 1789275246.8072686}, {"event_id": "7cb63eaa05ee4b5e8e5590ce174cd2d8", "step": 40, "value": 0.948276493069897, "stage": "fusion_draft", "created_at": 1789291074.7091804}], "maximize": true, "elapsed_seconds": 28759.142689228058, "node_count": 41, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-recovery-20260913/xixian.laplacian-anchor-logei.text-normalization-challenge-russian-language.yaml", "note": ""}, {"id": "xixian.laplacian-anchor-logei.the-icml-2013-whale-challenge-right-whale-redux", "experiment_id": "mlebench-gp7-recovery-20260913", "family": "MLEBench", "method": "laplacian_anchor_logei", "dataset": "the-icml-2013-whale-challenge-right-whale-redux", "status": "archived", "official_score": 0.98893, "medal": "silver", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.98961, "silver": 0.95017, "bronze": 0.90521}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7/logs-31ca423ebfab.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7", "member": "graph-selectors-recovery-44-runs/results/private_grades.jsonl:43", "sha256": "31ca423ebfabbe5e7b019284026d4b5e56ffcf69cd0b4e76caf8bb4a870dae41"}, {"bundle_id": "gp7", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7/logs-31ca423ebfab.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7", "member": "graph-selectors-recovery-44-runs/runs/laplacian_anchor_logei/22_the-icml-2013-whale-challenge-right-whale-redux/logs/journal.json", "sha256": "31ca423ebfabbe5e7b019284026d4b5e56ffcf69cd0b4e76caf8bb4a870dae41"}], "alternate_scores": [], "journal_ref": "gp7:graph-selectors-recovery-44-runs/runs/laplacian_anchor_logei/22_the-icml-2013-whale-challenge-right-whale-redux/logs/journal.json", "metrics": [{"event_id": "a2236328d4dd40a3934464dcf17f9d27", "step": 2, "value": 0.9476067524175986, "stage": "debug", "created_at": 1789266300.501497}, {"event_id": "7e5e263ab1f44adc82677c236e4762c3", "step": 5, "value": 0.985662499396155, "stage": "improve", "created_at": 1789266844.9451585}, {"event_id": "8b5ad83d94aa438b99272a34a307d902", "step": 6, "value": 0.8702492958090452, "stage": "debug", "created_at": 1789266669.4364817}, {"event_id": "a315a3235b2849259062ca3af8f1df74", "step": 7, "value": 0.9875664106363492, "stage": "improve", "created_at": 1789267207.0161226}, {"event_id": "1d13b766f1ee4e0c975099bf4a6cadd3", "step": 8, "value": 0.9853553024499844, "stage": "improve", "created_at": 1789267402.0728111}, {"event_id": "d96e2954c91f4b92a16758ec62d71cce", "step": 9, "value": 0.9908556657429068, "stage": "improve", "created_at": 1789267568.4745486}, {"event_id": "646c0da9df7649c382285515365f3c0c", "step": 10, "value": 0.9371078334235403, "stage": "improve", "created_at": 1789267785.5547256}, {"event_id": "be4f203fd53a41778bc8e5d9ccd931f9", "step": 11, "value": 0.9906793922705857, "stage": "improve", "created_at": 1789267944.2849972}, {"event_id": "abd7b2a20a454df2868886f466bb4f11", "step": 12, "value": 0.9924508026456794, "stage": "improve", "created_at": 1789268141.5937088}, {"event_id": "22583221485349b7ba9d6e6fab9b1e0f", "step": 13, "value": 0.9934187293521949, "stage": "improve", "created_at": 1789268517.124413}, {"event_id": "b38d48c7f5be487bb0d9d992f3e016e0", "step": 15, "value": 0.9933404513113544, "stage": "improve", "created_at": 1789268945.5611567}, {"event_id": "922da94a5caf44f48908e1c07094410b", "step": 16, "value": 0.9832273695614393, "stage": "debug", "created_at": 1789268909.4693177}, {"event_id": "2ff1edd3bc654c4eab891e36a30318a7", "step": 17, "value": 0.9854156376653427, "stage": "improve", "created_at": 1789269533.6190257}, {"event_id": "962b3e7146a248068194e6c649c8b95e", "step": 19, "value": 0.8968544334652665, "stage": "debug", "created_at": 1789266778.9589832}, {"event_id": "d3e0237ff2614de983d0a88c3c46e387", "step": 20, "value": 0.9938373295554813, "stage": "evolution", "created_at": 1789270061.2762532}, {"event_id": "f566750bf27c4c5ba632a8fcf50831e8", "step": 21, "value": 0.9803366579586493, "stage": "debug", "created_at": 1789270037.2459733}, {"event_id": "14eeade82fa049d7bad13266b5f8ab20", "step": 22, "value": 0.9940451508528264, "stage": "evolution", "created_at": 1789270286.8081553}, {"event_id": "574558af1401424ca1db2716c18ec8d1", "step": 24, "value": 0.9928112365465779, "stage": "improve", "created_at": 1789270712.7557786}, {"event_id": "e765dde1bdb54b0b9fdc5b51c04cba0f", "step": 26, "value": 0.9887790301607067, "stage": "improve", "created_at": 1789270834.0988197}, {"event_id": "8241c3a3124245d08218b21096839e29", "step": 27, "value": 0.9926465963347343, "stage": "improve", "created_at": 1789271208.765507}, {"event_id": "70b057272f684e4389a15a954ac78bee", "step": 28, "value": 0.992978045671392, "stage": "improve", "created_at": 1789271743.81382}, {"event_id": "89b27b3c894c44c7ab7bb2e6f784f8b0", "step": 29, "value": 0.9927225082886981, "stage": "evolution", "created_at": 1789271783.2012215}, {"event_id": "9e71eabbe45f49ddbd5c1e9208359199", "step": 30, "value": 0.9835123179468674, "stage": "debug", "created_at": 1789271674.0522642}, {"event_id": "ce9333e198d54e5c8c5269b1c67758bc", "step": 34, "value": 0.9860484737630952, "stage": "debug", "created_at": 1789272737.5869977}, {"event_id": "f3bdc492e2704eac86d175f3291b648c", "step": 35, "value": 0.9767244324312271, "stage": "debug", "created_at": 1789272852.2449055}, {"event_id": "bad985947d304ad582d3e69748705775", "step": 37, "value": 0.9807932498505574, "stage": "debug", "created_at": 1789272913.4017997}, {"event_id": "80ad0fa1f01446b7a04d6110f0e3f6e8", "step": 40, "value": 0.9906341462592585, "stage": "evolution", "created_at": 1789273322.7199676}, {"event_id": "8c33b6f6cd6d4d798c2813a4b7fa6a67", "step": 44, "value": 0.9935338789135323, "stage": "evolution", "created_at": 1789273782.2623081}, {"event_id": "c97d0c70d2ff46ff9dc01d423d968194", "step": 46, "value": 0.9789378882062725, "stage": "debug", "created_at": 1789273914.11809}, {"event_id": "3a4a7327b39847529e3dac71bbec17ba", "step": 49, "value": 0.97837888802574, "stage": "evolution", "created_at": 1789274293.9753582}, {"event_id": "a4d42597d34a4eb091e56f14ecc1493d", "step": 50, "value": 0.9770259535443163, "stage": "evolution", "created_at": 1789274457.7482276}, {"event_id": "8bc937babf90479e8f08044985eebd09", "step": 51, "value": 0.9801162856919892, "stage": "evolution", "created_at": 1789274619.7881598}, {"event_id": "475b94a06dfa4a8b90acb771689cef72", "step": 52, "value": 0.9668496904878071, "stage": "evolution", "created_at": 1789274964.9544153}, {"event_id": "0c66b3aaa995469880dc83bc69a96d07", "step": 54, "value": 0.9929735106715447, "stage": "evolution", "created_at": 1789275189.195775}, {"event_id": "6abff5fea1924397a7986ef3bc06b161", "step": 57, "value": 0.9845147324909699, "stage": "debug", "created_at": 1789275357.8788836}, {"event_id": "91e5173253624aee8ab36dbe4f1d4e3a", "step": 58, "value": 0.981570029682848, "stage": "debug", "created_at": 1789275831.7133408}, {"event_id": "264ee3113bda403d9ea0b4396c5ce055", "step": 59, "value": 0.9931271939463479, "stage": "debug", "created_at": 1789275905.4356112}, {"event_id": "fe185d257e004b12a5e044c7faefdffc", "step": 60, "value": 0.9899786362072416, "stage": "evolution", "created_at": 1789276161.6857038}, {"event_id": "ffb6438811604384b7568c005867833a", "step": 61, "value": 0.9826279929766654, "stage": "evolution", "created_at": 1789276401.448666}, {"event_id": "c7f50d4bf6134a73a38496279b85c01d", "step": 63, "value": 0.9759654444187009, "stage": "evolution", "created_at": 1789277387.0345075}, {"event_id": "c5992089957b474b856b0999120d41fa", "step": 64, "value": 0.9841271041554518, "stage": "evolution", "created_at": 1789277136.0557296}, {"event_id": "ad63da812b5e4eedac100ce458b9a4b2", "step": 65, "value": 0.9883996795009458, "stage": "evolution", "created_at": 1789276925.0591307}, {"event_id": "0d3cfafa21b54d33bf455d7e97dd0df9", "step": 66, "value": 0.9931817263167028, "stage": "evolution", "created_at": 1789278188.5783818}, {"event_id": "e6a5468e947b40ab8cd47c4626c6ae67", "step": 69, "value": 0.9777179440667533, "stage": "debug", "created_at": 1789278581.9936275}, {"event_id": "874505b34eb44b1b8442e8986a12fc5b", "step": 70, "value": 0.9941484699797798, "stage": "evolution", "created_at": 1789278629.6552892}, {"event_id": "d8a7fceffe2e4703be0d1ddf3b72c6d3", "step": 71, "value": 0.9764904489363323, "stage": "debug", "created_at": 1789278825.6024737}, {"event_id": "959b6966dc524afb95adda47fff893fe", "step": 74, "value": 0.9928347002414395, "stage": "improve", "created_at": 1789279307.9735131}, {"event_id": "6d2e615a4ad5429d814249957e16683e", "step": 75, "value": 0.9941015425900566, "stage": "improve", "created_at": 1789279577.152315}, {"event_id": "6655aa44e0344ae2be9ceaad189c1cdd", "step": 76, "value": 0.9934636850028541, "stage": "debug", "created_at": 1789279954.2880375}, {"event_id": "02734d04a7534030ad75160f0f426494", "step": 77, "value": 0.9939118612921003, "stage": "fusion", "created_at": 1789280271.705097}, {"event_id": "acb9df6a46764efdaada7a6b02514562", "step": 78, "value": 0.9937383482544687, "stage": "improve", "created_at": 1789280145.2578797}, {"event_id": "2ffbd4c988e749d4930f4cb646b80dbe", "step": 81, "value": 0.9873272386878864, "stage": "evolution", "created_at": 1789281089.251992}, {"event_id": "b4de515a2c114790b021c8a262cd9086", "step": 84, "value": 0.9938824823800467, "stage": "evolution", "created_at": 1789281590.4460495}, {"event_id": "5319a5e6092b44609cbeae6b3d6dc467", "step": 86, "value": 0.9812101531293425, "stage": "debug", "created_at": 1789282343.0526602}, {"event_id": "518fc06d8e554f1cbce99d8a3f945d45", "step": 90, "value": 0.9814789532818572, "stage": "debug", "created_at": 1789283200.6946576}, {"event_id": "b89a990ec09742aca9994edddad9a221", "step": 91, "value": 0.9933102837036751, "stage": "evolution", "created_at": 1789283049.4068232}, {"event_id": "a3dcb40596f144fdb1c08a177d54995a", "step": 92, "value": 0.9914156396370818, "stage": "evolution", "created_at": 1789283432.932307}, {"event_id": "c6e38c09c07f4a47b1872e2727ddd4a7", "step": 93, "value": 0.9769754114280025, "stage": "evolution", "created_at": 1789283810.0715463}, {"event_id": "ceb53c5d6d91407fb118dba81cb22857", "step": 94, "value": 0.9814140622913755, "stage": "evolution", "created_at": 1789283868.1476767}, {"event_id": "2932b7dbac674e8d8ce37615af90eaf4", "step": 95, "value": 0.992244473387629, "stage": "evolution", "created_at": 1789283968.881845}, {"event_id": "eeb65efc53c54a8b8a329e15ca648644", "step": 97, "value": 0.9943826139936294, "stage": "fusion", "created_at": 1789284942.2926114}, {"event_id": "ba7367fcc39c4c339da51efa4626ed6a", "step": 99, "value": 0.9972515929186964, "stage": "debug", "created_at": 1789285504.7826948}, {"event_id": "0dd81ea8ab1b455ca86a6146e4dac030", "step": 100, "value": 0.994482679751127, "stage": "improve", "created_at": 1789285808.1067305}, {"event_id": "7122e87a99c14a88a4e42ea5aa0bf76c", "step": 101, "value": 0.9965819903325633, "stage": "improve", "created_at": 1789286104.8506987}, {"event_id": "82c82014744c484c9ddec0aa0282f821", "step": 102, "value": 0.9825641570644134, "stage": "debug", "created_at": 1789285970.1448116}, {"event_id": "72dcbfd58c564300aef0d93a7c103e69", "step": 103, "value": 0.9968761738009115, "stage": "improve", "created_at": 1789286554.1158807}, {"event_id": "6bc92fba52f441d6979f89016c240b86", "step": 104, "value": 0.9886372621220054, "stage": "improve", "created_at": 1789286817.6892998}, {"event_id": "f1ec27cf032a44f9b03626730202d1fa", "step": 105, "value": 0.9965717372894306, "stage": "fusion", "created_at": 1789286959.7792356}, {"event_id": "d7de5541b7fd44869884e79349927742", "step": 106, "value": 0.9969369033640826, "stage": "fusion", "created_at": 1789287076.9867926}, {"event_id": "f1a7f85075c04f88ba0b121ad8d52575", "step": 107, "value": 0.9976728549697191, "stage": "fusion", "created_at": 1789287534.7908764}, {"event_id": "fc8004e91b324f889d55e6a0eec91469", "step": 108, "value": 0.9976727563827658, "stage": "fusion", "created_at": 1789287534.332404}, {"event_id": "51e414aa195b4cf2a3a910a566ab01c5", "step": 109, "value": 0.9971445274875214, "stage": "fusion", "created_at": 1789287657.5929964}, {"event_id": "fb58c480a6594b4db699b2eb5f87a25f", "step": 112, "value": 0.6034009541245331, "stage": "improve", "created_at": 1789288221.464403}, {"event_id": "69c17104a8e2498b8acf7c75b3e0ec83", "step": 113, "value": 0.998325204839042, "stage": "improve", "created_at": 1789288315.247452}, {"event_id": "938cd705ac834a258a58d597a9767ce3", "step": 115, "value": 0.997298323134513, "stage": "evolution", "created_at": 1789288570.714183}, {"event_id": "72f72466d752457c90e670bb48635437", "step": 116, "value": 0.997255930744637, "stage": "improve", "created_at": 1789288979.028937}, {"event_id": "ddb7ba521f7d4c5ba2612e1af5434b7e", "step": 117, "value": 0.9958297718796489, "stage": "improve", "created_at": 1789288908.4320142}, {"event_id": "239a4769a7ba4fe089cb54d7f6bbc7b1", "step": 118, "value": 0.9934082791351558, "stage": "improve", "created_at": 1789289175.8817604}, {"event_id": "2710524a516844fa9b871b4f41a68762", "step": 121, "value": 0.9874580093608953, "stage": "evolution", "created_at": 1789289726.0874677}, {"event_id": "6a7fb3ae9f6048f89838476fbfbaa07e", "step": 122, "value": 0.9511177583836739, "stage": "debug", "created_at": 1789290025.0713034}, {"event_id": "695ed461bbce4f518ab43d3da0155467", "step": 124, "value": 0.9886806649434997, "stage": "fusion", "created_at": 1789290222.4438343}, {"event_id": "5ef78fddae354c2aa290aca1e4df650b", "step": 126, "value": 0.9965553718551994, "stage": "evolution", "created_at": 1789290897.0772717}, {"event_id": "be1eee1437a04a10a3c3bde0442dfbce", "step": 128, "value": 0.8615776221555882, "stage": "debug", "created_at": 1789291251.141405}, {"event_id": "baa50fef99de40ffa636d934d1c78409", "step": 129, "value": 0.9880644651966943, "stage": "debug", "created_at": 1789291533.3001893}, {"event_id": "2cb6738f82ad4fc59f134e58f62996f3", "step": 130, "value": 0.9969994074924112, "stage": "evolution", "created_at": 1789292489.5360494}, {"event_id": "fdde406b68f04977a4d47f8bc9576479", "step": 131, "value": 0.9964843892488955, "stage": "evolution", "created_at": 1789292151.9037645}, {"event_id": "0dad47bd182a4453b244dccf97871d94", "step": 132, "value": 0.9953223448315297, "stage": "evolution", "created_at": 1789291444.8055303}, {"event_id": "35cf1690adf54a39b9fe9dfb5d1f7bf8", "step": 134, "value": 0.9975160031271781, "stage": "fusion", "created_at": 1789292986.325103}], "maximize": true, "elapsed_seconds": 28325.914436101913, "node_count": 135, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-recovery-20260913/xixian.laplacian-anchor-logei.the-icml-2013-whale-challenge-right-whale-redux.yaml", "note": ""}, {"id": "xixian.gp7-ancestry-logei.aerial-cactus-identification", "experiment_id": "mlebench-gp7-recovery-20260913", "family": "MLEBench", "method": "gp7_ancestry_logei", "dataset": "aerial-cactus-identification", "status": "archived", "official_score": 0.99998, "medal": "none", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 1.0, "silver": 1.0, "bronze": 1.0}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7/logs-31ca423ebfab.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7", "member": "graph-selectors-recovery-44-runs/results/private_grades.jsonl:44", "sha256": "31ca423ebfabbe5e7b019284026d4b5e56ffcf69cd0b4e76caf8bb4a870dae41"}, {"bundle_id": "gp7", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7/logs-31ca423ebfab.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7", "member": "graph-selectors-recovery-44-runs/runs/gp7_ancestry_logei/01_aerial-cactus-identification/logs/journal.json", "sha256": "31ca423ebfabbe5e7b019284026d4b5e56ffcf69cd0b4e76caf8bb4a870dae41"}], "alternate_scores": [], "journal_ref": "gp7:graph-selectors-recovery-44-runs/runs/gp7_ancestry_logei/01_aerial-cactus-identification/logs/journal.json", "metrics": [{"event_id": "5ed100ccf4a9400f99c8e7a3d8e3c52c", "step": 3, "value": 0.9996488085417304, "stage": "draft", "created_at": 1789136168.0719697}, {"event_id": "1945a5d780f341ef8227ea20445975f4", "step": 4, "value": 0.9999761167730575, "stage": "debug", "created_at": 1789136856.3430877}, {"event_id": "44618a6667bf41e0910684e829e53af9", "step": 5, "value": 0.9999926355518733, "stage": "debug", "created_at": 1789136884.8454697}, {"event_id": "f728db41a7b6422eabfbc4cfac946136", "step": 8, "value": 0.9999328257948947, "stage": "improve", "created_at": 1789137272.060908}, {"event_id": "9ec6b49c8f424059b5eaa455dc022eeb", "step": 9, "value": 1.0, "stage": "improve", "created_at": 1789137398.173849}, {"event_id": "bb5319f77a5b484abb65d1034cf93616", "step": 10, "value": 0.9890273157773924, "stage": "debug", "created_at": 1789137651.4492376}, {"event_id": "c30e3cb79c4c436d920a8036305ad103", "step": 11, "value": 0.99994476663905, "stage": "improve", "created_at": 1789138182.8876684}, {"event_id": "00200fac43d1468993f8f5459376953b", "step": 12, "value": 0.9999447666390501, "stage": "improve", "created_at": 1789138071.1599636}, {"event_id": "1b0d34ae509644298678665ee023e2e6", "step": 14, "value": 1.0, "stage": "improve", "created_at": 1789138698.21447}, {"event_id": "3f779347687c4694ae4a7ab78f503ae1", "step": 15, "value": 0.9999926355518733, "stage": "debug", "created_at": 1789139156.4823046}, {"event_id": "ca07afbe221747bf888b8de4d625e223", "step": 17, "value": 0.9998936799973771, "stage": "debug", "created_at": 1789140121.3482864}, {"event_id": "d5b944e0f31b40729b31b6f7a6da71f4", "step": 18, "value": 0.9999922541315456, "stage": "improve", "created_at": 1789138714.4739003}, {"event_id": "a75e6622e57a4c4fa0c9b8b78ec45632", "step": 19, "value": 0.9999890443709871, "stage": "improve", "created_at": 1789140091.4995253}, {"event_id": "3f77eb51fa2a40e4934e405f8cc8f200", "step": 20, "value": 0.9999849857481327, "stage": "evolution", "created_at": 1789142669.1158857}, {"event_id": "e40ac47154a549518832f84128ffb428", "step": 21, "value": 0.9999580211067489, "stage": "evolution", "created_at": 1789144575.3165977}, {"event_id": "21ffe619e61a4af5a5e0f7dcd00be027", "step": 22, "value": 0.9999925989818534, "stage": "improve", "created_at": 1789141300.3161592}, {"event_id": "dc1473c90d2344ae8acf907dabf66f37", "step": 23, "value": 0.9999961535927194, "stage": "evolution", "created_at": 1789145535.800755}, {"event_id": "cb5b37d7f1d544bb9ac143c3102da175", "step": 24, "value": 1.0, "stage": "fusion", "created_at": 1789151058.1322877}, {"event_id": "0497259036f5439fbefe4e6893766d49", "step": 26, "value": 0.9999930499399483, "stage": "evolution", "created_at": 1789149697.8377979}, {"event_id": "da629170f4844b2db2405875baa57bac", "step": 28, "value": 0.999986179460737, "stage": "improve", "created_at": 1789152322.0139914}, {"event_id": "c169262a38f946e58aa540836a64c8d3", "step": 30, "value": 0.9999946680837009, "stage": "debug", "created_at": 1789153051.5990486}, {"event_id": "6f7b1786af9d4be395d77f14e58afa36", "step": 31, "value": 0.99970173985087, "stage": "fusion_draft", "created_at": 1789158971.8795643}, {"event_id": "ca9c991b36d84dafa1473e8cc24dbebf", "step": 32, "value": 0.9999904502991656, "stage": "improve", "created_at": 1789156614.241193}], "maximize": true, "elapsed_seconds": 28680.73214697838, "node_count": 33, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-recovery-20260913/xixian.gp7-ancestry-logei.aerial-cactus-identification.yaml", "note": ""}, {"id": "xixian.gp7-ancestry-logei.aerial-cactus-identification", "experiment_id": "mlebench-gp7-three-20260916", "family": "MLEBench", "method": "gp7_ancestry_logei", "dataset": "aerial-cactus-identification", "status": "archived", "official_score": 0.99999, "medal": "none", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 1.0, "silver": 1.0, "bronze": 1.0}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/results/private_grades.jsonl:1", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}, {"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/runs/gp7_ancestry_logei/01_aerial-cactus-identification/logs/journal.json", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}], "alternate_scores": [], "journal_ref": "gp7-three-bo-analysis-20260916:gp7-three-66-runs/runs/gp7_ancestry_logei/01_aerial-cactus-identification/logs/journal.json", "metrics": [{"event_id": "18f56228e4e247aea38bdb7611b96468", "step": 1, "value": 0.9998676471173609, "stage": "draft", "created_at": 1789523079.0227854}, {"event_id": "a19a6fd50e324f1ebce901d80e22c655", "step": 2, "value": 0.9999847412716757, "stage": "draft", "created_at": 1789522698.3472815}, {"event_id": "0021752531924fa597e3c0677d3470d2", "step": 3, "value": 0.9999966828851469, "stage": "draft", "created_at": 1789523413.5100641}, {"event_id": "53a7970d6f4e4e6dab2c7a4321bbcec9", "step": 4, "value": 0.9998009731088133, "stage": "improve", "created_at": 1789523671.028071}, {"event_id": "5c16d3a3e00b4d93b74018f32ac60e8c", "step": 6, "value": 0.9999681556974102, "stage": "improve", "created_at": 1789523978.8909068}, {"event_id": "12fe978d4f6d4b62b8240faa6cd80bd7", "step": 7, "value": 0.9999648385825571, "stage": "debug", "created_at": 1789523984.890078}, {"event_id": "a3cd8d59d9284a8094c3a8aa846ff4c5", "step": 8, "value": 0.9999887218094994, "stage": "improve", "created_at": 1789524337.8448932}, {"event_id": "6a6e9d1bdb044766a8aadcb7cacc99d1", "step": 9, "value": 0.9999940291932644, "stage": "improve", "created_at": 1789523996.7779105}, {"event_id": "721ff6b63ad7488a81e861a341f4000b", "step": 12, "value": 0.9991564576928537, "stage": "debug", "created_at": 1789524748.9949837}, {"event_id": "6e4b51c5e69748d681d25b079565bec4", "step": 13, "value": 0.9999960194621762, "stage": "improve", "created_at": 1789524726.338701}, {"event_id": "d62fe9b8823444bdb7f90ba02784daef", "step": 15, "value": 0.9999980097310882, "stage": "improve", "created_at": 1789525259.2595685}, {"event_id": "f5f04a8a96d549a2be822be1f7a63ddc", "step": 16, "value": 0.9999847412716756, "stage": "debug", "created_at": 1789525342.8153129}, {"event_id": "420eaf15190548c1aad7dddd5f2335d8", "step": 17, "value": 0.9999688191203808, "stage": "improve", "created_at": 1789525369.211408}, {"event_id": "fda05a2d75804e40b199266711fcdf12", "step": 18, "value": 0.9999920389243525, "stage": "improve", "created_at": 1789525973.2634437}, {"event_id": "da63a54bffe34df5b00a3a8d5134ebe3", "step": 20, "value": 0.9999966828851469, "stage": "evolution", "created_at": 1789525991.4288833}, {"event_id": "f3814ecafa9d4d7ba00680e989683ef2", "step": 21, "value": 0.9999144184367896, "stage": "debug", "created_at": 1789527176.0594633}, {"event_id": "459427d4cce041f796e55665f61aef49", "step": 22, "value": 0.9999933657702937, "stage": "evolution", "created_at": 1789526035.3851578}, {"event_id": "e40967467969442fb02ffcf295bc38e7", "step": 25, "value": 0.9998719593666698, "stage": "debug", "created_at": 1789528476.603945}, {"event_id": "01bd32f5c31d477b885a81d3f3a8a7ab", "step": 26, "value": 0.9999641751595865, "stage": "improve", "created_at": 1789528240.1281111}, {"event_id": "083140a5c4d34c73a92c258518cd677b", "step": 27, "value": 0.9999966828851469, "stage": "improve", "created_at": 1789527894.4689646}, {"event_id": "cb3f8410c3cc4bb2a0488dc5fb08bba0", "step": 28, "value": 0.9997754313244444, "stage": "improve", "created_at": 1789529082.1372786}, {"event_id": "5727926f7a85411abb9df04a8f15c70d", "step": 29, "value": 0.9999263600502608, "stage": "improve", "created_at": 1789529289.3534281}, {"event_id": "fd17c3e3de81495c9a6d2fb4f1a08b0f", "step": 30, "value": 0.9998620080221106, "stage": "improve", "created_at": 1789529056.938692}, {"event_id": "1b53227ee44e49b682bde3aa2081f70b", "step": 31, "value": 0.9997565237697816, "stage": "improve", "created_at": 1789530068.4914873}, {"event_id": "22488c24e80241dfadd336cc0a057e18", "step": 32, "value": 0.9999071207841128, "stage": "improve", "created_at": 1789530049.0357263}, {"event_id": "a7ea2c6a5e8e44d4b3cd045204f4a1a7", "step": 33, "value": 0.9999482530082915, "stage": "evolution", "created_at": 1789530430.1019282}, {"event_id": "10d52aa0578149e5b1ec874ace7c7661", "step": 34, "value": 0.9999310040110554, "stage": "evolution", "created_at": 1789530365.9455805}, {"event_id": "dd7eb16a2cee435f8fc983ecf62b8f9c", "step": 35, "value": 0.99998938523247, "stage": "evolution", "created_at": 1789530111.256562}, {"event_id": "cf8c312033d04aaca2af0208d8bac2a1", "step": 36, "value": 0.9999323308569965, "stage": "improve", "created_at": 1789532869.3883936}, {"event_id": "d38294f2fdcd4dd4bd402a3136ad6b8d", "step": 37, "value": 0.9997545335008697, "stage": "evolution", "created_at": 1789532330.4614303}, {"event_id": "edc34b8fba3a41f78e733b1a256c5ece", "step": 38, "value": 0.9998082707614901, "stage": "evolution", "created_at": 1789532099.5669873}, {"event_id": "b197ed510099432ebc71600da73b4920", "step": 39, "value": 0.9999993365770294, "stage": "improve", "created_at": 1789536362.0897295}, {"event_id": "a2da88d3bd354200ab141fefba81f192", "step": 40, "value": 0.9999933657702937, "stage": "improve", "created_at": 1789537014.5124462}, {"event_id": "bdc1dfe36ce34f94b8b3e8d9980139e9", "step": 41, "value": 0.9999323308569965, "stage": "evolution", "created_at": 1789539284.069748}, {"event_id": "bf6de2dc50ce4120b32971d9c11aa6fe", "step": 42, "value": 0.9999223795124372, "stage": "evolution", "created_at": 1789539434.1654036}, {"event_id": "ea3a56d713bf411a90f08ad2bb9d2165", "step": 43, "value": 0.999954223815027, "stage": "evolution", "created_at": 1789538866.2820663}], "maximize": true, "elapsed_seconds": 28803.79738664627, "node_count": 47, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-three-20260916/xixian.gp7-ancestry-logei.aerial-cactus-identification.yaml", "note": ""}, {"id": "xixian.gp7-ancestry-logei.aptos2019-blindness-detection", "experiment_id": "mlebench-gp7-three-20260916", "family": "MLEBench", "method": "gp7_ancestry_logei", "dataset": "aptos2019-blindness-detection", "status": "archived", "official_score": 0.91735, "medal": "bronze", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.930508, "silver": 0.919654, "bronze": 0.914492}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/results/private_grades.jsonl:2", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}, {"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/runs/gp7_ancestry_logei/02_aptos2019-blindness-detection/logs/journal.json", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}], "alternate_scores": [], "journal_ref": "gp7-three-bo-analysis-20260916:gp7-three-66-runs/runs/gp7_ancestry_logei/02_aptos2019-blindness-detection/logs/journal.json", "metrics": [{"event_id": "5722eaea81fc4c0d914bd390d1c8dac0", "step": 5, "value": 0.9102659446324015, "stage": "debug", "created_at": 1789523265.8093631}, {"event_id": "ef2e6c8df6874ae8b569a1780f2d835e", "step": 9, "value": 0.8731493649920996, "stage": "debug", "created_at": 1789524860.5177824}, {"event_id": "174b06aabdab4e9b88d4e8d08e6f17a2", "step": 11, "value": 0.8942944379564098, "stage": "debug", "created_at": 1789525100.7005656}, {"event_id": "7143b854a99f4a3f8caaec1359281013", "step": 12, "value": 0.8950167057040507, "stage": "debug", "created_at": 1789526451.4119785}, {"event_id": "603dcc29faaf487d84d6d62606b72ca2", "step": 13, "value": 0.8945210595496035, "stage": "improve", "created_at": 1789526744.652677}, {"event_id": "9a782008ee5948888b713c23c0bae295", "step": 15, "value": 0.9129183514785311, "stage": "debug", "created_at": 1789525736.872937}, {"event_id": "98a7576ef45843e3ba5f61733bdb0040", "step": 18, "value": 0.8993399306326361, "stage": "debug", "created_at": 1789528562.706478}, {"event_id": "a89961d5c66b4d41b38914179edbb77c", "step": 19, "value": 0.8907608340526803, "stage": "debug", "created_at": 1789529734.995191}, {"event_id": "b97a90ba1444488b951e126944b7cc02", "step": 20, "value": 0.903391919766159, "stage": "debug", "created_at": 1789528730.293025}, {"event_id": "8a70c3a4a61542c5bbdc0f49483ebb42", "step": 22, "value": 0.9091451582701097, "stage": "draft", "created_at": 1789531166.150692}, {"event_id": "4ce946f07c364799b7c4c30d008d0087", "step": 23, "value": 0.9059566419574938, "stage": "improve", "created_at": 1789531228.777252}, {"event_id": "c32e73b52a464c5fa1f22dafb0a0623c", "step": 24, "value": 0.890067847874182, "stage": "evolution", "created_at": 1789532902.7694035}, {"event_id": "655c81f02e2d4e089e36c70cce7f0666", "step": 25, "value": 0.9033995822288458, "stage": "evolution", "created_at": 1789534267.919433}, {"event_id": "6bb38a1df5264ae599805a80ec4bc1c0", "step": 26, "value": 0.908130935349052, "stage": "debug", "created_at": 1789532830.2789469}, {"event_id": "370a394e42844647b3f1ef63fd63b086", "step": 27, "value": 0.9096769219567145, "stage": "improve", "created_at": 1789536084.0442128}, {"event_id": "9e791e1d0226449cb2cad04c60c36423", "step": 30, "value": 0.9095450423845136, "stage": "evolution", "created_at": 1789539649.9026635}, {"event_id": "d0bff3449c794a818abad7cf83ef59a6", "step": 32, "value": 0.907091626451876, "stage": "debug", "created_at": 1789539097.225362}, {"event_id": "92c44f4136e04806a4b0f298f0d4421a", "step": 33, "value": 0.8949646645074196, "stage": "debug", "created_at": 1789541495.8141987}, {"event_id": "bd526247a34f4d67a1eee0dd1ceb5ca8", "step": 34, "value": 0.9074157877681615, "stage": "evolution", "created_at": 1789542964.4492614}, {"event_id": "f305d98d2adc41979857f5410875c96c", "step": 35, "value": 0.9070845294147472, "stage": "fusion", "created_at": 1789541641.8838506}, {"event_id": "c434053a9e54413ba827c036889a206e", "step": 37, "value": 0.8922833661268559, "stage": "evolution", "created_at": 1789544004.860136}], "maximize": true, "elapsed_seconds": 28799.668531179428, "node_count": 39, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-three-20260916/xixian.gp7-ancestry-logei.aptos2019-blindness-detection.yaml", "note": ""}, {"id": "xixian.gp7-ancestry-logei.denoising-dirty-documents", "experiment_id": "mlebench-gp7-three-20260916", "family": "MLEBench", "method": "gp7_ancestry_logei", "dataset": "denoising-dirty-documents", "status": "archived", "official_score": 0.01198, "medal": "gold", "valid_submission": true, "score_maximize": false, "thresholds": {"gold": 0.01794, "silver": 0.02609, "bronze": 0.04517}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/results/private_grades.jsonl:3", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}, {"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/runs/gp7_ancestry_logei/03_denoising-dirty-documents/logs/journal.json", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}], "alternate_scores": [], "journal_ref": "gp7-three-bo-analysis-20260916:gp7-three-66-runs/runs/gp7_ancestry_logei/03_denoising-dirty-documents/logs/journal.json", "metrics": [{"event_id": "5aaf16e505534654a6c644f2a68775e0", "step": 8, "value": 0.021177936166706247, "stage": "debug", "created_at": 1789523199.8506386}, {"event_id": "bdd046a3a30f4849b8d4cbb83283f437", "step": 9, "value": 0.01784878251219238, "stage": "debug", "created_at": 1789523104.9008498}, {"event_id": "af4663690b8a477486d8f8f2e9ee317d", "step": 10, "value": 0.01989550679205737, "stage": "improve", "created_at": 1789523568.7910585}, {"event_id": "3894553b9380407d97292073e26eab08", "step": 11, "value": 0.022716557327377897, "stage": "debug", "created_at": 1789523332.388379}, {"event_id": "c899e71f66f14e42b3ddd121fbc1e400", "step": 23, "value": 0.9060511958192592, "stage": "improve", "created_at": 1789525193.446097}, {"event_id": "106c467585be4a13891ab40b1ff26413", "step": 24, "value": 0.020326554769947873, "stage": "improve", "created_at": 1789525295.7734294}, {"event_id": "a294f9bbbff94ea6b9f7049f7725b4e6", "step": 25, "value": 0.016975767973927004, "stage": "debug", "created_at": 1789525028.8746934}, {"event_id": "757cd0142eae42a584084ab40f16c323", "step": 26, "value": 0.019787762850514097, "stage": "improve", "created_at": 1789525462.3228993}, {"event_id": "73d84347b851464680a392f3bec0a6ca", "step": 27, "value": 0.9232623592513871, "stage": "improve", "created_at": 1789525623.5883958}, {"event_id": "7773d4ea5d474220bd063a3aa992a0fd", "step": 30, "value": 0.08811465999466273, "stage": "debug", "created_at": 1789525840.193321}, {"event_id": "8efefe1fce0a41dea31a8228d3e0aee5", "step": 31, "value": 0.018556996874804596, "stage": "debug", "created_at": 1789525968.8593621}, {"event_id": "c7d242c99c324950982b70760d687bc9", "step": 32, "value": 0.09424732077417933, "stage": "improve", "created_at": 1789526177.2315373}, {"event_id": "dce8f6c229814e81ad1afae22313e373", "step": 33, "value": 0.029064668252677152, "stage": "improve", "created_at": 1789526288.937295}, {"event_id": "984362c47c5d471d963819099087d2b8", "step": 34, "value": 0.014173728047641394, "stage": "improve", "created_at": 1789525977.4800038}, {"event_id": "3b88ef2b358c4154841be453605f8014", "step": 35, "value": 0.02352549172737721, "stage": "improve", "created_at": 1789526477.649357}, {"event_id": "00e0e88223054a6981407a4370c2ff81", "step": 38, "value": 0.09800139564603506, "stage": "improve", "created_at": 1789526701.070394}, {"event_id": "5df8648cae864b059fe4ef2fd0d2f6e7", "step": 42, "value": 0.09466667177593581, "stage": "debug", "created_at": 1789527108.3690665}, {"event_id": "df7b2cb94d314a799ecf3485216b4489", "step": 46, "value": 0.019325396295688836, "stage": "debug", "created_at": 1789527447.7547762}, {"event_id": "ac411b76168f4c6682c7e84f1a9efbec", "step": 47, "value": 0.018092513215178845, "stage": "debug", "created_at": 1789527690.1613872}, {"event_id": "40916b8c10ab4bec966bc3549857a925", "step": 48, "value": 0.032158025498840885, "stage": "improve", "created_at": 1789528051.3890886}, {"event_id": "089d4c26f25c48c6be29cb5712acd950", "step": 52, "value": 0.0689582177284246, "stage": "debug", "created_at": 1789528619.2647698}, {"event_id": "f77762d1e8be41f1b6482e381b441b53", "step": 53, "value": 0.017930965307985276, "stage": "debug", "created_at": 1789528570.8403573}, {"event_id": "be98592e80b94e8980a20fad0c08a9ec", "step": 55, "value": 0.026335928781641253, "stage": "improve", "created_at": 1789529028.642628}, {"event_id": "6615e321251d447a87be1ba659d397a3", "step": 56, "value": 0.07020565704784312, "stage": "debug", "created_at": 1789529195.897874}, {"event_id": "0bbbdb17112b4e739bc3be0cb04bd82f", "step": 59, "value": 0.08044123418679515, "stage": "debug", "created_at": 1789529662.5538466}, {"event_id": "a6a3c04845db406489e9b3739eb361b8", "step": 60, "value": 0.030285433800878506, "stage": "debug", "created_at": 1789529730.831145}, {"event_id": "490de7de45284e939637f543cc3d6d9f", "step": 61, "value": 0.024556647051808378, "stage": "evolution", "created_at": 1789529932.4400973}, {"event_id": "4337d250d28e4d9e8a7e7ef81b08fba2", "step": 62, "value": 0.08499107088988297, "stage": "debug", "created_at": 1789527376.053526}, {"event_id": "927063c539684e10a12bab87f4f565c5", "step": 63, "value": 0.028572296768246387, "stage": "evolution", "created_at": 1789530062.3512454}, {"event_id": "a3671d0d49964dff944890fc7fc5d96e", "step": 64, "value": 0.02019485561004064, "stage": "evolution", "created_at": 1789530239.3292596}, {"event_id": "9e352359f91c4b5fa41e9ea70598a791", "step": 66, "value": 0.018961668969162408, "stage": "debug", "created_at": 1789530817.9949152}, {"event_id": "78b49b950475438e9f46d07eeab2f614", "step": 67, "value": 0.02997858446693084, "stage": "evolution", "created_at": 1789530648.7052643}, {"event_id": "7498349c484947d99ce565b48fbbe64d", "step": 68, "value": 0.019898254044981627, "stage": "evolution", "created_at": 1789530748.021972}, {"event_id": "bc0aebf0875943cd8dbefd05e4517e28", "step": 71, "value": 0.018801861048244824, "stage": "debug", "created_at": 1789531285.4891188}, {"event_id": "f33eb5ece2574bb090dbf3c1b7eb9e60", "step": 72, "value": 0.07547758261963392, "stage": "evolution", "created_at": 1789531260.9245093}, {"event_id": "97e838078e5d4a13aabf104a6a902bfc", "step": 74, "value": 0.02357623391884338, "stage": "debug", "created_at": 1789531728.188766}, {"event_id": "b5e632f1884d40d5b896f3305d372c1d", "step": 76, "value": 0.014683456402494535, "stage": "debug", "created_at": 1789532055.2513394}, {"event_id": "db9fc50d160c4a8d8427b471c792876f", "step": 78, "value": 0.018895970594157718, "stage": "debug", "created_at": 1789532391.9232838}, {"event_id": "1fc2a5c8ce514343a3e9bc8535ca0197", "step": 79, "value": 0.028064245071470054, "stage": "improve", "created_at": 1789532471.8310928}, {"event_id": "0e2b442def624794991d0ce2591d7f98", "step": 80, "value": 0.02577852025930563, "stage": "evolution", "created_at": 1789532251.399298}, {"event_id": "5b7d789595e14855ad046c005b829124", "step": 81, "value": 0.02871376726004292, "stage": "improve", "created_at": 1789532999.8975322}, {"event_id": "71506db88d5d40658c4dd1666044d91a", "step": 83, "value": 0.015678875563150382, "stage": "evolution", "created_at": 1789532979.4093983}, {"event_id": "adb0c03b21304fc8ba59fbb942077b1d", "step": 84, "value": 0.027449583984316156, "stage": "debug", "created_at": 1789533418.5995002}, {"event_id": "a0a96d07ac334f099d908a8e70ff67d5", "step": 85, "value": 0.01666209091196731, "stage": "evolution", "created_at": 1789533445.8569293}, {"event_id": "1d61dfac4cc04fe0bbbf7d8e184f468f", "step": 86, "value": 0.017185218719075964, "stage": "evolution", "created_at": 1789533722.7457352}, {"event_id": "8a698daadacf48c6b844579a1c9738b9", "step": 87, "value": 0.013827688649427235, "stage": "evolution", "created_at": 1789533964.203564}, {"event_id": "477096e6142f4a77bec805a590320164", "step": 88, "value": 0.014513171649325123, "stage": "evolution", "created_at": 1789534169.9793086}, {"event_id": "1e1676c585994dd394209c96e81744c4", "step": 89, "value": 0.014188705801142629, "stage": "evolution", "created_at": 1789533876.137579}, {"event_id": "0e3426d64abb4b43a94f6dbf3d86e11a", "step": 91, "value": 0.032712890025807136, "stage": "improve", "created_at": 1789534642.5630686}, {"event_id": "2e7d04bc08f14a3290446ebcc237da76", "step": 92, "value": 0.10383235485336463, "stage": "improve", "created_at": 1789534764.0452008}, {"event_id": "f5000368e2334de1b093648705fcb0cf", "step": 93, "value": 0.026577313923216044, "stage": "improve", "created_at": 1789535085.1822796}, {"event_id": "51fb344810a94f01bbfc449fbaed6bba", "step": 94, "value": 0.013748966945304135, "stage": "evolution", "created_at": 1789535024.0420556}, {"event_id": "51cd5eff3b214af2b732fd8266e48eed", "step": 95, "value": 0.025145067495816888, "stage": "evolution", "created_at": 1789535072.73675}, {"event_id": "d98b495031324f7bb7d4d0618716bf77", "step": 96, "value": 0.027026532257827213, "stage": "improve", "created_at": 1789535543.1000564}, {"event_id": "24a35a21ec1f49feb9e0211a4b20c3d5", "step": 97, "value": 0.028787359147064383, "stage": "evolution", "created_at": 1789535435.4186525}, {"event_id": "0afeeb7424bf4a6a8b4bf843310f73e4", "step": 99, "value": 0.01372167509097275, "stage": "improve", "created_at": 1789535718.4448504}, {"event_id": "25fe21133d6744b386c7d458175f2e93", "step": 100, "value": 0.01386425474189683, "stage": "evolution", "created_at": 1789535988.0426373}, {"event_id": "e85edeee7696415abe38c7bee4b0cb06", "step": 101, "value": 0.013633089009321107, "stage": "improve", "created_at": 1789536162.0703964}, {"event_id": "ebe0c70a58264d35a439e50d944dde53", "step": 102, "value": 0.013659829641464425, "stage": "improve", "created_at": 1789536388.4378867}, {"event_id": "0c0b4485394747febb49695004949365", "step": 103, "value": 0.019594745301580386, "stage": "improve", "created_at": 1789536650.0467877}, {"event_id": "c378343a6eb2431091aa5fe2b007e571", "step": 104, "value": 0.02336196228191778, "stage": "debug", "created_at": 1789536036.003437}, {"event_id": "a83203ecc7d1409491bb066d0ff90e66", "step": 105, "value": 0.03945373036152798, "stage": "improve", "created_at": 1789536927.9116685}, {"event_id": "491b722a39e544c58915eac9cc762f30", "step": 107, "value": 0.013708683443053458, "stage": "evolution", "created_at": 1789537039.2275941}, {"event_id": "b726ef18a77c490f9ad7e2975478998a", "step": 110, "value": 0.018899079536957016, "stage": "evolution", "created_at": 1789537315.3852835}, {"event_id": "187843b3314448a291798eb399fcd9ca", "step": 111, "value": 0.035186803469346384, "stage": "fusion", "created_at": 1789537829.2543097}, {"event_id": "369800ca5ab94948bc78c74d589dc35f", "step": 112, "value": 0.015321954485862358, "stage": "debug", "created_at": 1789537774.556788}, {"event_id": "b6b1dfbc61ee463f8b47a8479edc80bb", "step": 115, "value": 0.011976191162292755, "stage": "evolution", "created_at": 1789538216.031591}, {"event_id": "a8f30da4145c477798f8bb1dab824b47", "step": 116, "value": 0.011410475396838649, "stage": "evolution", "created_at": 1789538211.199402}, {"event_id": "df6de27cb65c47b78576474abbb435ba", "step": 120, "value": 0.01859372871240821, "stage": "improve", "created_at": 1789539713.2398944}, {"event_id": "8eac0e8c1a6d438c93a668016dc54239", "step": 121, "value": 0.01317198299891526, "stage": "improve", "created_at": 1789540944.880918}, {"event_id": "68405eb7f7c940c5aef7c7b6ce0fc196", "step": 122, "value": 0.015210388850271893, "stage": "improve", "created_at": 1789539170.7999387}, {"event_id": "2cfb450022c24461b7bd59ac39df37ef", "step": 123, "value": 0.09342685841347731, "stage": "debug", "created_at": 1789539344.7621057}, {"event_id": "ec593a46b5a34d2cb4b968af0d24e168", "step": 125, "value": 0.01896741610541915, "stage": "improve", "created_at": 1789541680.510014}, {"event_id": "80fbd5ecd8084577aa13f54fcf01e996", "step": 126, "value": 0.011776405270666243, "stage": "fusion", "created_at": 1789541943.8936248}, {"event_id": "c77e10213b3f44519a8383e90bf30c0b", "step": 127, "value": 0.015278356664147608, "stage": "debug", "created_at": 1789542496.5074873}, {"event_id": "5b3d762524134a369846025bde8ea083", "step": 128, "value": 0.014385874449914198, "stage": "evolution", "created_at": 1789542860.667212}, {"event_id": "3976a249cfe249fd92e721a23e7cda40", "step": 129, "value": 0.014054830667475874, "stage": "evolution", "created_at": 1789542910.5243397}, {"event_id": "456e43216d714354a4b8897a19a5a687", "step": 130, "value": 0.0173504946030877, "stage": "evolution", "created_at": 1789543421.4781876}, {"event_id": "d7327cbd11f24dfe88f20c1487edfb60", "step": 131, "value": 0.036983795286288174, "stage": "evolution", "created_at": 1789543902.9801195}, {"event_id": "573c4e1523b5457d8a3dd8410b722e86", "step": 132, "value": 0.01627622212886086, "stage": "evolution", "created_at": 1789544122.060665}, {"event_id": "3b51e4401fc747d2935eb29b3bb24637", "step": 133, "value": 0.029598890663290897, "stage": "evolution", "created_at": 1789544421.1353157}, {"event_id": "8d9e9a3b72154325903f9575c7a2794e", "step": 135, "value": 0.013998044595930606, "stage": "evolution", "created_at": 1789544631.8705995}, {"event_id": "7869520f01d047f1b3f11d1ed6fcdfc0", "step": 137, "value": 0.0928737667477112, "stage": "fusion_draft", "created_at": 1789545024.8344607}, {"event_id": "6d99cafe2d86485babfe3bd1aa42f54e", "step": 138, "value": 0.09950917773976509, "stage": "fusion_draft", "created_at": 1789545295.7195807}, {"event_id": "573df57f4079431cb1f5c7be239a2a5b", "step": 142, "value": 0.011776031604994682, "stage": "evolution", "created_at": 1789545765.286128}, {"event_id": "6073a3d417ba4be396e2845a60259fd6", "step": 143, "value": 0.011690836813930433, "stage": "debug", "created_at": 1789545803.5377681}, {"event_id": "23a627e3aa59454785940e5e84f5da1d", "step": 144, "value": 0.013142435899794951, "stage": "fusion", "created_at": 1789545923.6969194}, {"event_id": "eb551764ce4a400285f95d02b535c63b", "step": 149, "value": 0.016706613156129514, "stage": "fusion", "created_at": 1789546952.352471}, {"event_id": "0c2b1319645f4f24a65d94a5399e9c27", "step": 150, "value": 0.015950536548277536, "stage": "fusion", "created_at": 1789547086.7380157}, {"event_id": "bd955acd2275499cae2af5549d879440", "step": 151, "value": 0.01318736958261391, "stage": "debug", "created_at": 1789548125.548091}, {"event_id": "93752e54c3254494b4fd5ced1457261c", "step": 152, "value": 0.014146338653704035, "stage": "fusion", "created_at": 1789548289.9704525}], "maximize": false, "elapsed_seconds": 28796.978075027466, "node_count": 156, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-three-20260916/xixian.gp7-ancestry-logei.denoising-dirty-documents.yaml", "note": ""}, {"id": "xixian.gp7-ancestry-logei.detecting-insults-in-social-commentary", "experiment_id": "mlebench-gp7-three-20260916", "family": "MLEBench", "method": "gp7_ancestry_logei", "dataset": "detecting-insults-in-social-commentary", "status": "archived", "official_score": 0.96149, "medal": "gold", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.83321, "silver": 0.82307, "bronze": 0.79111}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/results/private_grades.jsonl:4", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}, {"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/runs/gp7_ancestry_logei/04_detecting-insults-in-social-commentary/logs/journal.json", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}], "alternate_scores": [], "journal_ref": "gp7-three-bo-analysis-20260916:gp7-three-66-runs/runs/gp7_ancestry_logei/04_detecting-insults-in-social-commentary/logs/journal.json", "metrics": [{"event_id": "bb2d44702c014cc29ecfe6e7b78577fd", "step": 6, "value": 0.9589901477832512, "stage": "debug", "created_at": 1789522749.661153}, {"event_id": "e32028c254e94ae1b61ddf25265b3678", "step": 7, "value": 0.9397701149425287, "stage": "debug", "created_at": 1789522826.8464293}, {"event_id": "c8f89ce0acaf4e9f9aa732e820d6c699", "step": 8, "value": 0.9491912972085386, "stage": "debug", "created_at": 1789522818.4506402}, {"event_id": "4ce0a180d0ac4144b775cc26dc6a7322", "step": 11, "value": 0.9620525451559934, "stage": "improve", "created_at": 1789523164.5617018}, {"event_id": "a6193d1bb3834246a8eb50e3e63703cd", "step": 12, "value": 0.958727422003284, "stage": "debug", "created_at": 1789523392.4619248}, {"event_id": "1d4ba48bf7404da38325a00b596c8c69", "step": 13, "value": 0.958070607553366, "stage": "improve", "created_at": 1789523649.105708}, {"event_id": "c9969d7e2ab74deda859a72b335ca1bf", "step": 14, "value": 0.9569622331691298, "stage": "debug", "created_at": 1789523298.7537158}, {"event_id": "28fc8158d94a4e5297787b4c05861faa", "step": 15, "value": 0.9594991789819376, "stage": "improve", "created_at": 1789524057.693935}, {"event_id": "b4afb52c99734fcbbef6e5ed0565a893", "step": 16, "value": 0.8941954022988505, "stage": "draft", "created_at": 1789525452.7173054}, {"event_id": "6f0a7d14dd074e349d82d6516c1855c0", "step": 18, "value": 0.9592282430213465, "stage": "evolution", "created_at": 1789525123.480241}, {"event_id": "a54eef8b5ab74293b1093baba3392d69", "step": 19, "value": 0.9585714285714285, "stage": "improve", "created_at": 1789524241.4259222}, {"event_id": "8b0ba806435f4e9d8ad739f304efce7d", "step": 22, "value": 0.9567569786535304, "stage": "debug", "created_at": 1789525888.6611981}, {"event_id": "102d375473cc4f8588663014711ce802", "step": 24, "value": 0.9419540229885057, "stage": "debug", "created_at": 1789526557.0221958}, {"event_id": "302a3ff9b6954a2e8a2dd1feb76179fb", "step": 25, "value": 0.9614121510673235, "stage": "evolution", "created_at": 1789526170.0969234}, {"event_id": "ea1ad83045f64f36aebf401ae9fea6ab", "step": 26, "value": 0.9564614121510673, "stage": "evolution", "created_at": 1789526553.1366172}, {"event_id": "a98da063dc464b4c910c397d63e50edb", "step": 27, "value": 0.9604022988505747, "stage": "evolution", "created_at": 1789526850.332104}, {"event_id": "d1bb5ad98db845a9ac986e70c342e01c", "step": 28, "value": 0.959655172413793, "stage": "evolution", "created_at": 1789528408.5260792}, {"event_id": "5f50eda5316f4920bf74d74915d452eb", "step": 29, "value": 0.961272577996716, "stage": "evolution", "created_at": 1789529170.071935}, {"event_id": "e58bd99f1c7f4bcba888c637a8580b8e", "step": 30, "value": 0.9023234811165846, "stage": "evolution", "created_at": 1789529334.6943083}, {"event_id": "08cc76ded6a44aae885e4d73b160a2cd", "step": 31, "value": 0.9593185550082102, "stage": "evolution", "created_at": 1789531624.111296}, {"event_id": "bd6118f66fe348b297215e244e412955", "step": 33, "value": 0.9613136288998358, "stage": "evolution", "created_at": 1789535218.5491369}, {"event_id": "cf266e46270c4cf18f9f5528a56bb94a", "step": 34, "value": 0.9613628899835795, "stage": "evolution", "created_at": 1789535171.5219398}, {"event_id": "e0f22706aaec470f8482467ac509782d", "step": 38, "value": 0.960944170771757, "stage": "evolution", "created_at": 1789537601.1477575}, {"event_id": "e29c241891bf4253848302e4b9e50516", "step": 40, "value": 0.9593842364532019, "stage": "fusion", "created_at": 1789539106.5669146}, {"event_id": "54e2273887a74453ad1a19ba3cd413a7", "step": 41, "value": 0.963711001642036, "stage": "debug", "created_at": 1789537274.4654663}, {"event_id": "a41278472f5b4701a8ead17bb4af2179", "step": 42, "value": 0.9544540229885058, "stage": "evolution", "created_at": 1789540368.7643018}, {"event_id": "a43a9b1f36d24db58e1d02b37eb0c2b8", "step": 44, "value": 0.9629720853858785, "stage": "debug", "created_at": 1789542932.290224}, {"event_id": "cc05dd87ea20459796858182918019c6", "step": 45, "value": 0.962192118226601, "stage": "improve", "created_at": 1789541784.9453921}, {"event_id": "8ed52a57af78407cb038587871b073fd", "step": 46, "value": 0.9629474548440067, "stage": "improve", "created_at": 1789546254.3501916}, {"event_id": "1567361cb9f24747a754a0bf2717fdfb", "step": 47, "value": 0.9641215106732348, "stage": "improve", "created_at": 1789546781.6021252}, {"event_id": "75a41ed0608a4170be623f603ca301a1", "step": 48, "value": 0.9401067323481117, "stage": "improve", "created_at": 1789549102.7637098}], "maximize": true, "elapsed_seconds": 28802.254367113113, "node_count": 52, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-three-20260916/xixian.gp7-ancestry-logei.detecting-insults-in-social-commentary.yaml", "note": ""}, {"id": "xixian.gp7-ancestry-logei.dog-breed-identification", "experiment_id": "mlebench-gp7-three-20260916", "family": "MLEBench", "method": "gp7_ancestry_logei", "dataset": "dog-breed-identification", "status": "archived", "official_score": 0.20305, "medal": "none", "valid_submission": true, "score_maximize": false, "thresholds": {"gold": 0.0005, "silver": 0.00539, "bronze": 0.04598}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/results/private_grades.jsonl:5", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}, {"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/runs/gp7_ancestry_logei/05_dog-breed-identification/logs/journal.json", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}], "alternate_scores": [], "journal_ref": "gp7-three-bo-analysis-20260916:gp7-three-66-runs/runs/gp7_ancestry_logei/05_dog-breed-identification/logs/journal.json", "metrics": [{"event_id": "f3c1bab68a864f1f9c8a84148029b572", "step": 5, "value": 0.6224434420045443, "stage": "debug", "created_at": 1789524281.2424037}, {"event_id": "c198f425a9964b86b7011d7dfdd97238", "step": 9, "value": 0.37345569882514107, "stage": "debug", "created_at": 1789524860.2988136}, {"event_id": "0d6adfdabd1847d4b65998619df225b4", "step": 10, "value": 0.4124030633056241, "stage": "debug", "created_at": 1789525496.3936474}, {"event_id": "9583e6b349824c18b597ad4023fca8ec", "step": 11, "value": 0.5336842606185932, "stage": "debug", "created_at": 1789525618.2109718}, {"event_id": "66d8546ba69c4ac3b3ab2414d1c29445", "step": 15, "value": 0.3866542803052208, "stage": "debug", "created_at": 1789527103.520488}, {"event_id": "1e652be8756c49758ac4eb2eaed3c2ac", "step": 16, "value": 0.35726547933347735, "stage": "debug", "created_at": 1789526852.8194678}, {"event_id": "72f1a9de1f064999bc627d51fa752892", "step": 17, "value": 0.3458174773097373, "stage": "debug", "created_at": 1789527106.7246256}, {"event_id": "af053173ead945019577546aba494920", "step": 18, "value": 0.3826231690021623, "stage": "improve", "created_at": 1789528932.4230978}, {"event_id": "60c11cd19ada4dc2a7410652e2ee98fc", "step": 19, "value": 0.1384391686322331, "stage": "improve", "created_at": 1789528902.050123}, {"event_id": "1a4d89f3d1fa4616bff07069caccdb18", "step": 20, "value": 0.35473844184061576, "stage": "improve", "created_at": 1789532467.1692417}, {"event_id": "4427ac4818304c738ccb6fb59d364d7c", "step": 21, "value": 0.150611814026092, "stage": "improve", "created_at": 1789532507.611253}, {"event_id": "b6bf844099684d4ab76355c66dd80085", "step": 22, "value": 0.17819870174306546, "stage": "improve", "created_at": 1789535212.9294538}, {"event_id": "b6434b021877418f9e042e0b8eb15923", "step": 23, "value": 0.33262145195952586, "stage": "improve", "created_at": 1789529065.500222}, {"event_id": "8508694fe222453ca3078c3d3108f1b7", "step": 25, "value": 0.1598015472979618, "stage": "improve", "created_at": 1789537801.2819722}, {"event_id": "9f53eb307ce2488ba1832613fae19744", "step": 26, "value": 0.5509987415186968, "stage": "debug", "created_at": 1789539566.927724}, {"event_id": "5efcdcb9623440a29165ce2dc893ef04", "step": 29, "value": 0.14351895520574706, "stage": "improve", "created_at": 1789538979.5543976}, {"event_id": "8d56271f6d424153af67655db866c7b1", "step": 30, "value": 0.1386872199048372, "stage": "evolution", "created_at": 1789540578.3471053}, {"event_id": "3b76156eaeb54dd1882a532b548bda7b", "step": 31, "value": 0.21042715935070955, "stage": "fusion", "created_at": 1789544093.9897437}, {"event_id": "28249f1f67a34df0966650faec9db836", "step": 32, "value": 0.22357073639008626, "stage": "fusion", "created_at": 1789542281.0994651}, {"event_id": "5e34dd4add454d9a9f7fc3e7a8f8215b", "step": 33, "value": 0.43439928165236613, "stage": "draft", "created_at": 1789548715.476062}], "maximize": false, "elapsed_seconds": 28797.626705884933, "node_count": 34, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-three-20260916/xixian.gp7-ancestry-logei.dog-breed-identification.yaml", "note": ""}, {"id": "xixian.gp7-ancestry-logei.dogs-vs-cats-redux-kernels-edition", "experiment_id": "mlebench-gp7-three-20260916", "family": "MLEBench", "method": "gp7_ancestry_logei", "dataset": "dogs-vs-cats-redux-kernels-edition", "status": "archived", "official_score": 0.00324, "medal": "gold", "valid_submission": true, "score_maximize": false, "thresholds": {"gold": 0.03882, "silver": 0.05038, "bronze": 0.06127}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/results/private_grades.jsonl:6", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}, {"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/runs/gp7_ancestry_logei/06_dogs-vs-cats-redux-kernels-edition/logs/journal.json", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}], "alternate_scores": [], "journal_ref": "gp7-three-bo-analysis-20260916:gp7-three-66-runs/runs/gp7_ancestry_logei/06_dogs-vs-cats-redux-kernels-edition/logs/journal.json", "metrics": [{"event_id": "f3f410fcd18c4009a2158e5ee8c0c568", "step": 4, "value": 0.0032415211724425128, "stage": "draft", "created_at": 1789522420.4493854}, {"event_id": "7492e03743834bfcb01b74e3ad62fc28", "step": 6, "value": 0.0016747598007247262, "stage": "improve", "created_at": 1789523453.3683565}, {"event_id": "e1ce36ea1f74420589856060b73b539c", "step": 7, "value": 0.015403360145105233, "stage": "debug", "created_at": 1789522930.0865521}, {"event_id": "ba33433abfd14fa5b4ad5160ae9e18ec", "step": 8, "value": 0.0016374736088991186, "stage": "improve", "created_at": 1789524115.9185514}, {"event_id": "30a6933a588f43739834fc4e704b1ba9", "step": 10, "value": 0.008240571240982701, "stage": "debug", "created_at": 1789523442.8175087}, {"event_id": "f4ef532a16ef463ca71578860fbe8d1d", "step": 11, "value": 0.0018700630378356636, "stage": "improve", "created_at": 1789524742.6087098}, {"event_id": "9ffcd91175f04ed7ba49e3c55caa4819", "step": 13, "value": 0.002061237372070027, "stage": "improve", "created_at": 1789525394.6594908}, {"event_id": "22d28d5091ec4af5b497617a8091da11", "step": 14, "value": 0.0018109822130434898, "stage": "debug", "created_at": 1789525253.407665}, {"event_id": "5429cc3668eb4598b48952b27acb688d", "step": 15, "value": 0.0019528060172668933, "stage": "debug", "created_at": 1789526119.4596887}, {"event_id": "c4fd36c088804698b479af33beb728a4", "step": 18, "value": 0.001796864618298182, "stage": "improve", "created_at": 1789526832.570902}, {"event_id": "a4acdd17c117486696ad2ec528ca49a9", "step": 19, "value": 0.0012512542863676996, "stage": "evolution", "created_at": 1789527014.2737265}, {"event_id": "133f39fc21b44472a0698f67a53db0a5", "step": 20, "value": 0.001761614346130234, "stage": "debug", "created_at": 1789527666.4814897}, {"event_id": "cd97f936687849e09a02c7464d5d376e", "step": 22, "value": 0.004976225840407619, "stage": "evolution", "created_at": 1789528721.9848065}, {"event_id": "347ff9da0e784cdfbe33b28a704502f5", "step": 23, "value": 0.0029210532762772652, "stage": "improve", "created_at": 1789528906.1887999}, {"event_id": "1f2dffadce5c469a9b9cd4c068a85def", "step": 24, "value": 0.0029210532762772652, "stage": "debug", "created_at": 1789529495.6962132}, {"event_id": "ee439b53905644ae9c099ae9e9a395b9", "step": 26, "value": 0.0034986493367103804, "stage": "debug", "created_at": 1789531039.4878812}, {"event_id": "34b5b59f1e304802ab60098c449307e3", "step": 27, "value": 0.003789964928512709, "stage": "draft", "created_at": 1789531119.547804}, {"event_id": "87b80dc56ce74017a37724868cf31e3c", "step": 28, "value": 0.005211906827655778, "stage": "improve", "created_at": 1789530948.3738513}, {"event_id": "4002ef44d5b847938abd9cbf37d9f409", "step": 30, "value": 0.001956293021419425, "stage": "evolution", "created_at": 1789532775.0092773}, {"event_id": "276b715d60f34e74826996027768988d", "step": 32, "value": 0.0014395581649758005, "stage": "evolution", "created_at": 1789532935.699713}, {"event_id": "636b4e0d093b4245af3784dba93a3f6b", "step": 33, "value": 0.0021884713708814783, "stage": "debug", "created_at": 1789533049.4425182}, {"event_id": "d98d290f8d7f410fb34fd11955ae6fd6", "step": 34, "value": 0.002559044766368002, "stage": "improve", "created_at": 1789537368.0466373}, {"event_id": "7584078513954f018cb5c685cb7693dc", "step": 35, "value": 0.0023499670134614742, "stage": "improve", "created_at": 1789536955.9121256}, {"event_id": "c160a046b80f4d658cb02c8a5792e16d", "step": 36, "value": 0.0015795225662671804, "stage": "debug", "created_at": 1789536827.1040118}, {"event_id": "08553e0be1044a749bdfed1503a31327", "step": 37, "value": 0.002257945386834939, "stage": "evolution", "created_at": 1789538769.5046701}, {"event_id": "43a4fa5ce5c24beda9a548cceeb88a0b", "step": 41, "value": 0.0023559468320133907, "stage": "debug", "created_at": 1789542036.5327985}, {"event_id": "cf0929864f264deb9710725fe0af77d7", "step": 42, "value": 0.0018217949038657824, "stage": "fusion", "created_at": 1789540274.987983}, {"event_id": "63883468d75c43d2a2f4b44885a64aa3", "step": 46, "value": 0.0023140896250213646, "stage": "debug", "created_at": 1789541488.917824}, {"event_id": "f5944322e6c24228b0f9aed0bf47261a", "step": 52, "value": 0.005391328266707239, "stage": "debug", "created_at": 1789544304.9315584}, {"event_id": "b71658efaa49493781fb8d9717c305d1", "step": 54, "value": 0.001956293021419425, "stage": "evolution", "created_at": 1789543722.540858}, {"event_id": "172002fb638a4e01b7e7786bc5e9c258", "step": 56, "value": 0.002473174644313726, "stage": "evolution", "created_at": 1789546524.5918543}, {"event_id": "b0b93abf9dc549d69c6a80f0246dcc2b", "step": 58, "value": 0.002449453876759476, "stage": "debug", "created_at": 1789545938.9724228}], "maximize": false, "elapsed_seconds": 28810.460018396378, "node_count": 62, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-three-20260916/xixian.gp7-ancestry-logei.dogs-vs-cats-redux-kernels-edition.yaml", "note": ""}, {"id": "xixian.gp7-ancestry-logei.histopathologic-cancer-detection", "experiment_id": "mlebench-gp7-three-20260916", "family": "MLEBench", "method": "gp7_ancestry_logei", "dataset": "histopathologic-cancer-detection", "status": "archived", "official_score": 0.99339, "medal": "gold", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.9835, "silver": 0.9798, "bronze": 0.9738}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/results/private_grades.jsonl:7", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}, {"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/runs/gp7_ancestry_logei/07_histopathologic-cancer-detection/logs/journal.json", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}], "alternate_scores": [], "journal_ref": "gp7-three-bo-analysis-20260916:gp7-three-66-runs/runs/gp7_ancestry_logei/07_histopathologic-cancer-detection/logs/journal.json", "metrics": [{"event_id": "499b893e5f244c86b6a7038f0b28b398", "step": 1, "value": 0.9881233434925772, "stage": "draft", "created_at": 1789523134.3319974}, {"event_id": "53be781e99f64430b5cb79c3252409db", "step": 2, "value": 0.9810669839647203, "stage": "draft", "created_at": 1789522801.7754653}, {"event_id": "d7f3e75deda24c90af3bdac47b68576d", "step": 6, "value": 0.9890286613067443, "stage": "debug", "created_at": 1789533129.9874814}, {"event_id": "ce9a58006f0c40d894b794d202818be3", "step": 7, "value": 0.9115169883412044, "stage": "debug", "created_at": 1789530093.7145178}, {"event_id": "79903bf6886c408395eb2193230a2228", "step": 8, "value": 0.9882877804390062, "stage": "improve", "created_at": 1789538428.0351732}, {"event_id": "b03f2f8f6c6c43e79ee6618f3c31081a", "step": 9, "value": 0.9902758962047986, "stage": "improve", "created_at": 1789535886.752317}, {"event_id": "77200ba20ef84a83b9e92a0e2268db31", "step": 10, "value": 0.9887197639022516, "stage": "improve", "created_at": 1789540729.8132496}, {"event_id": "5d032fb48a024a5aa14eacdf1d51cf94", "step": 11, "value": 0.9934233694132557, "stage": "improve", "created_at": 1789527168.4868703}], "maximize": true, "elapsed_seconds": 28797.340569019318, "node_count": 13, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-three-20260916/xixian.gp7-ancestry-logei.histopathologic-cancer-detection.yaml", "note": ""}, {"id": "xixian.gp7-ancestry-logei.jigsaw-toxic-comment-classification-challenge", "experiment_id": "mlebench-gp7-three-20260916", "family": "MLEBench", "method": "gp7_ancestry_logei", "dataset": "jigsaw-toxic-comment-classification-challenge", "status": "archived", "official_score": 0.98328, "medal": "none", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.9874, "silver": 0.98668, "bronze": 0.98639}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/results/private_grades.jsonl:8", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}, {"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/runs/gp7_ancestry_logei/08_jigsaw-toxic-comment-classification-challenge/logs/journal.json", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}], "alternate_scores": [], "journal_ref": "gp7-three-bo-analysis-20260916:gp7-three-66-runs/runs/gp7_ancestry_logei/08_jigsaw-toxic-comment-classification-challenge/logs/journal.json", "metrics": [{"event_id": "625099ce29ce48a2b083be58947af6a5", "step": 5, "value": 0.9904553148252333, "stage": "draft", "created_at": 1789522417.0107446}, {"event_id": "6ac318ebef4e4168a886dae104d61636", "step": 6, "value": 0.9902462405046276, "stage": "debug", "created_at": 1789527889.4281712}], "maximize": true, "elapsed_seconds": 28795.34515094757, "node_count": 8, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-three-20260916/xixian.gp7-ancestry-logei.jigsaw-toxic-comment-classification-challenge.yaml", "note": ""}, {"id": "xixian.gp7-ancestry-logei.leaf-classification", "experiment_id": "mlebench-gp7-three-20260916", "family": "MLEBench", "method": "gp7_ancestry_logei", "dataset": "leaf-classification", "status": "archived", "official_score": 0.02138, "medal": "none", "valid_submission": true, "score_maximize": false, "thresholds": {"gold": 0.0, "silver": 0.00791, "bronze": 0.01526}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/results/private_grades.jsonl:9", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}, {"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/runs/gp7_ancestry_logei/09_leaf-classification/logs/journal.json", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}], "alternate_scores": [], "journal_ref": "gp7-three-bo-analysis-20260916:gp7-three-66-runs/runs/gp7_ancestry_logei/09_leaf-classification/logs/journal.json", "metrics": [{"event_id": "c401f8e177384475b59a3f97f38b580b", "step": 4, "value": 0.2756646259442251, "stage": "debug", "created_at": 1789522846.3856425}, {"event_id": "5111f262fc944aef899000df614a88c9", "step": 5, "value": 1.8764898324764328, "stage": "draft", "created_at": 1789522097.6492457}, {"event_id": "eeb5ee61884c4a1a9b9d0b0c9ff7842d", "step": 6, "value": 0.12201865147329997, "stage": "debug", "created_at": 1789523094.8514569}, {"event_id": "a8339acd1e0947cd9d2d7d5d64565689", "step": 7, "value": 2.4687598686808787, "stage": "improve", "created_at": 1789523309.08719}, {"event_id": "00ebdb2240a9460da59c7272a12d1e5f", "step": 8, "value": 2.465045178579368, "stage": "improve", "created_at": 1789523329.1379082}, {"event_id": "a4363003cfbd435497f59a6fc8fcada1", "step": 10, "value": 0.0041121454902750725, "stage": "improve", "created_at": 1789523548.0822}, {"event_id": "c1730976a45546f19107de591f7bef37", "step": 11, "value": 0.03390189675647878, "stage": "debug", "created_at": 1789524476.537369}, {"event_id": "63da0e58668d40a38d45ea28b519a188", "step": 18, "value": 0.002775506786978278, "stage": "debug", "created_at": 1789525266.124944}, {"event_id": "6929b35e5c69463abf60124607254c7f", "step": 20, "value": 0.030147369393448194, "stage": "improve", "created_at": 1789527291.7708588}, {"event_id": "4099579fd7eb4297921eec7b81b3fc13", "step": 22, "value": 0.05566860471054962, "stage": "improve", "created_at": 1789527760.7485588}, {"event_id": "2344645214274b549fdc4395bc83b153", "step": 23, "value": 34.53877639491068, "stage": "improve", "created_at": 1789527899.0639365}, {"event_id": "2d7782c351354a65a1c337484df49689", "step": 24, "value": 1.3302389746080852, "stage": "improve", "created_at": 1789528445.6421223}, {"event_id": "36570f0cae304f1f9ec03df1cdce6b19", "step": 25, "value": 0.13813216098044476, "stage": "evolution", "created_at": 1789529105.6881092}, {"event_id": "6c8952c1a53e43f191e6ff69c8408b48", "step": 28, "value": 1.8700658443648583, "stage": "improve", "created_at": 1789528791.4161963}, {"event_id": "5e07669bf8f54e47b5d3b35e2c0fed58", "step": 29, "value": 0.0007311479463584571, "stage": "debug", "created_at": 1789530527.7488537}, {"event_id": "2ef77a67d7c54633bc6b2b9e2cad3734", "step": 30, "value": 0.05284304722969445, "stage": "evolution", "created_at": 1789531271.3205209}, {"event_id": "79ffcd6bf290475fa5f3d7261ce46ec8", "step": 31, "value": 0.0074947523447959855, "stage": "debug", "created_at": 1789526876.3604963}, {"event_id": "52c5197839104573a9b3dcf095bcaa3c", "step": 32, "value": 0.14812336328824707, "stage": "evolution", "created_at": 1789531165.882888}, {"event_id": "f3cbb0ff14e04aed8fd0cb78b0b0e447", "step": 33, "value": 0.05093102489914879, "stage": "evolution", "created_at": 1789531749.7873058}, {"event_id": "dd282323eb5c471eaab59a46236caca8", "step": 34, "value": 0.05184988119493765, "stage": "evolution", "created_at": 1789533112.1577516}, {"event_id": "f96e06129d8f4f49931cc5470421a847", "step": 35, "value": 0.05096996880547628, "stage": "evolution", "created_at": 1789532462.3238869}, {"event_id": "4712b180cb1a40dfaa99a817e7ba1fdd", "step": 37, "value": 0.0521800463994064, "stage": "evolution", "created_at": 1789534235.8256729}, {"event_id": "3bf5feaef1ed4afe82cf75b4a502688e", "step": 39, "value": 0.008990013871527765, "stage": "improve", "created_at": 1789534809.7990077}, {"event_id": "d033a370716243baa164a926a251bcb9", "step": 41, "value": 0.04734988052220238, "stage": "debug", "created_at": 1789536842.7521095}, {"event_id": "4723b11d31584dc5b41a4c23bfbefff6", "step": 42, "value": 0.00899001382500316, "stage": "evolution", "created_at": 1789542015.8976912}, {"event_id": "86cc6621db004068b8b9ae3265d07251", "step": 43, "value": 0.10233124232389543, "stage": "evolution", "created_at": 1789539630.765336}, {"event_id": "c6bac0b3f6144bd5abc433cb9500e7b0", "step": 45, "value": 0.015232927811064377, "stage": "fusion", "created_at": 1789544895.0940356}, {"event_id": "119f115249024b02a20de343d2067a2d", "step": 46, "value": 0.017193641005397612, "stage": "improve", "created_at": 1789548449.3884425}, {"event_id": "60e68f8e920749aa97c726f342e17943", "step": 47, "value": 0.015242589429617218, "stage": "debug", "created_at": 1789546425.542559}], "maximize": false, "elapsed_seconds": 28796.351415872574, "node_count": 49, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-three-20260916/xixian.gp7-ancestry-logei.leaf-classification.yaml", "note": ""}, {"id": "xixian.gp7-ancestry-logei.mlsp-2013-birds", "experiment_id": "mlebench-gp7-three-20260916", "family": "MLEBench", "method": "gp7_ancestry_logei", "dataset": "mlsp-2013-birds", "status": "archived", "official_score": 0.89986, "medal": "bronze", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.93527, "silver": 0.90038, "bronze": 0.87372}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/results/private_grades.jsonl:10", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}, {"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/runs/gp7_ancestry_logei/10_mlsp-2013-birds/logs/journal.json", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}], "alternate_scores": [], "journal_ref": "gp7-three-bo-analysis-20260916:gp7-three-66-runs/runs/gp7_ancestry_logei/10_mlsp-2013-birds/logs/journal.json", "metrics": [{"event_id": "bd9f3e47db5a4104865be6de786826dc", "step": 7, "value": 0.7568925633995888, "stage": "debug", "created_at": 1789523445.5591707}, {"event_id": "3e80981582fb41c78b1b168ca75b74d7", "step": 9, "value": 0.7702964359150103, "stage": "improve", "created_at": 1789523817.9095323}, {"event_id": "a42b5bdb5ea64c22ac65c5916f7a3b39", "step": 10, "value": 0.509184372858122, "stage": "debug", "created_at": 1789523666.5565112}, {"event_id": "a699d3c6029640689d2625a79a6332db", "step": 11, "value": 0.7551919122686772, "stage": "debug", "created_at": 1789523722.1293294}, {"event_id": "12597db21338402f88fcae760139815a", "step": 12, "value": 0.8078821110349554, "stage": "improve", "created_at": 1789524149.4598722}, {"event_id": "5c11e7edbc6447d3a8d1185d421d287c", "step": 13, "value": 0.7955705962988349, "stage": "improve", "created_at": 1789524320.5575414}, {"event_id": "47948684bae043d2845e2f39f33204be", "step": 14, "value": 0.773209389993146, "stage": "improve", "created_at": 1789524547.3405404}, {"event_id": "39773cb89c3a4f6ebf88a76f00a5dd08", "step": 15, "value": 0.653564084989719, "stage": "improve", "created_at": 1789524658.909382}, {"event_id": "59e22d2222b84155bcb144412c38534b", "step": 16, "value": 0.8016877998629198, "stage": "improve", "created_at": 1789524713.4474444}, {"event_id": "b4107ced665846c3b03070c843360042", "step": 17, "value": 0.8156357093899932, "stage": "improve", "created_at": 1789524863.5739086}, {"event_id": "005b145dbb7646bfad7d102046fca2c4", "step": 18, "value": 0.7625813913639479, "stage": "evolution", "created_at": 1789525078.7968652}, {"event_id": "3e424dd5edbb4545b3893e5a00f24123", "step": 22, "value": 0.8144619602467443, "stage": "improve", "created_at": 1789525276.9373255}, {"event_id": "3d87195f5b2a4a55b83516621464f651", "step": 23, "value": 0.8029943454420837, "stage": "improve", "created_at": 1789525401.7385037}, {"event_id": "776bcbe127ab4a438fb543455e6ba28d", "step": 25, "value": 0.7935743660041124, "stage": "improve", "created_at": 1789525703.6007798}, {"event_id": "8c89185d5420405ea8e1a14a7a8fe51f", "step": 26, "value": 0.8063313913639479, "stage": "evolution", "created_at": 1789525911.1936834}, {"event_id": "901c3d00efd3467a94fcf383de9c1221", "step": 27, "value": 0.804806374228924, "stage": "evolution", "created_at": 1789525761.518198}, {"event_id": "91782a93d7b34a07a70531ab1cfb924a", "step": 28, "value": 0.7953521247429747, "stage": "evolution", "created_at": 1789526211.308586}, {"event_id": "42eb6f22e55e412cb0ec4d38f66f4929", "step": 29, "value": 0.7627056202878684, "stage": "evolution", "created_at": 1789526402.3818865}, {"event_id": "ce698b76d23642de862d5312d2773675", "step": 30, "value": 0.7982008224811514, "stage": "evolution", "created_at": 1789526449.5323918}, {"event_id": "8a7aa6f138cc465eb8a18310a3a21312", "step": 32, "value": 0.7864590472926661, "stage": "evolution", "created_at": 1789526876.953807}, {"event_id": "a25c6786640e4cf0b54889dc6ad113a2", "step": 33, "value": 0.7835332419465386, "stage": "debug", "created_at": 1789527091.2566974}, {"event_id": "6f675537a5cf4401b748f5a0a6cfceba", "step": 34, "value": 0.7671350239890335, "stage": "evolution", "created_at": 1789527246.207307}, {"event_id": "babcf4ad2dde4dfd9cc2f2e341bf525c", "step": 35, "value": 0.7873629198080877, "stage": "evolution", "created_at": 1789526994.5983853}, {"event_id": "fd6965426f4743a59c397a77abe8a4b9", "step": 38, "value": 0.7971470185058259, "stage": "debug", "created_at": 1789527864.4965491}, {"event_id": "a054cb2549454183bdd9988552bf0238", "step": 39, "value": 0.7841672378341329, "stage": "evolution", "created_at": 1789527662.8953066}, {"event_id": "af31d6648da043d4b9181af5575bbabd", "step": 41, "value": 0.8055688827964359, "stage": "debug", "created_at": 1789527993.203045}, {"event_id": "a72a24dca2414d649a11dc04f3b83956", "step": 42, "value": 0.7838630911583278, "stage": "evolution", "created_at": 1789528278.2936072}, {"event_id": "0b175d83ea9a421eafe8f948273d1f82", "step": 43, "value": 0.6593257368060315, "stage": "debug", "created_at": 1789528559.9705634}, {"event_id": "1c522597940d4c3b870586cbdd1f40a1", "step": 44, "value": 0.7636737491432487, "stage": "evolution", "created_at": 1789528715.7875047}, {"event_id": "b3051ee60cb84b70b3c8380dc08ef7df", "step": 45, "value": 0.801525017135024, "stage": "evolution", "created_at": 1789528827.7467787}, {"event_id": "ce20e8b2f4254741ba4e6e67859388fe", "step": 46, "value": 0.8046264564770391, "stage": "evolution", "created_at": 1789528719.5662055}, {"event_id": "c07a231b30dc48c2b295171da290f611", "step": 48, "value": 0.7884252912954078, "stage": "evolution", "created_at": 1789529692.1743731}, {"event_id": "18b3ce1e53b84e0cb5138e76bbe72528", "step": 49, "value": 0.7812285812200136, "stage": "debug", "created_at": 1789529854.084192}, {"event_id": "56efa590b1794890b21c00e23cf9790b", "step": 50, "value": 0.8078735435229609, "stage": "evolution", "created_at": 1789529678.089886}, {"event_id": "e9e374c6349440f2b54d51b8a255d4ec", "step": 51, "value": 0.7736549006168609, "stage": "evolution", "created_at": 1789530335.8050427}, {"event_id": "2c404b97c2d94920970cff47dc38f49a", "step": 52, "value": 0.7688313913639478, "stage": "evolution", "created_at": 1789530443.6831598}, {"event_id": "16afb68754c34e1597b640e5e1fd1927", "step": 53, "value": 0.803829677861549, "stage": "evolution", "created_at": 1789530574.0209327}, {"event_id": "5e92557d28f44d098b18c6d308a8f01d", "step": 55, "value": 0.7328221384509939, "stage": "evolution", "created_at": 1789531300.7787206}, {"event_id": "2258e0b8b4864bbcb92a56d3f48f3b91", "step": 56, "value": 0.7027844413982179, "stage": "evolution", "created_at": 1789531384.0005832}, {"event_id": "78a58590eff143feaa735488769847dd", "step": 57, "value": 0.7918265935572308, "stage": "debug", "created_at": 1789531398.3869693}, {"event_id": "ef9090c28c0e4539be070698ffd13740", "step": 58, "value": 0.7665652844413983, "stage": "evolution", "created_at": 1789532121.3777108}, {"event_id": "0504610774d6439f8a927a635934770a", "step": 59, "value": 0.7495030843043179, "stage": "evolution", "created_at": 1789532275.036364}, {"event_id": "cbc10690d4d0458fa239d0ef7c71a0b2", "step": 60, "value": 0.8175119945167922, "stage": "evolution", "created_at": 1789532436.3219793}, {"event_id": "cb8a08c336c24713bd20f987ac48c39c", "step": 61, "value": 0.7842443454420835, "stage": "evolution", "created_at": 1789532803.6997025}, {"event_id": "3f878247e3b14a71b135f9f137afaa8f", "step": 62, "value": 0.828632625085675, "stage": "evolution", "created_at": 1789533052.2579138}, {"event_id": "e267d70bf3274451a7c1fe0f97aba594", "step": 63, "value": 0.8044808087731322, "stage": "improve", "created_at": 1789533492.8868098}, {"event_id": "c49befbb78334dd28c47020235acb7b9", "step": 65, "value": 0.8011480466072652, "stage": "improve", "created_at": 1789533744.44556}, {"event_id": "945f961a3d054bb4a29daaf99ed75e18", "step": 66, "value": 0.8011137765592871, "stage": "improve", "created_at": 1789534244.2856476}, {"event_id": "585612dd8c754b13bb4a702fef7b2fc6", "step": 67, "value": 0.8177090472926662, "stage": "improve", "created_at": 1789534441.5202234}, {"event_id": "8f07461aa420454abe16c48d25bf2432", "step": 68, "value": 0.8147189856065797, "stage": "evolution", "created_at": 1789534747.0437183}, {"event_id": "5eb123a20fa842f4881667a705be23ff", "step": 70, "value": 0.8022361206305688, "stage": "evolution", "created_at": 1789534853.88876}, {"event_id": "8e10874f38e44ec7a1e6655f38be7722", "step": 73, "value": 0.8111634681288553, "stage": "debug", "created_at": 1789535492.6851456}, {"event_id": "5ac081140a424dd38f9a8b36a54d05b4", "step": 74, "value": 0.8132111034955448, "stage": "evolution", "created_at": 1789535868.3127806}, {"event_id": "2eb90cdb65b8483c81dd274e2d90e039", "step": 75, "value": 0.8057230980123372, "stage": "evolution", "created_at": 1789535997.6828547}, {"event_id": "372c87d6dd864313ba5fe58d07cf83bd", "step": 76, "value": 0.8123800548320768, "stage": "debug", "created_at": 1789535269.0736284}, {"event_id": "0b754c2753864864b458390c1b7bd104", "step": 78, "value": 0.8165181631254284, "stage": "evolution", "created_at": 1789536570.9112358}, {"event_id": "6ea5ebfc5cc84244ba5fdbbcb5fd8dfb", "step": 79, "value": 0.8233935915010281, "stage": "evolution", "created_at": 1789536542.7826707}, {"event_id": "8c2411bb648d4a83b5e15c30f32ee1a3", "step": 80, "value": 0.8111034955448937, "stage": "debug", "created_at": 1789536960.7363591}, {"event_id": "14814b07dca540c690fa9f079ddbb300", "step": 81, "value": 0.7960760795065113, "stage": "fusion", "created_at": 1789537146.3522804}, {"event_id": "84ee4fd413db4b53818752a7807b5cc3", "step": 82, "value": 0.7875428375599727, "stage": "fusion", "created_at": 1789537200.8063765}, {"event_id": "0925df5a033440cb97d5bd905adff57f", "step": 83, "value": 0.7715644276901987, "stage": "fusion", "created_at": 1789537420.1446466}, {"event_id": "004b73287f36452caba1eca45435381a", "step": 86, "value": 0.81790610006854, "stage": "fusion", "created_at": 1789537679.2799902}, {"event_id": "d47eed8712d84d4292d8869ccf768712", "step": 87, "value": 0.8237405757368059, "stage": "debug", "created_at": 1789537832.6544096}, {"event_id": "0c15d5dbac5542f0a3d1a5cd052b32b9", "step": 92, "value": 0.8267906100068539, "stage": "debug", "created_at": 1789538442.9969442}, {"event_id": "513e5671b2a646f8bab57ebe153567e4", "step": 93, "value": 0.7504883481836875, "stage": "fusion", "created_at": 1789538532.9597323}, {"event_id": "49f46b2c40544579bde0d0b1ecb6feef", "step": 94, "value": 0.7143420150788211, "stage": "debug", "created_at": 1789538690.4606676}, {"event_id": "5060b7ab4fb44fa58513d760fa4c0d48", "step": 95, "value": 0.8049691569568198, "stage": "fusion", "created_at": 1789539085.1322353}, {"event_id": "3abae7e9932c4fac959c4e21c7f3a8ae", "step": 96, "value": 0.7781699794379713, "stage": "evolution", "created_at": 1789539285.4657161}, {"event_id": "12a4e29924814b3187b8beee88f07d25", "step": 97, "value": 0.793882796435915, "stage": "evolution", "created_at": 1789539325.3014665}, {"event_id": "39fa560dea0047a5bd3432e5516aaefc", "step": 100, "value": 0.8021418779986291, "stage": "debug", "created_at": 1789540220.5075903}, {"event_id": "9f55a64018094aa6acedd121bc71f5ab", "step": 103, "value": 0.7835075394105553, "stage": "debug", "created_at": 1789541013.6179118}, {"event_id": "0623a92cdf3542d992c35c1109754535", "step": 104, "value": 0.8083618917066483, "stage": "debug", "created_at": 1789541136.9138818}, {"event_id": "6e4c2e2d905947ba9e8d0bdb0726ac77", "step": 105, "value": 0.7912440027416039, "stage": "evolution", "created_at": 1789541940.5804393}, {"event_id": "3111ac82f6064f0aa6f942bad6972d4f", "step": 106, "value": 0.7615661411925976, "stage": "evolution", "created_at": 1789541880.9165006}, {"event_id": "7bbe6fe8672947cd8da76a772ed98997", "step": 107, "value": 0.795407813570939, "stage": "evolution", "created_at": 1789542474.1410272}, {"event_id": "a0909b256a9c4a819feecb7254babcb9", "step": 108, "value": 0.8083404729266621, "stage": "evolution", "created_at": 1789542592.5359263}, {"event_id": "a1e46402491644b38579eab2a8faa39e", "step": 110, "value": 0.8810400959561344, "stage": "evolution", "created_at": 1789543092.5612638}, {"event_id": "ece26a57837246d582a7937875c2a6b7", "step": 111, "value": 0.8246230294722413, "stage": "fusion", "created_at": 1789543343.9900205}, {"event_id": "d2a75b3be45a43c29fd835bbd4867e14", "step": 113, "value": 0.8795407813570938, "stage": "debug", "created_at": 1789543800.5006988}, {"event_id": "8b72051b057a41f0a1f2cbc84dc923ad", "step": 114, "value": 0.8758310486634682, "stage": "improve", "created_at": 1789543879.2336178}, {"event_id": "282be37bf52b42a98f1d38c202b377c1", "step": 118, "value": 0.8687457162440027, "stage": "improve", "created_at": 1789545528.6630957}, {"event_id": "7850f8101a1a434d8b0492d8856129e8", "step": 123, "value": 0.8072909527073338, "stage": "evolution", "created_at": 1789539697.560714}, {"event_id": "8f5814acf4e44e4cb03b142aaa727b6b", "step": 125, "value": 0.8143591501028101, "stage": "debug", "created_at": 1789546936.9791572}, {"event_id": "39ca68ec55ec436cb8ccda95d1706d53", "step": 126, "value": 0.8670150788211103, "stage": "debug", "created_at": 1789547573.6022937}, {"event_id": "4b84fa5c70ca4bf3bc7f83112c2b82e3", "step": 127, "value": 0.8769705277587388, "stage": "evolution", "created_at": 1789547648.8616529}, {"event_id": "c5818d7cc0094248863002f93de8f392", "step": 128, "value": 0.8570339273474983, "stage": "evolution", "created_at": 1789547834.4271898}, {"event_id": "e4bb5a9878874e88a49aefbd80224dbd", "step": 130, "value": 0.8937714187799863, "stage": "fusion", "created_at": 1789548254.804445}, {"event_id": "d0d198c54ec244ceabeb25688428af46", "step": 131, "value": 0.8856065798492117, "stage": "fusion", "created_at": 1789548440.8809762}, {"event_id": "85cf84613bd3407781cce9a0d47f729e", "step": 132, "value": 0.8473526387936943, "stage": "debug", "created_at": 1789548707.9762619}, {"event_id": "3afc720b1c024d19934e8f1e627ad287", "step": 133, "value": 0.8844156956819739, "stage": "improve", "created_at": 1789549298.513613}, {"event_id": "3b4e79e5dcf64e40a9433181524c6c40", "step": 134, "value": 0.8745887594242632, "stage": "improve", "created_at": 1789549033.997744}], "maximize": true, "elapsed_seconds": 28794.308351278305, "node_count": 136, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-three-20260916/xixian.gp7-ancestry-logei.mlsp-2013-birds.yaml", "note": ""}, {"id": "xixian.gp7-ancestry-logei.new-york-city-taxi-fare-prediction", "experiment_id": "mlebench-gp7-three-20260916", "family": "MLEBench", "method": "gp7_ancestry_logei", "dataset": "new-york-city-taxi-fare-prediction", "status": "archived", "official_score": 4.46594, "medal": "none", "valid_submission": true, "score_maximize": false, "thresholds": {"gold": 2.83377, "silver": 2.88191, "bronze": 2.92371}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/results/private_grades.jsonl:11", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}, {"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/runs/gp7_ancestry_logei/11_new-york-city-taxi-fare-prediction/logs/journal.json", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}], "alternate_scores": [], "journal_ref": "gp7-three-bo-analysis-20260916:gp7-three-66-runs/runs/gp7_ancestry_logei/11_new-york-city-taxi-fare-prediction/logs/journal.json", "metrics": [{"event_id": "89e505d713654e6497995b30e0f4d764", "step": 2, "value": 5.187049752824063, "stage": "draft", "created_at": 1789523003.1241171}, {"event_id": "cc2599234bd0421189dea34c6250784a", "step": 3, "value": 7.723802948713816, "stage": "draft", "created_at": 1789522318.425099}, {"event_id": "00c8f76ee84b4824b5adeb8c74f4129e", "step": 4, "value": 5.187635768597087, "stage": "improve", "created_at": 1789523499.3551717}, {"event_id": "7ce420f7486e4cafa2804e53a11782f6", "step": 5, "value": 5.171864880932957, "stage": "improve", "created_at": 1789524315.931031}, {"event_id": "3a92149fcefb4f489ba9510b5e9a5c93", "step": 6, "value": 932.7645338249323, "stage": "improve", "created_at": 1789525140.7215328}, {"event_id": "db2726a7a94942b68725d3c3dfc9085b", "step": 7, "value": 4.874415211597578, "stage": "improve", "created_at": 1789523445.5702903}, {"event_id": "2645f2dfa6e34ae9809f223ebe660f38", "step": 8, "value": 5.240481638167214, "stage": "improve", "created_at": 1789526106.045598}, {"event_id": "000e177166d6429d82ea6eeab78b548c", "step": 9, "value": 5.2251258213011695, "stage": "improve", "created_at": 1789526932.4461203}, {"event_id": "161a6b8d2c4547bfb14ff3a45d3f4091", "step": 10, "value": 5.418316274010869, "stage": "improve", "created_at": 1789527317.1891756}, {"event_id": "6193c78e8111476980ba4cfab6ffdfb1", "step": 11, "value": 4.6857825332486005, "stage": "evolution", "created_at": 1789528213.383129}, {"event_id": "5312c0ae9c9e4607a95bd88065df26e3", "step": 12, "value": 4.982795417717331, "stage": "improve", "created_at": 1789528607.22905}, {"event_id": "8bfe3939ee264fc68c1bb2108f7fe70e", "step": 13, "value": 4.710786795484896, "stage": "improve", "created_at": 1789529278.9421577}, {"event_id": "07073572f6214ba48a8403e1cb51bf2d", "step": 14, "value": 5.480068015709534, "stage": "improve", "created_at": 1789530122.5579772}, {"event_id": "b09c1762c8fb4e3bb419489c4decd656", "step": 15, "value": 5.31450453530482, "stage": "evolution", "created_at": 1789531170.6652775}, {"event_id": "05531e8e0883403095b665cb2d49a2d7", "step": 19, "value": 5.361816287492463, "stage": "evolution", "created_at": 1789535916.9158678}, {"event_id": "0cd0621506ee45ab8a79ab3b5aa268a7", "step": 20, "value": 6.245228290813936, "stage": "improve", "created_at": 1789536695.9288886}, {"event_id": "eaecde85bdb6407db2c499e158a199ed", "step": 21, "value": 4.648651257101419, "stage": "evolution", "created_at": 1789537442.948701}, {"event_id": "ac9db1026adb4939b24fa98b76b071cb", "step": 22, "value": 5.4510279804503705, "stage": "improve", "created_at": 1789538106.0607882}, {"event_id": "10055127c9a2491dae80a81a6611a763", "step": 24, "value": 4.697041020068308, "stage": "debug", "created_at": 1789539879.4429636}, {"event_id": "ee71dc7b09d042bbad74a6aa549b646e", "step": 25, "value": 13.360241799229131, "stage": "improve", "created_at": 1789541146.5938892}, {"event_id": "72b6f9608d7147748b0d6f451535f2a5", "step": 29, "value": 5.037295372486645, "stage": "improve", "created_at": 1789544942.1540377}, {"event_id": "1a1cec4f7494495298627c78193be0dc", "step": 30, "value": 413.987856828825, "stage": "fusion_draft", "created_at": 1789549110.274404}, {"event_id": "1e97c6d9e955437687aff19da6ede37e", "step": 31, "value": 5.136960297034067, "stage": "improve", "created_at": 1789549898.8681023}], "maximize": false, "elapsed_seconds": 28795.229257822037, "node_count": 35, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-three-20260916/xixian.gp7-ancestry-logei.new-york-city-taxi-fare-prediction.yaml", "note": ""}, {"id": "xixian.gp7-ancestry-logei.nomad2018-predict-transparent-conductors", "experiment_id": "mlebench-gp7-three-20260916", "family": "MLEBench", "method": "gp7_ancestry_logei", "dataset": "nomad2018-predict-transparent-conductors", "status": "archived", "official_score": 0.15146, "medal": "none", "valid_submission": true, "score_maximize": false, "thresholds": {"gold": 0.05589, "silver": 0.06229, "bronze": 0.06582}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/results/private_grades.jsonl:12", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}, {"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/runs/gp7_ancestry_logei/12_nomad2018-predict-transparent-conductors/logs/journal.json", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}], "alternate_scores": [], "journal_ref": "gp7-three-bo-analysis-20260916:gp7-three-66-runs/runs/gp7_ancestry_logei/12_nomad2018-predict-transparent-conductors/logs/journal.json", "metrics": [{"event_id": "21816878499d411db9630153dcb6ab2d", "step": 23, "value": 0.14795424234963486, "stage": "debug", "created_at": 1789524871.2996695}, {"event_id": "1c2fac4193da449496af9e585e46211a", "step": 24, "value": 0.14749782512565715, "stage": "debug", "created_at": 1789524977.0466657}, {"event_id": "fcc4d36d2b7e4a35b89ea58bd47cc9f7", "step": 25, "value": 0.14763222420945393, "stage": "improve", "created_at": 1789525343.0895085}, {"event_id": "e5e4225965814e618396e966aa59f5b6", "step": 26, "value": 0.1490297594675288, "stage": "improve", "created_at": 1789526408.5128753}, {"event_id": "9e2a72f55383456d8014fc67feea32d0", "step": 27, "value": 0.14758876930581993, "stage": "improve", "created_at": 1789526827.4185426}, {"event_id": "e254f1a949ca489bb6b5642cca8a180d", "step": 28, "value": 0.1481543346785546, "stage": "improve", "created_at": 1789527751.0057285}, {"event_id": "ecfa2b6e13de45ca9d9250e266d6f39b", "step": 29, "value": 0.14810492436329456, "stage": "improve", "created_at": 1789529038.6420252}, {"event_id": "b9722e2441c04430b3a4d8e5a85d6bcd", "step": 30, "value": 0.21719751675483695, "stage": "debug", "created_at": 1789523839.0202265}, {"event_id": "90bc9bac80f34185838e04cc4c08a0a9", "step": 31, "value": 0.14749555085558838, "stage": "improve", "created_at": 1789530389.9927135}, {"event_id": "d64d797db9054e56a45f878ce25ec947", "step": 32, "value": 0.1477150747416603, "stage": "improve", "created_at": 1789536861.7315497}, {"event_id": "59af2b82a2ac43c7b79302a55c4cb329", "step": 33, "value": 0.1478032646589682, "stage": "improve", "created_at": 1789539564.189864}, {"event_id": "3a3e2b2a006e4da9815c6dfade01ffab", "step": 35, "value": 0.14703033272302632, "stage": "debug", "created_at": 1789547083.9102175}, {"event_id": "dd4303cda53e481bbf5746fcf59ad0a6", "step": 37, "value": 0.14739538171228284, "stage": "debug", "created_at": 1789547467.3322823}, {"event_id": "c141ee4170d74851aa4e392f6ecfcc10", "step": 38, "value": 0.1470674969642627, "stage": "improve", "created_at": 1789550300.0621066}], "maximize": false, "elapsed_seconds": 28795.76749110222, "node_count": 40, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-three-20260916/xixian.gp7-ancestry-logei.nomad2018-predict-transparent-conductors.yaml", "note": ""}, {"id": "xixian.gp7-ancestry-logei.plant-pathology-2020-fgvc7", "experiment_id": "mlebench-gp7-three-20260916", "family": "MLEBench", "method": "gp7_ancestry_logei", "dataset": "plant-pathology-2020-fgvc7", "status": "archived", "official_score": 0.98298, "medal": "gold", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.97836, "silver": 0.97465, "bronze": 0.97361}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/results/private_grades.jsonl:13", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}, {"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/runs/gp7_ancestry_logei/13_plant-pathology-2020-fgvc7/logs/journal.json", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}], "alternate_scores": [], "journal_ref": "gp7-three-bo-analysis-20260916:gp7-three-66-runs/runs/gp7_ancestry_logei/13_plant-pathology-2020-fgvc7/logs/journal.json", "metrics": [{"event_id": "83f6a6f7f2114ce2bf091f74636b7543", "step": 4, "value": 0.9701527076463525, "stage": "draft", "created_at": 1789522361.0530229}, {"event_id": "e53d6907f17a4065b25a85b31f8a7ca1", "step": 6, "value": 0.9741526132800241, "stage": "debug", "created_at": 1789523277.603955}, {"event_id": "69021879328f425e942fd279767d7ed8", "step": 7, "value": 0.9301698541331129, "stage": "debug", "created_at": 1789522884.5266683}, {"event_id": "c326d164fbcf4a74a372cfb5bb8191ab", "step": 8, "value": 0.9573505781875729, "stage": "improve", "created_at": 1789523203.9463272}, {"event_id": "c7c017d6fb384bc797becaaedc73dd44", "step": 10, "value": 0.9907543697918006, "stage": "improve", "created_at": 1789523834.910609}, {"event_id": "c274e73d478c43849173e3101280fd38", "step": 11, "value": 0.9917339596552671, "stage": "improve", "created_at": 1789523736.4771323}, {"event_id": "6b3b5314c4ed4cccb70e5f61a8f403d1", "step": 12, "value": 0.9862893729622666, "stage": "debug", "created_at": 1789523846.0214338}, {"event_id": "85f8f565d1154dc5a26522719085191f", "step": 13, "value": 0.9890345442822557, "stage": "improve", "created_at": 1789524436.8984973}, {"event_id": "e0372514eb9446ca81f796c6f057b827", "step": 14, "value": 0.9884665960585124, "stage": "improve", "created_at": 1789524543.2370481}, {"event_id": "9099de9ed0474b94bd1dcf2fa846bb33", "step": 17, "value": 0.988351733155417, "stage": "debug", "created_at": 1789525389.7230315}, {"event_id": "2ef5b3191dd740b89c0dda2067061083", "step": 20, "value": 0.9529324791714521, "stage": "debug", "created_at": 1789526140.1599944}, {"event_id": "0ece6f7a4b0b46c58e26ea3def37d484", "step": 21, "value": 0.9917520462088075, "stage": "evolution", "created_at": 1789526713.6210177}, {"event_id": "0309af31639941cc902491905d0bc4ba", "step": 26, "value": 0.988544001744864, "stage": "debug", "created_at": 1789530972.8453763}, {"event_id": "e2b343585b954a8aada6bbd8e600cd79", "step": 27, "value": 0.9898825594681794, "stage": "debug", "created_at": 1789529718.3486094}, {"event_id": "befdc6b4fdd94e1b90a8db3a118cd35e", "step": 28, "value": 0.9869991497761127, "stage": "debug", "created_at": 1789530533.7093372}, {"event_id": "72092c6dede2486d92b4d89118bd4420", "step": 30, "value": 0.936018283692771, "stage": "debug", "created_at": 1789536354.505784}, {"event_id": "a94d919773d948b09c16830fb265b395", "step": 31, "value": 0.9901796894900494, "stage": "improve", "created_at": 1789534812.702946}, {"event_id": "9643cac47e8148e89e6535de22a62d39", "step": 32, "value": 0.9937128719339887, "stage": "evolution", "created_at": 1789537913.5368807}, {"event_id": "ba536220894e481f8ba5f289061f068f", "step": 35, "value": 0.9908078395268409, "stage": "evolution", "created_at": 1789539136.316025}, {"event_id": "dd13a1d7bde94dd18e1611578951e924", "step": 36, "value": 0.9931717533935331, "stage": "debug", "created_at": 1789540109.1401393}, {"event_id": "281c3031ca464548b3fe6033762f86c7", "step": 37, "value": 0.9904300973398993, "stage": "improve", "created_at": 1789543897.226404}, {"event_id": "87fa3690a8b4477f99044324a011ec09", "step": 39, "value": 0.9550599190567168, "stage": "fusion_draft", "created_at": 1789547644.9357772}], "maximize": true, "elapsed_seconds": 28798.384091615677, "node_count": 44, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-three-20260916/xixian.gp7-ancestry-logei.plant-pathology-2020-fgvc7.yaml", "note": ""}, {"id": "xixian.gp7-ancestry-logei.random-acts-of-pizza", "experiment_id": "mlebench-gp7-three-20260916", "family": "MLEBench", "method": "gp7_ancestry_logei", "dataset": "random-acts-of-pizza", "status": "archived", "official_score": 0.69506, "medal": "bronze", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.97908, "silver": 0.76482, "bronze": 0.6921}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/results/private_grades.jsonl:14", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}, {"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/runs/gp7_ancestry_logei/14_random-acts-of-pizza/logs/journal.json", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}], "alternate_scores": [], "journal_ref": "gp7-three-bo-analysis-20260916:gp7-three-66-runs/runs/gp7_ancestry_logei/14_random-acts-of-pizza/logs/journal.json", "metrics": [{"event_id": "60b9dd012d804d8ab24b6abd2d32780a", "step": 3, "value": 0.5794828727854131, "stage": "draft", "created_at": 1789522603.1728487}, {"event_id": "a1da561e3cbe4f7fac1a964144c30fe5", "step": 4, "value": 0.6180493871025048, "stage": "debug", "created_at": 1789522719.5317066}, {"event_id": "e6c64b1975e54e8a83116552e797c711", "step": 5, "value": 0.6096997690531177, "stage": "debug", "created_at": 1789522810.19504}, {"event_id": "011bad6a635d4982b3551201a97a9a25", "step": 7, "value": 0.5894475039971576, "stage": "improve", "created_at": 1789522931.6005223}, {"event_id": "79334ee5cfbe4d4a91dac6611ef3b7c9", "step": 8, "value": 0.6240087856716032, "stage": "improve", "created_at": 1789523317.6441472}, {"event_id": "36312e6228a746d2baa1de2025c389be", "step": 10, "value": 0.6122514898496423, "stage": "debug", "created_at": 1789523305.6681595}, {"event_id": "13c4d0103a4e4bf3874204b05902d95b", "step": 11, "value": 0.6080766808249488, "stage": "debug", "created_at": 1789523585.4263673}, {"event_id": "d7392ae95848492bbe82e1fc9fc7e9a1", "step": 13, "value": 0.6274891390364832, "stage": "improve", "created_at": 1789523756.575574}, {"event_id": "4048fc9250374757b3f3c560b25ce1e0", "step": 15, "value": 0.6136888515641402, "stage": "debug", "created_at": 1789523903.0981898}, {"event_id": "56124d04f59048b68b9c6e2738f0400e", "step": 16, "value": 0.6618969944605049, "stage": "debug", "created_at": 1789524172.8290799}, {"event_id": "39f6636daec6492e9b1e4b59eac59703", "step": 17, "value": 0.6632697556485084, "stage": "improve", "created_at": 1789524407.1853383}, {"event_id": "e311e3707a28460f95a77023b418a2a3", "step": 18, "value": 0.6640288118348165, "stage": "improve", "created_at": 1789525195.4699118}, {"event_id": "86b56b85d05a443ba5e872953d17a22d", "step": 19, "value": 0.6502365994282853, "stage": "improve", "created_at": 1789525256.6396413}, {"event_id": "817e9339abc7405eab097ce7cf2518bd", "step": 20, "value": 0.653272824173517, "stage": "improve", "created_at": 1789527289.740932}, {"event_id": "bb3322d533df46869ea4f0ba4be01353", "step": 25, "value": 0.6543871832555436, "stage": "improve", "created_at": 1789528675.7624717}, {"event_id": "f1dbb1619a044f268750778069df36d5", "step": 30, "value": 0.6635443078861093, "stage": "evolution", "created_at": 1789532373.124203}, {"event_id": "bb2714be54ec43aeb0e56c24a06e04d9", "step": 32, "value": 0.6558003197726061, "stage": "debug", "created_at": 1789533264.1422608}, {"event_id": "ada3902a8cb5497fb2cbd9edf62ec6a7", "step": 33, "value": 0.6404092443353413, "stage": "improve", "created_at": 1789524234.4033759}, {"event_id": "50856f1a257a47cd9931d098b7b8687e", "step": 34, "value": 0.5998158884994913, "stage": "evolution", "created_at": 1789533532.0627453}, {"event_id": "34a04826b8404bd992aac4c747ce1e49", "step": 35, "value": 0.6813256028036628, "stage": "evolution", "created_at": 1789533959.2533846}, {"event_id": "18eef94c1921451abce6dbec03fb5711", "step": 36, "value": 0.6558891454965359, "stage": "improve", "created_at": 1789534349.798584}, {"event_id": "78149c0898354792b0afb69a51490121", "step": 37, "value": 0.6809702999079442, "stage": "improve", "created_at": 1789534689.1370778}, {"event_id": "b7c0508358ee4f3a8adb19549903609f", "step": 38, "value": 0.6808410988549557, "stage": "improve", "created_at": 1789534771.3201606}, {"event_id": "7e620d2fd7914ade84af590c7c5a0e52", "step": 39, "value": 0.6754631050243061, "stage": "improve", "created_at": 1789535589.6502}, {"event_id": "97e0bb0325c848d2a5e33efa70cf45f3", "step": 40, "value": 0.6830859671506324, "stage": "improve", "created_at": 1789536377.0187786}, {"event_id": "5a6e67edd3bd4e48a29d771caebfc4e4", "step": 41, "value": 0.6729598346226522, "stage": "improve", "created_at": 1789531089.638538}, {"event_id": "7071ff7eecc5486e9ebffcf36a2a0b6d", "step": 42, "value": 0.6806472972754728, "stage": "improve", "created_at": 1789535969.3250291}, {"event_id": "77552554c74148f68104c72f393a6b62", "step": 43, "value": 0.6796621392464349, "stage": "improve", "created_at": 1789537256.5506835}, {"event_id": "4bf7940269ef49b3812219602ef64902", "step": 44, "value": 0.6808087985917086, "stage": "improve", "created_at": 1789537115.7954457}, {"event_id": "6bb590cef1b04b72ad1d281b6b142a70", "step": 47, "value": 0.6792906862190926, "stage": "improve", "created_at": 1789537411.0666158}, {"event_id": "fe8a7c205a7d4688acb60c243e81da02", "step": 48, "value": 0.6812610022771686, "stage": "improve", "created_at": 1789538176.0305567}, {"event_id": "8c0940189f154da889918c4bdd3bbcde", "step": 49, "value": 0.5259128861900224, "stage": "debug", "created_at": 1789538594.8648038}, {"event_id": "0618c73a50e24062b6df9ec7eaf81b83", "step": 50, "value": 0.6857991892633926, "stage": "evolution", "created_at": 1789539200.222134}, {"event_id": "422ef857abbc428abd521d92ddd18d5f", "step": 51, "value": 0.6833928196514802, "stage": "evolution", "created_at": 1789539124.8302958}, {"event_id": "b088e26a5a1f4e0e81bfad5e5e4a1e0c", "step": 52, "value": 0.6876080040052327, "stage": "evolution", "created_at": 1789538782.4265935}, {"event_id": "b92a071e67c44a36b7992b49fd8fc0c1", "step": 53, "value": 0.6840549750480467, "stage": "improve", "created_at": 1789540067.818898}, {"event_id": "a6b3f170727b4ada8ae91561fdef3570", "step": 54, "value": 0.6842164763642824, "stage": "improve", "created_at": 1789540231.0839877}, {"event_id": "b9255a0496f64500b5c9f130e0f77c28", "step": 55, "value": 0.6849270821557195, "stage": "improve", "created_at": 1789540489.9702623}, {"event_id": "f40ed52c2f1f4602ad87f8314aaf977f", "step": 56, "value": 0.6837642726788224, "stage": "improve", "created_at": 1789541447.3206656}, {"event_id": "4244a6fc723a4c7aa739c532529678fc", "step": 57, "value": 0.6918554886222322, "stage": "improve", "created_at": 1789541295.9625103}, {"event_id": "e1ce684615684342b37e30071022a4fc", "step": 58, "value": 0.6875272533471148, "stage": "fusion", "created_at": 1789542326.3026721}, {"event_id": "1c8c023171c840ca8cb3d8a953b23db9", "step": 59, "value": 0.6950693648153232, "stage": "fusion", "created_at": 1789542321.7537088}, {"event_id": "b4a44c68b2104d58822473197d34fc6d", "step": 60, "value": 0.6915486361213844, "stage": "improve", "created_at": 1789542469.4140458}, {"event_id": "47b0fc9bc2cb4c87a70821d520e899bf", "step": 61, "value": 0.691677837174373, "stage": "improve", "created_at": 1789544020.627241}, {"event_id": "dec70c3dba254a3c87ed4a695542450d", "step": 62, "value": 0.6937289038905667, "stage": "improve", "created_at": 1789544153.7305713}, {"event_id": "4d4ea8e6fdca4759a69627ec54c87024", "step": 63, "value": 0.6959414719229962, "stage": "improve", "created_at": 1789544254.5174632}, {"event_id": "7bcb3597652e4e19be85daf151ef52e6", "step": 64, "value": 0.6755600058140474, "stage": "improve", "created_at": 1789545811.3631043}, {"event_id": "bb4ca8da83854d1f9f45e15a9f3c0ac1", "step": 65, "value": 0.6962402493580322, "stage": "evolution", "created_at": 1789546361.6335437}, {"event_id": "a47e88cf9ae24aa0849681fef58a3ecc", "step": 66, "value": 0.6869781488719132, "stage": "improve", "created_at": 1789546673.1457033}, {"event_id": "4056f828519249b18293291878b53b52", "step": 67, "value": 0.6955054183691598, "stage": "improve", "created_at": 1789547522.0757172}], "maximize": true, "elapsed_seconds": 28818.614602565765, "node_count": 72, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-three-20260916/xixian.gp7-ancestry-logei.random-acts-of-pizza.yaml", "note": ""}, {"id": "xixian.gp7-ancestry-logei.ranzcr-clip-catheter-line-classification", "experiment_id": "mlebench-gp7-three-20260916", "family": "MLEBench", "method": "gp7_ancestry_logei", "dataset": "ranzcr-clip-catheter-line-classification", "status": "archived", "official_score": 0.86532, "medal": "none", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.97357, "silver": 0.97152, "bronze": 0.9709}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/results/private_grades.jsonl:15", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}, {"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/runs/gp7_ancestry_logei/15_ranzcr-clip-catheter-line-classification/logs/journal.json", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}], "alternate_scores": [], "journal_ref": "gp7-three-bo-analysis-20260916:gp7-three-66-runs/runs/gp7_ancestry_logei/15_ranzcr-clip-catheter-line-classification/logs/journal.json", "metrics": [{"event_id": "f4af4abeaff14decad33ce893c1a0265", "step": 4, "value": 0.7844150748235047, "stage": "debug", "created_at": 1789524608.7322457}, {"event_id": "53c6434dfcf54b72bc1a8469fbcf095f", "step": 8, "value": 0.8217320345010398, "stage": "debug", "created_at": 1789528834.143265}, {"event_id": "b91315836bf74e458d6fc9131f1d0f6c", "step": 11, "value": 0.8279780498578392, "stage": "improve", "created_at": 1789531628.808154}, {"event_id": "219da0745914482185f35ac6230b3879", "step": 13, "value": 0.8256395996659378, "stage": "improve", "created_at": 1789537518.1958177}], "maximize": true, "elapsed_seconds": 28796.13661837578, "node_count": 15, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-three-20260916/xixian.gp7-ancestry-logei.ranzcr-clip-catheter-line-classification.yaml", "note": ""}, {"id": "xixian.gp7-ancestry-logei.siim-isic-melanoma-classification", "experiment_id": "mlebench-gp7-three-20260916", "family": "MLEBench", "method": "gp7_ancestry_logei", "dataset": "siim-isic-melanoma-classification", "status": "archived", "official_score": 0.86765, "medal": "none", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.9455, "silver": 0.9401, "bronze": 0.937}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/results/private_grades.jsonl:16", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}, {"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/runs/gp7_ancestry_logei/16_siim-isic-melanoma-classification/logs/journal.json", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}], "alternate_scores": [], "journal_ref": "gp7-three-bo-analysis-20260916:gp7-three-66-runs/runs/gp7_ancestry_logei/16_siim-isic-melanoma-classification/logs/journal.json", "metrics": [{"event_id": "75a309bc17de4c1dbce3155c2d69534b", "step": 3, "value": 0.9008783136378155, "stage": "draft", "created_at": 1789522579.522458}, {"event_id": "f403f4d138c34991a4ce9ffcba88dbe4", "step": 5, "value": 0.8913059557229068, "stage": "debug", "created_at": 1789532377.0256565}, {"event_id": "273d2c35dfc3469d92a7ac1827458bb6", "step": 9, "value": 0.896748978802804, "stage": "debug", "created_at": 1789540972.8867645}], "maximize": true, "elapsed_seconds": 28795.06623315811, "node_count": 13, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-three-20260916/xixian.gp7-ancestry-logei.siim-isic-melanoma-classification.yaml", "note": ""}, {"id": "xixian.gp7-ancestry-logei.spooky-author-identification", "experiment_id": "mlebench-gp7-three-20260916", "family": "MLEBench", "method": "gp7_ancestry_logei", "dataset": "spooky-author-identification", "status": "archived", "official_score": 0.23406, "medal": "silver", "valid_submission": true, "score_maximize": false, "thresholds": {"gold": 0.16506, "silver": 0.26996, "bronze": 0.29381}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/results/private_grades.jsonl:17", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}, {"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/runs/gp7_ancestry_logei/17_spooky-author-identification/logs/journal.json", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}], "alternate_scores": [], "journal_ref": "gp7-three-bo-analysis-20260916:gp7-three-66-runs/runs/gp7_ancestry_logei/17_spooky-author-identification/logs/journal.json", "metrics": [{"event_id": "743e6eef53d441cda07b487d59ad51a3", "step": 4, "value": 0.3986968631589547, "stage": "debug", "created_at": 1789522707.9973192}, {"event_id": "19e0c8bd69854a47bf1d79089eebed6b", "step": 5, "value": 0.30646913825525124, "stage": "draft", "created_at": 1789521957.105458}, {"event_id": "1fe6dd35346e4dcaa5b688a413b4c030", "step": 6, "value": 0.348895289556453, "stage": "improve", "created_at": 1789523311.5692778}, {"event_id": "7853ec02d48940e1844244abfe1cef77", "step": 7, "value": 0.29183825643477646, "stage": "improve", "created_at": 1789523329.5473168}, {"event_id": "1abdb54ec2a142f48bac950bcdbf1a51", "step": 8, "value": 0.2715007599252282, "stage": "improve", "created_at": 1789524528.3136914}, {"event_id": "ca2fca52b1a145d8a66f1a7f148d5b6e", "step": 9, "value": 0.2950991219601828, "stage": "improve", "created_at": 1789524345.4113638}, {"event_id": "c775b61d0b2e4de0ad7f6e0854933894", "step": 12, "value": 0.2599508092074436, "stage": "debug", "created_at": 1789529402.2797863}, {"event_id": "95dfc3e1faf54c8b81dc1981c5e51ef9", "step": 13, "value": 0.27193488949172356, "stage": "debug", "created_at": 1789529649.2673216}, {"event_id": "e91b11fc3e6b4261b623d9a019ea3e6b", "step": 14, "value": 0.25399031023213103, "stage": "improve", "created_at": 1789535460.6496463}, {"event_id": "ab35b54a8dd34a96ae19110cdae9fc36", "step": 15, "value": 0.27696349527740594, "stage": "improve", "created_at": 1789538967.0345778}, {"event_id": "be594d0226324a7a85d2fd0cec531b41", "step": 20, "value": 0.3067225038718091, "stage": "debug", "created_at": 1789545618.198364}, {"event_id": "cb72c65d718145d98c65c33dbd937555", "step": 21, "value": 0.23630756678103115, "stage": "improve", "created_at": 1789535584.9178476}, {"event_id": "f95e26b5ede343048eb339ec5a51c8a2", "step": 22, "value": 0.29827640908571723, "stage": "improve", "created_at": 1789546350.8622816}], "maximize": false, "elapsed_seconds": 28803.34746479988, "node_count": 26, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-three-20260916/xixian.gp7-ancestry-logei.spooky-author-identification.yaml", "note": ""}, {"id": "xixian.gp7-ancestry-logei.tabular-playground-series-dec-2021", "experiment_id": "mlebench-gp7-three-20260916", "family": "MLEBench", "method": "gp7_ancestry_logei", "dataset": "tabular-playground-series-dec-2021", "status": "archived", "official_score": 0.96273, "medal": "gold", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.9566, "silver": 0.95658, "bronze": 0.95658}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/results/private_grades.jsonl:18", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}, {"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/runs/gp7_ancestry_logei/18_tabular-playground-series-dec-2021/logs/journal.json", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}], "alternate_scores": [], "journal_ref": "gp7-three-bo-analysis-20260916:gp7-three-66-runs/runs/gp7_ancestry_logei/18_tabular-playground-series-dec-2021/logs/journal.json", "metrics": [{"event_id": "91d819eec48943a197a7182b23fbf484", "step": 3, "value": 0.9617888888888889, "stage": "debug", "created_at": 1789523067.1693249}, {"event_id": "66d2851030d34cb2b71c747bf029fdd7", "step": 4, "value": 0.9621777777777778, "stage": "improve", "created_at": 1789524515.4304116}, {"event_id": "c195559733cf47db8ce43c834ac319bc", "step": 5, "value": 0.9589638888888888, "stage": "draft", "created_at": 1789522940.0133886}, {"event_id": "f617d1cbee194d3e9bbc36ffb5354930", "step": 6, "value": 0.9612347222222222, "stage": "improve", "created_at": 1789531029.170431}], "maximize": true, "elapsed_seconds": 28803.33673787117, "node_count": 13, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-three-20260916/xixian.gp7-ancestry-logei.tabular-playground-series-dec-2021.yaml", "note": ""}, {"id": "xixian.gp7-ancestry-logei.tabular-playground-series-may-2022", "experiment_id": "mlebench-gp7-three-20260916", "family": "MLEBench", "method": "gp7_ancestry_logei", "dataset": "tabular-playground-series-may-2022", "status": "archived", "official_score": 0.99508, "medal": "none", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.99823, "silver": 0.99822, "bronze": 0.99818}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/results/private_grades.jsonl:19", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}, {"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/runs/gp7_ancestry_logei/19_tabular-playground-series-may-2022/logs/journal.json", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}], "alternate_scores": [], "journal_ref": "gp7-three-bo-analysis-20260916:gp7-three-66-runs/runs/gp7_ancestry_logei/19_tabular-playground-series-may-2022/logs/journal.json", "metrics": [{"event_id": "292c7e429d5a470e83e29a3a2819847b", "step": 1, "value": 0.9949845065092813, "stage": "draft", "created_at": 1789522010.6368937}, {"event_id": "e3565cd1ea51463f8acfd9f37abec2cf", "step": 2, "value": 0.8387555076328018, "stage": "draft", "created_at": 1789522346.3780007}, {"event_id": "a231f7c9e0394e1a8ca189b0ad5c84af", "step": 4, "value": 0.9895890649461158, "stage": "draft", "created_at": 1789522694.468886}], "maximize": true, "elapsed_seconds": 28802.64691543579, "node_count": 8, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-three-20260916/xixian.gp7-ancestry-logei.tabular-playground-series-may-2022.yaml", "note": ""}, {"id": "xixian.gp7-ancestry-logei.text-normalization-challenge-english-language", "experiment_id": "mlebench-gp7-three-20260916", "family": "MLEBench", "method": "gp7_ancestry_logei", "dataset": "text-normalization-challenge-english-language", "status": "archived", "official_score": 0.98724, "medal": "none", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.99724, "silver": 0.99135, "bronze": 0.99038}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/results/private_grades.jsonl:20", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}, {"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/runs/gp7_ancestry_logei/20_text-normalization-challenge-english-language/logs/journal.json", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}], "alternate_scores": [], "journal_ref": "gp7-three-bo-analysis-20260916:gp7-three-66-runs/runs/gp7_ancestry_logei/20_text-normalization-challenge-english-language/logs/journal.json", "metrics": [{"event_id": "ffaead5c39b8460f89cedf5b513db896", "step": 5, "value": 0.059005508017674076, "stage": "debug", "created_at": 1789523381.9450483}, {"event_id": "30839888ef0b4a58a6845f7da8a320df", "step": 8, "value": 0.9872914317483305, "stage": "debug", "created_at": 1789545881.1969779}, {"event_id": "e95198296e6f4e639b9d89eb34626e6b", "step": 9, "value": 0.9838951571141306, "stage": "improve", "created_at": 1789547639.5498679}], "maximize": true, "elapsed_seconds": 28799.156889677048, "node_count": 10, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-three-20260916/xixian.gp7-ancestry-logei.text-normalization-challenge-english-language.yaml", "note": ""}, {"id": "xixian.gp7-ancestry-logei.text-normalization-challenge-russian-language", "experiment_id": "mlebench-gp7-three-20260916", "family": "MLEBench", "method": "gp7_ancestry_logei", "dataset": "text-normalization-challenge-russian-language", "status": "archived", "official_score": 0.97403, "medal": "none", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.99012, "silver": 0.98232, "bronze": 0.97592}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/results/private_grades.jsonl:21", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}, {"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/runs/gp7_ancestry_logei/21_text-normalization-challenge-russian-language/logs/journal.json", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}], "alternate_scores": [], "journal_ref": "gp7-three-bo-analysis-20260916:gp7-three-66-runs/runs/gp7_ancestry_logei/21_text-normalization-challenge-russian-language/logs/journal.json", "metrics": [{"event_id": "6ab98e331e464620b101cfacfd228f4a", "step": 4, "value": 0.9713542782849713, "stage": "debug", "created_at": 1789523989.4839864}, {"event_id": "159ec52452db4c26a182dc05dcce6d96", "step": 8, "value": 0.9738545283099739, "stage": "debug", "created_at": 1789525482.129208}, {"event_id": "864f88a9b3ae4b02a97e6fdc448a9b2f", "step": 9, "value": 0.9660680353749661, "stage": "improve", "created_at": 1789524874.523802}, {"event_id": "69588d0b17c4426681cac95e6f46e64c", "step": 10, "value": 0.9736973697369737, "stage": "improve", "created_at": 1789529955.466482}, {"event_id": "4f93e3c5575c4884a537f3dc029a2677", "step": 11, "value": 0.9741116968839741, "stage": "improve", "created_at": 1789533123.244561}, {"event_id": "ae5fd6a11caf40a09a5ff6b68655e1fe", "step": 12, "value": 0.8775306102038776, "stage": "debug", "created_at": 1789526185.9610085}, {"event_id": "4c0bd94453f14cb19dcfd3e34e0f9b18", "step": 14, "value": 0.9605674853199606, "stage": "fusion_draft", "created_at": 1789548483.3553872}, {"event_id": "d1176c09287e452cb2942efadf9753ba", "step": 15, "value": 0.9741402711699741, "stage": "improve", "created_at": 1789540023.5801585}], "maximize": true, "elapsed_seconds": 28798.731213092804, "node_count": 18, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-three-20260916/xixian.gp7-ancestry-logei.text-normalization-challenge-russian-language.yaml", "note": ""}, {"id": "xixian.gp7-ancestry-logei.the-icml-2013-whale-challenge-right-whale-redux", "experiment_id": "mlebench-gp7-three-20260916", "family": "MLEBench", "method": "gp7_ancestry_logei", "dataset": "the-icml-2013-whale-challenge-right-whale-redux", "status": "archived", "official_score": 0.97812, "medal": "silver", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.98961, "silver": 0.95017, "bronze": 0.90521}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/results/private_grades.jsonl:22", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}, {"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/runs/gp7_ancestry_logei/22_the-icml-2013-whale-challenge-right-whale-redux/logs/journal.json", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}], "alternate_scores": [], "journal_ref": "gp7-three-bo-analysis-20260916:gp7-three-66-runs/runs/gp7_ancestry_logei/22_the-icml-2013-whale-challenge-right-whale-redux/logs/journal.json", "metrics": [{"event_id": "11bc865c932e4f7792753f0861369284", "step": 2, "value": 0.9114989086159749, "stage": "debug", "created_at": 1789524093.8538918}, {"event_id": "b56fb47c37884a34bebf8d0b5af096d0", "step": 3, "value": 0.9685059395869671, "stage": "draft", "created_at": 1789523438.7443416}, {"event_id": "bdfe9c668d9f48f5974594fea3b9f262", "step": 4, "value": 0.9156327039430142, "stage": "improve", "created_at": 1789525234.7540472}, {"event_id": "2af57932fd5944da85a4b86dbf3cbf78", "step": 5, "value": 0.8660888759877552, "stage": "improve", "created_at": 1789526499.8561196}, {"event_id": "e230ee8c5837437ea41c6acb6a6b11b7", "step": 6, "value": 0.9569557788195591, "stage": "improve", "created_at": 1789527916.3085566}, {"event_id": "b0fd191555e84a3b9918043834657b70", "step": 7, "value": 0.9342231102274129, "stage": "improve", "created_at": 1789526265.725718}, {"event_id": "272096009520481087e27963dc52523d", "step": 8, "value": 0.8963571084683364, "stage": "improve", "created_at": 1789529350.0122788}, {"event_id": "e03326d7698c4e37b387ee3c50d9194c", "step": 9, "value": 0.9537430490615527, "stage": "improve", "created_at": 1789530839.017659}, {"event_id": "ce5b09aeecb14ff38ce4bcdd50dffdda", "step": 10, "value": 0.9721798506121161, "stage": "improve", "created_at": 1789529640.2995648}, {"event_id": "c6a388570c0946a6999598b83b4ab113", "step": 11, "value": 0.8258635231361227, "stage": "improve", "created_at": 1789532779.5869412}, {"event_id": "5b9fadc422df41dbb34da9d10fbfb353", "step": 12, "value": 0.9333192967433498, "stage": "improve", "created_at": 1789531994.8016493}, {"event_id": "bd06885d4b224e01b53cad83cd07000c", "step": 13, "value": 0.9554667648249123, "stage": "evolution", "created_at": 1789534118.6749778}, {"event_id": "c18f27e896ba4365aa69c586021aa3f8", "step": 14, "value": 0.9349482606301108, "stage": "evolution", "created_at": 1789535022.1026547}, {"event_id": "b6cac024d3f1408a889103481175e726", "step": 16, "value": 0.6753613748967139, "stage": "debug", "created_at": 1789537890.125378}, {"event_id": "290b5b79206f428ca60566a9c76df40d", "step": 17, "value": 0.9710248663477307, "stage": "improve", "created_at": 1789537980.9824007}, {"event_id": "5a56e9245f554a95890d907e37cf0614", "step": 18, "value": 0.9716855844954999, "stage": "improve", "created_at": 1789539648.9996598}, {"event_id": "76eb3626ff1748df8b277c1f8ccbdb7f", "step": 19, "value": 0.9528581516933495, "stage": "evolution", "created_at": 1789541130.6789274}, {"event_id": "7f6a5e37bad9489a890318ba946e3883", "step": 20, "value": 0.9711322942243494, "stage": "evolution", "created_at": 1789542347.5393348}, {"event_id": "72f068c31cf64ea29cd9bca8ac6446fb", "step": 22, "value": 0.9737732580741103, "stage": "draft", "created_at": 1789545375.1915884}, {"event_id": "9fe4f9e9da064625bf4f47f358f5b3da", "step": 23, "value": 0.9725664930837736, "stage": "fusion", "created_at": 1789543748.050735}, {"event_id": "9770b01ba73e41489a9db3eb90ff2835", "step": 24, "value": 0.968981093819383, "stage": "improve", "created_at": 1789547137.6891193}, {"event_id": "da864cd1c641415f9331e6bcfbcc613a", "step": 25, "value": 0.966489550155188, "stage": "fusion", "created_at": 1789545870.935739}], "maximize": true, "elapsed_seconds": 28795.046082019806, "node_count": 29, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-three-20260916/xixian.gp7-ancestry-logei.the-icml-2013-whale-challenge-right-whale-redux.yaml", "note": ""}, {"id": "xixian.gp7-long-horizon-logei.aerial-cactus-identification", "experiment_id": "mlebench-gp7-three-20260916", "family": "MLEBench", "method": "gp7_long_horizon_logei", "dataset": "aerial-cactus-identification", "status": "archived", "official_score": 0.99999, "medal": "none", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 1.0, "silver": 1.0, "bronze": 1.0}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/results/private_grades.jsonl:23", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}, {"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/runs/gp7_long_horizon_logei/01_aerial-cactus-identification/logs/journal.json", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}], "alternate_scores": [], "journal_ref": "gp7-three-bo-analysis-20260916:gp7-three-66-runs/runs/gp7_long_horizon_logei/01_aerial-cactus-identification/logs/journal.json", "metrics": [{"event_id": "ac1398870f5a4d64be91cf5818147029", "step": 3, "value": 0.9999389650867028, "stage": "debug", "created_at": 1789523474.2306163}, {"event_id": "a5d22bc7df1f4e5abcfe5a3893a05669", "step": 4, "value": 0.99998938523247, "stage": "debug", "created_at": 1789523495.9713674}, {"event_id": "3d8a82e156f7448f81afdb0da1fa6d95", "step": 5, "value": 0.9994463735310157, "stage": "draft", "created_at": 1789522682.736955}, {"event_id": "74879e1c32444362a4f599afcd4f0d69", "step": 6, "value": 0.9999834144257345, "stage": "improve", "created_at": 1789524095.3133705}, {"event_id": "fe0761eb7e214a83ad1dbba76bbc0773", "step": 8, "value": 0.9999469261623501, "stage": "improve", "created_at": 1789524404.2285428}, {"event_id": "7aa3d31d47a14c7197a45968953e0f1e", "step": 9, "value": 0.9999545555265124, "stage": "improve", "created_at": 1789524600.393124}, {"event_id": "662818b0e76b4f9dad5d4a0fab994dfd", "step": 10, "value": 0.9999973463081174, "stage": "debug", "created_at": 1789524591.8202765}, {"event_id": "c26b1cb023ae456da354e786293eb0f9", "step": 11, "value": 0.9999144184367897, "stage": "improve", "created_at": 1789525033.8375103}, {"event_id": "047ba6e100d54522b5f088622ccec72e", "step": 12, "value": 0.999950906700174, "stage": "improve", "created_at": 1789525463.713842}, {"event_id": "452773226bd040c88eb738d8656969aa", "step": 13, "value": 0.9998626714450812, "stage": "improve", "created_at": 1789525369.2390285}, {"event_id": "918c0dc28b1e4fa79e6f2b53a913cd2b", "step": 14, "value": 0.9991813360542521, "stage": "improve", "created_at": 1789525451.9325652}, {"event_id": "620dba6571874eeda238e4e3f2593010", "step": 16, "value": 0.9998397833525947, "stage": "debug", "created_at": 1789526263.3470814}, {"event_id": "21cd518bd783482d90a8883d887ae41b", "step": 17, "value": 0.9999847412716756, "stage": "improve", "created_at": 1789526016.1143978}, {"event_id": "a4cfb87f73884e56bf9c229ce0d89c1a", "step": 18, "value": 0.9999940291932644, "stage": "evolution", "created_at": 1789526290.2849097}, {"event_id": "f65f138a9bbc41aea5626f3b6dfda6aa", "step": 19, "value": 0.9998712959436994, "stage": "improve", "created_at": 1789528459.234945}, {"event_id": "8da1210a3c3646ea94556cc86405609a", "step": 20, "value": 0.9999834144257345, "stage": "evolution", "created_at": 1789527047.7422044}, {"event_id": "7abcdf963dc2474bb5e3651bd0e1795b", "step": 23, "value": 0.9999422822015559, "stage": "debug", "created_at": 1789529805.5280468}, {"event_id": "b99461e5d420431b8383ec1a6f17e2a8", "step": 24, "value": 0.9999920389243525, "stage": "improve", "created_at": 1789528169.3219204}, {"event_id": "3b33c499b20b434b85160c52b39357c8", "step": 25, "value": 0.9999343211259085, "stage": "debug", "created_at": 1789529393.1057637}, {"event_id": "96750a16f9a4422e93ea4e2c3610de82", "step": 26, "value": 0.9999714728122632, "stage": "improve", "created_at": 1789530591.0704722}, {"event_id": "15a8adf02e134fa2ba3b679bb210fc6f", "step": 29, "value": 0.9995190183462987, "stage": "improve", "created_at": 1789535559.271011}, {"event_id": "a787453c6b564909bf8493aadac50b28", "step": 35, "value": 0.9999502432772033, "stage": "debug", "created_at": 1789539003.7159407}, {"event_id": "0aa1dd3278c0438dbb64d11b80d08542", "step": 36, "value": 0.9997983194169308, "stage": "evolution", "created_at": 1789545797.5818598}], "maximize": true, "elapsed_seconds": 28798.947548389435, "node_count": 37, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-three-20260916/xixian.gp7-long-horizon-logei.aerial-cactus-identification.yaml", "note": ""}, {"id": "xixian.gp7-long-horizon-logei.aptos2019-blindness-detection", "experiment_id": "mlebench-gp7-three-20260916", "family": "MLEBench", "method": "gp7_long_horizon_logei", "dataset": "aptos2019-blindness-detection", "status": "archived", "official_score": 0.90622, "medal": "none", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.930508, "silver": 0.919654, "bronze": 0.914492}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/results/private_grades.jsonl:24", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}, {"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/runs/gp7_long_horizon_logei/02_aptos2019-blindness-detection/logs/journal.json", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}], "alternate_scores": [], "journal_ref": "gp7-three-bo-analysis-20260916:gp7-three-66-runs/runs/gp7_long_horizon_logei/02_aptos2019-blindness-detection/logs/journal.json", "metrics": [{"event_id": "a19be3d1de18442c8165d8290d4c1f52", "step": 5, "value": 0.8877973590630449, "stage": "debug", "created_at": 1789523654.17883}, {"event_id": "d49b13044a614621913839a5ce40e6ea", "step": 8, "value": 0.9027359691907422, "stage": "improve", "created_at": 1789525810.8551168}, {"event_id": "366d9c1dc7af4b8b89e938d9193a1e68", "step": 10, "value": 0.908120896309238, "stage": "debug", "created_at": 1789528204.8013198}, {"event_id": "0442ee47abe74c8499e19c29e4eab6c9", "step": 11, "value": 0.9097042280653678, "stage": "improve", "created_at": 1789529518.8689733}, {"event_id": "7e9f5b95da144bbd9c95761946cbafa9", "step": 12, "value": 0.9052269577209394, "stage": "debug", "created_at": 1789530763.626437}, {"event_id": "8d8d2a5096eb4090b254ebb130e486ae", "step": 14, "value": 0.9121070875330828, "stage": "improve", "created_at": 1789534501.2423515}, {"event_id": "bdde4724154f454caa7fba4aa3fc5f75", "step": 15, "value": 0.910517106220953, "stage": "improve", "created_at": 1789535082.9570873}, {"event_id": "6aef9ea1d3604b4099c8ebfef984202f", "step": 16, "value": 0.9107684626093285, "stage": "improve", "created_at": 1789539671.3057697}], "maximize": true, "elapsed_seconds": 28804.349596977234, "node_count": 22, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-three-20260916/xixian.gp7-long-horizon-logei.aptos2019-blindness-detection.yaml", "note": ""}, {"id": "xixian.gp7-long-horizon-logei.denoising-dirty-documents", "experiment_id": "mlebench-gp7-three-20260916", "family": "MLEBench", "method": "gp7_long_horizon_logei", "dataset": "denoising-dirty-documents", "status": "archived", "official_score": 0.01139, "medal": "gold", "valid_submission": true, "score_maximize": false, "thresholds": {"gold": 0.01794, "silver": 0.02609, "bronze": 0.04517}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/results/private_grades.jsonl:25", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}, {"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/runs/gp7_long_horizon_logei/03_denoising-dirty-documents/logs/journal.json", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}], "alternate_scores": [], "journal_ref": "gp7-three-bo-analysis-20260916:gp7-three-66-runs/runs/gp7_long_horizon_logei/03_denoising-dirty-documents/logs/journal.json", "metrics": [{"event_id": "013f50c9842143ce9e515f9701ad1863", "step": 3, "value": 0.06381864900189832, "stage": "draft", "created_at": 1789522757.8580306}, {"event_id": "1c034eb2b0c04a5eac64a83e077a07fe", "step": 4, "value": 0.018678604072152747, "stage": "draft", "created_at": 1789522481.1920738}, {"event_id": "bc2e4715fe3741f08c91fc5a808f475c", "step": 5, "value": 0.06195425917679933, "stage": "debug", "created_at": 1789523112.455926}, {"event_id": "575a6b8c24a34eb68f17d1a8b95e9523", "step": 6, "value": 0.05747449188242878, "stage": "improve", "created_at": 1789523427.814859}, {"event_id": "b717dcb4b9b14e828ab2948a1ed5c0e4", "step": 7, "value": 0.01613975643349255, "stage": "improve", "created_at": 1789523438.6448789}, {"event_id": "89f42c7aaab449879ceff4a1aa1b7826", "step": 8, "value": 0.015112663349504028, "stage": "improve", "created_at": 1789523821.40712}, {"event_id": "b7b4c24c8da14ec893635b23e5c69cd1", "step": 9, "value": 0.06012548711655753, "stage": "improve", "created_at": 1789523987.1329865}, {"event_id": "278d2b4f268743fe81415a3fc8e9436c", "step": 10, "value": 0.014256541558905293, "stage": "improve", "created_at": 1789524197.710118}, {"event_id": "1fa7429b0f504cf5b9e7dddedb82e998", "step": 11, "value": 0.019346410105564368, "stage": "improve", "created_at": 1789524479.8427796}, {"event_id": "60640ca9c7a747ea95e3b56302fc5698", "step": 16, "value": 0.01875987200891397, "stage": "improve", "created_at": 1789525050.3928385}, {"event_id": "1ab529835a9041ad81690e5f1c111ef9", "step": 17, "value": 0.019581286764908046, "stage": "debug", "created_at": 1789525181.5397053}, {"event_id": "330a72b47e3a4dbfb946f1bd7a0fb97e", "step": 21, "value": 0.016919544282214826, "stage": "debug", "created_at": 1789525345.2668686}, {"event_id": "d58ede984a0544d4b0c823a1cf3fa61a", "step": 22, "value": 0.024129398243313897, "stage": "debug", "created_at": 1789525737.883193}, {"event_id": "0b28b4d311b84ce48ed8d7ac4172d23f", "step": 27, "value": 0.09583531115582097, "stage": "debug", "created_at": 1789526347.6494412}, {"event_id": "f0774a3b9e0c45a88c33e739409b5324", "step": 28, "value": 0.015137949319863366, "stage": "debug", "created_at": 1789526572.744047}, {"event_id": "f444928f470d4877865be08e5eff6984", "step": 29, "value": 0.01601741793182896, "stage": "evolution", "created_at": 1789526129.4488392}, {"event_id": "7f11bd05a34e48dd9fb7b24f8a51d370", "step": 31, "value": 0.016422238888366383, "stage": "evolution", "created_at": 1789527557.3632972}, {"event_id": "36fc40033a2e42ee8d7d8e622bc12118", "step": 32, "value": 0.0787935548781404, "stage": "debug", "created_at": 1789528704.101641}, {"event_id": "db0f38774edd40fd8dddca4fe4442cc8", "step": 34, "value": 0.028190274134724958, "stage": "draft", "created_at": 1789530504.886799}, {"event_id": "efe5461a8df5455cbcf599570be63abc", "step": 39, "value": 0.01646798968221009, "stage": "debug", "created_at": 1789532503.9828787}, {"event_id": "d4955c20f9494d81914b334fcd8845d0", "step": 40, "value": 0.04483614345431247, "stage": "debug", "created_at": 1789532800.0683231}, {"event_id": "2b209b27d5f84abca95a5764474b6ba1", "step": 41, "value": 0.09546906579752497, "stage": "debug", "created_at": 1789532879.2412622}, {"event_id": "67ce1e08a56442f480124f7f0cbc2093", "step": 42, "value": 0.013728207621926473, "stage": "evolution", "created_at": 1789535013.2640064}, {"event_id": "53ec5d5c1c2d4aceaed11e708e66e7b5", "step": 43, "value": 0.0175121484066173, "stage": "evolution", "created_at": 1789535184.6766438}, {"event_id": "e5a9b76b58284a1fb3e9ae56e8cdff21", "step": 45, "value": 0.014004183496604924, "stage": "improve", "created_at": 1789536969.133861}, {"event_id": "1762530e765a4b1eb06778b6709d56b3", "step": 47, "value": 0.013632242470099679, "stage": "improve", "created_at": 1789538575.1254497}, {"event_id": "ea57e08c604043be9e660d88ffb32e5c", "step": 48, "value": 0.018164881516198463, "stage": "improve", "created_at": 1789538704.9899988}, {"event_id": "02298475523a43599c79b158d5db35f2", "step": 49, "value": 0.09442684009390327, "stage": "debug", "created_at": 1789538241.4379618}, {"event_id": "2efcdf05d41e400ba6d052b5394d3e42", "step": 50, "value": 0.011149270491041436, "stage": "improve", "created_at": 1789540114.6104817}, {"event_id": "6c31e96b46b94bc98e2be9430bed2ac5", "step": 51, "value": 0.06539350349328255, "stage": "improve", "created_at": 1789541364.792931}, {"event_id": "cae7f7ff411442548fdeebe75f7d96c5", "step": 52, "value": 0.016404209957560804, "stage": "improve", "created_at": 1789540530.3282425}, {"event_id": "80a642e18bd541d3893f2a13d0cb8797", "step": 53, "value": 0.22857726825543112, "stage": "improve", "created_at": 1789542109.331074}, {"event_id": "1fe7b11b25a640e998ad82a6bb3449f5", "step": 54, "value": 0.010934900229690528, "stage": "improve", "created_at": 1789542053.7327178}, {"event_id": "65434aa9fa514367bb78742fd7af57dd", "step": 56, "value": 0.058474997083998295, "stage": "improve", "created_at": 1789543708.404845}, {"event_id": "137339f94026473da34ddbd989e741c9", "step": 57, "value": 0.011983142055100511, "stage": "improve", "created_at": 1789544263.4197264}, {"event_id": "bf6a0f8c864a417eb65c903774210013", "step": 58, "value": 0.04031744290217197, "stage": "debug", "created_at": 1789545047.892085}, {"event_id": "ed42edd7c1134e47b5904b7b7fb2377a", "step": 59, "value": 0.12322976902759462, "stage": "improve", "created_at": 1789545860.383439}, {"event_id": "85de2adb129546d89d72fd4b9afd330a", "step": 60, "value": 0.011370161659566216, "stage": "improve", "created_at": 1789546515.2106974}, {"event_id": "a8c99670ab004b6786de4f7582830811", "step": 61, "value": 0.011211915959073953, "stage": "improve", "created_at": 1789547379.6709793}, {"event_id": "bdf01b0796ab4f33b219673a727812e5", "step": 62, "value": 0.016511295376333637, "stage": "evolution", "created_at": 1789548955.5175984}], "maximize": false, "elapsed_seconds": 28812.6501891613, "node_count": 65, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-three-20260916/xixian.gp7-long-horizon-logei.denoising-dirty-documents.yaml", "note": ""}, {"id": "xixian.gp7-long-horizon-logei.detecting-insults-in-social-commentary", "experiment_id": "mlebench-gp7-three-20260916", "family": "MLEBench", "method": "gp7_long_horizon_logei", "dataset": "detecting-insults-in-social-commentary", "status": "archived", "official_score": 0.95551, "medal": "gold", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.83321, "silver": 0.82307, "bronze": 0.79111}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/results/private_grades.jsonl:26", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}, {"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/runs/gp7_long_horizon_logei/04_detecting-insults-in-social-commentary/logs/journal.json", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}], "alternate_scores": [], "journal_ref": "gp7-three-bo-analysis-20260916:gp7-three-66-runs/runs/gp7_long_horizon_logei/04_detecting-insults-in-social-commentary/logs/journal.json", "metrics": [{"event_id": "c75751c436874ffeb4b54592b18ab372", "step": 5, "value": 0.9003448275862069, "stage": "debug", "created_at": 1789522999.0875645}, {"event_id": "6814d161d76549e2a62d7f19e107843f", "step": 6, "value": 0.8591091954022989, "stage": "debug", "created_at": 1789523002.083654}, {"event_id": "8a281f679156459fbe80998b5c1fd02a", "step": 8, "value": 0.9391502463054189, "stage": "debug", "created_at": 1789523300.6141474}, {"event_id": "997ee38f92eb4732b12e9df8bc75828c", "step": 9, "value": 0.9098440065681445, "stage": "improve", "created_at": 1789523367.3465884}, {"event_id": "be1e40a24a5343789cc9ecca8a2e6643", "step": 10, "value": 0.9209441707717569, "stage": "improve", "created_at": 1789523486.2321012}, {"event_id": "12421d1750e746eab18aef85d4917887", "step": 11, "value": 0.9299261083743843, "stage": "improve", "created_at": 1789523686.327774}, {"event_id": "f278ed772ba04f8b83e2b74c1a93f794", "step": 12, "value": 0.9291050903119868, "stage": "improve", "created_at": 1789523867.8029332}, {"event_id": "dc917daecf1f4551b415fdbdc89b2230", "step": 16, "value": 0.9157060755336617, "stage": "improve", "created_at": 1789524166.3376698}, {"event_id": "ccd733080096436b9a7714b9acf6856f", "step": 18, "value": 0.9259031198686372, "stage": "improve", "created_at": 1789523687.7328784}, {"event_id": "0a2173debc4948debbf09706653bb195", "step": 19, "value": 0.9529228243021346, "stage": "evolution", "created_at": 1789524644.2715018}, {"event_id": "c61bc484ae924c95a25f83537001865b", "step": 21, "value": 0.9320032840722496, "stage": "evolution", "created_at": 1789524789.8940413}, {"event_id": "69bf989673e04c1c95be2f2cc6157f86", "step": 22, "value": 0.9469293924466339, "stage": "debug", "created_at": 1789525467.2263017}, {"event_id": "9a691fece68f4b5cb5520c950fcfd5fa", "step": 23, "value": 0.9563464696223318, "stage": "improve", "created_at": 1789525287.3894272}, {"event_id": "e9a58c584c1d4de0a3144eacd1d7cb60", "step": 24, "value": 0.9527504105090312, "stage": "improve", "created_at": 1789525723.8011062}, {"event_id": "d4b5a48425194b949bb0e50dd1a0ea1b", "step": 26, "value": 0.9554597701149425, "stage": "improve", "created_at": 1789525973.9334927}, {"event_id": "dffbbb8921a141e88580213ea485e682", "step": 28, "value": 0.9294991789819376, "stage": "debug", "created_at": 1789526839.2320817}, {"event_id": "ea5eae518e344142ba2b5db32c7f64bd", "step": 29, "value": 0.9578571428571429, "stage": "improve", "created_at": 1789527095.4847093}, {"event_id": "b3a134e65d6247c28d4cdd578de68451", "step": 31, "value": 0.5, "stage": "debug", "created_at": 1789527801.9971876}, {"event_id": "622afac4b95d424798ea18ca4fcb7086", "step": 32, "value": 0.9555418719211823, "stage": "debug", "created_at": 1789528191.691174}, {"event_id": "a9c1110c51cd46fbb8823888be195587", "step": 33, "value": 0.9539696223316914, "stage": "improve", "created_at": 1789528241.5751286}, {"event_id": "dc09d0f1f0964a83a77a05dff442ee74", "step": 34, "value": 0.9550656814449918, "stage": "improve", "created_at": 1789528532.901198}, {"event_id": "b36d1d57f33e4dd5a33ab4a71facde9e", "step": 36, "value": 0.9555254515599343, "stage": "improve", "created_at": 1789528907.55064}, {"event_id": "a185df42974c4722bf716da86a635e77", "step": 37, "value": 0.8917651888341542, "stage": "debug", "created_at": 1789529826.4712405}, {"event_id": "fc80e33054884be18b870ddab001d063", "step": 41, "value": 0.9553776683087027, "stage": "evolution", "created_at": 1789529953.5930498}, {"event_id": "4e152e8d0bf2439aa09256a184af8d5e", "step": 42, "value": 0.9580952380952381, "stage": "evolution", "created_at": 1789528919.9152021}, {"event_id": "f79b9d8497734596acd7f745fa5e27f7", "step": 43, "value": 0.9552709359605911, "stage": "evolution", "created_at": 1789531336.174166}, {"event_id": "a904eae56e6a406184c8758a4903cca1", "step": 44, "value": 0.9314860426929392, "stage": "improve", "created_at": 1789531437.9001951}, {"event_id": "f026a9d780774afdb51bdc876f8b903e", "step": 45, "value": 0.9540722495894909, "stage": "improve", "created_at": 1789532922.7421727}, {"event_id": "a9442625405040c0820dd6faa15b1d43", "step": 46, "value": 0.9555418719211823, "stage": "debug", "created_at": 1789531090.7214904}, {"event_id": "29902fb431a24709a39be28cb1a379bc", "step": 50, "value": 0.9555500821018064, "stage": "evolution", "created_at": 1789534611.4348443}, {"event_id": "0e49ce9c24a24c74b815c4c1093bbc5c", "step": 52, "value": 0.9482183908045977, "stage": "improve", "created_at": 1789534490.8517342}, {"event_id": "1be1d8659ba64c29b8da6d0caff05005", "step": 53, "value": 0.9588998357963875, "stage": "debug", "created_at": 1789535563.9978616}, {"event_id": "7deaf2f77e5e47fd8caa792e86533e77", "step": 54, "value": 0.9574548440065682, "stage": "debug", "created_at": 1789535921.603619}, {"event_id": "1e6416633b944b6f85e60746f2a0539b", "step": 55, "value": 0.9583333333333334, "stage": "improve", "created_at": 1789538592.2817726}, {"event_id": "398fd86cf7d9458fbe626dfbaa9ac7b7", "step": 56, "value": 0.9563054187192119, "stage": "improve", "created_at": 1789540580.2376282}, {"event_id": "7a94d84eb7ef4da186d449083d16ab9b", "step": 57, "value": 0.9592282430213465, "stage": "improve", "created_at": 1789537157.7868922}, {"event_id": "3ebb7f65238648f88f44bf05d6cbad69", "step": 58, "value": 0.9580213464696222, "stage": "evolution", "created_at": 1789542520.8222036}, {"event_id": "542681cdd3cb4bf6bdd492a3ae7c649d", "step": 59, "value": 0.952487684729064, "stage": "evolution", "created_at": 1789536018.649981}, {"event_id": "d6ad8f72f065486e845158802db12ad6", "step": 60, "value": 0.9542692939244664, "stage": "improve", "created_at": 1789544292.844731}, {"event_id": "b5e79548c66a4deea446e7f447b88c1d", "step": 61, "value": 0.9411986863711, "stage": "improve", "created_at": 1789545189.4145443}, {"event_id": "69bfc427f774404496ac23ae0d81254c", "step": 62, "value": 0.9543185550082102, "stage": "improve", "created_at": 1789543676.9161963}, {"event_id": "e1d8e55c3db74e7fa9f5f83c9d7fcf3b", "step": 63, "value": 0.9567816091954023, "stage": "evolution", "created_at": 1789546750.9745433}, {"event_id": "c865cb172f5d4ababc5e01b62d40c3d2", "step": 64, "value": 0.9554761904761906, "stage": "evolution", "created_at": 1789546121.040056}], "maximize": true, "elapsed_seconds": 28798.432750940323, "node_count": 66, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-three-20260916/xixian.gp7-long-horizon-logei.detecting-insults-in-social-commentary.yaml", "note": ""}, {"id": "xixian.gp7-long-horizon-logei.dog-breed-identification", "experiment_id": "mlebench-gp7-three-20260916", "family": "MLEBench", "method": "gp7_long_horizon_logei", "dataset": "dog-breed-identification", "status": "archived", "official_score": 0.3973, "medal": "none", "valid_submission": true, "score_maximize": false, "thresholds": {"gold": 0.0005, "silver": 0.00539, "bronze": 0.04598}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/results/private_grades.jsonl:27", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}, {"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/runs/gp7_long_horizon_logei/05_dog-breed-identification/logs/journal.json", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}], "alternate_scores": [], "journal_ref": "gp7-three-bo-analysis-20260916:gp7-three-66-runs/runs/gp7_long_horizon_logei/05_dog-breed-identification/logs/journal.json", "metrics": [{"event_id": "71580928b9234577bb3c8f24c59199cf", "step": 3, "value": 0.4514973328213347, "stage": "draft", "created_at": 1789522772.5625958}, {"event_id": "190a8f927cde4fa685ff8d225c3fc3cd", "step": 5, "value": 0.40779278641005595, "stage": "draft", "created_at": 1789522102.2173321}, {"event_id": "1403060b93c24372a40eee8db54398f7", "step": 7, "value": 2.2309522949528584, "stage": "debug", "created_at": 1789523112.4244952}, {"event_id": "d3a4cc34c49b498b91a2ce63f6fc2eb2", "step": 8, "value": 0.44700045160128987, "stage": "debug", "created_at": 1789524080.0098855}, {"event_id": "b415faa6072a41609288ac6f8063bbf8", "step": 9, "value": 0.4681337721830777, "stage": "debug", "created_at": 1789524593.864551}, {"event_id": "cf3436a9134444259cf83e5db6fd5b19", "step": 10, "value": 0.44736112592706484, "stage": "improve", "created_at": 1789525046.6826496}, {"event_id": "8a33e487c6814c5781e6e840344e2208", "step": 11, "value": 0.4266967959972344, "stage": "improve", "created_at": 1789526774.5735314}, {"event_id": "296a35aa39124a6494080b36d66ba814", "step": 12, "value": 0.43003799745776755, "stage": "improve", "created_at": 1789525666.330421}, {"event_id": "601c98fc77094765a619e4b2bf71db93", "step": 13, "value": 0.4173786838814061, "stage": "improve", "created_at": 1789538438.285426}, {"event_id": "a0ce7d721d72459780d4f82272cb8e71", "step": 14, "value": 0.42094858551998954, "stage": "improve", "created_at": 1789527769.644671}, {"event_id": "9d4a5ee2cfb84a01b8b340b3126788ac", "step": 15, "value": 0.3999693706136994, "stage": "improve", "created_at": 1789530159.3214903}, {"event_id": "e6036341d8e647368c1755c743a8c6d4", "step": 16, "value": 0.37573417978525625, "stage": "improve", "created_at": 1789540967.5521643}, {"event_id": "d88a1e0583a946ef9fa67c17342bcba2", "step": 18, "value": 0.3720814318767362, "stage": "improve", "created_at": 1789543607.1828787}, {"event_id": "df028d858ffa47efbbfd14a85ae3d202", "step": 19, "value": 0.6866445429279325, "stage": "fusion_draft", "created_at": 1789547866.9624405}], "maximize": false, "elapsed_seconds": 28805.42104244232, "node_count": 23, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-three-20260916/xixian.gp7-long-horizon-logei.dog-breed-identification.yaml", "note": ""}, {"id": "xixian.gp7-long-horizon-logei.dogs-vs-cats-redux-kernels-edition", "experiment_id": "mlebench-gp7-three-20260916", "family": "MLEBench", "method": "gp7_long_horizon_logei", "dataset": "dogs-vs-cats-redux-kernels-edition", "status": "archived", "official_score": 0.00289, "medal": "gold", "valid_submission": true, "score_maximize": false, "thresholds": {"gold": 0.03882, "silver": 0.05038, "bronze": 0.06127}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/results/private_grades.jsonl:28", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}, {"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/runs/gp7_long_horizon_logei/06_dogs-vs-cats-redux-kernels-edition/logs/journal.json", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}], "alternate_scores": [], "journal_ref": "gp7-three-bo-analysis-20260916:gp7-three-66-runs/runs/gp7_long_horizon_logei/06_dogs-vs-cats-redux-kernels-edition/logs/journal.json", "metrics": [{"event_id": "97d70171dbad4afb8d4c77632917ec74", "step": 2, "value": 0.003181836825071791, "stage": "draft", "created_at": 1789522435.8487532}, {"event_id": "f9913a37339f4f4682fadd3793940fe3", "step": 3, "value": 0.003958156203662259, "stage": "debug", "created_at": 1789522957.6982594}, {"event_id": "7136af9163304626a37a118b5dbe29b9", "step": 4, "value": 0.003154026488442023, "stage": "draft", "created_at": 1789522735.3203394}, {"event_id": "39b4e86947a4462f941a2bac5aec4d11", "step": 6, "value": 0.0034086001161368635, "stage": "improve", "created_at": 1789523561.1791246}, {"event_id": "611e2c0ba26a4813b0caf0b938014aec", "step": 7, "value": 0.003998737246237634, "stage": "debug", "created_at": 1789523816.4690652}, {"event_id": "4ee9078e133f4f9db62bf45e37fe8b93", "step": 8, "value": 0.003832458860539297, "stage": "improve", "created_at": 1789524141.5546098}, {"event_id": "b09d6599ea2b42cba3da3a75307f4e8b", "step": 9, "value": 0.0049938272253442694, "stage": "improve", "created_at": 1789523169.7903595}, {"event_id": "9b31ba8c8991499aa42e622f20aad9bf", "step": 10, "value": 0.003990975588004748, "stage": "improve", "created_at": 1789524851.2402942}, {"event_id": "2c4adc881c6a444f8fcbb9494f8fa525", "step": 11, "value": 0.005236209309393902, "stage": "improve", "created_at": 1789524812.375986}, {"event_id": "c8a8d561b06547b98290f1f78e05ae4f", "step": 12, "value": 0.0033588857141179707, "stage": "improve", "created_at": 1789525444.8627698}, {"event_id": "da13021a16a14625ad9735de7764aa51", "step": 13, "value": 0.004432503011541136, "stage": "improve", "created_at": 1789524852.9048822}, {"event_id": "4066f9ef30cd425bb2808249a2dffacf", "step": 14, "value": 0.013849525200180329, "stage": "improve", "created_at": 1789525467.018012}, {"event_id": "49a99b65d5834d30b80e14c28c551987", "step": 15, "value": 0.0034935176208912267, "stage": "improve", "created_at": 1789525934.0673482}, {"event_id": "ef202e121a6c41f8b77a14eeda2c677a", "step": 16, "value": 0.003617032930738533, "stage": "evolution", "created_at": 1789526042.2555187}, {"event_id": "5302fec7f51047c492ab31dbdf0fe829", "step": 17, "value": 0.0031741214880303147, "stage": "improve", "created_at": 1789525784.001544}, {"event_id": "1fd5b262799d4585be0f97b10e6414e9", "step": 19, "value": 0.8353274356606409, "stage": "debug", "created_at": 1789526780.2999709}, {"event_id": "0eb50d7e05c542e3a0dfbd9be56c53d6", "step": 20, "value": 0.003057405999292871, "stage": "improve", "created_at": 1789526605.4469123}, {"event_id": "33c544f472a64f83b016d884b8b8f392", "step": 21, "value": 0.002086020335688552, "stage": "improve", "created_at": 1789526664.8184578}, {"event_id": "2bc2ddbd742c4d9b9110c6fa2fbfed44", "step": 23, "value": 0.0014331368061005361, "stage": "improve", "created_at": 1789527444.279753}, {"event_id": "d7e612fca0f9435c80397938d1e6bbe7", "step": 24, "value": 0.0020344375032028744, "stage": "improve", "created_at": 1789527946.7372992}, {"event_id": "d9c858f482474c36a427da7d8ddb81c9", "step": 25, "value": 0.0024957858823268543, "stage": "debug", "created_at": 1789528288.92352}, {"event_id": "b68deef46a524fe381509ca0fcd080c0", "step": 27, "value": 0.0018668310225796057, "stage": "improve", "created_at": 1789529562.9324858}, {"event_id": "f398e6629ba342208d042148e83c58b3", "step": 28, "value": 0.0037441978147098715, "stage": "debug", "created_at": 1789530410.321981}, {"event_id": "d92928d9870d4dc0a5e65ecd9cab0906", "step": 29, "value": 0.0022575041092011074, "stage": "evolution", "created_at": 1789531582.096665}, {"event_id": "6db93092851149ea91bf612e21f3973c", "step": 30, "value": 0.0018668310225796057, "stage": "improve", "created_at": 1789530698.2042675}, {"event_id": "2c1448c9929f4c63848bac6d90995df4", "step": 32, "value": 0.0024663039543893653, "stage": "debug", "created_at": 1789533090.5215654}, {"event_id": "ec354a6d37e44a67b6db5df629e32797", "step": 35, "value": 0.00199364310505049, "stage": "evolution", "created_at": 1789532982.9737632}, {"event_id": "d551d29e2b48423e8357bd15f29e6849", "step": 36, "value": 0.0051106325712272915, "stage": "debug", "created_at": 1789534819.8590162}, {"event_id": "7706bea9d15547f58755fd816740acb9", "step": 37, "value": 0.003294235586278496, "stage": "improve", "created_at": 1789528582.2606957}, {"event_id": "5a2ba7441f884eb5a659793923490d32", "step": 38, "value": 0.001620151740175994, "stage": "evolution", "created_at": 1789537449.6058512}, {"event_id": "e81c06be16844e34b6170ec96bc14f5b", "step": 39, "value": 0.002439981189910822, "stage": "evolution", "created_at": 1789537078.6148992}, {"event_id": "7190d499188048dba0cda6f6d4fc59bd", "step": 40, "value": 0.0027864730454814917, "stage": "evolution", "created_at": 1789537385.594297}, {"event_id": "6a9289b81a244b2a8adb72a78c9613fa", "step": 41, "value": 0.021336706496326626, "stage": "evolution", "created_at": 1789541271.1159945}, {"event_id": "fbe6d19395a04d0a83bf44505a2ecdb1", "step": 42, "value": 0.0014331368061005361, "stage": "evolution", "created_at": 1789542478.3791304}, {"event_id": "64f6456326d04b1ab5e9ad040083f041", "step": 43, "value": 0.002307524390842963, "stage": "fusion", "created_at": 1789539012.3679066}, {"event_id": "ed4e687a4af645ff86ebba30d6cf3481", "step": 45, "value": 0.0014331368061005361, "stage": "improve", "created_at": 1789544471.8594148}, {"event_id": "1a617a11025a4d548768df3ae645d6e2", "step": 46, "value": 0.0016648203397067124, "stage": "debug", "created_at": 1789544274.4465988}, {"event_id": "98e9c48a2317408bb5b93dcf9f610580", "step": 47, "value": 0.002413659827309026, "stage": "fusion", "created_at": 1789540633.4858105}, {"event_id": "b73c253798d04bd3bfad6e0e035f7be2", "step": 48, "value": 0.00797031776526508, "stage": "improve", "created_at": 1789545629.9793587}, {"event_id": "3b3344673f824fc38b338767942d8d95", "step": 50, "value": 0.0030722596233755737, "stage": "improve", "created_at": 1789546477.142316}, {"event_id": "fab2a041f4e448a0a996a5602af7ac3b", "step": 51, "value": 0.0015946461607384821, "stage": "improve", "created_at": 1789546674.131395}, {"event_id": "4c64e1c2baf342cf871e7e4057febde4", "step": 55, "value": 0.0016451513955701264, "stage": "debug", "created_at": 1789548417.6877968}, {"event_id": "7f0080db474f410ca2ad3c1cd8fc48db", "step": 56, "value": 0.006194961239838201, "stage": "debug", "created_at": 1789549315.5978663}], "maximize": false, "elapsed_seconds": 28796.72275876999, "node_count": 58, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-three-20260916/xixian.gp7-long-horizon-logei.dogs-vs-cats-redux-kernels-edition.yaml", "note": ""}, {"id": "xixian.gp7-long-horizon-logei.histopathologic-cancer-detection", "experiment_id": "mlebench-gp7-three-20260916", "family": "MLEBench", "method": "gp7_long_horizon_logei", "dataset": "histopathologic-cancer-detection", "status": "archived", "official_score": 0.99541, "medal": "gold", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.9835, "silver": 0.9798, "bronze": 0.9738}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/results/private_grades.jsonl:29", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}, {"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/runs/gp7_long_horizon_logei/07_histopathologic-cancer-detection/logs/journal.json", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}], "alternate_scores": [], "journal_ref": "gp7-three-bo-analysis-20260916:gp7-three-66-runs/runs/gp7_long_horizon_logei/07_histopathologic-cancer-detection/logs/journal.json", "metrics": [{"event_id": "08643f7e98ac4f48abe10bd4192f40ae", "step": 1, "value": 0.9845538682459796, "stage": "draft", "created_at": 1789522846.845892}, {"event_id": "3fa402a46baa4960bbaa3aa3003dabf7", "step": 2, "value": 0.9829881244532976, "stage": "improve", "created_at": 1789525260.4278982}, {"event_id": "5e3917db02c4443285c3bfb12e0f34bf", "step": 3, "value": 0.9930907143417669, "stage": "draft", "created_at": 1789523227.1385086}, {"event_id": "87297eea254f436f9c15bb174b2ccb63", "step": 4, "value": 0.9948798613512373, "stage": "draft", "created_at": 1789523585.5233312}, {"event_id": "33717ebba068420a883fa6b07d9371ad", "step": 5, "value": 0.9928034334138466, "stage": "improve", "created_at": 1789527655.950262}, {"event_id": "58477496ce8d4918a68f8fe4bad0a8b1", "step": 6, "value": 0.9953551101582465, "stage": "improve", "created_at": 1789529175.8596523}], "maximize": true, "elapsed_seconds": 28795.951303482056, "node_count": 7, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-three-20260916/xixian.gp7-long-horizon-logei.histopathologic-cancer-detection.yaml", "note": ""}, {"id": "xixian.gp7-long-horizon-logei.jigsaw-toxic-comment-classification-challenge", "experiment_id": "mlebench-gp7-three-20260916", "family": "MLEBench", "method": "gp7_long_horizon_logei", "dataset": "jigsaw-toxic-comment-classification-challenge", "status": "archived", "official_score": 0.98608, "medal": "none", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.9874, "silver": 0.98668, "bronze": 0.98639}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/results/private_grades.jsonl:30", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}, {"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/runs/gp7_long_horizon_logei/08_jigsaw-toxic-comment-classification-challenge/logs/journal.json", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}], "alternate_scores": [], "journal_ref": "gp7-three-bo-analysis-20260916:gp7-three-66-runs/runs/gp7_long_horizon_logei/08_jigsaw-toxic-comment-classification-challenge/logs/journal.json", "metrics": [{"event_id": "932e10b1514044179d67bcf87f7b9de6", "step": 3, "value": 0.990950582738377, "stage": "debug", "created_at": 1789522975.4957573}, {"event_id": "b5eb5b6e784341b3a1b3c1cd0ba26711", "step": 5, "value": 0.9142889367664933, "stage": "draft", "created_at": 1789522857.1765153}, {"event_id": "1615d17b77e548afabbd90da682e750b", "step": 8, "value": 0.9919442068163286, "stage": "debug", "created_at": 1789526499.3180044}, {"event_id": "95cf35f1d98a40fc97113acb220da91a", "step": 10, "value": 0.9914176635873299, "stage": "debug", "created_at": 1789530701.2290194}, {"event_id": "a00d85e5c4394c9280e85caf5264e2b6", "step": 11, "value": 0.9912508873083187, "stage": "debug", "created_at": 1789535150.7946417}, {"event_id": "6be8067e50be41149092c2defa8e2869", "step": 12, "value": 0.9850495453088142, "stage": "improve", "created_at": 1789533349.129441}, {"event_id": "8f1808fc2f764f7583ac9a24b3f7b35e", "step": 13, "value": 0.987726269657303, "stage": "improve", "created_at": 1789540987.5930588}, {"event_id": "a2f5604561cc434ab0d7efe6bb686071", "step": 14, "value": 0.9871695324073064, "stage": "improve", "created_at": 1789537179.3175666}, {"event_id": "60edc32635a84eebb8543b41e07947b5", "step": 15, "value": 0.9920824464384727, "stage": "improve", "created_at": 1789539594.534421}], "maximize": true, "elapsed_seconds": 28795.40893292427, "node_count": 20, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-three-20260916/xixian.gp7-long-horizon-logei.jigsaw-toxic-comment-classification-challenge.yaml", "note": ""}, {"id": "xixian.gp7-long-horizon-logei.leaf-classification", "experiment_id": "mlebench-gp7-three-20260916", "family": "MLEBench", "method": "gp7_long_horizon_logei", "dataset": "leaf-classification", "status": "archived", "official_score": 0.00633, "medal": "silver", "valid_submission": true, "score_maximize": false, "thresholds": {"gold": 0.0, "silver": 0.00791, "bronze": 0.01526}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/results/private_grades.jsonl:31", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}, {"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/runs/gp7_long_horizon_logei/09_leaf-classification/logs/journal.json", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}], "alternate_scores": [], "journal_ref": "gp7-three-bo-analysis-20260916:gp7-three-66-runs/runs/gp7_long_horizon_logei/09_leaf-classification/logs/journal.json", "metrics": [{"event_id": "d0326a38fa7b441681bd9d729d2a35e2", "step": 4, "value": 2.3264587640165306, "stage": "debug", "created_at": 1789523021.2728665}, {"event_id": "077750b0790d4b5e82cd86744831f1dd", "step": 6, "value": 1.419589551924649, "stage": "improve", "created_at": 1789523633.3470623}, {"event_id": "c5012640ab194ad08b326e0f88ad949f", "step": 7, "value": 0.0031853040393883376, "stage": "debug", "created_at": 1789523081.3320842}, {"event_id": "91179d3c739a4894a36d1848a7f505f9", "step": 8, "value": 0.15106595220700295, "stage": "debug", "created_at": 1789523829.8303778}, {"event_id": "63997e5de90c4da99bb8ca43d111c7d6", "step": 9, "value": 1.7760462854647112, "stage": "improve", "created_at": 1789524343.6195667}], "maximize": false, "elapsed_seconds": 28803.153406858444, "node_count": 17, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-three-20260916/xixian.gp7-long-horizon-logei.leaf-classification.yaml", "note": ""}, {"id": "xixian.gp7-long-horizon-logei.mlsp-2013-birds", "experiment_id": "mlebench-gp7-three-20260916", "family": "MLEBench", "method": "gp7_long_horizon_logei", "dataset": "mlsp-2013-birds", "status": "archived", "official_score": 0.89432, "medal": "bronze", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.93527, "silver": 0.90038, "bronze": 0.87372}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/results/private_grades.jsonl:32", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}, {"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/runs/gp7_long_horizon_logei/10_mlsp-2013-birds/logs/journal.json", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}], "alternate_scores": [], "journal_ref": "gp7-three-bo-analysis-20260916:gp7-three-66-runs/runs/gp7_long_horizon_logei/10_mlsp-2013-birds/logs/journal.json", "metrics": [{"event_id": "58efbc9485b24338bb286a9aea027331", "step": 5, "value": 0.6308087731322823, "stage": "debug", "created_at": 1789523343.4336548}, {"event_id": "c7c836050aa24b5aa2e4405e4b2609d4", "step": 10, "value": 0.6555945853324194, "stage": "debug", "created_at": 1789523727.213716}, {"event_id": "ca738e4298884ddea430528f05fae8fd", "step": 13, "value": 0.7884981151473612, "stage": "debug", "created_at": 1789523786.4930866}, {"event_id": "bff03b74a9824ac1b77d3128dced8b88", "step": 14, "value": 0.6830363262508568, "stage": "improve", "created_at": 1789524122.6349185}, {"event_id": "881286f9301c42828b76322c25dfa501", "step": 15, "value": 0.6919465387251542, "stage": "improve", "created_at": 1789524347.380561}, {"event_id": "92cca3fe105b4279b6542664b7f90853", "step": 17, "value": 0.7832633653187113, "stage": "improve", "created_at": 1789524468.1969419}, {"event_id": "03cd8f4e610f421ab34577a1813ce978", "step": 19, "value": 0.782993488690884, "stage": "improve", "created_at": 1789524841.7298183}, {"event_id": "ac4147a9e8334c41a7832359e5d69f38", "step": 20, "value": 0.785957847840987, "stage": "improve", "created_at": 1789525151.5501885}, {"event_id": "f16bfd8431464c84809b35217cca1e27", "step": 21, "value": 0.7598269362577108, "stage": "improve", "created_at": 1789525609.2509701}, {"event_id": "a91e6a2b9df546ab9f6e661ccf042f69", "step": 22, "value": 0.7897189856065798, "stage": "debug", "created_at": 1789525319.9220397}, {"event_id": "ff66f53cb28244c3a2f6ea38736f782c", "step": 26, "value": 0.7963759424263195, "stage": "improve", "created_at": 1789526550.8805237}, {"event_id": "92762c270ef9414583074f3b3f5ed204", "step": 28, "value": 0.8079763536668951, "stage": "debug", "created_at": 1789527923.3864408}, {"event_id": "862fe16d17df434aa4a6e081ee191042", "step": 29, "value": 0.793051747772447, "stage": "improve", "created_at": 1789527870.7960994}, {"event_id": "a109974009de42eb9cba24eb4c8c6a3b", "step": 30, "value": 0.8167237834132969, "stage": "improve", "created_at": 1789529042.5005774}, {"event_id": "e7fb96eae5f94cc98911e26623e71bbe", "step": 32, "value": 0.7665267306374229, "stage": "debug", "created_at": 1789527613.090675}, {"event_id": "97d67d089d944936b3f9a7c8e4484065", "step": 41, "value": 0.803795407813571, "stage": "debug", "created_at": 1789532138.7200968}, {"event_id": "848f4d51b2e94b2c9213f81e71e5de53", "step": 44, "value": 0.7836274845784784, "stage": "improve", "created_at": 1789534049.0565631}, {"event_id": "f93d02b6893b423086bbadbfb4962294", "step": 45, "value": 0.7898132282385195, "stage": "debug", "created_at": 1789535057.470194}, {"event_id": "f2facdeb26b74cf68b851cdfbe29a7f0", "step": 46, "value": 0.8052733036326251, "stage": "improve", "created_at": 1789535668.3182597}, {"event_id": "88d8c01cd35a45e98fd6828f0dcd730e", "step": 47, "value": 0.778101439342015, "stage": "improve", "created_at": 1789536869.0872664}, {"event_id": "db34ae0e7a484ada9db68aaba9c6ddb5", "step": 48, "value": 0.7014607607950651, "stage": "draft", "created_at": 1789537969.6984615}, {"event_id": "e85efa3ea6d24c47aa4c5de43637a771", "step": 51, "value": 0.7938056888279644, "stage": "evolution", "created_at": 1789538111.0528035}, {"event_id": "ec509b26e08c4aadaa2719a64b8b6f20", "step": 52, "value": 0.8233893077450308, "stage": "evolution", "created_at": 1789539082.6845412}, {"event_id": "cf0d9011194941359be60882a2018f1c", "step": 53, "value": 0.7587217272104182, "stage": "debug", "created_at": 1789539110.6744342}, {"event_id": "f1b9640e77bc4a00b42c713faa70eb76", "step": 54, "value": 0.8093642906100068, "stage": "fusion", "created_at": 1789540179.7367523}, {"event_id": "212e192d3b4741cba039947a436bbea7", "step": 56, "value": 0.8246744345442083, "stage": "improve", "created_at": 1789540957.708256}, {"event_id": "70e26d2132784ea89b75332b72c1ca2c", "step": 57, "value": 0.8140678546949965, "stage": "improve", "created_at": 1789541288.2073474}, {"event_id": "a68e5748f0254d46a22d3eed756cbbab", "step": 58, "value": 0.8125771076079507, "stage": "debug", "created_at": 1789541843.3090625}, {"event_id": "8cd752b626f94ba9b8faf97e76c07362", "step": 59, "value": 0.822181288553804, "stage": "improve", "created_at": 1789542848.8986497}, {"event_id": "a1fb2d95de9f4d4d872d92a32f2ebecb", "step": 60, "value": 0.8167237834132968, "stage": "improve", "created_at": 1789543204.4935043}, {"event_id": "a1c4a32c603147bd843daadad738db26", "step": 62, "value": 0.8235520904729267, "stage": "improve", "created_at": 1789544099.191998}, {"event_id": "bacf0b746e8840d99e05a45abc7a1648", "step": 63, "value": 0.8027244688142563, "stage": "improve", "created_at": 1789545041.285166}, {"event_id": "ddccae045eb54c808105c8de2999a356", "step": 65, "value": 0.7657813570939, "stage": "debug", "created_at": 1789545655.662897}, {"event_id": "a50231e85c4742f98ddda98cbe1d08c7", "step": 66, "value": 0.6239804660726525, "stage": "fusion_draft", "created_at": 1789546767.133658}, {"event_id": "385781d7fe6948649c36b03e49dd36b4", "step": 68, "value": 0.789539067854695, "stage": "evolution", "created_at": 1789546031.7074673}, {"event_id": "b6fdf815fdeb4a19a949f91e31cb42e5", "step": 70, "value": 0.7953050034270047, "stage": "fusion", "created_at": 1789546956.8834593}, {"event_id": "248f2cf6620c4d63ba36130038861acb", "step": 71, "value": 0.8179318026045236, "stage": "evolution", "created_at": 1789547674.2234333}, {"event_id": "f3fa06abeaba45e98f794a6f3bb4aeea", "step": 73, "value": 0.8153444139821794, "stage": "debug", "created_at": 1789548121.2634609}], "maximize": true, "elapsed_seconds": 28797.177559137344, "node_count": 76, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-three-20260916/xixian.gp7-long-horizon-logei.mlsp-2013-birds.yaml", "note": ""}, {"id": "xixian.gp7-long-horizon-logei.new-york-city-taxi-fare-prediction", "experiment_id": "mlebench-gp7-three-20260916", "family": "MLEBench", "method": "gp7_long_horizon_logei", "dataset": "new-york-city-taxi-fare-prediction", "status": "archived", "official_score": 4.43022, "medal": "none", "valid_submission": true, "score_maximize": false, "thresholds": {"gold": 2.83377, "silver": 2.88191, "bronze": 2.92371}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/results/private_grades.jsonl:33", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}, {"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/runs/gp7_long_horizon_logei/11_new-york-city-taxi-fare-prediction/logs/journal.json", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}], "alternate_scores": [], "journal_ref": "gp7-three-bo-analysis-20260916:gp7-three-66-runs/runs/gp7_long_horizon_logei/11_new-york-city-taxi-fare-prediction/logs/journal.json", "metrics": [{"event_id": "6ef54a69c232475e954a2025e1c87cd8", "step": 1, "value": 7.063928369419729, "stage": "draft", "created_at": 1789523085.5199242}, {"event_id": "222da94ba8784b0ab5d6cfcee9635eda", "step": 2, "value": 5.730138590177686, "stage": "draft", "created_at": 1789522286.248672}, {"event_id": "abaf05dda5d2400ebed41c809c313edd", "step": 3, "value": 5.121103262380428, "stage": "improve", "created_at": 1789523582.2845657}, {"event_id": "d28b51f56456482e9818f8298c24f0a5", "step": 5, "value": 5.417446928453276, "stage": "debug", "created_at": 1789524472.3082538}, {"event_id": "2c1f6077a38b4bd1807582f967ec8f64", "step": 6, "value": 5.057565200817678, "stage": "improve", "created_at": 1789524248.7261784}, {"event_id": "1f8ece3e2e9446968b02782ed7746f04", "step": 7, "value": 8.786568232836894, "stage": "improve", "created_at": 1789525123.8933756}, {"event_id": "310f277c4d3a42f4abfbba3d71385a7a", "step": 8, "value": 5.030644161114645, "stage": "improve", "created_at": 1789525657.4490535}, {"event_id": "2b33339ddcb440aea4598130f425d25e", "step": 9, "value": 5.098744606342496, "stage": "improve", "created_at": 1789526230.6569743}, {"event_id": "334cc29a59274c7bbd39de43efbb2585", "step": 10, "value": 6.615177174133526, "stage": "improve", "created_at": 1789527449.0238411}, {"event_id": "dc150e20aaaa47159909db875fd015f7", "step": 11, "value": 4.762503895328117, "stage": "improve", "created_at": 1789526958.9887877}, {"event_id": "e3a341cbf17542a58ccc81ea52ab2954", "step": 12, "value": 10.107584187206863, "stage": "improve", "created_at": 1789528693.3229067}, {"event_id": "54f17764e34f4ad58b4102ab9cc92062", "step": 13, "value": 4.759662691709561, "stage": "improve", "created_at": 1789528557.831431}, {"event_id": "7dc5a8c38cd54422963e18f1934df140", "step": 14, "value": 9.530245409104984, "stage": "improve", "created_at": 1789529820.1658678}, {"event_id": "98a6b734df1a40d895e6938bfdda6bd5", "step": 15, "value": 9.283511628685606, "stage": "improve", "created_at": 1789529953.4981525}, {"event_id": "5cd8b8e7205a4478a27186684ab10750", "step": 16, "value": 5.65132941059032, "stage": "improve", "created_at": 1789530542.6349602}, {"event_id": "804c71fa070a4c25aa148fbe7d223093", "step": 17, "value": 6.131132078200128, "stage": "improve", "created_at": 1789531393.0727792}, {"event_id": "82a42e2764824b4e91e08b21f7dbb713", "step": 19, "value": 4.889699638409642, "stage": "debug", "created_at": 1789534921.8980076}, {"event_id": "5be35d43caa94ecfa28d9337060e08af", "step": 20, "value": 4.946605812314693, "stage": "improve", "created_at": 1789536023.8382804}, {"event_id": "269d632526b444728c5d162c5e291656", "step": 23, "value": 5.78483117065006, "stage": "evolution", "created_at": 1789532315.9819598}, {"event_id": "ef59e2e705a04aa18e3658c767f5674b", "step": 24, "value": 21.920184138504595, "stage": "improve", "created_at": 1789536724.1610124}, {"event_id": "f7a0dcee0a5b4c54a3517eb5cf6f766f", "step": 25, "value": 4.837677503344312, "stage": "improve", "created_at": 1789537796.6179268}, {"event_id": "84476a4e1f5247aebc1a09badeeed8bc", "step": 26, "value": 21.870836503287403, "stage": "improve", "created_at": 1789537705.1085029}, {"event_id": "ed6e3db1c60349a5bcd32faa7541bd2c", "step": 27, "value": 4.90073394004397, "stage": "improve", "created_at": 1789539184.0853925}, {"event_id": "315cfc99aa0143d59837d27d2cf6ef7b", "step": 28, "value": 5.43548076433574, "stage": "improve", "created_at": 1789538831.5390794}, {"event_id": "49f874aa717e456199811648828b76c0", "step": 29, "value": 4.803005449704852, "stage": "evolution", "created_at": 1789540841.3523915}, {"event_id": "859518fd54c64a84a9a1ce1ae27d6462", "step": 30, "value": 4.706541867311193, "stage": "improve", "created_at": 1789540792.2468746}, {"event_id": "c2c5a5b506bc42159334cc86e3944738", "step": 31, "value": 4.746873587609969, "stage": "improve", "created_at": 1789541955.0202432}, {"event_id": "43f5cd226e35464ca8f80526eb198700", "step": 32, "value": 5.748481737023087, "stage": "improve", "created_at": 1789543257.365972}, {"event_id": "2ca896b7d2c64fea8f7952d1f48c2b89", "step": 34, "value": 4.929005292708343, "stage": "improve", "created_at": 1789542772.7313335}, {"event_id": "0435ae012dbf438f9c58e894e4079960", "step": 35, "value": 4.838445401865656, "stage": "improve", "created_at": 1789544957.888522}, {"event_id": "6794bac9295347dc9f18efe15f1b79a9", "step": 36, "value": 4.838445408261927, "stage": "improve", "created_at": 1789544854.7947097}, {"event_id": "d761cdbb62224fd591e8e791d1809dc5", "step": 37, "value": 10.310114358013793, "stage": "improve", "created_at": 1789545862.2197914}, {"event_id": "a047f483738a4853a2aededc0ee2e2fe", "step": 38, "value": 10.187148233616742, "stage": "improve", "created_at": 1789546497.5106063}, {"event_id": "403913bcf6ba43c78a09bed94fca3bba", "step": 39, "value": 4.823008296980745, "stage": "evolution", "created_at": 1789547571.9258244}, {"event_id": "a5633f2c6c76436a8115ed46bb5b51b0", "step": 41, "value": 34.751755909758096, "stage": "draft", "created_at": 1789549489.6549115}], "maximize": false, "elapsed_seconds": 28795.865642547607, "node_count": 45, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-three-20260916/xixian.gp7-long-horizon-logei.new-york-city-taxi-fare-prediction.yaml", "note": ""}, {"id": "xixian.gp7-long-horizon-logei.nomad2018-predict-transparent-conductors", "experiment_id": "mlebench-gp7-three-20260916", "family": "MLEBench", "method": "gp7_long_horizon_logei", "dataset": "nomad2018-predict-transparent-conductors", "status": "archived", "official_score": 0.13312, "medal": "none", "valid_submission": true, "score_maximize": false, "thresholds": {"gold": 0.05589, "silver": 0.06229, "bronze": 0.06582}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/results/private_grades.jsonl:34", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}, {"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/runs/gp7_long_horizon_logei/12_nomad2018-predict-transparent-conductors/logs/journal.json", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}], "alternate_scores": [], "journal_ref": "gp7-three-bo-analysis-20260916:gp7-three-66-runs/runs/gp7_long_horizon_logei/12_nomad2018-predict-transparent-conductors/logs/journal.json", "metrics": [{"event_id": "ceb6ca349a334f898daebbd743b40702", "step": 11, "value": 0.2915044043820808, "stage": "debug", "created_at": 1789523434.102456}, {"event_id": "2fad4238bbe6487998ec11eb09b286ac", "step": 17, "value": 0.2967705495310326, "stage": "debug", "created_at": 1789524156.1714056}, {"event_id": "b73eaf14a99c4e44a070806f46a57275", "step": 18, "value": 0.22270760676492865, "stage": "debug", "created_at": 1789524144.9970324}, {"event_id": "0022bcf38c374ff98c4cb23f0a1b67bc", "step": 19, "value": 0.292030259692396, "stage": "debug", "created_at": 1789524196.4382925}, {"event_id": "722540664dce4fee9b1a96fbc8615004", "step": 21, "value": 0.2997231186911676, "stage": "debug", "created_at": 1789524633.052289}, {"event_id": "fbbb747dd86a478d97099c35f2a5e1fb", "step": 23, "value": 0.22290693427972127, "stage": "improve", "created_at": 1789524584.3479483}, {"event_id": "68253bd69e2047309a686bab1b26dc9b", "step": 25, "value": 0.2127370402655872, "stage": "improve", "created_at": 1789525121.5830963}, {"event_id": "f0bdb0f7ebcb40dca144e3cd8e309479", "step": 28, "value": 0.2127339713713155, "stage": "improve", "created_at": 1789525561.5184639}, {"event_id": "a0e34a6ff0f64af68db1f1e23308d306", "step": 31, "value": 0.21272858737107123, "stage": "improve", "created_at": 1789526058.411778}, {"event_id": "a148b1c160714cd7b4f05832af68d3b2", "step": 32, "value": 0.1496214760522084, "stage": "debug", "created_at": 1789526433.8373115}, {"event_id": "aaf01adcb98a4e81a7af27bd102dbcba", "step": 34, "value": 0.21274899085981538, "stage": "improve", "created_at": 1789526582.2241871}, {"event_id": "ab6448a66b274a5ba2676bc2bf5a115f", "step": 37, "value": 0.15453812843220982, "stage": "debug", "created_at": 1789527397.9103234}, {"event_id": "2e458bb67bcb4323987652fd6e459490", "step": 40, "value": 0.1571147082562555, "stage": "debug", "created_at": 1789527916.040061}, {"event_id": "f83545bc911f4b78b864d0e5f3e81871", "step": 41, "value": 0.1934402512220813, "stage": "evolution", "created_at": 1789528359.951856}, {"event_id": "4744d25de75649b38b79d3a7aed45260", "step": 45, "value": 0.22334296048174976, "stage": "improve", "created_at": 1789524910.3364925}, {"event_id": "72b31dfc01b345e0b97db3b12be4b937", "step": 46, "value": 0.15455869639349532, "stage": "evolution", "created_at": 1789531126.3805468}, {"event_id": "5f1051f3b82642abb414ba18c18e68fa", "step": 48, "value": 0.17685670857068078, "stage": "evolution", "created_at": 1789531591.7984438}, {"event_id": "8d817c24e3f3422090ea9807c5d41fb8", "step": 49, "value": 0.4188042225074642, "stage": "evolution", "created_at": 1789531634.874177}, {"event_id": "53ee3f777b1c4fe1b02ee826c2cd8b5b", "step": 50, "value": 0.27830060565789727, "stage": "debug", "created_at": 1789528974.0344255}, {"event_id": "fd391ce00d9f44ecb0fdbbb1c06b7581", "step": 51, "value": 0.1545039675013796, "stage": "evolution", "created_at": 1789531898.7565007}, {"event_id": "475435f081964ff3928d5a67c7fb68ba", "step": 52, "value": 0.1751197762637113, "stage": "evolution", "created_at": 1789531911.451177}, {"event_id": "a1d80330083a46df9a5cfa46c8899942", "step": 53, "value": 0.1602679930066967, "stage": "evolution", "created_at": 1789532187.6624167}, {"event_id": "dfbe234bf57c482a9a74db6e18994262", "step": 54, "value": 0.21957108972776682, "stage": "evolution", "created_at": 1789532108.1638317}, {"event_id": "b08a367069ec457db9852588c5ff2963", "step": 55, "value": 0.15435748318392606, "stage": "evolution", "created_at": 1789532188.7915576}, {"event_id": "d4b4544a22b649b99bef3e81f69a3cfc", "step": 57, "value": 0.458166825088561, "stage": "evolution", "created_at": 1789532452.6077347}, {"event_id": "c543be4c4dd54c9ca7b63c781af49679", "step": 59, "value": 0.15451209444659877, "stage": "debug", "created_at": 1789532601.528219}, {"event_id": "5ef61384d8cd4f9bb8324d1c3ed88271", "step": 60, "value": 0.1759657056712125, "stage": "evolution", "created_at": 1789532652.348223}, {"event_id": "358e9c228fa14eebb338b18269eedb53", "step": 62, "value": 0.14277550089426447, "stage": "evolution", "created_at": 1789532826.4686873}, {"event_id": "daaaad51412b4482b039fa96195dab0b", "step": 64, "value": 0.14234133849529512, "stage": "evolution", "created_at": 1789532867.9701273}, {"event_id": "27ef52f07a74484581e2b2f808d0e482", "step": 67, "value": 0.15442845398581975, "stage": "improve", "created_at": 1789533182.5587227}, {"event_id": "45e3ff85e58a4585998c6e657a78d83e", "step": 68, "value": 0.15444580353434173, "stage": "debug", "created_at": 1789533207.3333194}, {"event_id": "4cc20ce4ff8e42468495bb9277d36e9f", "step": 70, "value": 0.1433156941495572, "stage": "improve", "created_at": 1789533725.7798955}, {"event_id": "cc54fa8312fa41c1934e36c91166c813", "step": 72, "value": 0.15448349370842887, "stage": "improve", "created_at": 1789533690.9269452}, {"event_id": "716532963cbe4381bb1b6c1eac46f1f2", "step": 73, "value": 0.14231158397707871, "stage": "evolution", "created_at": 1789534026.5547082}, {"event_id": "0c27076adb414da29b3b05553103d3cc", "step": 75, "value": 0.14449741216532463, "stage": "evolution", "created_at": 1789534199.748631}, {"event_id": "d172a88bcd0a4f14b3270a882540ce6b", "step": 77, "value": 0.45249956348203235, "stage": "debug", "created_at": 1789534540.9355247}, {"event_id": "c9c449122edb4d18995444129c3b03bd", "step": 79, "value": 0.15455455887713118, "stage": "improve", "created_at": 1789534599.5695229}, {"event_id": "7a70218ebc694864b5391f18688a33f5", "step": 81, "value": 0.17472008092575939, "stage": "improve", "created_at": 1789535091.4156895}, {"event_id": "1d0a71d4350f46a8824b3d8b399bb5ef", "step": 82, "value": 0.19737460194683076, "stage": "evolution", "created_at": 1789535064.5227861}, {"event_id": "ebc8e9b4b14f40f0a4e389aa862794a4", "step": 83, "value": 0.1978984317816761, "stage": "evolution", "created_at": 1789535172.3962665}, {"event_id": "d70dd96801c642fa9ee45d666691179c", "step": 84, "value": 0.14264387814299317, "stage": "evolution", "created_at": 1789535378.9141023}, {"event_id": "63dc8287a0614a3e8f394733d34895c2", "step": 85, "value": 0.15012228651498716, "stage": "evolution", "created_at": 1789535436.5294354}, {"event_id": "c91a0ef071e64670a00df29389bb56a4", "step": 87, "value": 0.15132140830605328, "stage": "evolution", "created_at": 1789535622.3294394}, {"event_id": "76c914f75cfd42249be7579c82a2680d", "step": 88, "value": 0.14404617196520209, "stage": "evolution", "created_at": 1789535670.2890513}, {"event_id": "aab8bbefcb1a441282cd62f6f355f711", "step": 90, "value": 0.13750127123186986, "stage": "evolution", "created_at": 1789535896.096367}, {"event_id": "7259430bdcec4c85922c95059b0e46a2", "step": 91, "value": 0.1526910006094696, "stage": "evolution", "created_at": 1789536009.6673017}, {"event_id": "bcc7a597713e45c5ac60c19c0dcaac51", "step": 92, "value": 0.15452101785092626, "stage": "debug", "created_at": 1789535993.0338025}, {"event_id": "5a852cbfb9534e14827a33d493bbd5b0", "step": 93, "value": 0.15460372673118963, "stage": "improve", "created_at": 1789536226.3446968}, {"event_id": "f557f6b7b5c4400990a6ad84734ce4c7", "step": 95, "value": 0.13750127123186986, "stage": "improve", "created_at": 1789536516.6792502}, {"event_id": "b89e2b109b1045c58817287e1aad204c", "step": 96, "value": 0.1456047529567845, "stage": "improve", "created_at": 1789536563.098436}, {"event_id": "93ff8a3ed76a436eb1925857be197796", "step": 98, "value": 0.15421951738021933, "stage": "improve", "created_at": 1789536902.4262993}, {"event_id": "13b085d2f8fc4e5da131586952340ba5", "step": 99, "value": 0.15427116540584018, "stage": "improve", "created_at": 1789536909.7601163}, {"event_id": "86e04de39a204a5cb512f05f596c8e52", "step": 100, "value": 0.1545342335699079, "stage": "debug", "created_at": 1789536852.425214}, {"event_id": "d107a90c09024e998031a832b3de803f", "step": 102, "value": 0.1409255697345576, "stage": "improve", "created_at": 1789537430.1455853}, {"event_id": "714c81596d5c40afb628b478bb83eca6", "step": 104, "value": 0.15427116540584018, "stage": "debug", "created_at": 1789537519.742912}, {"event_id": "cb74abd869774ee9adb9462492f45966", "step": 106, "value": 0.18168447975869145, "stage": "evolution", "created_at": 1789537859.3926978}, {"event_id": "bfa82fce91594d3e9f9d9e729317279c", "step": 107, "value": 0.15427116540584018, "stage": "debug", "created_at": 1789538037.964894}, {"event_id": "23b7b51181d94c228a02bffb0eb6a89d", "step": 108, "value": 0.13254375284491274, "stage": "evolution", "created_at": 1789538220.9083385}, {"event_id": "ae001b5b91e14f349e34ad287a6d0b73", "step": 109, "value": 0.13881888151782273, "stage": "evolution", "created_at": 1789538373.7296402}, {"event_id": "2d21b1b4f16d4ceabdea090aa815194b", "step": 111, "value": 0.15746002236400272, "stage": "improve", "created_at": 1789537836.3587701}, {"event_id": "8b81f0a0bcdb4a37a8430660fe22d6b0", "step": 112, "value": 0.13254375284491274, "stage": "improve", "created_at": 1789538784.7907002}, {"event_id": "e82955042fa14e10a76d4d39510313a2", "step": 116, "value": 0.13091555736296334, "stage": "improve", "created_at": 1789539231.2853062}, {"event_id": "d12ed15499634c69816c2a729f04dc2d", "step": 117, "value": 0.15439900930901732, "stage": "debug", "created_at": 1789539449.2207162}, {"event_id": "e0e4e00f77764759a942ed9eaf6cb0d1", "step": 118, "value": 0.1544175577437646, "stage": "debug", "created_at": 1789539369.6569717}, {"event_id": "fce8d3c59c6244fcaf0f366bab0dc67c", "step": 119, "value": 0.13091555736296334, "stage": "improve", "created_at": 1789539555.285867}, {"event_id": "ee9d13872a5f44ee9e3c8552d6efdfec", "step": 120, "value": 0.13091555736296334, "stage": "improve", "created_at": 1789539833.778073}, {"event_id": "722b7271d1df4a298787b6ec7fd7e973", "step": 121, "value": 0.13746956435056212, "stage": "improve", "created_at": 1789539891.3737113}, {"event_id": "f20a561d68be40809518d1b69d9efd38", "step": 122, "value": 0.13403155360540664, "stage": "improve", "created_at": 1789539941.8812945}, {"event_id": "7afe60af06e34fd8a6800049dfde3608", "step": 123, "value": 0.13091555736296334, "stage": "improve", "created_at": 1789540137.9399555}, {"event_id": "bce181e81496427f85de25ee437224cb", "step": 124, "value": 0.12896936374986215, "stage": "improve", "created_at": 1789540226.6919117}, {"event_id": "82e049ed9ff44576a8e84facefa9f090", "step": 125, "value": 0.2250229577927234, "stage": "improve", "created_at": 1789540269.134157}, {"event_id": "68f749ace9c449f9ad774297ba1779b7", "step": 126, "value": 0.18679078605340194, "stage": "improve", "created_at": 1789540453.1194675}, {"event_id": "83dedb5bc59f47049b814fdf68045aba", "step": 127, "value": 0.12896936372943862, "stage": "improve", "created_at": 1789540581.4138265}, {"event_id": "bc928f4ca5aa40e3b27524dbfb0bf50d", "step": 128, "value": 0.5476329588520115, "stage": "improve", "created_at": 1789540670.4174154}, {"event_id": "4336ef344c154502b2967ffeeb7877c5", "step": 130, "value": 0.12896936372943862, "stage": "improve", "created_at": 1789540980.0489233}, {"event_id": "be5d5eeba83b41fb9cb82b59641ca896", "step": 131, "value": 0.12896936372943862, "stage": "improve", "created_at": 1789540983.5837011}, {"event_id": "016a57983d9c46d78ef2a6e21459f381", "step": 132, "value": 0.3189544551345218, "stage": "improve", "created_at": 1789541139.095218}, {"event_id": "6b8cd66f2e264470826156ac6d093f43", "step": 134, "value": 0.12896936372943862, "stage": "improve", "created_at": 1789541443.1398516}, {"event_id": "269ecad4f1f54bbabd3169066e8581d3", "step": 135, "value": 0.1333348217747357, "stage": "improve", "created_at": 1789541469.7538042}, {"event_id": "b07d1af412af4a2ab84808acf8daca61", "step": 138, "value": 0.13940443428099175, "stage": "improve", "created_at": 1789541821.1626525}, {"event_id": "d43e2f62807d4dcab3dff34c93e8a854", "step": 139, "value": 0.12896936372943862, "stage": "improve", "created_at": 1789541855.1492615}, {"event_id": "f4e2ed782f36420db5cc82f96e9c38b9", "step": 140, "value": 0.13009372193667162, "stage": "improve", "created_at": 1789542134.9956858}, {"event_id": "43aefb8496cd42d49987a45617dfb0a3", "step": 141, "value": 0.12896936372943862, "stage": "improve", "created_at": 1789542206.4936054}, {"event_id": "f133f6ff62af4d7b86c4cee1ecb00587", "step": 142, "value": 0.24621582862555513, "stage": "improve", "created_at": 1789542384.5171902}, {"event_id": "8d3ecb5a595c457c8c17c01cd261d414", "step": 143, "value": 0.12896936372943862, "stage": "improve", "created_at": 1789542454.0674849}, {"event_id": "1b4fda933c574d228b361a2d61604560", "step": 144, "value": 0.1299378935930124, "stage": "improve", "created_at": 1789542539.0217311}, {"event_id": "4d8dc00926b845d2a8fc113bd025c40a", "step": 145, "value": 0.12896936372943862, "stage": "improve", "created_at": 1789542742.4678752}, {"event_id": "c0c34d04790245e5ae5b14a7c613159f", "step": 146, "value": 0.1298346138561115, "stage": "improve", "created_at": 1789542766.6071086}, {"event_id": "dbf4f455755f4a9fafce636d9d9b679e", "step": 147, "value": 0.13009372193667162, "stage": "improve", "created_at": 1789542883.700358}, {"event_id": "138ea2dfb244493e82b600d5c7024025", "step": 148, "value": 0.12896936372943862, "stage": "improve", "created_at": 1789543126.7114558}, {"event_id": "f7a7eedc7079498ca6df076bd32e503c", "step": 149, "value": 0.12896936372943862, "stage": "improve", "created_at": 1789543135.3596442}, {"event_id": "4b079c506e25415085316af3eabf9b33", "step": 151, "value": 0.20764487991055058, "stage": "debug", "created_at": 1789543459.732231}, {"event_id": "ad2d93f8b2ac4b19bda83a4d3b6f2ae1", "step": 152, "value": 0.12896936372943862, "stage": "improve", "created_at": 1789543511.3993073}, {"event_id": "4b93127b1ce44fc4accdc31cdd90b9d8", "step": 153, "value": 0.2725385385005383, "stage": "improve", "created_at": 1789543559.6788073}, {"event_id": "e176fca5a8d045b8976bd168fc80d4c1", "step": 154, "value": 0.12896936372943862, "stage": "improve", "created_at": 1789543933.2973845}, {"event_id": "73a943ac8171440fbba5fdfca18b5d30", "step": 155, "value": 0.13616162761898246, "stage": "improve", "created_at": 1789543929.1767454}, {"event_id": "70a9754761ba41b0b24ece60feb9a155", "step": 156, "value": 0.13530624076509434, "stage": "improve", "created_at": 1789543876.9716382}, {"event_id": "4fd6194ec32343348896bef7dc658765", "step": 157, "value": 0.12896936372943862, "stage": "improve", "created_at": 1789544420.84644}, {"event_id": "8de747d666e043abb1c33fb13ced9acc", "step": 159, "value": 0.12896936372943862, "stage": "improve", "created_at": 1789544442.6833901}, {"event_id": "3746273773274559b33936b2c4cf4eaa", "step": 160, "value": 0.1463992434247485, "stage": "debug", "created_at": 1789544684.0227056}, {"event_id": "6c0ba24a917e497ba2f2b89155555c53", "step": 161, "value": 0.13659212862624792, "stage": "improve", "created_at": 1789544790.115437}, {"event_id": "4202a23274a5499f8726080e8fd89175", "step": 163, "value": 0.13537538964109963, "stage": "improve", "created_at": 1789545039.1674433}, {"event_id": "a426b6ef5c7342c397a4660e5172d486", "step": 165, "value": 0.6492838364484214, "stage": "fusion_draft", "created_at": 1789545248.0766573}, {"event_id": "4a56bf953eff4ae0a48030e67a90df6a", "step": 166, "value": 0.2814429245521543, "stage": "debug", "created_at": 1789545253.7200544}, {"event_id": "8ee189420d044a69b8a27ff41df5177a", "step": 167, "value": 0.13781266466176714, "stage": "evolution", "created_at": 1789545388.7878752}, {"event_id": "3e93c81d25dc41f9ba46bb83bbea8850", "step": 168, "value": 0.13268022614436978, "stage": "evolution", "created_at": 1789545450.933971}, {"event_id": "97d428a35d694233bd7d8e3ddb87a883", "step": 169, "value": 0.12896936372943862, "stage": "fusion", "created_at": 1789545523.8236237}, {"event_id": "a60167f42e634a1889c635fbdb2fd779", "step": 170, "value": 0.12896936372943862, "stage": "fusion", "created_at": 1789545708.5861733}, {"event_id": "525baf3c1b56494487c17ad87e4e497f", "step": 171, "value": 0.24167247486610136, "stage": "evolution", "created_at": 1789545717.2455354}, {"event_id": "0b145c39a6184c9cae0f7e9aa02adb9a", "step": 172, "value": 0.13374412375952058, "stage": "improve", "created_at": 1789545877.3464458}, {"event_id": "bb7da3fd8300486aafb25c2733cff184", "step": 173, "value": 0.13050049747183046, "stage": "improve", "created_at": 1789546063.7372391}, {"event_id": "127c95fd3104438ca2a81fb265a22eda", "step": 175, "value": 0.13278113317658474, "stage": "improve", "created_at": 1789546308.3602357}, {"event_id": "5aff247c4c1d4bf5a6234689578e6b30", "step": 176, "value": 0.13009372193667162, "stage": "debug", "created_at": 1789546285.8287466}, {"event_id": "b49df5a2a9c8493fb3533011a3893f30", "step": 177, "value": 0.14476417058746144, "stage": "evolution", "created_at": 1789546424.4887652}, {"event_id": "f3b299fe2a8f4478bba585d6ed709bab", "step": 178, "value": 0.21078452008506962, "stage": "evolution", "created_at": 1789546619.2351048}, {"event_id": "4a13e945a2634b5d8fa8ea8477d1a7d0", "step": 179, "value": 0.13131883397154615, "stage": "evolution", "created_at": 1789546661.5691645}, {"event_id": "bc965166057d405c8cb7dcdd6a10c14d", "step": 180, "value": 0.17543811400275838, "stage": "evolution", "created_at": 1789546771.452359}, {"event_id": "3d8d1fa327f1468b9ac68a85074ce461", "step": 181, "value": 0.136421844895569, "stage": "evolution", "created_at": 1789546992.890527}, {"event_id": "7945fceb01384aa2a1ba1aa397d25821", "step": 182, "value": 0.43843837579254963, "stage": "evolution", "created_at": 1789547020.7506754}, {"event_id": "6b559381cbdc4f809ad7b4f317daf160", "step": 183, "value": 0.12897198732558374, "stage": "fusion", "created_at": 1789547055.6014304}, {"event_id": "318a0d62d4f0477fb3bd2795e9a8c287", "step": 185, "value": 0.1455157405507693, "stage": "fusion", "created_at": 1789547352.201267}, {"event_id": "1430d85a69744806bd7c7ca63ee2e8aa", "step": 186, "value": 1.7135562149958217, "stage": "debug", "created_at": 1789547480.8827662}, {"event_id": "aff6d06a9b5e44f5b29a13177fd0130c", "step": 187, "value": 0.12897198732558374, "stage": "fusion", "created_at": 1789547402.4765866}, {"event_id": "6fb4a3a3444a4ce38b021cd217190bd2", "step": 188, "value": 0.37185295829169207, "stage": "evolution", "created_at": 1789547652.7337098}, {"event_id": "72ce2aa9d79f403eabbfe9fd134f54a6", "step": 189, "value": 0.9527982352049538, "stage": "evolution", "created_at": 1789547684.7811928}, {"event_id": "b852e52a63374623903585438f3501bd", "step": 190, "value": 0.2800132423517903, "stage": "evolution", "created_at": 1789547742.3748877}, {"event_id": "6f9467ddeb3946f99b1c7e3e406a2724", "step": 191, "value": 0.9375022481902489, "stage": "evolution", "created_at": 1789548108.9426737}, {"event_id": "56784ad43b7c4812bb2693718f909720", "step": 192, "value": 0.1378192259836426, "stage": "evolution", "created_at": 1789548185.3557248}, {"event_id": "caf79cd1a24d4637be4886e074d7d917", "step": 193, "value": 0.1456948540341763, "stage": "evolution", "created_at": 1789548207.064171}, {"event_id": "562543dab1754645ae7deb254a1041bd", "step": 194, "value": 0.136174031050842, "stage": "fusion", "created_at": 1789548512.3118868}, {"event_id": "bf955cbb8944403c82b33a6a0480b1cb", "step": 195, "value": 0.1475238574382154, "stage": "evolution", "created_at": 1789548526.4045146}, {"event_id": "14fe635c7841461eb8f9141282326f9c", "step": 196, "value": 0.14207488296127663, "stage": "fusion", "created_at": 1789548521.6715448}, {"event_id": "6ff5e3f421324b7eb5a764459ffcbdab", "step": 197, "value": 0.12910684242686496, "stage": "fusion", "created_at": 1789548818.1342998}, {"event_id": "0de789b7c0834a2facd5ea7c52b4fe27", "step": 199, "value": 0.15292104861940048, "stage": "evolution", "created_at": 1789548938.6631563}, {"event_id": "878614f90d8948ff95a61a7dbdfdd628", "step": 200, "value": 0.1336450764521978, "stage": "evolution", "created_at": 1789549093.8937755}, {"event_id": "b4a6517561b74f9db1fa460743d0b5fe", "step": 201, "value": 0.13294914656929502, "stage": "evolution", "created_at": 1789549268.504859}, {"event_id": "f0ee394eb2534cbabf13a8bf19295cb7", "step": 202, "value": 0.12902402810012195, "stage": "evolution", "created_at": 1789549276.2123842}, {"event_id": "0e65589fc3db435889e8bb5e5af935be", "step": 203, "value": 0.12896936372943862, "stage": "fusion", "created_at": 1789549359.8152442}, {"event_id": "b17b24cb40a24fab8ee8f21c3c26205d", "step": 204, "value": 0.12959132016939087, "stage": "fusion", "created_at": 1789549552.9578874}, {"event_id": "44ca8786a43043ea98731c97eac436c4", "step": 205, "value": 0.1296205385914159, "stage": "fusion", "created_at": 1789549563.4317482}, {"event_id": "a322d286827b42eeb5ba48feb8b00add", "step": 206, "value": 0.12897198732558374, "stage": "improve", "created_at": 1789549715.9353359}, {"event_id": "2fa9c5b04e9d4708a95d888a246259a6", "step": 207, "value": 0.1347361999616855, "stage": "improve", "created_at": 1789550058.715862}, {"event_id": "05500f737100444bbcacc1e214e9eae5", "step": 208, "value": 0.12896936372943862, "stage": "improve", "created_at": 1789550004.2682629}, {"event_id": "51db40ab66c74d57b53740ed70fc41e3", "step": 209, "value": 0.4052112937454422, "stage": "evolution", "created_at": 1789550035.314115}], "maximize": false, "elapsed_seconds": 28861.21573472023, "node_count": 213, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-three-20260916/xixian.gp7-long-horizon-logei.nomad2018-predict-transparent-conductors.yaml", "note": ""}, {"id": "xixian.gp7-long-horizon-logei.plant-pathology-2020-fgvc7", "experiment_id": "mlebench-gp7-three-20260916", "family": "MLEBench", "method": "gp7_long_horizon_logei", "dataset": "plant-pathology-2020-fgvc7", "status": "archived", "official_score": 0.99713, "medal": "gold", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.97836, "silver": 0.97465, "bronze": 0.97361}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/results/private_grades.jsonl:35", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}, {"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/runs/gp7_long_horizon_logei/13_plant-pathology-2020-fgvc7/logs/journal.json", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}], "alternate_scores": [], "journal_ref": "gp7-three-bo-analysis-20260916:gp7-three-66-runs/runs/gp7_long_horizon_logei/13_plant-pathology-2020-fgvc7/logs/journal.json", "metrics": [{"event_id": "89b6a6cd22174e36b760b65c82d1ab3f", "step": 5, "value": 0.9857596340906589, "stage": "debug", "created_at": 1789523528.9114392}, {"event_id": "e24d94e3fb174b3f9633456b2ecbe622", "step": 6, "value": 0.9780188758927729, "stage": "debug", "created_at": 1789523516.1099513}, {"event_id": "58354c534336413cb886b7fb3de3644b", "step": 9, "value": 0.9812502869955515, "stage": "improve", "created_at": 1789524111.1916342}, {"event_id": "0a6f6bda574a49139d569dd16b974eb3", "step": 10, "value": 0.9798922155269338, "stage": "improve", "created_at": 1789524977.0507014}, {"event_id": "a09b095c3a164fadac3d3cc40bf042ff", "step": 11, "value": 0.9833109285221623, "stage": "debug", "created_at": 1789524307.0530167}, {"event_id": "56b3ea2c4af04b5fbe92cd9d15075ce0", "step": 12, "value": 0.9716592496120635, "stage": "debug", "created_at": 1789524035.7955163}, {"event_id": "1f9bdedb449846a899e81c670c32daa0", "step": 13, "value": 0.9830872914269042, "stage": "improve", "created_at": 1789525589.5952315}, {"event_id": "14b20c8e71cc4fc2baec037d996b570e", "step": 14, "value": 0.9856166080845725, "stage": "evolution", "created_at": 1789525901.0930111}, {"event_id": "64b2eab42c1f4d0b81c4de8c43d15a15", "step": 16, "value": 0.984850750838191, "stage": "evolution", "created_at": 1789529248.9832933}, {"event_id": "a9ee2fcc738a42dbb8b7ce209adb435b", "step": 17, "value": 0.9592964686499914, "stage": "evolution", "created_at": 1789525566.637377}, {"event_id": "84fbb149c00843cdb2994da5b5b8f08a", "step": 21, "value": 0.9591074827363562, "stage": "debug", "created_at": 1789531379.7009966}, {"event_id": "f8c7885e806e45eda04848fe34160217", "step": 23, "value": 0.9826330028828221, "stage": "evolution", "created_at": 1789533930.4026778}, {"event_id": "e85031352a1a4c20aa7c52d84b096c94", "step": 24, "value": 0.9852289349723786, "stage": "evolution", "created_at": 1789534008.2645195}, {"event_id": "77b9fdd7b60b494394e3c9f77ce341b2", "step": 27, "value": 0.9820315614232575, "stage": "debug", "created_at": 1789533767.5437212}, {"event_id": "be192d45124b4da996c4b509f2666c82", "step": 30, "value": 0.9875145605855887, "stage": "evolution", "created_at": 1789536957.8328042}, {"event_id": "03f85099b10b4146b21270914ae6238d", "step": 31, "value": 0.9858992337419666, "stage": "evolution", "created_at": 1789538705.7842093}, {"event_id": "aa15f1bf503047abbc1a3c152bfabb86", "step": 32, "value": 0.9873600836322435, "stage": "improve", "created_at": 1789540126.423633}, {"event_id": "571e216639ec481ca64d0bacefa5e283", "step": 33, "value": 0.9851268722280527, "stage": "debug", "created_at": 1789539900.3750796}, {"event_id": "83347bc4e1d9407494890c764aee6930", "step": 34, "value": 0.9838299150177456, "stage": "improve", "created_at": 1789541664.6650016}, {"event_id": "031d87a02a4d48a8825f3a0cfe878be1", "step": 35, "value": 0.9875145605855887, "stage": "fusion", "created_at": 1789544891.5500274}, {"event_id": "77e524c266b348c0a3a23ab2deb84d67", "step": 36, "value": 0.9882734209143088, "stage": "improve", "created_at": 1789543442.1031353}, {"event_id": "d544e2c7fc494178906618c9e65d7f1d", "step": 37, "value": 0.9859235704721017, "stage": "fusion", "created_at": 1789544562.7818022}], "maximize": true, "elapsed_seconds": 28804.358114480972, "node_count": 41, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-three-20260916/xixian.gp7-long-horizon-logei.plant-pathology-2020-fgvc7.yaml", "note": ""}, {"id": "xixian.gp7-long-horizon-logei.random-acts-of-pizza", "experiment_id": "mlebench-gp7-three-20260916", "family": "MLEBench", "method": "gp7_long_horizon_logei", "dataset": "random-acts-of-pizza", "status": "archived", "official_score": 0.70655, "medal": "bronze", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.97908, "silver": 0.76482, "bronze": 0.6921}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/results/private_grades.jsonl:36", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}, {"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/runs/gp7_long_horizon_logei/14_random-acts-of-pizza/logs/journal.json", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}], "alternate_scores": [], "journal_ref": "gp7-three-bo-analysis-20260916:gp7-three-66-runs/runs/gp7_long_horizon_logei/14_random-acts-of-pizza/logs/journal.json", "metrics": [{"event_id": "efad1fca3b45403eaf9a1a5e7d7006c6", "step": 6, "value": 0.5671926226198742, "stage": "debug", "created_at": 1789522771.6716785}, {"event_id": "82425685572243e1968b0474b02dc7fe", "step": 7, "value": 0.639666338280657, "stage": "debug", "created_at": 1789522900.7207892}, {"event_id": "1f1fde2dc3fe4347a41181dd0a053b29", "step": 8, "value": 0.5938403397987693, "stage": "debug", "created_at": 1789522926.2136452}, {"event_id": "938f557ac36a41d2966401df9452f13a", "step": 9, "value": 0.6600397293237941, "stage": "improve", "created_at": 1789523351.6791458}, {"event_id": "aa2c9db6e8c4461aaf3d19165e0a214d", "step": 10, "value": 0.6669842859219303, "stage": "improve", "created_at": 1789523454.00019}, {"event_id": "c371abd9b281476f8d933969cadcd4ec", "step": 11, "value": 0.5498393061903455, "stage": "improve", "created_at": 1789523233.1066248}, {"event_id": "05e9c2b6bb5c4f4a9deaf0bc7cbe1778", "step": 12, "value": 0.6683085967150633, "stage": "improve", "created_at": 1789523722.7089598}, {"event_id": "c75b9762876b4fbc820dc2295b5d3a2a", "step": 14, "value": 0.6738319417303252, "stage": "improve", "created_at": 1789524023.2468467}, {"event_id": "6cbccf1e332a4d88ad6a1b39631f8ba6", "step": 15, "value": 0.6698751594825497, "stage": "debug", "created_at": 1789524242.7608366}, {"event_id": "7362354a44c64e67bd324e252ac3c281", "step": 17, "value": 0.6785800804276556, "stage": "improve", "created_at": 1789524160.1952999}, {"event_id": "da6149bc0bf242de89e7b7ce57087b18", "step": 18, "value": 0.6853954359728032, "stage": "debug", "created_at": 1789525243.034583}, {"event_id": "bc3d92b235794c88a842b2b0a5f874ab", "step": 19, "value": 0.6662736801304932, "stage": "improve", "created_at": 1789525121.58702}, {"event_id": "549b10b81f214be2a002275063cb17c4", "step": 20, "value": 0.6713609715919184, "stage": "improve", "created_at": 1789526274.939423}, {"event_id": "479c2cd3043d4683834887446b66732c", "step": 21, "value": 0.6833443692566095, "stage": "improve", "created_at": 1789526314.3404262}, {"event_id": "2dca86bf72c74d5fa5647cf78c428ded", "step": 22, "value": 0.666919685395436, "stage": "evolution", "created_at": 1789527451.216365}, {"event_id": "a50a78c0b0d64080a24a222637f71493", "step": 25, "value": 0.6738803921251959, "stage": "debug", "created_at": 1789528058.9484432}, {"event_id": "cce4bfc8b1f94eac859be6a250584376", "step": 26, "value": 0.6715870734346485, "stage": "evolution", "created_at": 1789529573.193084}, {"event_id": "a668385c93f54a689980f67060212ed7", "step": 27, "value": 0.6792583859558456, "stage": "debug", "created_at": 1789528425.3346026}, {"event_id": "de3e7000db854125a312a431be0884d7", "step": 28, "value": 0.6794198872720812, "stage": "evolution", "created_at": 1789530472.367886}, {"event_id": "0f73be41d0674bf0a1ec975d72fea8d7", "step": 29, "value": 0.6851693341300733, "stage": "improve", "created_at": 1789525844.7217855}, {"event_id": "1e8aa2f7b3054997bf82f537e384a37b", "step": 30, "value": 0.6554853922059465, "stage": "draft", "created_at": 1789537562.0380666}, {"event_id": "ce433d9be6b24ddab2df15e20d7ad6a8", "step": 31, "value": 0.6830052164925143, "stage": "improve", "created_at": 1789536990.1599238}], "maximize": true, "elapsed_seconds": 28796.58027768135, "node_count": 33, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-three-20260916/xixian.gp7-long-horizon-logei.random-acts-of-pizza.yaml", "note": ""}, {"id": "xixian.gp7-long-horizon-logei.ranzcr-clip-catheter-line-classification", "experiment_id": "mlebench-gp7-three-20260916", "family": "MLEBench", "method": "gp7_long_horizon_logei", "dataset": "ranzcr-clip-catheter-line-classification", "status": "archived", "official_score": 0.8678, "medal": "none", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.97357, "silver": 0.97152, "bronze": 0.9709}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/results/private_grades.jsonl:37", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}, {"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/runs/gp7_long_horizon_logei/15_ranzcr-clip-catheter-line-classification/logs/journal.json", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}], "alternate_scores": [], "journal_ref": "gp7-three-bo-analysis-20260916:gp7-three-66-runs/runs/gp7_long_horizon_logei/15_ranzcr-clip-catheter-line-classification/logs/journal.json", "metrics": [{"event_id": "4ede2fbe7c834a178ced2bb41bc47cce", "step": 1, "value": 0.7837707300999383, "stage": "draft", "created_at": 1789522642.965722}, {"event_id": "85288afca0e74c1c8adcdd079d56e24c", "step": 3, "value": 0.6857565143994828, "stage": "debug", "created_at": 1789531778.6620412}, {"event_id": "3379004df0e34fb68d5aa97803a81551", "step": 5, "value": 0.828624827482173, "stage": "improve", "created_at": 1789531713.5835037}], "maximize": true, "elapsed_seconds": 28795.868311405182, "node_count": 10, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-three-20260916/xixian.gp7-long-horizon-logei.ranzcr-clip-catheter-line-classification.yaml", "note": ""}, {"id": "xixian.gp7-long-horizon-logei.siim-isic-melanoma-classification", "experiment_id": "mlebench-gp7-three-20260916", "family": "MLEBench", "method": "gp7_long_horizon_logei", "dataset": "siim-isic-melanoma-classification", "status": "archived", "official_score": 0.88704, "medal": "none", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.9455, "silver": 0.9401, "bronze": 0.937}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/results/private_grades.jsonl:38", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}, {"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/runs/gp7_long_horizon_logei/16_siim-isic-melanoma-classification/logs/journal.json", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}], "alternate_scores": [], "journal_ref": "gp7-three-bo-analysis-20260916:gp7-three-66-runs/runs/gp7_long_horizon_logei/16_siim-isic-melanoma-classification/logs/journal.json", "metrics": [{"event_id": "c7b42e324738495e809d76f58d6eb0b1", "step": 5, "value": 0.9164139588831548, "stage": "debug", "created_at": 1789536042.4077282}], "maximize": true, "elapsed_seconds": 28795.702367544174, "node_count": 9, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-three-20260916/xixian.gp7-long-horizon-logei.siim-isic-melanoma-classification.yaml", "note": ""}, {"id": "xixian.gp7-long-horizon-logei.spooky-author-identification", "experiment_id": "mlebench-gp7-three-20260916", "family": "MLEBench", "method": "gp7_long_horizon_logei", "dataset": "spooky-author-identification", "status": "archived", "official_score": 0.24131, "medal": "silver", "valid_submission": true, "score_maximize": false, "thresholds": {"gold": 0.16506, "silver": 0.26996, "bronze": 0.29381}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/results/private_grades.jsonl:39", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}, {"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/runs/gp7_long_horizon_logei/17_spooky-author-identification/logs/journal.json", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}], "alternate_scores": [], "journal_ref": "gp7-three-bo-analysis-20260916:gp7-three-66-runs/runs/gp7_long_horizon_logei/17_spooky-author-identification/logs/journal.json", "metrics": [{"event_id": "e4f2d5283517457cbea009dbb984a6db", "step": 3, "value": 0.4498344748630599, "stage": "draft", "created_at": 1789522326.243678}, {"event_id": "bd2645de78a74627ad54a08375f84afd", "step": 4, "value": 0.3424504616744041, "stage": "debug", "created_at": 1789522775.8398414}, {"event_id": "538efd3ef2f8497d9bc32df4eac26f7a", "step": 5, "value": 0.608085741873886, "stage": "debug", "created_at": 1789522765.0025935}, {"event_id": "ee1d0b1b8de641e99b11d310b7e7a9fc", "step": 7, "value": 0.2776903145549353, "stage": "improve", "created_at": 1789523384.0573564}, {"event_id": "0695238d7e24472f9af3895f23332570", "step": 8, "value": 0.2654292046036224, "stage": "improve", "created_at": 1789523477.3057785}, {"event_id": "2ca2e451ba5148bcb71371dbff9f795f", "step": 9, "value": 0.2623796338528268, "stage": "debug", "created_at": 1789523672.3181047}, {"event_id": "0bb603cae71e4dd8affffee23fcc56ba", "step": 10, "value": 0.2776903145549353, "stage": "improve", "created_at": 1789523958.2600913}, {"event_id": "2d5fca39433a48cbb835721ee5c75ab7", "step": 11, "value": 0.25733258515636664, "stage": "improve", "created_at": 1789524028.3568196}, {"event_id": "b439b29357704ec7a9bdfe21427e3dd2", "step": 12, "value": 0.27422856896265607, "stage": "improve", "created_at": 1789524314.0115957}, {"event_id": "0850e3070d0a4fec852c3d6b91637cfd", "step": 13, "value": 0.31323155938814917, "stage": "improve", "created_at": 1789524488.915114}, {"event_id": "0d8be9289b4043a894ef070034e6b017", "step": 17, "value": 0.25920828218972986, "stage": "improve", "created_at": 1789524663.5448244}, {"event_id": "ed218d78614a42aa9426123a28e50b46", "step": 18, "value": 0.24262933741385087, "stage": "improve", "created_at": 1789525040.7371624}, {"event_id": "8cc7e78acd08468aa6786cdd71699988", "step": 19, "value": 0.3215628292330933, "stage": "debug", "created_at": 1789525679.8918073}, {"event_id": "74565e0ba5844b3ca16391d95b934db6", "step": 20, "value": 0.31748939741160126, "stage": "evolution", "created_at": 1789527219.45584}, {"event_id": "b2b60235316046b3ac68ccd2118298d6", "step": 21, "value": 0.2499639904147976, "stage": "improve", "created_at": 1789527932.6644742}, {"event_id": "94650d0d864c4d789b072267c1aedeb1", "step": 22, "value": 0.2545276086179919, "stage": "improve", "created_at": 1789532239.7375147}, {"event_id": "c0905f087b5a4a46b65a838fa8f5b09e", "step": 24, "value": 0.24209115100533632, "stage": "improve", "created_at": 1789531906.2585673}, {"event_id": "6df6de5ffd1e4aa684061e2aa003a209", "step": 25, "value": 0.5043105867182723, "stage": "debug", "created_at": 1789535972.634157}, {"event_id": "2043eea75f1c433283112dcf6630a7bf", "step": 27, "value": 0.24364937642115234, "stage": "evolution", "created_at": 1789535083.9213293}, {"event_id": "0a86cbda08df4455a23aa1076d60f510", "step": 28, "value": 0.2497905776203322, "stage": "improve", "created_at": 1789537089.0738025}, {"event_id": "953921e19a5e48d08d0f9188378eacf9", "step": 29, "value": 0.3368117704816371, "stage": "debug", "created_at": 1789544731.34257}], "maximize": false, "elapsed_seconds": 28806.28068971634, "node_count": 33, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-three-20260916/xixian.gp7-long-horizon-logei.spooky-author-identification.yaml", "note": ""}, {"id": "xixian.gp7-long-horizon-logei.tabular-playground-series-dec-2021", "experiment_id": "mlebench-gp7-three-20260916", "family": "MLEBench", "method": "gp7_long_horizon_logei", "dataset": "tabular-playground-series-dec-2021", "status": "archived", "official_score": 0.96313, "medal": "gold", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.9566, "silver": 0.95658, "bronze": 0.95658}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/results/private_grades.jsonl:40", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}, {"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/runs/gp7_long_horizon_logei/18_tabular-playground-series-dec-2021/logs/journal.json", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}], "alternate_scores": [], "journal_ref": "gp7-three-bo-analysis-20260916:gp7-three-66-runs/runs/gp7_long_horizon_logei/18_tabular-playground-series-dec-2021/logs/journal.json", "metrics": [{"event_id": "c61ab40bba1040c18bbd007ecec2a020", "step": 1, "value": 0.9612458333333334, "stage": "draft", "created_at": 1789522282.3051097}, {"event_id": "83f46ad62cec426b81e05f3d5ebd3f7f", "step": 2, "value": 0.9621361111111111, "stage": "improve", "created_at": 1789526494.9439068}, {"event_id": "5fea3e7f2eb24043bc4f668bc8e65053", "step": 4, "value": 0.9621847222222222, "stage": "debug", "created_at": 1789534014.691831}, {"event_id": "54ab216f970040e8954dab8884b7cb92", "step": 7, "value": 0.945675, "stage": "debug", "created_at": 1789544654.9527915}], "maximize": true, "elapsed_seconds": 28797.265469551086, "node_count": 10, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-three-20260916/xixian.gp7-long-horizon-logei.tabular-playground-series-dec-2021.yaml", "note": ""}, {"id": "xixian.gp7-long-horizon-logei.tabular-playground-series-may-2022", "experiment_id": "mlebench-gp7-three-20260916", "family": "MLEBench", "method": "gp7_long_horizon_logei", "dataset": "tabular-playground-series-may-2022", "status": "archived", "official_score": 0.99291, "medal": "none", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.99823, "silver": 0.99822, "bronze": 0.99818}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/results/private_grades.jsonl:41", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}, {"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/runs/gp7_long_horizon_logei/19_tabular-playground-series-may-2022/logs/journal.json", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}], "alternate_scores": [], "journal_ref": "gp7-three-bo-analysis-20260916:gp7-three-66-runs/runs/gp7_long_horizon_logei/19_tabular-playground-series-may-2022/logs/journal.json", "metrics": [{"event_id": "5d043db69d9a4c7b80e1e4f13a5532dc", "step": 4, "value": 0.9920013631271776, "stage": "draft", "created_at": 1789522007.4083788}, {"event_id": "fc9f5fe2030546b9b193431a687f9954", "step": 5, "value": 0.9642284879199698, "stage": "debug", "created_at": 1789522812.622084}, {"event_id": "cbcf4fb6e92249f2a35dce05d968f3cf", "step": 6, "value": 0.9158529153746335, "stage": "debug", "created_at": 1789523001.5015202}, {"event_id": "cbc15c44566540d8aeeb6ab69b2746d2", "step": 7, "value": 0.9856422957702278, "stage": "improve", "created_at": 1789523456.8983045}, {"event_id": "f115e967dc9241c9abf1f6e617916e94", "step": 8, "value": 0.9899653200235975, "stage": "improve", "created_at": 1789523178.0392067}, {"event_id": "0f35440c9e1544569d6cf93d7d78b169", "step": 10, "value": 0.9928065333700425, "stage": "improve", "created_at": 1789523205.4211621}, {"event_id": "f385e368dfa547e89444482d7cf72e7b", "step": 11, "value": 0.9914403685449416, "stage": "improve", "created_at": 1789527772.7550712}, {"event_id": "412027c972f64d2d91803c9f513e259a", "step": 12, "value": 0.9887512829166154, "stage": "improve", "created_at": 1789524565.812465}, {"event_id": "d32974aa85654b66b258dd82ac49570f", "step": 13, "value": 0.9899890973631589, "stage": "improve", "created_at": 1789532291.326718}], "maximize": true, "elapsed_seconds": 28795.40119624138, "node_count": 18, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-three-20260916/xixian.gp7-long-horizon-logei.tabular-playground-series-may-2022.yaml", "note": ""}, {"id": "xixian.gp7-long-horizon-logei.text-normalization-challenge-english-language", "experiment_id": "mlebench-gp7-three-20260916", "family": "MLEBench", "method": "gp7_long_horizon_logei", "dataset": "text-normalization-challenge-english-language", "status": "archived", "official_score": 0.9642, "medal": "none", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.99724, "silver": 0.99135, "bronze": 0.99038}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/results/private_grades.jsonl:42", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}, {"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/runs/gp7_long_horizon_logei/20_text-normalization-challenge-english-language/logs/journal.json", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}], "alternate_scores": [], "journal_ref": "gp7-three-bo-analysis-20260916:gp7-three-66-runs/runs/gp7_long_horizon_logei/20_text-normalization-challenge-english-language/logs/journal.json", "metrics": [{"event_id": "aadcb54f31ee4bd1ae05202942bda2e8", "step": 10, "value": 0.9633859924034042, "stage": "debug", "created_at": 1789545184.433493}, {"event_id": "3ff9d171e22948a6ae3ea10874a8c796", "step": 13, "value": 0.964157906968229, "stage": "improve", "created_at": 1789547280.5783038}], "maximize": true, "elapsed_seconds": 28798.154797315598, "node_count": 14, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-three-20260916/xixian.gp7-long-horizon-logei.text-normalization-challenge-english-language.yaml", "note": ""}, {"id": "xixian.gp7-long-horizon-logei.text-normalization-challenge-russian-language", "experiment_id": "mlebench-gp7-three-20260916", "family": "MLEBench", "method": "gp7_long_horizon_logei", "dataset": "text-normalization-challenge-russian-language", "status": "archived", "official_score": 0.90758, "medal": "none", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.99012, "silver": 0.98232, "bronze": 0.97592}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/results/private_grades.jsonl:43", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}, {"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/runs/gp7_long_horizon_logei/21_text-normalization-challenge-russian-language/logs/journal.json", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}], "alternate_scores": [], "journal_ref": "gp7-three-bo-analysis-20260916:gp7-three-66-runs/runs/gp7_long_horizon_logei/21_text-normalization-challenge-russian-language/logs/journal.json", "metrics": [{"event_id": "9633412001414f34a0b01881664f9da0", "step": 7, "value": 0.9733973397339734, "stage": "debug", "created_at": 1789531237.3737993}, {"event_id": "8ba806603de3456eb620a485a48ae379", "step": 8, "value": 0.9785692854999786, "stage": "improve", "created_at": 1789533038.3606343}, {"event_id": "b44c5679ff0a455ebc83247bc1639122", "step": 11, "value": 0.978969325503979, "stage": "debug", "created_at": 1789538059.1136985}, {"event_id": "17f1d6081dd34c0a92ad10714dc9833b", "step": 13, "value": 0.9827125569699827, "stage": "improve", "created_at": 1789544103.5544114}, {"event_id": "d79c217687b84ce58169076bbde9184f", "step": 14, "value": 0.8810881088108811, "stage": "debug", "created_at": 1789544760.7132351}], "maximize": true, "elapsed_seconds": 28799.9811065197, "node_count": 23, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-three-20260916/xixian.gp7-long-horizon-logei.text-normalization-challenge-russian-language.yaml", "note": ""}, {"id": "xixian.gp7-long-horizon-logei.the-icml-2013-whale-challenge-right-whale-redux", "experiment_id": "mlebench-gp7-three-20260916", "family": "MLEBench", "method": "gp7_long_horizon_logei", "dataset": "the-icml-2013-whale-challenge-right-whale-redux", "status": "archived", "official_score": 0.99151, "medal": "gold", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.98961, "silver": 0.95017, "bronze": 0.90521}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/results/private_grades.jsonl:44", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}, {"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/runs/gp7_long_horizon_logei/22_the-icml-2013-whale-challenge-right-whale-redux/logs/journal.json", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}], "alternate_scores": [], "journal_ref": "gp7-three-bo-analysis-20260916:gp7-three-66-runs/runs/gp7_long_horizon_logei/22_the-icml-2013-whale-challenge-right-whale-redux/logs/journal.json", "metrics": [{"event_id": "6dcf3fb92de248c4b79396c608b9408d", "step": 2, "value": 0.976804045631055, "stage": "draft", "created_at": 1789522946.430469}, {"event_id": "cbd95974569e4cb2816b46e42efa29fb", "step": 3, "value": 0.9070127302767925, "stage": "debug", "created_at": 1789523635.6302261}, {"event_id": "d88d5cb4784f4fc992a3588851885c8b", "step": 4, "value": 0.9807649530427612, "stage": "improve", "created_at": 1789524143.6882405}, {"event_id": "e36e21b1c20f4f44aebdafb27b9dba50", "step": 5, "value": 0.937430358471897, "stage": "improve", "created_at": 1789524355.3932724}, {"event_id": "cd11f46cd4eb4733b0dc420d01ef2800", "step": 7, "value": 0.9857895187882058, "stage": "improve", "created_at": 1789525095.8963733}, {"event_id": "adefe844690e4d298d1955c291993dee", "step": 8, "value": 0.98595969041782, "stage": "debug", "created_at": 1789525492.074675}, {"event_id": "b324a2afdd274afeb8c9504529672153", "step": 11, "value": 0.9847189351494371, "stage": "improve", "created_at": 1789526152.5367289}, {"event_id": "b6a04a7272874c878af6181fa5096241", "step": 12, "value": 0.9877594132392157, "stage": "debug", "created_at": 1789526740.1758013}, {"event_id": "757319ce0fae40f2ad8109f6af72fa7b", "step": 13, "value": 0.9807612823863847, "stage": "improve", "created_at": 1789527041.3023589}, {"event_id": "42154df19d7647ef98b1d93ff7524a77", "step": 14, "value": 0.9847981234429994, "stage": "improve", "created_at": 1789527433.2892303}, {"event_id": "f04c5506f05b4c8f876eb2fe15c3cf6b", "step": 15, "value": 0.9780586759805413, "stage": "improve", "created_at": 1789528098.9071114}, {"event_id": "ab9c218966aa4d42a1ff940ec6a93e3d", "step": 16, "value": 0.9906705129272442, "stage": "improve", "created_at": 1789528236.6180637}, {"event_id": "b53b749c405b4c028e543863dd512c72", "step": 17, "value": 0.9827469851308562, "stage": "evolution", "created_at": 1789528849.1383166}, {"event_id": "c0d5504fbf1b4196bfbe4452a5ebd60f", "step": 18, "value": 0.7503975443210957, "stage": "debug", "created_at": 1789526246.1486003}, {"event_id": "632f004c012449489df4f3970ae2bde0", "step": 19, "value": 0.9864436052834548, "stage": "improve", "created_at": 1789529699.013599}, {"event_id": "27a799b81fc84f6d8050c77b8dfbb830", "step": 20, "value": 0.9894922567014316, "stage": "improve", "created_at": 1789529750.1212027}, {"event_id": "ca376ed7d8374b9cb6e837d0f12b57d8", "step": 22, "value": 0.9866251559478363, "stage": "improve", "created_at": 1789530185.0677617}, {"event_id": "73f102c1e96a41f4bc2c5280224ac356", "step": 23, "value": 0.9858559821396629, "stage": "evolution", "created_at": 1789531340.9510405}, {"event_id": "1771bf2fc1ca46799bd92fdee1ecfa08", "step": 25, "value": 0.9887359791326611, "stage": "evolution", "created_at": 1789532870.2536168}, {"event_id": "ea8fc5e5322e42acb02d5515acf6fb09", "step": 26, "value": 0.9876613822429208, "stage": "debug", "created_at": 1789533472.0190961}, {"event_id": "5dffe179344541d7812b2f235cc8c42c", "step": 29, "value": 0.9819027341642623, "stage": "evolution", "created_at": 1789535201.1416864}, {"event_id": "ff577e8a646b417099594b579f6ac927", "step": 30, "value": 0.9859282451281948, "stage": "debug", "created_at": 1789535588.7603717}, {"event_id": "3171c926c25c40f8b82ef14ce754aa6e", "step": 31, "value": 0.9835526207923694, "stage": "evolution", "created_at": 1789536071.4707484}, {"event_id": "f6c5a76a128a4c1f8312db58d3fb49ed", "step": 33, "value": 0.9864067518934347, "stage": "evolution", "created_at": 1789537245.2001235}, {"event_id": "30d7725e39b54f6dae090768afbeef47", "step": 35, "value": 0.9870240828828337, "stage": "fusion", "created_at": 1789538001.3806825}, {"event_id": "5ebe3680b03f43bc9e355dccf1e92396", "step": 36, "value": 0.9907863588424864, "stage": "fusion", "created_at": 1789538806.6842523}, {"event_id": "509b544949ec454395acaf8bb48a2841", "step": 37, "value": 0.9900738354977235, "stage": "fusion", "created_at": 1789539395.962228}, {"event_id": "2748e6e7c0454ccbbe186999ce692351", "step": 41, "value": 0.9907863588424864, "stage": "improve", "created_at": 1789541113.5804212}, {"event_id": "52bd6f056b0844c99241c0fd7c007f7a", "step": 43, "value": 0.9869623424425811, "stage": "improve", "created_at": 1789542630.524988}, {"event_id": "4d069abce4954949a059a3ea4c1fe81a", "step": 48, "value": 0.9595780223217997, "stage": "debug", "created_at": 1789545794.887946}, {"event_id": "fcde88c7b1a74f2bbd7684b068334c18", "step": 54, "value": 0.9863481192755809, "stage": "improve", "created_at": 1789548047.9655142}, {"event_id": "dae15eeba2ec457582330efbeb2f4d33", "step": 55, "value": 0.9905203341393605, "stage": "improve", "created_at": 1789548598.6021225}], "maximize": true, "elapsed_seconds": 28795.765117883682, "node_count": 57, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-three-20260916/xixian.gp7-long-horizon-logei.the-icml-2013-whale-challenge-right-whale-redux.yaml", "note": ""}, {"id": "xixian.gp7-long-horizon-pibo.aerial-cactus-identification", "experiment_id": "mlebench-gp7-three-20260916", "family": "MLEBench", "method": "gp7_long_horizon_pibo", "dataset": "aerial-cactus-identification", "status": "archived", "official_score": 0.99998, "medal": "none", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 1.0, "silver": 1.0, "bronze": 1.0}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/results/private_grades.jsonl:45", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}, {"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/runs/gp7_long_horizon_pibo/01_aerial-cactus-identification/logs/journal.json", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}], "alternate_scores": [], "journal_ref": "gp7-three-bo-analysis-20260916:gp7-three-66-runs/runs/gp7_long_horizon_pibo/01_aerial-cactus-identification/logs/journal.json", "metrics": [{"event_id": "766dada620ab42149913b13bff32530e", "step": 2, "value": 0.9999144184367897, "stage": "draft", "created_at": 1789523294.8860373}, {"event_id": "11882f3e18124068a0e4659593bab319", "step": 3, "value": 0.9994559931640897, "stage": "draft", "created_at": 1789522644.9373598}, {"event_id": "c973a02bf55e4ab4a2fc184145cd8e3b", "step": 5, "value": 0.9999329942799671, "stage": "debug", "created_at": 1789523964.4240525}, {"event_id": "4dc97c6e33174403af265d05ef6dd414", "step": 6, "value": 0.9998845644031118, "stage": "improve", "created_at": 1789524035.28423}, {"event_id": "5d9d485a2d4c4c128f0b5fd1d04301ff", "step": 7, "value": 0.999896506016583, "stage": "improve", "created_at": 1789523777.3223224}, {"event_id": "86008bc49f7f431597eaf2713803e56e", "step": 8, "value": 0.9998872180949943, "stage": "improve", "created_at": 1789524640.016374}, {"event_id": "39d62dbad8434421b302778ad9b3213b", "step": 9, "value": 0.9999887218094994, "stage": "improve", "created_at": 1789524615.197894}, {"event_id": "17d56ecd9ac84634beb18a9594caaa0d", "step": 10, "value": 0.999956214083939, "stage": "improve", "created_at": 1789525006.7387316}, {"event_id": "d7d7b2fcce43476fa3aa9329ad9e3374", "step": 11, "value": 0.9999794338879107, "stage": "improve", "created_at": 1789525262.692526}, {"event_id": "19f47656f61a4326871d069cce34e02f", "step": 12, "value": 0.9999688191203807, "stage": "improve", "created_at": 1789525256.5093887}, {"event_id": "0957c4af99c843b6a122c0e08610b098", "step": 13, "value": 0.9999661654284983, "stage": "improve", "created_at": 1789525586.2241607}, {"event_id": "752420ddc10d4b7d99593e8ec8e364c7", "step": 14, "value": 0.9999144184367896, "stage": "improve", "created_at": 1789525824.853713}, {"event_id": "89c73915f7844a50a3737d67708a64b2", "step": 15, "value": 0.9999084476300542, "stage": "draft", "created_at": 1789526147.0399458}, {"event_id": "dd59499d394b40afa0956c5f999c58c4", "step": 16, "value": 0.9999761167730576, "stage": "evolution", "created_at": 1789526454.800136}, {"event_id": "dc0a73f60f1044ffa037ce00c091be2b", "step": 17, "value": 0.9999588677758213, "stage": "evolution", "created_at": 1789526856.0332675}, {"event_id": "0cd4c3241a494a6b8bfe22e9a9afb5c1", "step": 19, "value": 0.9999562140839389, "stage": "improve", "created_at": 1789526315.2045097}, {"event_id": "e9e9242e67f94a03a49221f021a48f5a", "step": 21, "value": 0.9993780409650416, "stage": "debug", "created_at": 1789529004.618715}, {"event_id": "313c6578572b48dfb1b182fac4018ee3", "step": 22, "value": 0.9999071207841129, "stage": "evolution", "created_at": 1789529654.4341376}, {"event_id": "8f4edb99cd3543ba9f0680a3759eaa35", "step": 23, "value": 0.9999741265041457, "stage": "evolution", "created_at": 1789530354.669627}, {"event_id": "9e262e4f359b49f9aec0de61c2c6c292", "step": 24, "value": 0.9999475895853209, "stage": "debug", "created_at": 1789529600.3511362}, {"event_id": "2e4faac4daa643e58637d5a536f5b13f", "step": 25, "value": 0.9999535603920564, "stage": "evolution", "created_at": 1789529106.3229806}, {"event_id": "879aa46c19134807a1cc28dad13a0442", "step": 29, "value": 0.999991375501382, "stage": "debug", "created_at": 1789532157.4697955}, {"event_id": "afc9a76beab14218b60c9e0145a42fdb", "step": 30, "value": 0.9999986731540588, "stage": "debug", "created_at": 1789531903.3333113}, {"event_id": "d679e357ff124c15b24c7c1b9d9c9e50", "step": 31, "value": 0.999821870932388, "stage": "debug", "created_at": 1789532218.9954698}, {"event_id": "0a8930f68a72462bb244252065843ba6", "step": 32, "value": 0.9999907120784113, "stage": "improve", "created_at": 1789532855.7754166}, {"event_id": "7d07959f323f48b6b438059c64c1db4c", "step": 33, "value": 0.9999164087057016, "stage": "improve", "created_at": 1789532917.7322102}, {"event_id": "d15e484982044893a053bee80b89b0e1", "step": 35, "value": 0.9996958205679696, "stage": "improve", "created_at": 1789533544.1172814}, {"event_id": "e5b1a77e94824aa4ad95920fa29a15db", "step": 36, "value": 0.9997532066549284, "stage": "debug", "created_at": 1789533961.1332238}, {"event_id": "3750c8df5c294b6bba796f71e6308a1b", "step": 37, "value": 0.9998945157476711, "stage": "improve", "created_at": 1789533997.3341532}, {"event_id": "992a3d2a662347d2918878f43411e62b", "step": 39, "value": 0.999342216124628, "stage": "debug", "created_at": 1789535147.7560434}, {"event_id": "f4f1a72039ea421d8749bf2df21a4a61", "step": 40, "value": 0.9999727996582044, "stage": "evolution", "created_at": 1789535033.982995}, {"event_id": "927624b105f945f5ab4734256dabd5de", "step": 41, "value": 0.9999582043528508, "stage": "improve", "created_at": 1789534644.4497972}, {"event_id": "c613a5a4160b47f386f4d65fc943e959", "step": 42, "value": 0.9999263600502608, "stage": "evolution", "created_at": 1789536824.1618364}, {"event_id": "24a66966a3a34bb580bb290fe4a02f48", "step": 43, "value": 0.9999840778487051, "stage": "evolution", "created_at": 1789537889.7544394}, {"event_id": "baa5e6a859d545d59e6023329f0e1a93", "step": 44, "value": 0.9999960194621763, "stage": "evolution", "created_at": 1789537962.6147304}, {"event_id": "b98359a56ef141f69f7513a724b1f8ad", "step": 45, "value": 0.9999814241568227, "stage": "fusion", "created_at": 1789538684.009097}, {"event_id": "ed51e126ac904f2ab2ff3991d9da8319", "step": 46, "value": 0.9999694825433514, "stage": "evolution", "created_at": 1789541660.7392752}, {"event_id": "0b36285fd31647f7ada99b706bc157a8", "step": 47, "value": 0.9999854046946464, "stage": "evolution", "created_at": 1789543107.8237474}, {"event_id": "d048ed6117b24442a067bfd35ced8c6e", "step": 48, "value": 0.9999223795124372, "stage": "fusion", "created_at": 1789539348.937217}, {"event_id": "ffbc24a987b5499b949efa2c30d13181", "step": 52, "value": 1.0, "stage": "debug", "created_at": 1789546567.1296833}, {"event_id": "01348e5d2eb24172ba71a597eb3ca1cc", "step": 53, "value": 0.9999774436189989, "stage": "evolution", "created_at": 1789545558.234757}], "maximize": true, "elapsed_seconds": 28847.59518456459, "node_count": 61, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-three-20260916/xixian.gp7-long-horizon-pibo.aerial-cactus-identification.yaml", "note": ""}, {"id": "xixian.gp7-long-horizon-pibo.aptos2019-blindness-detection", "experiment_id": "mlebench-gp7-three-20260916", "family": "MLEBench", "method": "gp7_long_horizon_pibo", "dataset": "aptos2019-blindness-detection", "status": "archived", "official_score": 0.90696, "medal": "none", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.930508, "silver": 0.919654, "bronze": 0.914492}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/results/private_grades.jsonl:46", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}, {"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/runs/gp7_long_horizon_pibo/02_aptos2019-blindness-detection/logs/journal.json", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}], "alternate_scores": [], "journal_ref": "gp7-three-bo-analysis-20260916:gp7-three-66-runs/runs/gp7_long_horizon_pibo/02_aptos2019-blindness-detection/logs/journal.json", "metrics": [{"event_id": "4fc1a1de9488450f880eec5c0c2be03a", "step": 5, "value": 0.8912710505239293, "stage": "debug", "created_at": 1789522983.558641}, {"event_id": "acbfedc3140741a49906c5d2f2e9f013", "step": 6, "value": 0.866807868543821, "stage": "debug", "created_at": 1789523501.576266}, {"event_id": "4601f8dce11e4fe484c3ac6ac7d90ffb", "step": 8, "value": 0.8632034712879636, "stage": "debug", "created_at": 1789523550.9891517}, {"event_id": "f44e9a989e874f1eb58ee2d2a09503d9", "step": 10, "value": 0.9034973693214507, "stage": "debug", "created_at": 1789524841.6147022}, {"event_id": "735ff33c611440518019ec41ed181d7c", "step": 12, "value": 0.8530033182674472, "stage": "improve", "created_at": 1789526359.1321523}, {"event_id": "7ac81b9e067440ffa74a2e0c8e73530d", "step": 13, "value": 0.8609369483311902, "stage": "debug", "created_at": 1789525807.939623}, {"event_id": "887db6c078c64c71998dba88e8e99b9b", "step": 14, "value": 0.8806600000823148, "stage": "debug", "created_at": 1789526485.866841}, {"event_id": "7fa340f57f0640ab865d3c1606fabfb5", "step": 17, "value": 0.893414287622168, "stage": "improve", "created_at": 1789527840.6561582}, {"event_id": "14441653320440f79784a77e2d230f09", "step": 18, "value": 0.8991746636180503, "stage": "improve", "created_at": 1789528473.6179643}, {"event_id": "195140739ca7473ea6f69fe83426aad3", "step": 20, "value": 0.8947888523859137, "stage": "debug", "created_at": 1789529060.3343427}, {"event_id": "8f70e89ddd394564a251bbfd98a5d768", "step": 22, "value": 0.9122891647664894, "stage": "debug", "created_at": 1789530801.212529}, {"event_id": "100e814e49024252a34017e262df09cb", "step": 23, "value": 0.9057581112020185, "stage": "debug", "created_at": 1789531764.2398133}, {"event_id": "42a65ab52c504af69c19f2ef61849363", "step": 28, "value": 0.9087147219344817, "stage": "improve", "created_at": 1789533382.2847433}, {"event_id": "2f0c599164b54a8391a7889364739e9a", "step": 29, "value": 0.906304311689414, "stage": "debug", "created_at": 1789536079.9128728}, {"event_id": "d6d37b552dc34660b0dfeb1a6c41587b", "step": 34, "value": 0.911237946114766, "stage": "fusion_draft", "created_at": 1789544345.378573}, {"event_id": "977676c343004a538ae0901986f0be20", "step": 35, "value": 0.9238163317657119, "stage": "improve", "created_at": 1789537492.0137138}, {"event_id": "0b1f861da167497484f556017c61f28b", "step": 36, "value": 0.9211474127280258, "stage": "improve", "created_at": 1789533337.3304942}, {"event_id": "7b555cda922641b7999be2482aefc915", "step": 37, "value": 0.9045055439377239, "stage": "improve", "created_at": 1789548193.7447457}], "maximize": true, "elapsed_seconds": 28818.250648021698, "node_count": 41, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-three-20260916/xixian.gp7-long-horizon-pibo.aptos2019-blindness-detection.yaml", "note": ""}, {"id": "xixian.gp7-long-horizon-pibo.denoising-dirty-documents", "experiment_id": "mlebench-gp7-three-20260916", "family": "MLEBench", "method": "gp7_long_horizon_pibo", "dataset": "denoising-dirty-documents", "status": "archived", "official_score": 0.01166, "medal": "gold", "valid_submission": true, "score_maximize": false, "thresholds": {"gold": 0.01794, "silver": 0.02609, "bronze": 0.04517}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/results/private_grades.jsonl:47", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}, {"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/runs/gp7_long_horizon_pibo/03_denoising-dirty-documents/logs/journal.json", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}], "alternate_scores": [], "journal_ref": "gp7-three-bo-analysis-20260916:gp7-three-66-runs/runs/gp7_long_horizon_pibo/03_denoising-dirty-documents/logs/journal.json", "metrics": [{"event_id": "3b4ca3a95a0347fb9c2b569fff6de3ee", "step": 5, "value": 0.020736210436633016, "stage": "debug", "created_at": 1789522939.1168947}, {"event_id": "4716d0a4b32245bf9c577044201679fe", "step": 6, "value": 0.03157242449349179, "stage": "debug", "created_at": 1789522958.7644958}, {"event_id": "eb94abdd6df4448d993430b45124d2d2", "step": 11, "value": 0.020415892111096394, "stage": "improve", "created_at": 1789523457.4134352}, {"event_id": "33dd940aeb0849718c26370f00e335ab", "step": 13, "value": 0.016451882908177753, "stage": "improve", "created_at": 1789523934.6516235}, {"event_id": "ad9e65572e394c2982e68a9024d98155", "step": 14, "value": 0.014388036993424374, "stage": "debug", "created_at": 1789524242.8161879}, {"event_id": "582252e538d64e5086d280b8385f32d0", "step": 15, "value": 0.014548377004421019, "stage": "improve", "created_at": 1789524413.4550261}, {"event_id": "9d300851492f41fbad79b930bc7f7447", "step": 17, "value": 0.01435531000752168, "stage": "debug", "created_at": 1789524851.0544667}, {"event_id": "7b3e1685ebcd4bb18325d77730807b26", "step": 18, "value": 0.014056459052282916, "stage": "improve", "created_at": 1789524942.1874957}, {"event_id": "06fa89ee0ba84e518a4f959a55baa412", "step": 20, "value": 0.014792119541283935, "stage": "improve", "created_at": 1789525236.1819956}, {"event_id": "2cb444e479f14bdba139fcdb21c6e412", "step": 21, "value": 0.0135437423839976, "stage": "improve", "created_at": 1789525496.508082}, {"event_id": "e29e9c81bc0e451cac07a18db1915491", "step": 22, "value": 0.014941433353153719, "stage": "improve", "created_at": 1789525768.3436542}, {"event_id": "ede686218d2a42169acac11629a80cdc", "step": 23, "value": 0.013802448788138666, "stage": "improve", "created_at": 1789526141.0418472}, {"event_id": "d589ae6190184e7389e76999fe2b7d43", "step": 28, "value": 0.013311728202222773, "stage": "improve", "created_at": 1789526547.8670688}, {"event_id": "b71aefbfc2914e659f4dd872ab6c7744", "step": 31, "value": 0.01354862082062107, "stage": "debug", "created_at": 1789527276.0438628}, {"event_id": "1c9856502e5d4604b3f695e72cb70ea3", "step": 32, "value": 0.070561782060924, "stage": "debug", "created_at": 1789525513.7541053}, {"event_id": "af04b5df45d840a4a64220e07006cb9a", "step": 33, "value": 0.014623388777705061, "stage": "debug", "created_at": 1789527550.3652432}, {"event_id": "7b9fb074e5264cc98ebe56270114c9fc", "step": 39, "value": 0.01380295295419976, "stage": "debug", "created_at": 1789528652.6407518}, {"event_id": "b7bded1f6e1247e4a8fb24dd19298b0f", "step": 43, "value": 0.01376298010420629, "stage": "debug", "created_at": 1789529680.0422344}, {"event_id": "cab5217b0b4549f4894103d4e9f70fe3", "step": 44, "value": 0.05242466357179718, "stage": "debug", "created_at": 1789529824.4332042}, {"event_id": "3b0df83f98a34d1b8c28832fd9607c37", "step": 45, "value": 0.01462403886923282, "stage": "draft", "created_at": 1789530356.6209733}, {"event_id": "3d4bd04bbd484041b1116b4471938ca1", "step": 46, "value": 0.012226030469645353, "stage": "debug", "created_at": 1789529805.472169}, {"event_id": "2102c48a0d584b639dc931f0c6d57497", "step": 52, "value": 0.015607409652803982, "stage": "debug", "created_at": 1789531447.899832}, {"event_id": "10de3fd232d24b4194297fec69f4cded", "step": 53, "value": 0.013023378668252978, "stage": "debug", "created_at": 1789531628.291832}, {"event_id": "bcb2e7ad6ede4dca9fcbe984f9ee7cf2", "step": 55, "value": 0.01893332048631041, "stage": "debug", "created_at": 1789531974.5705626}, {"event_id": "c35df92802124502b534fe3bccd4540c", "step": 58, "value": 0.03808029858919181, "stage": "debug", "created_at": 1789532883.718902}, {"event_id": "e2e6fd465d934299bb207cf9be7be875", "step": 59, "value": 0.012298250798799738, "stage": "debug", "created_at": 1789533476.9415965}, {"event_id": "98e2c2bedf9e4af8b7b5af2ee747eee5", "step": 60, "value": 0.015660155869083058, "stage": "evolution", "created_at": 1789533918.7252102}, {"event_id": "64069818dc524386be24dbf355f2d343", "step": 61, "value": 0.013186049004646358, "stage": "evolution", "created_at": 1789534140.1834497}, {"event_id": "ac50a3632f3041fa96989f5e43f687f6", "step": 62, "value": 0.011986069592428211, "stage": "evolution", "created_at": 1789534305.1218169}, {"event_id": "04216985f7274d4f89b5f01f38abb35e", "step": 63, "value": 0.013591920481097721, "stage": "evolution", "created_at": 1789534758.3716567}, {"event_id": "7b3edd0b5ca1426caadfd5ac6c64a36a", "step": 64, "value": 0.013556611673433078, "stage": "evolution", "created_at": 1789535246.4940805}, {"event_id": "218fd4a7795f46adb1dfb88338fa3bb7", "step": 65, "value": 0.027007635031909092, "stage": "improve", "created_at": 1789535477.8450382}, {"event_id": "68bd401b06c44a958626db55b568e18c", "step": 66, "value": 0.15617692544484688, "stage": "improve", "created_at": 1789535676.4443636}, {"event_id": "a24c5afacba6478892500878b32d75fd", "step": 69, "value": 0.04552730226476118, "stage": "improve", "created_at": 1789536348.4167347}, {"event_id": "0d527b4e350b4be8beefd0291210a32d", "step": 70, "value": 0.10763434530258541, "stage": "improve", "created_at": 1789536981.6360266}, {"event_id": "fb430d34056043fbacbf28d17487887b", "step": 71, "value": 0.03321716898521317, "stage": "debug", "created_at": 1789537427.2510376}, {"event_id": "44c7a7b69b4349bfa0b3dc554ec2411d", "step": 73, "value": 0.013197562999550012, "stage": "improve", "created_at": 1789537690.5191002}, {"event_id": "e8c905d271eb4d00b72315c1d2341b50", "step": 75, "value": 0.12367717355862946, "stage": "evolution", "created_at": 1789538489.2689593}, {"event_id": "22d42fec10f54008b87dd00cd98c380c", "step": 76, "value": 0.012325341797031448, "stage": "fusion", "created_at": 1789538866.1093938}, {"event_id": "b6fe8803df894df58da00e63abe5cab9", "step": 83, "value": 0.012487423439161332, "stage": "debug", "created_at": 1789540520.4085002}, {"event_id": "90f06ca767664128a248e7e5c93a68c6", "step": 87, "value": 0.01312256682983262, "stage": "debug", "created_at": 1789542018.6664743}, {"event_id": "9c8be65c95a54495a0070e370b094b0e", "step": 88, "value": 0.05856596752272471, "stage": "debug", "created_at": 1789542524.44395}, {"event_id": "fe41564c6d56449b8d04730838c7651d", "step": 93, "value": 0.012144788757051281, "stage": "evolution", "created_at": 1789543397.0019739}, {"event_id": "f45184ec69ed4eac9ca8817cc9a903b7", "step": 94, "value": 0.09265093994306518, "stage": "debug", "created_at": 1789543783.865354}, {"event_id": "5734f0fd10344146af17088ee4934ad2", "step": 95, "value": 0.07107742602244654, "stage": "debug", "created_at": 1789543738.0696926}, {"event_id": "e6cc28c06047446a855056d57030a945", "step": 96, "value": 0.0118571364253124, "stage": "evolution", "created_at": 1789544488.8071713}, {"event_id": "425ddc55921e4c63abe418f50ca662b2", "step": 97, "value": 0.028723003812240695, "stage": "evolution", "created_at": 1789544862.917852}, {"event_id": "c4abdf3478b74cb698a316e0f930920d", "step": 98, "value": 0.011213749163117334, "stage": "evolution", "created_at": 1789544931.4036987}, {"event_id": "b0838922034040c5bc26f823a43db3dd", "step": 99, "value": 0.011291303618555168, "stage": "improve", "created_at": 1789545582.7099307}, {"event_id": "3fd359aa5bb943d2a16bc92752a9abb8", "step": 100, "value": 0.011282153314462072, "stage": "improve", "created_at": 1789546102.9984448}, {"event_id": "5af92ab9b18b4cf1a11f08a8c3394c0a", "step": 101, "value": 0.011477859514208266, "stage": "improve", "created_at": 1789546222.5673616}, {"event_id": "e65e3814328241e38fd74a4f9a35bf7a", "step": 103, "value": 0.011288303995257314, "stage": "improve", "created_at": 1789546728.5413775}, {"event_id": "c3ca71b42410477684477bb4a264a4ed", "step": 104, "value": 0.013950974122799447, "stage": "evolution", "created_at": 1789547477.2203133}, {"event_id": "5f09d9709d9647a78e82ff538272bc32", "step": 105, "value": 0.012741043637952315, "stage": "debug", "created_at": 1789547613.4017496}, {"event_id": "cb31eadeb41545b8a48c721556b9af90", "step": 106, "value": 0.01150103471879497, "stage": "fusion", "created_at": 1789548690.2712116}, {"event_id": "47ad525e506a4dc9b8f78cb67915177c", "step": 107, "value": 0.011252273350076867, "stage": "improve", "created_at": 1789548705.0528817}, {"event_id": "172095f5f638462ca517da3f557a94d8", "step": 108, "value": 0.0115883787435717, "stage": "improve", "created_at": 1789547889.8759584}], "maximize": false, "elapsed_seconds": 28811.168864011765, "node_count": 112, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-three-20260916/xixian.gp7-long-horizon-pibo.denoising-dirty-documents.yaml", "note": ""}, {"id": "xixian.gp7-long-horizon-pibo.detecting-insults-in-social-commentary", "experiment_id": "mlebench-gp7-three-20260916", "family": "MLEBench", "method": "gp7_long_horizon_pibo", "dataset": "detecting-insults-in-social-commentary", "status": "archived", "official_score": 0.95271, "medal": "gold", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.83321, "silver": 0.82307, "bronze": 0.79111}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/results/private_grades.jsonl:48", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}, {"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/runs/gp7_long_horizon_pibo/04_detecting-insults-in-social-commentary/logs/journal.json", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}], "alternate_scores": [], "journal_ref": "gp7-three-bo-analysis-20260916:gp7-three-66-runs/runs/gp7_long_horizon_pibo/04_detecting-insults-in-social-commentary/logs/journal.json", "metrics": [{"event_id": "48cc9f17c1da4da69a5be6c23f43ccae", "step": 7, "value": 0.9416543513957307, "stage": "debug", "created_at": 1789523091.2041707}, {"event_id": "f02ea513ffeb41a0ad392993790c95ea", "step": 8, "value": 0.945935960591133, "stage": "improve", "created_at": 1789523601.2091289}, {"event_id": "55b4b3234a55457db281412895263d08", "step": 10, "value": 0.9422577996715928, "stage": "debug", "created_at": 1789523505.0839458}, {"event_id": "4ccd63ef0d1543a6b4b5a2d6e85a45d2", "step": 11, "value": 0.8786042692939244, "stage": "draft", "created_at": 1789522819.9274743}, {"event_id": "5e89a8b63dd943ab90ae881f7b0593b2", "step": 12, "value": 0.9288259441707718, "stage": "debug", "created_at": 1789524206.3091776}, {"event_id": "935917f602c8432fbcfe1cfbbe686879", "step": 13, "value": 0.9498111658456486, "stage": "improve", "created_at": 1789524497.566995}, {"event_id": "fefc7c3ab7c24137bd9f11395feb689c", "step": 14, "value": 0.947828407224959, "stage": "improve", "created_at": 1789524519.280211}, {"event_id": "050b3fa123e849d2915650e76c91f6ce", "step": 15, "value": 0.9216174055829227, "stage": "improve", "created_at": 1789524572.1744466}, {"event_id": "4bdcaa2c722e4354be4f1399860efb56", "step": 16, "value": 0.9496387520525451, "stage": "improve", "created_at": 1789525214.8831372}, {"event_id": "709b2b30dbf341dfb3c1c7a9aae15018", "step": 17, "value": 0.9352134646962234, "stage": "improve", "created_at": 1789524826.7288074}, {"event_id": "5a29bce761cb4f7b8ce62966c9ebb28e", "step": 18, "value": 0.9527175697865353, "stage": "improve", "created_at": 1789525703.6088283}, {"event_id": "6f29bf8eb55047c1b49ad60fac7d008e", "step": 19, "value": 0.9520443349753694, "stage": "improve", "created_at": 1789526078.998422}, {"event_id": "d8c4b06f4dd14021b3fcdab9540ca55d", "step": 20, "value": 0.9535385878489326, "stage": "improve", "created_at": 1789526615.4147139}, {"event_id": "aa469fb57a3047b4aea79851ea7bec8a", "step": 21, "value": 0.9475697865353038, "stage": "improve", "created_at": 1789525682.3557193}, {"event_id": "a0e009561bb041af8b57093a9e138468", "step": 24, "value": 0.9489901477832512, "stage": "debug", "created_at": 1789527664.195844}, {"event_id": "44c6201a3a4940af9305fcb7056a265c", "step": 25, "value": 0.9529638752052546, "stage": "improve", "created_at": 1789527208.5055916}, {"event_id": "139ce3b9a69f4df9b7ebff1d960c105e", "step": 26, "value": 0.9548440065681445, "stage": "evolution", "created_at": 1789528264.8827653}, {"event_id": "62781e68ee9d438c97ff0363ecaf2618", "step": 27, "value": 0.9332512315270937, "stage": "improve", "created_at": 1789525101.6931636}, {"event_id": "ae1063ace46d4a1ea91399d5e4600f8b", "step": 28, "value": 0.9428981937602626, "stage": "improve", "created_at": 1789529321.17796}, {"event_id": "cc9ad40efb434311aad94e0fcc85970b", "step": 31, "value": 0.9492610837438423, "stage": "improve", "created_at": 1789533474.2373354}, {"event_id": "21aa209d60fc4492bf93ad3c515858c8", "step": 32, "value": 0.9501970443349753, "stage": "debug", "created_at": 1789533299.068392}, {"event_id": "6b51e371427f4c90abcd54eca9dbe81d", "step": 33, "value": 0.9524220032840722, "stage": "fusion", "created_at": 1789537204.203834}, {"event_id": "b9a75a201a57410e9a826a7ce24014c3", "step": 35, "value": 0.9126067323481116, "stage": "debug", "created_at": 1789538679.1522117}, {"event_id": "b2f668df825143ada3868aa86c5cafcb", "step": 36, "value": 0.895944170771757, "stage": "improve", "created_at": 1789539108.7060385}, {"event_id": "d8a259c9e4774460b3ce74a7819cddc4", "step": 38, "value": 0.9508456486042692, "stage": "debug", "created_at": 1789540254.7482471}, {"event_id": "e7b4f0f20cbf41ab8756e6ad4dd3310a", "step": 39, "value": 0.9423070607553365, "stage": "evolution", "created_at": 1789533847.2258117}, {"event_id": "5821981c08c54bf4bba279fb419250a2", "step": 42, "value": 0.9517651888341543, "stage": "improve", "created_at": 1789528311.9609473}, {"event_id": "24a72db0fa534b048df1203d8518b5da", "step": 43, "value": 0.8932881773399015, "stage": "debug", "created_at": 1789543787.2884936}, {"event_id": "7e6c0dbabdd942fd9063d93eb6bcc9c6", "step": 44, "value": 0.950623973727422, "stage": "fusion", "created_at": 1789543915.4912922}, {"event_id": "6af0f849c29d4bfc968b958eea081fb2", "step": 45, "value": 0.9501231527093597, "stage": "fusion", "created_at": 1789544140.3787649}, {"event_id": "53ab236d3d5e4f0da8815493260f4e60", "step": 47, "value": 0.955927750410509, "stage": "debug", "created_at": 1789545563.4330227}, {"event_id": "8e113ea08d174118a242835f42ada045", "step": 48, "value": 0.9536124794745484, "stage": "evolution", "created_at": 1789541666.4063892}, {"event_id": "02fd7592fdc84cb6ac18e8320bcaf4d0", "step": 49, "value": 0.9554022988505747, "stage": "improve", "created_at": 1789547042.5286207}, {"event_id": "e75854eb2d6741369599eab93b655334", "step": 50, "value": 0.948464696223317, "stage": "improve", "created_at": 1789547125.1091068}, {"event_id": "80e5627991924ed88c426c6841a61d66", "step": 52, "value": 0.9476272577996715, "stage": "fusion_draft", "created_at": 1789549163.1853554}, {"event_id": "1be72442d2834f98b7814fb49fbbc163", "step": 53, "value": 0.9504105090311987, "stage": "improve", "created_at": 1789548796.755387}], "maximize": true, "elapsed_seconds": 28806.30499482155, "node_count": 57, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-three-20260916/xixian.gp7-long-horizon-pibo.detecting-insults-in-social-commentary.yaml", "note": ""}, {"id": "xixian.gp7-long-horizon-pibo.dog-breed-identification", "experiment_id": "mlebench-gp7-three-20260916", "family": "MLEBench", "method": "gp7_long_horizon_pibo", "dataset": "dog-breed-identification", "status": "archived", "official_score": 0.30621, "medal": "none", "valid_submission": true, "score_maximize": false, "thresholds": {"gold": 0.0005, "silver": 0.00539, "bronze": 0.04598}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/results/private_grades.jsonl:49", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}, {"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/runs/gp7_long_horizon_pibo/05_dog-breed-identification/logs/journal.json", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}], "alternate_scores": [], "journal_ref": "gp7-three-bo-analysis-20260916:gp7-three-66-runs/runs/gp7_long_horizon_pibo/05_dog-breed-identification/logs/journal.json", "metrics": [{"event_id": "5262a9bc94ab4761b4475b10236bfd50", "step": 4, "value": 0.779084850598222, "stage": "draft", "created_at": 1789522860.766957}, {"event_id": "015838bb74484ed4bda5c548cc2ef5be", "step": 6, "value": 0.49838375459763573, "stage": "debug", "created_at": 1789523238.6624131}, {"event_id": "24dab341573c40c5817d54446413163f", "step": 7, "value": 1.0884697212498682, "stage": "debug", "created_at": 1789523881.9378295}, {"event_id": "e22946854073482a869cd5b2d9bbd04a", "step": 8, "value": 2.056545785019293, "stage": "debug", "created_at": 1789523117.9472163}, {"event_id": "e4f28604b8dd4834bd744bc91efca5bf", "step": 9, "value": 0.5461839923292148, "stage": "improve", "created_at": 1789524449.3491597}, {"event_id": "749db399a8454c318d076885089c7083", "step": 10, "value": 2.371842298562693, "stage": "improve", "created_at": 1789524559.6665928}, {"event_id": "5519ba41b468443e8db8568176fe2149", "step": 12, "value": 0.5592301095269103, "stage": "improve", "created_at": 1789525558.786041}, {"event_id": "f5fd020bfcbc4024959dce89d06a5945", "step": 13, "value": 0.4409009299264881, "stage": "debug", "created_at": 1789526627.300961}, {"event_id": "014410587f0d4e77af22cd705dc41447", "step": 14, "value": 2.5942086946246383, "stage": "improve", "created_at": 1789526351.0760646}, {"event_id": "10146c83d51f479b87ac80317372a926", "step": 15, "value": 0.43558929494699267, "stage": "improve", "created_at": 1789527565.428652}, {"event_id": "88a6b04f1c0847d7b69e2a0baa0a6f64", "step": 16, "value": 1.318377376159611, "stage": "improve", "created_at": 1789527360.4787474}, {"event_id": "6fe3a84b2eff4c83aaaf774a318fcf33", "step": 17, "value": 0.42545721083171567, "stage": "improve", "created_at": 1789527682.6729133}, {"event_id": "c6631daf8dd24e698455ef86995fbb2f", "step": 22, "value": 0.8362478710577114, "stage": "improve", "created_at": 1789530092.0488877}, {"event_id": "5b58f77adeaf4768a8f7fc766d345f76", "step": 23, "value": 0.44960048267688907, "stage": "improve", "created_at": 1789536594.3251717}, {"event_id": "41ad5c741c164a8398c86d381430b61f", "step": 24, "value": 1.3810766069250768, "stage": "debug", "created_at": 1789536372.2573004}, {"event_id": "ec3689d7be584597afc12c5d9e301bb2", "step": 26, "value": 0.44729360859289835, "stage": "improve", "created_at": 1789538034.2931623}, {"event_id": "b2ec35333fd443d790bfa6839a27023a", "step": 28, "value": 0.27145820998371917, "stage": "improve", "created_at": 1789540180.400606}, {"event_id": "13b46fef8d644cbea3f279cedfe190b9", "step": 29, "value": 0.40343772032112885, "stage": "debug", "created_at": 1789541861.8118958}, {"event_id": "abb31633e86f44fb8330b0c08aae4d46", "step": 30, "value": 0.49838375459763573, "stage": "improve", "created_at": 1789543335.5138593}, {"event_id": "e031355ed8e3415783858cb99d8f6bbb", "step": 31, "value": 0.5329081411718859, "stage": "improve", "created_at": 1789544128.081331}, {"event_id": "c06a26fe776148a3bdc621e072ae899d", "step": 32, "value": 0.5385274603896357, "stage": "improve", "created_at": 1789545369.0604389}, {"event_id": "74acae4981ad4169a33106ba6dd471d2", "step": 33, "value": 0.5169340954769993, "stage": "draft", "created_at": 1789548039.4450839}, {"event_id": "a08f93d139d340779e04e8e8f9f123ca", "step": 34, "value": 0.6543041787501013, "stage": "improve", "created_at": 1789544333.3818238}, {"event_id": "ce81e8d713e64517bdc908856b577d3e", "step": 35, "value": 0.27274711651080585, "stage": "improve", "created_at": 1789533811.0300233}], "maximize": false, "elapsed_seconds": 28798.042140722275, "node_count": 36, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-three-20260916/xixian.gp7-long-horizon-pibo.dog-breed-identification.yaml", "note": ""}, {"id": "xixian.gp7-long-horizon-pibo.dogs-vs-cats-redux-kernels-edition", "experiment_id": "mlebench-gp7-three-20260916", "family": "MLEBench", "method": "gp7_long_horizon_pibo", "dataset": "dogs-vs-cats-redux-kernels-edition", "status": "archived", "official_score": 0.00421, "medal": "gold", "valid_submission": true, "score_maximize": false, "thresholds": {"gold": 0.03882, "silver": 0.05038, "bronze": 0.06127}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/results/private_grades.jsonl:50", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}, {"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/runs/gp7_long_horizon_pibo/06_dogs-vs-cats-redux-kernels-edition/logs/journal.json", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}], "alternate_scores": [], "journal_ref": "gp7-three-bo-analysis-20260916:gp7-three-66-runs/runs/gp7_long_horizon_pibo/06_dogs-vs-cats-redux-kernels-edition/logs/journal.json", "metrics": [{"event_id": "d4c6ac9a50ff4673a77575f652f276b0", "step": 4, "value": 0.003760777152462075, "stage": "debug", "created_at": 1789523434.3551524}, {"event_id": "febf72ce1cd540f18e4c3920091fa62a", "step": 5, "value": 0.003685233802649595, "stage": "draft", "created_at": 1789522933.7995763}, {"event_id": "2a9e2055f8bf42a19726bc1a0b270a74", "step": 6, "value": 0.003858054804314962, "stage": "improve", "created_at": 1789523746.8433394}, {"event_id": "7f99962b03a64b9c8f2f8fbef659f927", "step": 8, "value": 0.0036153761664666543, "stage": "improve", "created_at": 1789524487.5419128}, {"event_id": "fb45d161345843a4b558ca568b3b305c", "step": 9, "value": 0.003080644243900596, "stage": "improve", "created_at": 1789524828.074517}, {"event_id": "5892dc16e5a440c89a40c0d83f734ab7", "step": 10, "value": 0.002424695725060185, "stage": "improve", "created_at": 1789525898.7457469}, {"event_id": "21e8fd3b8d524a58bb27dd2f3661bacf", "step": 11, "value": 0.002708237100780825, "stage": "improve", "created_at": 1789523969.2356753}, {"event_id": "8f50d624d6414adcb24d735142548fa8", "step": 12, "value": 0.018635278570788595, "stage": "debug", "created_at": 1789524628.4781005}, {"event_id": "78414572fe914dc7b60e29c46b874c59", "step": 14, "value": 0.0022596742419025953, "stage": "improve", "created_at": 1789526946.3629503}, {"event_id": "1c289557dd4949d89a95f86ead84e9a7", "step": 15, "value": 0.003054626724397716, "stage": "improve", "created_at": 1789526889.4386356}, {"event_id": "1685bb155fca4a7fb0b52cf9a0321325", "step": 17, "value": 0.006688808560817412, "stage": "fusion_draft", "created_at": 1789546208.4139326}, {"event_id": "398a21db2d4c4e5e838edd2e4afa2c74", "step": 18, "value": 0.004679583683475016, "stage": "improve", "created_at": 1789549609.7435455}], "maximize": false, "elapsed_seconds": 28810.38814687729, "node_count": 22, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-three-20260916/xixian.gp7-long-horizon-pibo.dogs-vs-cats-redux-kernels-edition.yaml", "note": ""}, {"id": "xixian.gp7-long-horizon-pibo.histopathologic-cancer-detection", "experiment_id": "mlebench-gp7-three-20260916", "family": "MLEBench", "method": "gp7_long_horizon_pibo", "dataset": "histopathologic-cancer-detection", "status": "archived", "official_score": 0.99709, "medal": "gold", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.9835, "silver": 0.9798, "bronze": 0.9738}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/results/private_grades.jsonl:51", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}, {"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/runs/gp7_long_horizon_pibo/07_histopathologic-cancer-detection/logs/journal.json", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}], "alternate_scores": [], "journal_ref": "gp7-three-bo-analysis-20260916:gp7-three-66-runs/runs/gp7_long_horizon_pibo/07_histopathologic-cancer-detection/logs/journal.json", "metrics": [{"event_id": "261c95b4fb4b401ca85a0d38c0096fb2", "step": 3, "value": 0.9887689703675338, "stage": "draft", "created_at": 1789523070.6768384}, {"event_id": "3edb50bfa6fa4928924d878eb0d53ffe", "step": 5, "value": 0.997157116243646, "stage": "debug", "created_at": 1789524304.844648}, {"event_id": "632aa1a21ef84227891f3c599639f480", "step": 9, "value": 0.9934623387380163, "stage": "improve", "created_at": 1789527184.3772047}, {"event_id": "788853dfa3e5428992ef371b44e6d47e", "step": 11, "value": 0.9971099725493932, "stage": "debug", "created_at": 1789534075.8000574}, {"event_id": "12633db435a34061b490a1f56b0d9a1b", "step": 13, "value": 0.9898515160132813, "stage": "improve", "created_at": 1789541173.330315}], "maximize": true, "elapsed_seconds": 28796.563272714615, "node_count": 15, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-three-20260916/xixian.gp7-long-horizon-pibo.histopathologic-cancer-detection.yaml", "note": ""}, {"id": "xixian.gp7-long-horizon-pibo.jigsaw-toxic-comment-classification-challenge", "experiment_id": "mlebench-gp7-three-20260916", "family": "MLEBench", "method": "gp7_long_horizon_pibo", "dataset": "jigsaw-toxic-comment-classification-challenge", "status": "archived", "official_score": 0.98497, "medal": "none", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.9874, "silver": 0.98668, "bronze": 0.98639}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/results/private_grades.jsonl:52", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}, {"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/runs/gp7_long_horizon_pibo/08_jigsaw-toxic-comment-classification-challenge/logs/journal.json", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}], "alternate_scores": [], "journal_ref": "gp7-three-bo-analysis-20260916:gp7-three-66-runs/runs/gp7_long_horizon_pibo/08_jigsaw-toxic-comment-classification-challenge/logs/journal.json", "metrics": [{"event_id": "63c2fa6053d44688be38c647d28152d3", "step": 6, "value": 0.9825794425069851, "stage": "debug", "created_at": 1789523493.1552334}, {"event_id": "213e35b332a249c19dde4e568fe077b9", "step": 7, "value": 0.9909413078787246, "stage": "debug", "created_at": 1789523377.0447807}, {"event_id": "6b1f6ad36d3749f69f922c4863a3c7d3", "step": 8, "value": 0.9878445388115352, "stage": "improve", "created_at": 1789526840.9840093}, {"event_id": "f14e0edc92fb40a591beb9dfb12385a7", "step": 11, "value": 0.9910127147746152, "stage": "debug", "created_at": 1789523262.6267898}, {"event_id": "810cbc6d2ecd405593f403f10398444e", "step": 12, "value": 0.985378774496362, "stage": "debug", "created_at": 1789530517.5282297}, {"event_id": "37521e0a26fb461ca7a9dfdef5b6431c", "step": 13, "value": 0.9887948373698724, "stage": "improve", "created_at": 1789531910.147373}, {"event_id": "20e469065a644de1adaff250b548582b", "step": 14, "value": 0.9896797240139357, "stage": "improve", "created_at": 1789527431.8070393}, {"event_id": "0c883040e6824aee9dd3485b881c39a2", "step": 15, "value": 0.988214448339432, "stage": "improve", "created_at": 1789539700.8796582}, {"event_id": "79510f8288df40eab33b6fad8358f539", "step": 16, "value": 0.4828218865259941, "stage": "improve", "created_at": 1789539606.695028}], "maximize": true, "elapsed_seconds": 28795.464302301407, "node_count": 17, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-three-20260916/xixian.gp7-long-horizon-pibo.jigsaw-toxic-comment-classification-challenge.yaml", "note": ""}, {"id": "xixian.gp7-long-horizon-pibo.leaf-classification", "experiment_id": "mlebench-gp7-three-20260916", "family": "MLEBench", "method": "gp7_long_horizon_pibo", "dataset": "leaf-classification", "status": "archived", "official_score": 0.01901, "medal": "none", "valid_submission": true, "score_maximize": false, "thresholds": {"gold": 0.0, "silver": 0.00791, "bronze": 0.01526}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/results/private_grades.jsonl:53", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}, {"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/runs/gp7_long_horizon_pibo/09_leaf-classification/logs/journal.json", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}], "alternate_scores": [], "journal_ref": "gp7-three-bo-analysis-20260916:gp7-three-66-runs/runs/gp7_long_horizon_pibo/09_leaf-classification/logs/journal.json", "metrics": [{"event_id": "a3517a11988246bdb26ff137a341d00c", "step": 3, "value": 0.021182096907269517, "stage": "draft", "created_at": 1789522079.3547492}, {"event_id": "6586f27eb5cf413997cae6d17ae91d25", "step": 4, "value": 0.026210978357404054, "stage": "draft", "created_at": 1789522417.6150765}, {"event_id": "e6443716182941f0a7997fbad70137a2", "step": 6, "value": 0.09312927047977297, "stage": "debug", "created_at": 1789523527.9288135}, {"event_id": "88e4207f89ff49dba31499faa548a5e0", "step": 7, "value": 0.042020655767594166, "stage": "debug", "created_at": 1789523914.8219945}, {"event_id": "02803dc7585f46299fa8c1b8892ff824", "step": 8, "value": 0.08340120290792884, "stage": "improve", "created_at": 1789524318.0103364}, {"event_id": "8cecd26442f54c92928cfaa2f1919dc2", "step": 9, "value": 0.0002443592614799995, "stage": "improve", "created_at": 1789524010.7769468}, {"event_id": "7ed1b760deae4988aa75327156e0c8ac", "step": 10, "value": 0.009651029484399179, "stage": "improve", "created_at": 1789524936.686282}, {"event_id": "affeafc8aafa4cd78af1981c73383f59", "step": 11, "value": 0.002968752400189587, "stage": "improve", "created_at": 1789524684.7981913}, {"event_id": "4e0f5ef8ddf2484eb445d8082e331edd", "step": 13, "value": 0.0024796077604401574, "stage": "improve", "created_at": 1789526638.6488447}, {"event_id": "bb350cfd0e1c43489a57fcfdffcfb716", "step": 14, "value": 0.002857342136886265, "stage": "improve", "created_at": 1789527894.12687}, {"event_id": "31825c2efd654650a47ee2ba088bd54d", "step": 15, "value": 0.0014519078398110878, "stage": "debug", "created_at": 1789527124.501469}, {"event_id": "fc8c64a5dac84ecc80c30595e16b543f", "step": 16, "value": 0.01922999860865067, "stage": "improve", "created_at": 1789532458.896872}, {"event_id": "2544116444a74d6fba9182f9660a63e7", "step": 17, "value": 0.011080322406415467, "stage": "improve", "created_at": 1789533000.5316331}, {"event_id": "2db4f22ceb15472095cfe14a642b4e0e", "step": 18, "value": 0.0013968680956914547, "stage": "improve", "created_at": 1789535088.2889278}, {"event_id": "fe3e28ab43ca4948977eeda89b530dd6", "step": 19, "value": 0.13543630279756344, "stage": "improve", "created_at": 1789539901.6923106}, {"event_id": "74e4d8aeb9ee4cd09aecb416b5452f78", "step": 22, "value": 0.008423951148818123, "stage": "debug", "created_at": 1789544682.3599136}], "maximize": false, "elapsed_seconds": 28805.948400735855, "node_count": 26, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-three-20260916/xixian.gp7-long-horizon-pibo.leaf-classification.yaml", "note": ""}, {"id": "xixian.gp7-long-horizon-pibo.mlsp-2013-birds", "experiment_id": "mlebench-gp7-three-20260916", "family": "MLEBench", "method": "gp7_long_horizon_pibo", "dataset": "mlsp-2013-birds", "status": "archived", "official_score": 0.91782, "medal": "silver", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.93527, "silver": 0.90038, "bronze": 0.87372}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/results/private_grades.jsonl:54", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}, {"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/runs/gp7_long_horizon_pibo/10_mlsp-2013-birds/logs/journal.json", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}], "alternate_scores": [], "journal_ref": "gp7-three-bo-analysis-20260916:gp7-three-66-runs/runs/gp7_long_horizon_pibo/10_mlsp-2013-birds/logs/journal.json", "metrics": [{"event_id": "2d007443d53d4b52a233c2047785c8df", "step": 6, "value": 0.7481579849211788, "stage": "debug", "created_at": 1789523339.4595315}, {"event_id": "9764463445744e3d88a5b3ac1fab24b9", "step": 9, "value": 0.7870159355723098, "stage": "debug", "created_at": 1789523579.8876905}, {"event_id": "126badb23a554e08bf3c562ea30fa041", "step": 14, "value": 0.7089487662782727, "stage": "debug", "created_at": 1789523970.7888796}, {"event_id": "541341779c344144a667688a56e626c5", "step": 15, "value": 0.7505997258396162, "stage": "debug", "created_at": 1789524241.4930544}, {"event_id": "b29cc63f434e424591669ce03852bf18", "step": 16, "value": 0.7667751884852638, "stage": "debug", "created_at": 1789524227.4565926}, {"event_id": "c75a5e4084b042e9b8cb46c70ec7c402", "step": 17, "value": 0.7371144619602468, "stage": "improve", "created_at": 1789524574.5072465}, {"event_id": "1a03ed924e32454eaec2ac1f50f643ff", "step": 18, "value": 0.7570767649074709, "stage": "improve", "created_at": 1789524633.1634068}, {"event_id": "5d567dad870c481da13f0766007f333a", "step": 19, "value": 0.7203221384509939, "stage": "improve", "created_at": 1789524768.100582}, {"event_id": "42b7453e73d747ab90377c6301ef7b91", "step": 21, "value": 0.7069482522275532, "stage": "improve", "created_at": 1789525037.9055538}, {"event_id": "3fb54b3f27b64543bfe0abce3d7d2ef1", "step": 22, "value": 0.7139950308430432, "stage": "evolution", "created_at": 1789525190.0142388}, {"event_id": "0215cf3d509b49fb9ad2d8f53d34c422", "step": 23, "value": 0.7119473954763537, "stage": "evolution", "created_at": 1789525411.3029118}, {"event_id": "61c8fa0852db41a3aa8d643426effba1", "step": 24, "value": 0.7997943797121316, "stage": "debug", "created_at": 1789525318.961257}, {"event_id": "8157fef022234d4aac55654e0f5904b5", "step": 28, "value": 0.7477296093214529, "stage": "debug", "created_at": 1789526218.3026588}, {"event_id": "56dec17c176942cf801974daa458dd87", "step": 29, "value": 0.7424091843728581, "stage": "improve", "created_at": 1789526060.9778686}, {"event_id": "0baf790913f54dceac3c139460d0de3f", "step": 31, "value": 0.8079420836189171, "stage": "debug", "created_at": 1789526319.6709187}, {"event_id": "7aaf76b6f42c499d992ba79ae73db99b", "step": 34, "value": 0.701790610006854, "stage": "debug", "created_at": 1789527265.9301314}, {"event_id": "6f0f7bc6ba494fb68fed03479a7daab8", "step": 35, "value": 0.8408456134338589, "stage": "improve", "created_at": 1789527188.6526735}, {"event_id": "bef630eee1874a91b7d013970ae12d47", "step": 36, "value": 0.693086017820425, "stage": "debug", "created_at": 1789527396.7738922}, {"event_id": "edd0f1096e8c4d49a9c4747980a3f2a5", "step": 37, "value": 0.7984192940370117, "stage": "improve", "created_at": 1789527953.2276342}, {"event_id": "d49ebe649fc54f4fbd1016099873f875", "step": 38, "value": 0.778482693625771, "stage": "improve", "created_at": 1789527886.1130757}, {"event_id": "03c2d9a2ff4f4ce0bdd7d721b25f7e83", "step": 39, "value": 0.7944568197395477, "stage": "improve", "created_at": 1789528506.3566947}, {"event_id": "85b48017a45e4136837e7a3418cb5d57", "step": 40, "value": 0.802882967786155, "stage": "evolution", "created_at": 1789528688.4880767}, {"event_id": "23334a2b90584806a2e82af1b4290f47", "step": 42, "value": 0.8106237148732007, "stage": "improve", "created_at": 1789528687.9186742}, {"event_id": "a4dab725d81b459280dd134dde59ffcd", "step": 43, "value": 0.8227724468814256, "stage": "evolution", "created_at": 1789529710.8388486}, {"event_id": "f9008b03cc9b44f29f2f2510feb685cd", "step": 44, "value": 0.7770947566826594, "stage": "evolution", "created_at": 1789529442.2811005}, {"event_id": "c2cfbb5baab843088ff455cae55da973", "step": 45, "value": 0.8081991089787525, "stage": "evolution", "created_at": 1789530350.6514933}, {"event_id": "6d53c159c1f24e688f41c922f0b01bd9", "step": 46, "value": 0.7904386566141193, "stage": "evolution", "created_at": 1789530604.246818}, {"event_id": "483fef6f133444bc817ab86961f424ec", "step": 47, "value": 0.8164239204934888, "stage": "evolution", "created_at": 1789530874.383635}, {"event_id": "e0897d76849445ae827e72033718e210", "step": 48, "value": 0.8339616175462645, "stage": "evolution", "created_at": 1789531199.763894}, {"event_id": "0c26371219544c9088bc51e65f712221", "step": 49, "value": 0.8347069910897875, "stage": "evolution", "created_at": 1789531297.3609555}, {"event_id": "18aeebd34c4e4b48ae9e07f8b6129a35", "step": 50, "value": 0.8241775188485264, "stage": "evolution", "created_at": 1789532055.4913309}, {"event_id": "369394290e75419d9df939138980bf52", "step": 51, "value": 0.7968471555860177, "stage": "evolution", "created_at": 1789532840.6247861}, {"event_id": "517551b97b204307adf9c67b2aed677f", "step": 52, "value": 0.8461703221384511, "stage": "evolution", "created_at": 1789532457.4845982}, {"event_id": "e6653f70254343b4aaeead35c977101d", "step": 54, "value": 0.8172549691569568, "stage": "improve", "created_at": 1789533986.1972973}, {"event_id": "8ca023dd4a344246b0295eada2dd2646", "step": 55, "value": 0.8049348869088417, "stage": "evolution", "created_at": 1789533728.329468}, {"event_id": "e4a52189b41c4b42ab30ccff77b01516", "step": 57, "value": 0.8246915695681974, "stage": "improve", "created_at": 1789535923.0018153}, {"event_id": "acddaa98ea014085ab3c10ae45c505f0", "step": 58, "value": 0.8516792323509252, "stage": "improve", "created_at": 1789536683.3412828}, {"event_id": "33401aec6ab547e7af87236d84afc89c", "step": 59, "value": 0.7407213845099382, "stage": "debug", "created_at": 1789536400.875471}, {"event_id": "0897af6e7542492c8c489e2651a87eba", "step": 60, "value": 0.8333875942426319, "stage": "improve", "created_at": 1789538145.9495533}, {"event_id": "e4dbb6e2f67e48e09f45c0c53e15a6ed", "step": 61, "value": 0.837714187799863, "stage": "improve", "created_at": 1789538840.122258}, {"event_id": "de5cc5be405444af9a7b67e31e0d7dbc", "step": 62, "value": 0.764821795750514, "stage": "debug", "created_at": 1789535185.476042}, {"event_id": "9b85841c345e4ee8835f80976a5d821e", "step": 63, "value": 0.832873543522961, "stage": "evolution", "created_at": 1789540718.9373274}, {"event_id": "67d2794c85ac47f680e0982193f96a52", "step": 64, "value": 0.8434886908841672, "stage": "evolution", "created_at": 1789541350.9906733}, {"event_id": "dc7106626fb0474a950ceb953a90084a", "step": 65, "value": 0.836309115832762, "stage": "improve", "created_at": 1789539648.735053}, {"event_id": "6715d47c882a4b2a906e867065830ed6", "step": 66, "value": 0.8290867032213846, "stage": "evolution", "created_at": 1789542570.7310548}, {"event_id": "568be8eaa7cc4d4499b49fbc6a9f2eb6", "step": 67, "value": 0.844096984235778, "stage": "improve", "created_at": 1789542822.3221922}, {"event_id": "7aaf35ca18454f3e87df048849c06857", "step": 68, "value": 0.8312457162440027, "stage": "fusion", "created_at": 1789543158.6567671}, {"event_id": "7c688a3ec83845339f597b0001b5df96", "step": 70, "value": 0.8088159698423577, "stage": "fusion", "created_at": 1789543890.8792253}, {"event_id": "30d518458677432ba7be7fa19ba0a43b", "step": 72, "value": 0.8293865661411927, "stage": "fusion", "created_at": 1789545047.887133}, {"event_id": "3f0ba87f3c944aa985df946e935fc686", "step": 73, "value": 0.6150959561343385, "stage": "debug", "created_at": 1789544978.964996}, {"event_id": "c09f91e03c9141c9a4dd5035e6b2e3f0", "step": 74, "value": 0.8256168608636052, "stage": "debug", "created_at": 1789545357.1705697}, {"event_id": "075a8afd05aa4266aeae57d7d5b68676", "step": 75, "value": 0.8348098012337217, "stage": "evolution", "created_at": 1789546206.8369536}, {"event_id": "4b55b5f501344f829052b4bb9e041ff8", "step": 76, "value": 0.8221470185058258, "stage": "fusion", "created_at": 1789546246.9561248}, {"event_id": "a63f2efb99524a2c93a340afb8a44fd1", "step": 77, "value": 0.8546778615490062, "stage": "evolution", "created_at": 1789546420.9499326}, {"event_id": "262c13e582734ee0bd4f308bb8843853", "step": 78, "value": 0.8304232350925291, "stage": "evolution", "created_at": 1789547433.7975616}, {"event_id": "656489639ae647d489680461b29353ba", "step": 79, "value": 0.8611034955448937, "stage": "evolution", "created_at": 1789547415.7533786}, {"event_id": "940090e6004144e49452982438dfb574", "step": 80, "value": 0.8200222755311858, "stage": "improve", "created_at": 1789547606.5404646}], "maximize": true, "elapsed_seconds": 28798.486842393875, "node_count": 85, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-three-20260916/xixian.gp7-long-horizon-pibo.mlsp-2013-birds.yaml", "note": ""}, {"id": "xixian.gp7-long-horizon-pibo.new-york-city-taxi-fare-prediction", "experiment_id": "mlebench-gp7-three-20260916", "family": "MLEBench", "method": "gp7_long_horizon_pibo", "dataset": "new-york-city-taxi-fare-prediction", "status": "archived", "official_score": 4.27511, "medal": "none", "valid_submission": true, "score_maximize": false, "thresholds": {"gold": 2.83377, "silver": 2.88191, "bronze": 2.92371}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/results/private_grades.jsonl:55", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}, {"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/runs/gp7_long_horizon_pibo/11_new-york-city-taxi-fare-prediction/logs/journal.json", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}], "alternate_scores": [], "journal_ref": "gp7-three-bo-analysis-20260916:gp7-three-66-runs/runs/gp7_long_horizon_pibo/11_new-york-city-taxi-fare-prediction/logs/journal.json", "metrics": [{"event_id": "49b9c4472dc8439fa707c5537300950d", "step": 3, "value": 31.149507724038205, "stage": "draft", "created_at": 1789522361.3764122}, {"event_id": "bd620524be324e5c990b140c0b8d66f1", "step": 4, "value": 5.529631343814458, "stage": "improve", "created_at": 1789523453.8000722}, {"event_id": "0935faa22bf44ee19a0f5726965f4f09", "step": 5, "value": 5.780740470846615, "stage": "improve", "created_at": 1789523917.8285482}, {"event_id": "4497dbc2a24b4d78819e6691804f26a0", "step": 6, "value": 4.9706652036722225, "stage": "debug", "created_at": 1789523176.5155492}, {"event_id": "cec61950a9754cd48c5f127d89ebc2a0", "step": 7, "value": 5.5647841542461425, "stage": "improve", "created_at": 1789524403.5070639}, {"event_id": "749b20b15a23463389608e2833390588", "step": 8, "value": 5.54689382618693, "stage": "improve", "created_at": 1789524693.0843434}, {"event_id": "c49a0467e5df444d91523ebfc67d0ee7", "step": 9, "value": 4.6165765972926, "stage": "improve", "created_at": 1789525414.1248317}, {"event_id": "a6fd4a8ac43b40e48178ccdaa71aad4a", "step": 12, "value": 5.294353197274259, "stage": "improve", "created_at": 1789526061.016019}, {"event_id": "970bf7d1cd0344229b0570fccdc891d4", "step": 13, "value": 5.637562024221839, "stage": "debug", "created_at": 1789526324.4024105}, {"event_id": "7ffdea9d942843daa1371312d0481537", "step": 14, "value": 4.637203522234928, "stage": "improve", "created_at": 1789527743.1165352}, {"event_id": "d12cf256f6e4404483a736d389240bdf", "step": 15, "value": 22.249522195414315, "stage": "evolution", "created_at": 1789528336.2671688}, {"event_id": "af9eb5d15f4b43f1825a3d7be6c90361", "step": 16, "value": 5.474162243212261, "stage": "improve", "created_at": 1789528085.3928227}, {"event_id": "cb98230fceda46b9aa2fd2796aaa65e7", "step": 17, "value": 4.629972742472987, "stage": "evolution", "created_at": 1789529075.2483478}, {"event_id": "58b31416654b4ed997a72a86cbbe2520", "step": 18, "value": 4.84160717545498, "stage": "draft", "created_at": 1789528785.6019335}, {"event_id": "8c1cbaf6ac9443df8ac5ab6fba543ae9", "step": 19, "value": 4.603504846372798, "stage": "improve", "created_at": 1789529760.613652}, {"event_id": "e509160abe4747feb08734968dde9c74", "step": 20, "value": 4.637203522234928, "stage": "evolution", "created_at": 1789529716.3769848}, {"event_id": "4df14c89ebe5416b84e0974d1642a9d2", "step": 21, "value": 4.603790183068429, "stage": "improve", "created_at": 1789530246.4547546}, {"event_id": "daae3f6f53bb4bbd964f02d841a9617a", "step": 22, "value": 5.76377432683376, "stage": "improve", "created_at": 1789530540.2591102}, {"event_id": "bc9d028d6a7d4ad08901e8defe6ec17b", "step": 23, "value": 4.637202391107411, "stage": "evolution", "created_at": 1789531332.332875}, {"event_id": "58b25c5f055e47f8beefa3cccc227938", "step": 24, "value": 4.633758793445427, "stage": "evolution", "created_at": 1789531872.416961}, {"event_id": "6e78ae18434a47759a780cd0860799db", "step": 25, "value": 5.165135783293129, "stage": "draft", "created_at": 1789533616.5124738}, {"event_id": "e4abe47895ba4c3394e280c9700b0e1a", "step": 26, "value": 5.435202102689335, "stage": "evolution", "created_at": 1789534272.602081}, {"event_id": "9d1084bab2f54a6980aea863c1768e12", "step": 27, "value": 4.586403859095055, "stage": "evolution", "created_at": 1789537795.8768668}, {"event_id": "992ddafe8f4e477cbaa388f89874c02f", "step": 28, "value": 4.959368461513053, "stage": "evolution", "created_at": 1789534281.8130062}, {"event_id": "85bb266e469b4167b68680577ae99316", "step": 29, "value": 4.634185380923426, "stage": "improve", "created_at": 1789541226.3800228}, {"event_id": "2eb77507e754461a967e18dfdf73e946", "step": 30, "value": 13.143418240194997, "stage": "improve", "created_at": 1789542167.7551575}, {"event_id": "6660283fbcc44e1e901e0a46fbb6b14d", "step": 31, "value": 4.645153094053672, "stage": "evolution", "created_at": 1789543025.1977556}, {"event_id": "694407af9d4b41d6b13a876e0b2d63ce", "step": 33, "value": 5.529284757320815, "stage": "fusion_draft", "created_at": 1789544886.8312414}, {"event_id": "88bf90313b9e47bfa61649cb9c42002b", "step": 34, "value": 4.967751784738628, "stage": "evolution", "created_at": 1789544876.4475503}, {"event_id": "6b6ad1cc0c26474eb5d47f15f9ec0e0a", "step": 35, "value": 5.402432225451, "stage": "improve", "created_at": 1789545662.2343009}, {"event_id": "9534f1b5b0d04ac790eae05875e7fdfc", "step": 36, "value": 4.627648447352281, "stage": "evolution", "created_at": 1789546543.0200756}, {"event_id": "b61eb2e641814e829f9c9c1c9d6d51e7", "step": 37, "value": 4.888769989344005, "stage": "evolution", "created_at": 1789545248.1444461}, {"event_id": "0ff3759ec5b644d3b1e3ff6529673b67", "step": 38, "value": 4.573737463252284, "stage": "improve", "created_at": 1789540884.9547396}, {"event_id": "6a7a0eb4820c405795a23c153481a0bc", "step": 39, "value": 5.531373487140773, "stage": "fusion", "created_at": 1789548460.5843842}, {"event_id": "2d1416e415624ea996d28a69efc3915a", "step": 41, "value": 4.589950350810269, "stage": "evolution", "created_at": 1789547200.3810985}, {"event_id": "9f7e52174eeb4b44835b9bfcf35a9d1f", "step": 42, "value": 10.511479839850864, "stage": "improve", "created_at": 1789549960.093598}], "maximize": false, "elapsed_seconds": 28795.84944319725, "node_count": 45, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-three-20260916/xixian.gp7-long-horizon-pibo.new-york-city-taxi-fare-prediction.yaml", "note": ""}, {"id": "xixian.gp7-long-horizon-pibo.nomad2018-predict-transparent-conductors", "experiment_id": "mlebench-gp7-three-20260916", "family": "MLEBench", "method": "gp7_long_horizon_pibo", "dataset": "nomad2018-predict-transparent-conductors", "status": "archived", "official_score": 0.05917, "medal": "silver", "valid_submission": true, "score_maximize": false, "thresholds": {"gold": 0.05589, "silver": 0.06229, "bronze": 0.06582}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/results/private_grades.jsonl:56", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}, {"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/runs/gp7_long_horizon_pibo/12_nomad2018-predict-transparent-conductors/logs/journal.json", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}], "alternate_scores": [], "journal_ref": "gp7-three-bo-analysis-20260916:gp7-three-66-runs/runs/gp7_long_horizon_pibo/12_nomad2018-predict-transparent-conductors/logs/journal.json", "metrics": [{"event_id": "da05c049ec894e92bb5ce80e3c1d7529", "step": 9, "value": 0.46710030159822696, "stage": "debug", "created_at": 1789524057.779242}, {"event_id": "f5de9768e2884553bc2ee2beacad9b52", "step": 14, "value": 0.05485446197342115, "stage": "debug", "created_at": 1789524579.0748758}, {"event_id": "c46e56d5dee047118b624db2a5eb0359", "step": 17, "value": 0.07355088861131569, "stage": "debug", "created_at": 1789531191.5673358}, {"event_id": "a1aa1be42f764b54b0ee0bfee7a4762f", "step": 18, "value": 0.07244867617123858, "stage": "improve", "created_at": 1789534334.2666707}, {"event_id": "b59b9a2a98c74c3f88315a5f6a7a9aa3", "step": 19, "value": 0.46578841909916735, "stage": "debug", "created_at": 1789523957.6104438}, {"event_id": "64409dd08182415681f6de246a9a8c07", "step": 20, "value": 0.056482812878762514, "stage": "improve", "created_at": 1789537478.6700504}], "maximize": false, "elapsed_seconds": 28803.03304219246, "node_count": 26, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-three-20260916/xixian.gp7-long-horizon-pibo.nomad2018-predict-transparent-conductors.yaml", "note": ""}, {"id": "xixian.gp7-long-horizon-pibo.plant-pathology-2020-fgvc7", "experiment_id": "mlebench-gp7-three-20260916", "family": "MLEBench", "method": "gp7_long_horizon_pibo", "dataset": "plant-pathology-2020-fgvc7", "status": "archived", "official_score": 0.99282, "medal": "gold", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.97836, "silver": 0.97465, "bronze": 0.97361}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/results/private_grades.jsonl:57", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}, {"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/runs/gp7_long_horizon_pibo/13_plant-pathology-2020-fgvc7/logs/journal.json", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}], "alternate_scores": [], "journal_ref": "gp7-three-bo-analysis-20260916:gp7-three-66-runs/runs/gp7_long_horizon_pibo/13_plant-pathology-2020-fgvc7/logs/journal.json", "metrics": [{"event_id": "a5ff0db7401546d5a1eb284dd4f07131", "step": 2, "value": 0.9843006283989106, "stage": "draft", "created_at": 1789522217.4696262}, {"event_id": "7453136975ca4faba4c24534dd260f4c", "step": 4, "value": 0.9399371349019188, "stage": "draft", "created_at": 1789522893.4817288}, {"event_id": "6018e5a3587e4a3bb4b4066ddb76e6cf", "step": 5, "value": 0.9409102979816737, "stage": "debug", "created_at": 1789523543.8527288}, {"event_id": "5303f9f1aab849859059e35872de8f5f", "step": 6, "value": 0.9632641406669312, "stage": "improve", "created_at": 1789524141.9231186}, {"event_id": "da191efe6c0f4740be9dacde089692cc", "step": 7, "value": 0.9866884648949485, "stage": "improve", "created_at": 1789523556.5039752}, {"event_id": "001a15ea8a274e71948632b08c6010ab", "step": 8, "value": 0.9428405666859484, "stage": "improve", "created_at": 1789524730.15201}, {"event_id": "5df51e8184bf4f6a9d96133ec7e8eda9", "step": 13, "value": 0.9357609618321044, "stage": "debug", "created_at": 1789526039.2747672}, {"event_id": "0166eab64b2c4fb797745cc51dcb83c5", "step": 17, "value": 0.9887683427043616, "stage": "debug", "created_at": 1789529392.020945}, {"event_id": "0b65afe6ba43471bb34da66020d50bc2", "step": 18, "value": 0.9874922343175676, "stage": "debug", "created_at": 1789532029.7672396}, {"event_id": "ec51baac0b9e494da7eb65bf54a9d360", "step": 19, "value": 0.9158204237211789, "stage": "improve", "created_at": 1789534341.4913585}, {"event_id": "516eb9f9db0f4494b2784af89f792a61", "step": 20, "value": 0.9886927701763696, "stage": "debug", "created_at": 1789532018.1387253}, {"event_id": "e815dcc4af71486ba2581259760662fa", "step": 22, "value": 0.9126461330451939, "stage": "improve", "created_at": 1789536299.914419}, {"event_id": "0e03cb6c12884e8fbd5931a1338f7d49", "step": 27, "value": 0.9908675351858354, "stage": "debug", "created_at": 1789536862.2622714}, {"event_id": "6baedafde2dd4d608783bb47ec5ae00f", "step": 30, "value": 0.9842519956652835, "stage": "debug", "created_at": 1789540076.3931844}, {"event_id": "2ed5cfd8638542c0b34da17a12a4fc6e", "step": 31, "value": 0.991406949642257, "stage": "improve", "created_at": 1789541435.824107}, {"event_id": "85e16d2b02fb4573bc3a5f37406282a5", "step": 33, "value": 0.9615101696408617, "stage": "debug", "created_at": 1789543244.7616236}, {"event_id": "298f22f651ff48b7b81714358bea7068", "step": 35, "value": 0.9915181941722522, "stage": "improve", "created_at": 1789545168.5446935}], "maximize": true, "elapsed_seconds": 28806.681033611298, "node_count": 39, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-three-20260916/xixian.gp7-long-horizon-pibo.plant-pathology-2020-fgvc7.yaml", "note": ""}, {"id": "xixian.gp7-long-horizon-pibo.random-acts-of-pizza", "experiment_id": "mlebench-gp7-three-20260916", "family": "MLEBench", "method": "gp7_long_horizon_pibo", "dataset": "random-acts-of-pizza", "status": "archived", "official_score": 0.69289, "medal": "bronze", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.97908, "silver": 0.76482, "bronze": 0.6921}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/results/private_grades.jsonl:58", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}, {"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/runs/gp7_long_horizon_pibo/14_random-acts-of-pizza/logs/journal.json", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}], "alternate_scores": [], "journal_ref": "gp7-three-bo-analysis-20260916:gp7-three-66-runs/runs/gp7_long_horizon_pibo/14_random-acts-of-pizza/logs/journal.json", "metrics": [{"event_id": "6e8051407de64778bed4fd0bcf7c53ea", "step": 6, "value": 0.6385762043960659, "stage": "debug", "created_at": 1789523319.2910347}, {"event_id": "6de77c6da7f34db1858957291f83d405", "step": 7, "value": 0.6431466916455368, "stage": "debug", "created_at": 1789523207.5766363}, {"event_id": "025490769bd54a3d9133a1f0e3164bf1", "step": 8, "value": 0.6761091102892489, "stage": "debug", "created_at": 1789523399.7057745}, {"event_id": "e8a2b9c5734640109fa6cecfdfdefe4b", "step": 9, "value": 0.6497843957428253, "stage": "improve", "created_at": 1789523587.1243553}, {"event_id": "1ceac7f38b6b454189c4edc1c40eae05", "step": 10, "value": 0.6546940357563914, "stage": "improve", "created_at": 1789523629.239621}, {"event_id": "ce651c96224a4f9b820f54089a3b3c6b", "step": 11, "value": 0.655695343917053, "stage": "improve", "created_at": 1789523701.2199235}, {"event_id": "76a978f49d2e456caf8a652ae201f6bc", "step": 12, "value": 0.653466625753, "stage": "improve", "created_at": 1789523900.2932005}, {"event_id": "b81787347d7e4f508ad5115fda2b5230", "step": 13, "value": 0.669826709087679, "stage": "improve", "created_at": 1789524084.7776246}, {"event_id": "2f7bea8f8ece446a9122e0789843e14a", "step": 14, "value": 0.6549039874674979, "stage": "improve", "created_at": 1789523922.5489905}, {"event_id": "7ce6f87dac254ccf998205c2684051d0", "step": 15, "value": 0.67304058528077, "stage": "improve", "created_at": 1789524338.0086846}, {"event_id": "31b15d50ade54fe0a1912f7cd9d640ce", "step": 16, "value": 0.6878987063744568, "stage": "improve", "created_at": 1789524409.3751833}, {"event_id": "2fa867aa6b044d78a2eed53f1c512afe", "step": 17, "value": 0.6867358968975598, "stage": "improve", "created_at": 1789524636.27976}, {"event_id": "1b0dab6720144082a6454e83f9c4223c", "step": 18, "value": 0.6781763271370663, "stage": "improve", "created_at": 1789524860.70266}, {"event_id": "7ab737235f6c4b2bb695e8da8a7bce39", "step": 20, "value": 0.5588107043072401, "stage": "debug", "created_at": 1789525141.3786306}, {"event_id": "489b89b9382645ea917094bf216cc41b", "step": 21, "value": 0.6728144834380401, "stage": "improve", "created_at": 1789525173.6586726}, {"event_id": "8be191e118a7452f9d1c47de462ff886", "step": 22, "value": 0.6608472359049726, "stage": "improve", "created_at": 1789525280.5250711}, {"event_id": "6ab3894781504b51b482bcebdb8d89f5", "step": 23, "value": 0.6909187809880651, "stage": "improve", "created_at": 1789525513.1418657}, {"event_id": "a43b9eb88eab4167afcbb3139651e5be", "step": 25, "value": 0.683247468466868, "stage": "evolution", "created_at": 1789525657.2212563}, {"event_id": "a124d95ac42943e3b33e4c305559079b", "step": 26, "value": 0.6574234080007754, "stage": "improve", "created_at": 1789526047.2108388}, {"event_id": "e02d845731dc4644aaba18f15c252ae3", "step": 27, "value": 0.6855569372890389, "stage": "improve", "created_at": 1789526615.683595}, {"event_id": "5dae299a757d478fb3088150d9cf9621", "step": 28, "value": 0.6430255656583601, "stage": "improve", "created_at": 1789526873.9486008}, {"event_id": "d25f335127324d628d46ef123a5e9d8d", "step": 29, "value": 0.6797913402994235, "stage": "evolution", "created_at": 1789527202.2146158}, {"event_id": "283702d7758a42c2ae45616d2c3ac4c5", "step": 30, "value": 0.6850401330770847, "stage": "evolution", "created_at": 1789527629.66272}, {"event_id": "abd380619925439fa692c0b446a60c8f", "step": 31, "value": 0.6763190620003553, "stage": "evolution", "created_at": 1789527743.612835}, {"event_id": "cba85d4e593a4469978a6b7b5c58d3be", "step": 32, "value": 0.6846525299181189, "stage": "evolution", "created_at": 1789528662.2106304}, {"event_id": "088e48306c3d4b7f8786bcdf2a91eeb7", "step": 33, "value": 0.6624783991989536, "stage": "evolution", "created_at": 1789528116.4949157}, {"event_id": "13301c4779bc4f1d8035d2e6ee51d11c", "step": 35, "value": 0.6938742550751789, "stage": "evolution", "created_at": 1789530936.114745}, {"event_id": "576e4554a6b24366b4a05195cd7ef783", "step": 36, "value": 0.6661767793407517, "stage": "improve", "created_at": 1789532638.1632168}, {"event_id": "c2746f9a6713479ba532f50e72cd88ff", "step": 37, "value": 0.5869280834638803, "stage": "debug", "created_at": 1789531178.4453776}, {"event_id": "e76a1968dbd04eb480331863d345ab2c", "step": 38, "value": 0.6917101374376201, "stage": "improve", "created_at": 1789533100.034731}, {"event_id": "e6ed3673218a4fcd928e73f06fcb056f", "step": 39, "value": 0.6860898916326168, "stage": "improve", "created_at": 1789533461.609124}, {"event_id": "e34384a9645242259b44b165b9009127", "step": 40, "value": 0.6932443999418596, "stage": "evolution", "created_at": 1789535256.924848}, {"event_id": "0959182ada3b4cb3ac82c027867de04d", "step": 41, "value": 0.6955861690272775, "stage": "evolution", "created_at": 1789536855.7435863}, {"event_id": "16805319582b46e58e40c9c8114ee699", "step": 42, "value": 0.6597813272178168, "stage": "debug", "created_at": 1789525933.507872}, {"event_id": "be9ffd5fc87248aa8c4f444c91daa4e1", "step": 43, "value": 0.7050824464219383, "stage": "improve", "created_at": 1789536910.2313159}, {"event_id": "6eff2c529c344f87911dcbaac9b77711", "step": 44, "value": 0.6894652691419435, "stage": "improve", "created_at": 1789538647.5823123}, {"event_id": "a8803a23e06644fe8b24d6a10a5d19f8", "step": 46, "value": 0.6842972270224004, "stage": "improve", "created_at": 1789538606.3089797}, {"event_id": "1d3d6981a2034e36bed11b6634c23190", "step": 47, "value": 0.6968297291622927, "stage": "debug", "created_at": 1789539894.4854329}, {"event_id": "dc9e6b5f75c847cf8bb07f4fb6c73e99", "step": 49, "value": 0.6943264587606389, "stage": "improve", "created_at": 1789540044.479831}, {"event_id": "bd4fdcafcddf4063b1d2ddda110db84b", "step": 50, "value": 0.6855892375522861, "stage": "debug", "created_at": 1789541719.720409}, {"event_id": "fbc3715f61d7455488305a65831f1eee", "step": 51, "value": 0.7050824464219383, "stage": "evolution", "created_at": 1789541893.5111563}, {"event_id": "c24e6b2c8619497988656810181b595c", "step": 52, "value": 0.6976210856118478, "stage": "fusion", "created_at": 1789543259.1822321}, {"event_id": "b18d33187dad4006a189300c0a999599", "step": 56, "value": 0.6812125518822979, "stage": "debug", "created_at": 1789546011.8072033}, {"event_id": "d6febc9a96c74491acab9643c2e5c16b", "step": 58, "value": 0.6876887546633506, "stage": "debug", "created_at": 1789546379.0101986}, {"event_id": "966d3d71fa8e41cbb62b8192e6880b22", "step": 59, "value": 0.6900143736171449, "stage": "fusion_draft", "created_at": 1789547246.3911607}, {"event_id": "aa9ab0710f2048eabc54ea6307ba931c", "step": 61, "value": 0.6875434034787384, "stage": "improve", "created_at": 1789548449.519627}], "maximize": true, "elapsed_seconds": 28798.301104068756, "node_count": 66, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-three-20260916/xixian.gp7-long-horizon-pibo.random-acts-of-pizza.yaml", "note": ""}, {"id": "xixian.gp7-long-horizon-pibo.ranzcr-clip-catheter-line-classification", "experiment_id": "mlebench-gp7-three-20260916", "family": "MLEBench", "method": "gp7_long_horizon_pibo", "dataset": "ranzcr-clip-catheter-line-classification", "status": "archived", "official_score": 0.91088, "medal": "none", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.97357, "silver": 0.97152, "bronze": 0.9709}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/results/private_grades.jsonl:59", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}, {"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/runs/gp7_long_horizon_pibo/15_ranzcr-clip-catheter-line-classification/logs/journal.json", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}], "alternate_scores": [], "journal_ref": "gp7-three-bo-analysis-20260916:gp7-three-66-runs/runs/gp7_long_horizon_pibo/15_ranzcr-clip-catheter-line-classification/logs/journal.json", "metrics": [{"event_id": "a7db1d2667e1477e8476ab7ae5b1be02", "step": 2, "value": 0.8357124564848738, "stage": "draft", "created_at": 1789522337.8852284}, {"event_id": "0526b40e80134fed815276f889a2f583", "step": 4, "value": 0.6251347343509678, "stage": "debug", "created_at": 1789526146.7486203}, {"event_id": "958be379ff7844ed8b7f467f91f3e75f", "step": 5, "value": 0.8481060983833809, "stage": "improve", "created_at": 1789528536.93412}, {"event_id": "d1df6de0dbb740218b87d1ea70e477e8", "step": 6, "value": 0.8773935289551439, "stage": "improve", "created_at": 1789531753.808608}, {"event_id": "22a4f470d41e435fbba7ea29b59770bb", "step": 7, "value": 0.8405276726243182, "stage": "debug", "created_at": 1789523709.6222434}, {"event_id": "fa02775dfc2946ea8656fa9ace08fed4", "step": 10, "value": 0.8830953896617998, "stage": "improve", "created_at": 1789536867.7127678}, {"event_id": "400e34a03aa8465296740cd9ae6afb5c", "step": 11, "value": 0.8833797107917337, "stage": "improve", "created_at": 1789538810.1032434}, {"event_id": "3b458300ba1c4e82848790d0725b1b1b", "step": 14, "value": 0.8461455600357476, "stage": "improve", "created_at": 1789545122.2187843}], "maximize": true, "elapsed_seconds": 28795.65812587738, "node_count": 17, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-three-20260916/xixian.gp7-long-horizon-pibo.ranzcr-clip-catheter-line-classification.yaml", "note": ""}, {"id": "xixian.gp7-long-horizon-pibo.siim-isic-melanoma-classification", "experiment_id": "mlebench-gp7-three-20260916", "family": "MLEBench", "method": "gp7_long_horizon_pibo", "dataset": "siim-isic-melanoma-classification", "status": "archived", "official_score": null, "medal": "none", "valid_submission": false, "score_maximize": null, "thresholds": {"gold": null, "silver": null, "bronze": null}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/results/private_grades.jsonl:60", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}, {"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/runs/gp7_long_horizon_pibo/16_siim-isic-melanoma-classification/logs/journal.json", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}], "alternate_scores": [], "journal_ref": "gp7-three-bo-analysis-20260916:gp7-three-66-runs/runs/gp7_long_horizon_pibo/16_siim-isic-melanoma-classification/logs/journal.json", "metrics": [], "maximize": null, "elapsed_seconds": 28796.224885463715, "node_count": 7, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-three-20260916/xixian.gp7-long-horizon-pibo.siim-isic-melanoma-classification.yaml", "note": ""}, {"id": "xixian.gp7-long-horizon-pibo.spooky-author-identification", "experiment_id": "mlebench-gp7-three-20260916", "family": "MLEBench", "method": "gp7_long_horizon_pibo", "dataset": "spooky-author-identification", "status": "archived", "official_score": 0.24651, "medal": "silver", "valid_submission": true, "score_maximize": false, "thresholds": {"gold": 0.16506, "silver": 0.26996, "bronze": 0.29381}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/results/private_grades.jsonl:61", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}, {"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/runs/gp7_long_horizon_pibo/17_spooky-author-identification/logs/journal.json", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}], "alternate_scores": [], "journal_ref": "gp7-three-bo-analysis-20260916:gp7-three-66-runs/runs/gp7_long_horizon_pibo/17_spooky-author-identification/logs/journal.json", "metrics": [{"event_id": "374ea83cbe3c44f9ab193affd8f38422", "step": 7, "value": 0.4103067773843083, "stage": "debug", "created_at": 1789522826.8595235}, {"event_id": "0d2977e8b2294f52b98c4f4f2b58983c", "step": 9, "value": 0.38508258046341803, "stage": "debug", "created_at": 1789522914.6579924}, {"event_id": "056154e62f2e4109bd4fe4b5cad4082a", "step": 10, "value": 0.549944858305475, "stage": "improve", "created_at": 1789523418.7283828}, {"event_id": "00a0c651aa3549b192d19db373e4fbf6", "step": 11, "value": 0.33277488150442447, "stage": "improve", "created_at": 1789523509.0897605}, {"event_id": "beb28acab48e4b66ae3da62adf343abc", "step": 12, "value": 0.3427410330707227, "stage": "improve", "created_at": 1789527208.4276395}, {"event_id": "15aa6f40ae834e749eea1016aa986bac", "step": 13, "value": 0.3631198272946057, "stage": "improve", "created_at": 1789523447.1184447}, {"event_id": "c65064600aca487382ff015783ec3e66", "step": 14, "value": 0.33229849134232475, "stage": "improve", "created_at": 1789524472.3490229}, {"event_id": "939daed1d8cd43f094d55571f6bfafd4", "step": 15, "value": 0.333772566235975, "stage": "improve", "created_at": 1789528183.4677043}, {"event_id": "74dc03bf62b04c1392c1e50327b95d94", "step": 16, "value": 0.3163376209898673, "stage": "improve", "created_at": 1789528272.5606751}, {"event_id": "bfdc443bbdef4177a9f7060e4278f2fe", "step": 18, "value": 0.26526501169070943, "stage": "improve", "created_at": 1789528590.8191848}, {"event_id": "fbc4ca7a8f564639a497d1e44b4dc236", "step": 19, "value": 0.30189255256639785, "stage": "debug", "created_at": 1789530704.1681538}, {"event_id": "202473808b884ee0b4fa7ecb020a890a", "step": 22, "value": 0.2581143931354482, "stage": "improve", "created_at": 1789532158.8681836}, {"event_id": "1153a3c4ef5f4de1a282c76bb0ec7599", "step": 23, "value": 0.2683970626146427, "stage": "debug", "created_at": 1789536388.93434}, {"event_id": "9cc45b95a994433a957292495473d722", "step": 24, "value": 0.2524206380279631, "stage": "improve", "created_at": 1789537216.7784371}, {"event_id": "28f9dc3808a74c818d43698983cd858a", "step": 25, "value": 0.25451606307139735, "stage": "improve", "created_at": 1789541970.8535173}, {"event_id": "79d46ec21e9d43e884bae6bc020e3c59", "step": 26, "value": 0.2561976509302444, "stage": "improve", "created_at": 1789542796.2387116}], "maximize": false, "elapsed_seconds": 28796.41957139969, "node_count": 27, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-three-20260916/xixian.gp7-long-horizon-pibo.spooky-author-identification.yaml", "note": ""}, {"id": "xixian.gp7-long-horizon-pibo.tabular-playground-series-dec-2021", "experiment_id": "mlebench-gp7-three-20260916", "family": "MLEBench", "method": "gp7_long_horizon_pibo", "dataset": "tabular-playground-series-dec-2021", "status": "archived", "official_score": 0.96314, "medal": "gold", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.9566, "silver": 0.95658, "bronze": 0.95658}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/results/private_grades.jsonl:62", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}, {"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/runs/gp7_long_horizon_pibo/18_tabular-playground-series-dec-2021/logs/journal.json", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}], "alternate_scores": [], "journal_ref": "gp7-three-bo-analysis-20260916:gp7-three-66-runs/runs/gp7_long_horizon_pibo/18_tabular-playground-series-dec-2021/logs/journal.json", "metrics": [{"event_id": "320cb0dd9eb3477eb4f99e6d591503d8", "step": 1, "value": 0.8820055555555556, "stage": "draft", "created_at": 1789522419.0449739}, {"event_id": "fe0a84f7a748412f914c3de6fcc53e22", "step": 2, "value": 9.166666666666667e-05, "stage": "draft", "created_at": 1789522936.2264545}, {"event_id": "ed92c85dfa41447d81c75b896b6fe55d", "step": 3, "value": 0.9601430555555556, "stage": "improve", "created_at": 1789530544.64353}, {"event_id": "dd4e640270f74e85a85467e1c17e6f5b", "step": 5, "value": 0.9602319444444445, "stage": "improve", "created_at": 1789524833.615135}, {"event_id": "c9f22d6a16e94374819b8d64a8507cdd", "step": 7, "value": 0.9622777777777778, "stage": "improve", "created_at": 1789534179.9803064}], "maximize": true, "elapsed_seconds": 28803.141937494278, "node_count": 11, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-three-20260916/xixian.gp7-long-horizon-pibo.tabular-playground-series-dec-2021.yaml", "note": ""}, {"id": "xixian.gp7-long-horizon-pibo.tabular-playground-series-may-2022", "experiment_id": "mlebench-gp7-three-20260916", "family": "MLEBench", "method": "gp7_long_horizon_pibo", "dataset": "tabular-playground-series-may-2022", "status": "archived", "official_score": 0.99639, "medal": "none", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.99823, "silver": 0.99822, "bronze": 0.99818}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/results/private_grades.jsonl:63", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}, {"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/runs/gp7_long_horizon_pibo/19_tabular-playground-series-may-2022/logs/journal.json", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}], "alternate_scores": [], "journal_ref": "gp7-three-bo-analysis-20260916:gp7-three-66-runs/runs/gp7_long_horizon_pibo/19_tabular-playground-series-may-2022/logs/journal.json", "metrics": [{"event_id": "b7307e15f0194a759fef1e753c8bd623", "step": 3, "value": 0.995695641969901, "stage": "debug", "created_at": 1789522671.5005}, {"event_id": "6497f0c72ce44924aa120a469ff9e069", "step": 4, "value": 0.9943972944305448, "stage": "debug", "created_at": 1789522691.7026522}, {"event_id": "c2848b0e10e44a5d88ebbc0851eaea66", "step": 5, "value": 0.9958247194698789, "stage": "improve", "created_at": 1789523621.951548}, {"event_id": "a6f17dabebb34a4c807b91aaf17eeb40", "step": 6, "value": 0.9953544967711521, "stage": "improve", "created_at": 1789525995.063183}, {"event_id": "ff4fa019b9194c61a2b47571d5acd9c2", "step": 7, "value": 0.9959395463282361, "stage": "improve", "created_at": 1789523203.1490812}, {"event_id": "a20a259bf7d14d40abbe68c8fd6b0226", "step": 8, "value": 0.9954345780151523, "stage": "improve", "created_at": 1789528754.335146}, {"event_id": "dc26596090ce476b95d8c659d01ccc8a", "step": 9, "value": 0.9943293040429911, "stage": "improve", "created_at": 1789529522.4636574}, {"event_id": "ab6cbbeae52940e3bf83962da8faf361", "step": 10, "value": 0.994590736405926, "stage": "improve", "created_at": 1789531454.0822194}, {"event_id": "401720ea84364be0b06f791dfa5ccd32", "step": 11, "value": 0.9947827660456794, "stage": "improve", "created_at": 1789531991.3718138}, {"event_id": "a6f2e6de557c43a785db332ef49f1936", "step": 12, "value": 0.9963283967906083, "stage": "evolution", "created_at": 1789534786.510076}, {"event_id": "9637443b25384d5f8cc6814cff0d357b", "step": 15, "value": 0.9955966393064668, "stage": "improve", "created_at": 1789536905.4038846}], "maximize": true, "elapsed_seconds": 28803.438116550446, "node_count": 19, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-three-20260916/xixian.gp7-long-horizon-pibo.tabular-playground-series-may-2022.yaml", "note": ""}, {"id": "xixian.gp7-long-horizon-pibo.text-normalization-challenge-english-language", "experiment_id": "mlebench-gp7-three-20260916", "family": "MLEBench", "method": "gp7_long_horizon_pibo", "dataset": "text-normalization-challenge-english-language", "status": "archived", "official_score": 0.98405, "medal": "none", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.99724, "silver": 0.99135, "bronze": 0.99038}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/results/private_grades.jsonl:64", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}, {"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/runs/gp7_long_horizon_pibo/20_text-normalization-challenge-english-language/logs/journal.json", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}], "alternate_scores": [], "journal_ref": "gp7-three-bo-analysis-20260916:gp7-three-66-runs/runs/gp7_long_horizon_pibo/20_text-normalization-challenge-english-language/logs/journal.json", "metrics": [{"event_id": "7fd0995949c6455498a191163b01ca38", "step": 13, "value": 0.9666089038439551, "stage": "debug", "created_at": 1789538379.5702846}, {"event_id": "f86dee9417e44076ac8f772c335cce43", "step": 14, "value": 0.9726713848356524, "stage": "debug", "created_at": 1789539669.9837577}, {"event_id": "92cd74dd59bb40889110786a5ca169f7", "step": 15, "value": 0.9797038030056097, "stage": "improve", "created_at": 1789540744.6369853}, {"event_id": "7d2c0ce89dd14dcd9e5e61601be19482", "step": 16, "value": 0.9842643011557796, "stage": "improve", "created_at": 1789540353.0557714}, {"event_id": "a8bb15ae1502469c82f616713f65110b", "step": 17, "value": 0.979846528738312, "stage": "improve", "created_at": 1789542381.7282345}, {"event_id": "f7c49c9308f74e09a4e76b9457223359", "step": 25, "value": 0.9805220473894268, "stage": "fusion_draft", "created_at": 1789547530.4552188}], "maximize": true, "elapsed_seconds": 28888.51161456108, "node_count": 32, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-three-20260916/xixian.gp7-long-horizon-pibo.text-normalization-challenge-english-language.yaml", "note": ""}, {"id": "xixian.gp7-long-horizon-pibo.text-normalization-challenge-russian-language", "experiment_id": "mlebench-gp7-three-20260916", "family": "MLEBench", "method": "gp7_long_horizon_pibo", "dataset": "text-normalization-challenge-russian-language", "status": "archived", "official_score": 0.97874, "medal": "bronze", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.99012, "silver": 0.98232, "bronze": 0.97592}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/results/private_grades.jsonl:65", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}, {"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/runs/gp7_long_horizon_pibo/21_text-normalization-challenge-russian-language/logs/journal.json", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}], "alternate_scores": [], "journal_ref": "gp7-three-bo-analysis-20260916:gp7-three-66-runs/runs/gp7_long_horizon_pibo/21_text-normalization-challenge-russian-language/logs/journal.json", "metrics": [{"event_id": "7a40b138d9b9421aa51fc13507bb3c44", "step": 6, "value": 0.9488520280599488, "stage": "debug", "created_at": 1789524636.327535}, {"event_id": "a6b48dd383d14ddb82a141fad36826a7", "step": 10, "value": 0.9795122369379795, "stage": "improve", "created_at": 1789545121.020475}], "maximize": true, "elapsed_seconds": 28795.800258398056, "node_count": 13, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-three-20260916/xixian.gp7-long-horizon-pibo.text-normalization-challenge-russian-language.yaml", "note": ""}, {"id": "xixian.gp7-long-horizon-pibo.the-icml-2013-whale-challenge-right-whale-redux", "experiment_id": "mlebench-gp7-three-20260916", "family": "MLEBench", "method": "gp7_long_horizon_pibo", "dataset": "the-icml-2013-whale-challenge-right-whale-redux", "status": "archived", "official_score": 0.98769, "medal": "silver", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.98961, "silver": 0.95017, "bronze": 0.90521}, "grading_policy": "selected", "artifacts": [{"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/results/private_grades.jsonl:66", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}, {"bundle_id": "gp7-three-bo-analysis-20260916", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "member": "gp7-three-66-runs/runs/gp7_long_horizon_pibo/22_the-icml-2013-whale-challenge-right-whale-redux/logs/journal.json", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f"}], "alternate_scores": [], "journal_ref": "gp7-three-bo-analysis-20260916:gp7-three-66-runs/runs/gp7_long_horizon_pibo/22_the-icml-2013-whale-challenge-right-whale-redux/logs/journal.json", "metrics": [{"event_id": "9055537bd4b442ebbcfed6b979dcc150", "step": 1, "value": 0.707707712778284, "stage": "draft", "created_at": 1789523132.0093935}, {"event_id": "477d109cb2fd4f63854677790bbf6950", "step": 3, "value": 0.7064975463130386, "stage": "debug", "created_at": 1789525237.101617}, {"event_id": "2bc1c2f5fa4d4a759d67c86c7c14d85a", "step": 4, "value": 0.9108716179122744, "stage": "draft", "created_at": 1789523565.08783}, {"event_id": "455059f630d64492b607553fae17984a", "step": 6, "value": 0.7376522423085433, "stage": "improve", "created_at": 1789526956.0184193}, {"event_id": "c0dca6db808049bca69e941ed8f22067", "step": 7, "value": 0.7235329646721836, "stage": "improve", "created_at": 1789528467.1586018}, {"event_id": "5bf8e33b4ca04851b08e8b01b4444a21", "step": 8, "value": 0.7354254508532637, "stage": "improve", "created_at": 1789530239.407872}, {"event_id": "f6aad081aaff4067865d63a7c61608df", "step": 9, "value": 0.6145207104061101, "stage": "debug", "created_at": 1789527721.8753219}, {"event_id": "6ae16f9ebe38461ab61d4434099fd1b7", "step": 10, "value": 0.9200058750078857, "stage": "improve", "created_at": 1789527421.1137981}, {"event_id": "a1846af2368740ac95b2716b2e15c327", "step": 11, "value": 0.7305506234169378, "stage": "improve", "created_at": 1789532170.8541408}, {"event_id": "a03ad3afb8e94284b7c9af14f495dfe8", "step": 12, "value": 0.7281189114516795, "stage": "improve", "created_at": 1789532685.6682289}, {"event_id": "db5c598d8e5544bdbe6c7fa1261e248f", "step": 14, "value": 0.9306015917042773, "stage": "debug", "created_at": 1789535357.1406395}, {"event_id": "c5b24725058c443ca1dd21820ded6862", "step": 15, "value": 0.9355205649012915, "stage": "improve", "created_at": 1789536239.0085773}, {"event_id": "0fab40197cdb4f9a91a57b38748800a4", "step": 17, "value": 0.9433114596472754, "stage": "improve", "created_at": 1789537253.239637}, {"event_id": "92d73ece92df4b7093a36aae84881e11", "step": 18, "value": 0.9186532626041898, "stage": "improve", "created_at": 1789538119.898143}, {"event_id": "84892832c58e47ab82d8ea3da13bdc95", "step": 20, "value": 0.9454171928552583, "stage": "improve", "created_at": 1789539195.726375}, {"event_id": "f9848f8e9e8049c4b9babccc2755ec94", "step": 21, "value": 0.9862423064877677, "stage": "evolution", "created_at": 1789539972.0042748}, {"event_id": "406d09ccc8534de4ae09ef6efaedd961", "step": 25, "value": 0.9851306114975822, "stage": "improve", "created_at": 1789542294.1062362}, {"event_id": "36672d25e08144efb6c1749aaef58eb0", "step": 29, "value": 0.9848841391574219, "stage": "improve", "created_at": 1789544363.661469}, {"event_id": "dca8d51c3af74b688972ac69269d059e", "step": 30, "value": 0.9857863864947644, "stage": "debug", "created_at": 1789544611.2910018}, {"event_id": "4699a111520d4b13b4baba0fd8399537", "step": 31, "value": 0.9848890333659238, "stage": "improve", "created_at": 1789546621.312687}, {"event_id": "04783b99b1c144c498e3b5e3a56dd89b", "step": 32, "value": 0.9858488610662923, "stage": "fusion", "created_at": 1789546698.147386}, {"event_id": "c353bac6032f49028d94d74fc407fa6c", "step": 33, "value": 0.9320024610038031, "stage": "debug", "created_at": 1789545055.5833116}], "maximize": true, "elapsed_seconds": 28795.26293683052, "node_count": 35, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-three-20260916/xixian.gp7-long-horizon-pibo.the-icml-2013-whale-challenge-right-whale-redux.yaml", "note": ""}, {"id": "xixian.gp7-ancestry-logei.aerial-cactus-identification", "experiment_id": "mlebench-gp7-hard14-20260917", "family": "MLEBench", "method": "gp7_ancestry_logei", "dataset": "aerial-cactus-identification", "status": "archived", "official_score": 1.0, "medal": "gold", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 1.0, "silver": 1.0, "bronze": 1.0}, "grading_policy": "ensemble", "artifacts": [{"bundle_id": "gp7-ancestry-logei-hard14-full-logs-20260917", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917/logs-77c0e49ab8d6.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917", "member": "results/official_private_grades.jsonl:2", "sha256": "77c0e49ab8d6df7268cefe20565a32eaa589661c5946ef2499c567afceab8104"}, {"bundle_id": "gp7-ancestry-logei-hard14-full-logs-20260917", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917/logs-77c0e49ab8d6.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917", "member": "gp7_ancestry_logei-hard14/runs/01_aerial-cactus-identification/logs/journal.json", "sha256": "77c0e49ab8d6df7268cefe20565a32eaa589661c5946ef2499c567afceab8104"}], "alternate_scores": [{"cohort": "09-17", "workflow_id": "09-17 gp7_ancestry_logei", "method": "gp7_ancestry_logei", "task": "aerial-cactus-identification", "policy": "best_node", "status": "graded", "valid_submission": true, "score": 0.99992, "medal": "none", "is_lower_better": false, "gold_threshold": 1.0, "silver_threshold": 1.0, "bronze_threshold": 1.0, "submission_sha256": "3bea6afe2bc0f892ce2c049667aeed6050fabe2413934b5c5a4883caad555bfd", "source_archive": "gp7_ancestry_logei_hard14_full_logs_20260917.zip", "source_member": "results/official_private_grades.jsonl", "source_line": 1}], "journal_ref": "gp7-ancestry-logei-hard14-full-logs-20260917:gp7_ancestry_logei-hard14/runs/01_aerial-cactus-identification/logs/journal.json", "metrics": [{"event_id": "f2d74779f9284ac9bb6fb89c5e86699f", "step": 3, "value": 0.9998242941104329, "stage": "draft", "created_at": 1789626857.4573538}, {"event_id": "b7fbfe4e2ae446fca50a22be8c0c4610", "step": 4, "value": 0.9992976170834611, "stage": "debug", "created_at": 1789627026.242707}, {"event_id": "45fcc37da20b454d92262de7a05bd2e3", "step": 5, "value": 1.0, "stage": "debug", "created_at": 1789627313.4852967}, {"event_id": "710f0d289b7740daa7ec911e61a5b170", "step": 7, "value": 0.9999964645155208, "stage": "improve", "created_at": 1789627527.927437}, {"event_id": "9a274028241e418d9b6caa05223ca7a7", "step": 8, "value": 0.9998820765841833, "stage": "improve", "created_at": 1789627426.731829}, {"event_id": "9942aa7abe464703a4d2d26f0fec8910", "step": 9, "value": 0.9999976430103472, "stage": "debug", "created_at": 1789628058.404752}, {"event_id": "dd4c8b3a0a6444c0bbb3d13194abdad6", "step": 10, "value": 0.9999952860206944, "stage": "improve", "created_at": 1789628703.599269}, {"event_id": "5d03a15aa5184316b339770b3f7bd693", "step": 12, "value": 0.9999870284242602, "stage": "improve", "created_at": 1789628872.4790707}, {"event_id": "73ca8f73c48643a49e4ecc783e7835d9", "step": 16, "value": 1.0, "stage": "debug", "created_at": 1789630227.4601219}, {"event_id": "d095aa1eaecf4f3790291bbe378063b9", "step": 17, "value": 0.999965262963215, "stage": "debug", "created_at": 1789630148.0475497}, {"event_id": "0ca6cf3f081c45a0b1ad9ec3118fce16", "step": 19, "value": 0.9999787870931246, "stage": "debug", "created_at": 1789631968.5682502}, {"event_id": "37de85b21bc649f2b04c6173e973ee2c", "step": 20, "value": 0.9999661781428781, "stage": "improve", "created_at": 1789629450.8613794}, {"event_id": "86223902685a484da11d6f731766e347", "step": 21, "value": 0.9999764301034719, "stage": "improve", "created_at": 1789632885.4248831}, {"event_id": "df5a829c18eb4f7c93e534347237e883", "step": 22, "value": 0.9999422906273188, "stage": "improve", "created_at": 1789631539.53128}, {"event_id": "edf325415e3243e09270f5df12bac626", "step": 23, "value": 1.0, "stage": "improve", "created_at": 1789633503.6748817}, {"event_id": "890e478cf57841c5b4937349ee0e688c", "step": 24, "value": 0.9999351150882196, "stage": "evolution", "created_at": 1789634644.0240362}, {"event_id": "21aa789c00c643ca803139b16ea2e5ed", "step": 25, "value": 0.9999964645155208, "stage": "improve", "created_at": 1789633713.863029}, {"event_id": "b38ef9f0164041639c6b5ca994951d4f", "step": 26, "value": 0.9999539492204208, "stage": "evolution", "created_at": 1789634650.6807363}, {"event_id": "e4cde8c7cc344a9fae348bad5ca81e30", "step": 27, "value": 0.9999811440827775, "stage": "draft", "created_at": 1789638714.205341}, {"event_id": "9e80c58a81bd4bc98cddcfdf8aafe4ea", "step": 31, "value": 0.9999988215051736, "stage": "evolution", "created_at": 1789640950.3542325}, {"event_id": "df5adfc3d637481d96bb0367971e3912", "step": 32, "value": 0.9999952860206943, "stage": "improve", "created_at": 1789641947.1484094}, {"event_id": "4705cae6df9a4b7fa7d947c659275963", "step": 33, "value": 0.9999244247286744, "stage": "debug", "created_at": 1789640740.4277272}, {"event_id": "e981a047ae784b6fa4ac1561662af2f8", "step": 35, "value": 0.999997320778377, "stage": "debug", "created_at": 1789640553.4118009}, {"event_id": "17a21b3740e9472d84f1212a380f713b", "step": 39, "value": 0.9996641289744738, "stage": "debug", "created_at": 1789650093.46141}, {"event_id": "2b43ff99316844639c2ba54c7db60f8c", "step": 42, "value": 0.9999634666603814, "stage": "fusion_draft", "created_at": 1789652727.7076755}, {"event_id": "2eb6f25f413a4be0b48ccf55a5ba537f", "step": 44, "value": 1.0, "stage": "improve", "created_at": 1789651296.1048439}], "maximize": true, "elapsed_seconds": 28685.26997756958, "node_count": 46, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-hard14-20260917/xixian.gp7-ancestry-logei.aerial-cactus-identification.yaml", "note": ""}, {"id": "xixian.gp7-ancestry-logei.aptos2019-blindness-detection", "experiment_id": "mlebench-gp7-hard14-20260917", "family": "MLEBench", "method": "gp7_ancestry_logei", "dataset": "aptos2019-blindness-detection", "status": "archived", "official_score": 0.89417, "medal": "none", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.930508, "silver": 0.919654, "bronze": 0.914492}, "grading_policy": "ensemble", "artifacts": [{"bundle_id": "gp7-ancestry-logei-hard14-full-logs-20260917", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917/logs-77c0e49ab8d6.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917", "member": "results/official_private_grades.jsonl:4", "sha256": "77c0e49ab8d6df7268cefe20565a32eaa589661c5946ef2499c567afceab8104"}, {"bundle_id": "gp7-ancestry-logei-hard14-full-logs-20260917", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917/logs-77c0e49ab8d6.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917", "member": "gp7_ancestry_logei-hard14/runs/02_aptos2019-blindness-detection/logs/journal.json", "sha256": "77c0e49ab8d6df7268cefe20565a32eaa589661c5946ef2499c567afceab8104"}], "alternate_scores": [{"cohort": "09-17", "workflow_id": "09-17 gp7_ancestry_logei", "method": "gp7_ancestry_logei", "task": "aptos2019-blindness-detection", "policy": "best_node", "status": "graded", "valid_submission": true, "score": 0.89587, "medal": "none", "is_lower_better": false, "gold_threshold": 0.930508, "silver_threshold": 0.919654, "bronze_threshold": 0.914492, "submission_sha256": "3915640731c24fc9245679b33c71cf31d69bf06dcb42b6116923d96d0be080c7", "source_archive": "gp7_ancestry_logei_hard14_full_logs_20260917.zip", "source_member": "results/official_private_grades.jsonl", "source_line": 3}], "journal_ref": "gp7-ancestry-logei-hard14-full-logs-20260917:gp7_ancestry_logei-hard14/runs/02_aptos2019-blindness-detection/logs/journal.json", "metrics": [{"event_id": "d761a3de33224bfa8a0abb0480330f54", "step": 2, "value": 0.8915360625043082, "stage": "draft", "created_at": 1789626153.9642138}, {"event_id": "c4a8e0c81a0140d3ba28e3d55787b0c3", "step": 3, "value": 0.9121870718432139, "stage": "draft", "created_at": 1789626678.082071}, {"event_id": "19c900ae4ff3471190ece14ca56d7c2f", "step": 4, "value": 0.9159189275129886, "stage": "improve", "created_at": 1789627247.9411972}, {"event_id": "b202dbdd98f74e63b632516dbb9f3ac9", "step": 5, "value": 0.9083004471856827, "stage": "debug", "created_at": 1789626992.111389}, {"event_id": "5c85120b7c3b4a9db90320c405651cd0", "step": 9, "value": 0.9048693720798274, "stage": "debug", "created_at": 1789628841.9023578}, {"event_id": "8ddfc1ee019e4f6586809b49e19b9c6f", "step": 10, "value": 0.9183400790630956, "stage": "debug", "created_at": 1789628756.26675}, {"event_id": "df44ae103e4241cf81d4a6117ec1ddc5", "step": 14, "value": 0.9198792805464483, "stage": "debug", "created_at": 1789629932.9265862}, {"event_id": "87226024dfd648f08edd7f5ef9d11b1c", "step": 16, "value": 0.8580476165589777, "stage": "debug", "created_at": 1789630832.2797294}, {"event_id": "19c87104746d48788e24a80ea612f2a4", "step": 17, "value": 0.9174542648641354, "stage": "improve", "created_at": 1789633536.2159038}, {"event_id": "1e2b4991bc684afe86ba4646a335880b", "step": 18, "value": 0.9023052337566577, "stage": "improve", "created_at": 1789631890.2603161}, {"event_id": "4b2b2a43dfd5413cb1f2112a0ecb9d45", "step": 19, "value": 0.8507878648959157, "stage": "debug", "created_at": 1789633421.4347878}, {"event_id": "697451725e8d4a22b6867a8828d703cf", "step": 20, "value": 0.9153831802088055, "stage": "improve", "created_at": 1789635535.6671414}, {"event_id": "73a719033c3a40b790c5a8e121b06b25", "step": 21, "value": 0.9116411753051107, "stage": "improve", "created_at": 1789635857.6103375}, {"event_id": "63267dbfbe754d09aaed4a75eba7bdb1", "step": 22, "value": 0.9085109168519099, "stage": "improve", "created_at": 1789636764.4761345}, {"event_id": "4c377ec8e59249b68a4612acbcde008c", "step": 23, "value": 0.9153831802088055, "stage": "improve", "created_at": 1789637319.447657}, {"event_id": "5d9b4960f9714ecf8fde962427fa3336", "step": 24, "value": 0.8792810352154989, "stage": "fusion", "created_at": 1789641582.028714}, {"event_id": "24f4cab23f91493ca19d1180d1d040ad", "step": 25, "value": 0.9132695492089502, "stage": "draft", "created_at": 1789642401.1605484}, {"event_id": "9efc8322bd74496a8c30561af7101567", "step": 27, "value": 0.9027067066327433, "stage": "evolution", "created_at": 1789643047.188694}, {"event_id": "d28920b7edca4c4aa3544fd909d7c803", "step": 29, "value": 0.8773863546346488, "stage": "improve", "created_at": 1789646305.9501503}, {"event_id": "65a3168556414070b6b4fa1173fa1c2f", "step": 31, "value": 0.9153831802088055, "stage": "fusion", "created_at": 1789645301.4999475}, {"event_id": "cb9231ece93f43df8ee12dcae94b411f", "step": 33, "value": 0.9153831802088055, "stage": "debug", "created_at": 1789648826.7738354}], "maximize": true, "elapsed_seconds": 28755.02280473709, "node_count": 34, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-hard14-20260917/xixian.gp7-ancestry-logei.aptos2019-blindness-detection.yaml", "note": ""}, {"id": "xixian.gp7-ancestry-logei.dog-breed-identification", "experiment_id": "mlebench-gp7-hard14-20260917", "family": "MLEBench", "method": "gp7_ancestry_logei", "dataset": "dog-breed-identification", "status": "archived", "official_score": 0.29511, "medal": "none", "valid_submission": true, "score_maximize": false, "thresholds": {"gold": 0.0005, "silver": 0.00539, "bronze": 0.04598}, "grading_policy": "ensemble", "artifacts": [{"bundle_id": "gp7-ancestry-logei-hard14-full-logs-20260917", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917/logs-77c0e49ab8d6.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917", "member": "results/official_private_grades.jsonl:6", "sha256": "77c0e49ab8d6df7268cefe20565a32eaa589661c5946ef2499c567afceab8104"}, {"bundle_id": "gp7-ancestry-logei-hard14-full-logs-20260917", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917/logs-77c0e49ab8d6.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917", "member": "gp7_ancestry_logei-hard14/runs/03_dog-breed-identification/logs/journal.json", "sha256": "77c0e49ab8d6df7268cefe20565a32eaa589661c5946ef2499c567afceab8104"}], "alternate_scores": [{"cohort": "09-17", "workflow_id": "09-17 gp7_ancestry_logei", "method": "gp7_ancestry_logei", "task": "dog-breed-identification", "policy": "best_node", "status": "graded", "valid_submission": true, "score": 0.30392, "medal": "none", "is_lower_better": true, "gold_threshold": 0.0005, "silver_threshold": 0.00539, "bronze_threshold": 0.04598, "submission_sha256": "0891ad6d3ad72550b48579965648ed89ddd793a553ce5946675ecebc5b36bbdf", "source_archive": "gp7_ancestry_logei_hard14_full_logs_20260917.zip", "source_member": "results/official_private_grades.jsonl", "source_line": 5}], "journal_ref": "gp7-ancestry-logei-hard14-full-logs-20260917:gp7_ancestry_logei-hard14/runs/03_dog-breed-identification/logs/journal.json", "metrics": [{"event_id": "0a705232a74b4c90838dd9b01cd122be", "step": 2, "value": 0.5633742867497828, "stage": "draft", "created_at": 1789626743.5361521}, {"event_id": "8fee2bededbb4f329b441cac28291c9a", "step": 3, "value": 0.7371433780530684, "stage": "draft", "created_at": 1789626192.5561535}, {"event_id": "e0e5e00e8763410fbdf7badd0df07a03", "step": 6, "value": 0.4106781370886051, "stage": "debug", "created_at": 1789626891.100909}, {"event_id": "366cababe5a54a7c889071475449de25", "step": 7, "value": 0.641433955436846, "stage": "debug", "created_at": 1789627839.6643004}, {"event_id": "4645a665cdda4e7c8ddf27b89f67bed7", "step": 9, "value": 0.615332673230766, "stage": "debug", "created_at": 1789628421.2442007}, {"event_id": "482282602f804a4ba3713ec24227ee3f", "step": 11, "value": 0.41666641690356204, "stage": "improve", "created_at": 1789630762.3543243}, {"event_id": "3cd0b23634be43a8a2015a93763b4d9e", "step": 14, "value": 0.39315984517315217, "stage": "debug", "created_at": 1789630717.4314113}, {"event_id": "7ac767742c5a4c1498567c8d703f7186", "step": 15, "value": 0.3962893280550003, "stage": "debug", "created_at": 1789630622.028336}, {"event_id": "d31a5539d88f4aa1a9ba5cbfed00687e", "step": 17, "value": 0.39791466351210664, "stage": "improve", "created_at": 1789633816.1161623}, {"event_id": "b05a97b7619745ceb8e341f873cbd616", "step": 23, "value": 0.22720583264635555, "stage": "debug", "created_at": 1789636084.3098886}, {"event_id": "9f32c60a59a84452bf7f9b6ae7b036aa", "step": 31, "value": 0.26365459590400464, "stage": "debug", "created_at": 1789645697.6935995}, {"event_id": "02ec9463cfc54894b2bf7321df9484ee", "step": 32, "value": 0.6622073247991602, "stage": "fusion_draft", "created_at": 1789653937.2826707}], "maximize": false, "elapsed_seconds": 28770.406395196915, "node_count": 33, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-hard14-20260917/xixian.gp7-ancestry-logei.dog-breed-identification.yaml", "note": ""}, {"id": "xixian.gp7-ancestry-logei.jigsaw-toxic-comment-classification-challenge", "experiment_id": "mlebench-gp7-hard14-20260917", "family": "MLEBench", "method": "gp7_ancestry_logei", "dataset": "jigsaw-toxic-comment-classification-challenge", "status": "archived", "official_score": 0.98832, "medal": "gold", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.9874, "silver": 0.98668, "bronze": 0.98639}, "grading_policy": "ensemble", "artifacts": [{"bundle_id": "gp7-ancestry-logei-hard14-full-logs-20260917", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917/logs-77c0e49ab8d6.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917", "member": "results/official_private_grades.jsonl:8", "sha256": "77c0e49ab8d6df7268cefe20565a32eaa589661c5946ef2499c567afceab8104"}, {"bundle_id": "gp7-ancestry-logei-hard14-full-logs-20260917", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917/logs-77c0e49ab8d6.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917", "member": "gp7_ancestry_logei-hard14/runs/04_jigsaw-toxic-comment-classification-challenge/logs/journal.json", "sha256": "77c0e49ab8d6df7268cefe20565a32eaa589661c5946ef2499c567afceab8104"}], "alternate_scores": [{"cohort": "09-17", "workflow_id": "09-17 gp7_ancestry_logei", "method": "gp7_ancestry_logei", "task": "jigsaw-toxic-comment-classification-challenge", "policy": "best_node", "status": "graded", "valid_submission": true, "score": 0.98667, "medal": "bronze", "is_lower_better": false, "gold_threshold": 0.9874, "silver_threshold": 0.98668, "bronze_threshold": 0.98639, "submission_sha256": "b38737dd62c5e947f16deb1ddc00067d0b25386ec9941de55e4d568de4602d7b", "source_archive": "gp7_ancestry_logei_hard14_full_logs_20260917.zip", "source_member": "results/official_private_grades.jsonl", "source_line": 7}], "journal_ref": "gp7-ancestry-logei-hard14-full-logs-20260917:gp7_ancestry_logei-hard14/runs/04_jigsaw-toxic-comment-classification-challenge/logs/journal.json", "metrics": [{"event_id": "62719b29dbe34ce6bad2fcf182ad2652", "step": 4, "value": 0.9716887462770424, "stage": "debug", "created_at": 1789627048.6030016}, {"event_id": "092d04cf18984c468c988700f1dafe34", "step": 5, "value": 0.9930548906062641, "stage": "debug", "created_at": 1789627340.305106}, {"event_id": "f4643564763847208714b2ded7285e17", "step": 6, "value": 0.9912178620922775, "stage": "draft", "created_at": 1789626248.2074475}, {"event_id": "f3e50ca0c4db48a498ca10241b8f514d", "step": 7, "value": 0.9923837412284587, "stage": "improve", "created_at": 1789631169.1735106}, {"event_id": "e362aa91427d4d769553b81a33d56934", "step": 8, "value": 0.9819984938205316, "stage": "improve", "created_at": 1789637086.776317}, {"event_id": "2918fbf1b417490e973ae1486e1afbe9", "step": 9, "value": 0.9641646928022991, "stage": "improve", "created_at": 1789630542.2632105}, {"event_id": "96d570f67cac4accbffda4c5b42d11e3", "step": 10, "value": 0.9911597487063304, "stage": "improve", "created_at": 1789643428.2264721}], "maximize": true, "elapsed_seconds": 28760.78512072563, "node_count": 12, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-hard14-20260917/xixian.gp7-ancestry-logei.jigsaw-toxic-comment-classification-challenge.yaml", "note": ""}, {"id": "xixian.gp7-ancestry-logei.leaf-classification", "experiment_id": "mlebench-gp7-hard14-20260917", "family": "MLEBench", "method": "gp7_ancestry_logei", "dataset": "leaf-classification", "status": "archived", "official_score": 2e-05, "medal": "silver", "valid_submission": true, "score_maximize": false, "thresholds": {"gold": 0.0, "silver": 0.00791, "bronze": 0.01526}, "grading_policy": "ensemble", "artifacts": [{"bundle_id": "gp7-ancestry-logei-hard14-full-logs-20260917", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917/logs-77c0e49ab8d6.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917", "member": "results/official_private_grades.jsonl:10", "sha256": "77c0e49ab8d6df7268cefe20565a32eaa589661c5946ef2499c567afceab8104"}, {"bundle_id": "gp7-ancestry-logei-hard14-full-logs-20260917", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917/logs-77c0e49ab8d6.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917", "member": "gp7_ancestry_logei-hard14/runs/05_leaf-classification/logs/journal.json", "sha256": "77c0e49ab8d6df7268cefe20565a32eaa589661c5946ef2499c567afceab8104"}], "alternate_scores": [{"cohort": "09-17", "workflow_id": "09-17 gp7_ancestry_logei", "method": "gp7_ancestry_logei", "task": "leaf-classification", "policy": "best_node", "status": "graded", "valid_submission": true, "score": 1e-05, "medal": "silver", "is_lower_better": true, "gold_threshold": 0.0, "silver_threshold": 0.00791, "bronze_threshold": 0.01526, "submission_sha256": "fce7cec39512f9f950110807898f466cb17cef71b314d3fb2aca6b4137fe7b53", "source_archive": "gp7_ancestry_logei_hard14_full_logs_20260917.zip", "source_member": "results/official_private_grades.jsonl", "source_line": 9}], "journal_ref": "gp7-ancestry-logei-hard14-full-logs-20260917:gp7_ancestry_logei-hard14/runs/05_leaf-classification/logs/journal.json", "metrics": [{"event_id": "6e42bc61952b4ea0a621653118da6e9c", "step": 2, "value": 1.3268864994370696e-06, "stage": "draft", "created_at": 1789626550.887345}, {"event_id": "e851f4f3c0f0495cb020bcc1325eb48f", "step": 3, "value": 1.8340078384546196e-07, "stage": "debug", "created_at": 1789627095.1229324}, {"event_id": "11390a8400014227ae653381cf694696", "step": 4, "value": 0.009363606292841305, "stage": "improve", "created_at": 1789627246.8398108}, {"event_id": "3f46197d3287423285d0931bb81fe2f9", "step": 5, "value": 0.012894212577872774, "stage": "improve", "created_at": 1789627622.2833207}, {"event_id": "b5d30014f1084913910508a6896d5e1b", "step": 6, "value": 4.175379483327618e-09, "stage": "improve", "created_at": 1789627676.5619943}, {"event_id": "97b6c71584914931968d50c610e91c1d", "step": 7, "value": 3.005791660602471e-06, "stage": "improve", "created_at": 1789628752.8550715}, {"event_id": "b70feb7801a94ebfb2a38ae5f0994e73", "step": 8, "value": 0.0002308095257304494, "stage": "improve", "created_at": 1789629575.054593}, {"event_id": "aa716569c35341cea1112d9cd2616816", "step": 9, "value": 1.4155577481871226e-08, "stage": "improve", "created_at": 1789628968.3054402}, {"event_id": "1baa2b21badb4b34846eb77b225b9af0", "step": 11, "value": 0.00550476461648941, "stage": "debug", "created_at": 1789630530.5826411}, {"event_id": "325448b49ae74f85984f33ccedf51cb4", "step": 12, "value": 0.010679036664260282, "stage": "improve", "created_at": 1789630083.8557613}, {"event_id": "6918b403dc964b2abacb0274084a53fc", "step": 14, "value": 0.19455700950775265, "stage": "debug", "created_at": 1789631391.587833}, {"event_id": "bebeafd2110e4d3f987829b73c88a95a", "step": 15, "value": 3.0, "stage": "improve", "created_at": 1789630857.0726159}, {"event_id": "c0b835bd0af14d548a164db1a7ac0216", "step": 16, "value": 0.1818067122506862, "stage": "improve", "created_at": 1789633066.9122412}, {"event_id": "cf61441b0a014a21962b2f16075d98ba", "step": 17, "value": 0.008693811483681202, "stage": "improve", "created_at": 1789633559.5513122}, {"event_id": "8d37a4bb6fed4bd58ea77c2bf9781716", "step": 18, "value": 0.13479601572369512, "stage": "improve", "created_at": 1789634075.3124127}, {"event_id": "7cc54c7b54a042d383a5b5506651d279", "step": 20, "value": 0.0032734450571544373, "stage": "debug", "created_at": 1789635761.3287683}, {"event_id": "827c6494ddbb430d97c6c9b2788fd34b", "step": 22, "value": 3.0, "stage": "debug", "created_at": 1789641231.4286776}, {"event_id": "f7c1692c049b43d5b85cadb9073af557", "step": 23, "value": 0.016933007165789604, "stage": "evolution", "created_at": 1789641913.0973873}, {"event_id": "52fc0ab36198440cbac788c8ccf4820d", "step": 25, "value": 0.12363770052902609, "stage": "debug", "created_at": 1789642616.7514124}], "maximize": false, "elapsed_seconds": 28770.633812904358, "node_count": 29, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-hard14-20260917/xixian.gp7-ancestry-logei.leaf-classification.yaml", "note": ""}, {"id": "xixian.gp7-ancestry-logei.mlsp-2013-birds", "experiment_id": "mlebench-gp7-hard14-20260917", "family": "MLEBench", "method": "gp7_ancestry_logei", "dataset": "mlsp-2013-birds", "status": "archived", "official_score": 0.92429, "medal": "silver", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.93527, "silver": 0.90038, "bronze": 0.87372}, "grading_policy": "ensemble", "artifacts": [{"bundle_id": "gp7-ancestry-logei-hard14-full-logs-20260917", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917/logs-77c0e49ab8d6.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917", "member": "results/official_private_grades.jsonl:12", "sha256": "77c0e49ab8d6df7268cefe20565a32eaa589661c5946ef2499c567afceab8104"}, {"bundle_id": "gp7-ancestry-logei-hard14-full-logs-20260917", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917/logs-77c0e49ab8d6.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917", "member": "gp7_ancestry_logei-hard14/runs/06_mlsp-2013-birds/logs/journal.json", "sha256": "77c0e49ab8d6df7268cefe20565a32eaa589661c5946ef2499c567afceab8104"}], "alternate_scores": [{"cohort": "09-17", "workflow_id": "09-17 gp7_ancestry_logei", "method": "gp7_ancestry_logei", "task": "mlsp-2013-birds", "policy": "best_node", "status": "graded", "valid_submission": true, "score": 0.90858, "medal": "silver", "is_lower_better": false, "gold_threshold": 0.93527, "silver_threshold": 0.90038, "bronze_threshold": 0.87372, "submission_sha256": "4ccfb3bf9818a6197796a064a74f92411820d0eb665a578aeca368538361b467", "source_archive": "gp7_ancestry_logei_hard14_full_logs_20260917.zip", "source_member": "results/official_private_grades.jsonl", "source_line": 11}], "journal_ref": "gp7-ancestry-logei-hard14-full-logs-20260917:gp7_ancestry_logei-hard14/runs/06_mlsp-2013-birds/logs/journal.json", "metrics": [{"event_id": "01db2c29ade94d4fb505f1e675a12387", "step": 10, "value": 0.7927518848526388, "stage": "debug", "created_at": 1789628755.426261}, {"event_id": "a2785de113884f4f992ac2a3df8c9767", "step": 11, "value": 0.7493917066483893, "stage": "improve", "created_at": 1789629054.9199102}, {"event_id": "348149cc6a4d41caa92fdde6d6dcd886", "step": 12, "value": 0.8183087731322823, "stage": "improve", "created_at": 1789629399.2973359}, {"event_id": "3ceab1c31d034a068686f5f922effe10", "step": 13, "value": 0.7021864454443195, "stage": "debug", "created_at": 1789628644.086962}, {"event_id": "b39596bc292a40d2a4117514cf0461a8", "step": 14, "value": 0.8378084304318025, "stage": "improve", "created_at": 1789629732.6894503}, {"event_id": "0c1c43922fea4c6e9828d5874369d224", "step": 15, "value": 0.7635795065113091, "stage": "improve", "created_at": 1789629808.6215005}, {"event_id": "2c32096c928d437d9715ced1b080f86d", "step": 16, "value": 0.828367032213845, "stage": "improve", "created_at": 1789630102.2801952}, {"event_id": "84900828aa98484ba75868614248467b", "step": 17, "value": 0.8423320767649075, "stage": "improve", "created_at": 1789630176.4045198}, {"event_id": "2c13c6ac3986445ba71405c6a202c9f3", "step": 18, "value": 0.8623886223440712, "stage": "improve", "created_at": 1789630545.2159297}, {"event_id": "25a86ad1e12a4d8cbe4b5e6528a1f061", "step": 19, "value": 0.7627595611479576, "stage": "improve", "created_at": 1789630522.5095143}, {"event_id": "91031f8e0c274e3b8fa8fdb9b66e7230", "step": 20, "value": 0.8468214530500343, "stage": "improve", "created_at": 1789631131.4163995}, {"event_id": "2fb519d048fd47c9862ba0ab47f429d5", "step": 22, "value": 0.8426405071967101, "stage": "improve", "created_at": 1789631492.1353366}, {"event_id": "70e9c980eb374d2dbde1275d986f266a", "step": 23, "value": 0.7917188371660573, "stage": "improve", "created_at": 1789631566.7991958}, {"event_id": "c8cfc0d0640d43fba66e2a91ed5e6da6", "step": 25, "value": 0.7828478409869774, "stage": "debug", "created_at": 1789632314.1803746}, {"event_id": "d6902ce063b244199a457a716f0ae485", "step": 26, "value": 0.8241996097997824, "stage": "evolution", "created_at": 1789632566.7164912}, {"event_id": "97e1a32534e1432a9f56214485a94167", "step": 27, "value": 0.7960931064098294, "stage": "debug", "created_at": 1789631600.4260604}, {"event_id": "c59ad7728d374894b79956ff408adaef", "step": 29, "value": 0.8181235207573724, "stage": "evolution", "created_at": 1789633402.0211549}, {"event_id": "607cd86c00b0423dbf501be4a58fb166", "step": 30, "value": 0.7467297966611649, "stage": "debug", "created_at": 1789634203.4430761}, {"event_id": "ae59a5d639934e089524ea6169e3f32b", "step": 31, "value": 0.8808944482522275, "stage": "evolution", "created_at": 1789634898.5529907}, {"event_id": "c1ad48627fee4251a9899159251d2634", "step": 32, "value": 0.8836360520904729, "stage": "improve", "created_at": 1789635520.6761642}, {"event_id": "bfc0d69138b84f5fa6a4cb7a3fee714f", "step": 33, "value": 0.882659355723098, "stage": "improve", "created_at": 1789636088.6781192}, {"event_id": "3c47d0541f304a7daf1de0959072ebab", "step": 36, "value": 0.8474640164496229, "stage": "evolution", "created_at": 1789634325.8644142}, {"event_id": "22182efca5534b4eb41ec6f2b476f2c9", "step": 37, "value": 0.8453478409869774, "stage": "debug", "created_at": 1789636985.627912}, {"event_id": "76398e6502454602b8a1a11b30b1219a", "step": 39, "value": 0.8776216586703222, "stage": "improve", "created_at": 1789637675.5799441}, {"event_id": "98c947f6d15c498290afd41206bab93b", "step": 40, "value": 0.8848440712816998, "stage": "debug", "created_at": 1789638054.9664507}, {"event_id": "83d20652075944928ade709e5dc27e3b", "step": 41, "value": 0.9360383483656367, "stage": "evolution", "created_at": 1789638349.5559711}, {"event_id": "19d7c003ba714a0192f935273d4e1b70", "step": 42, "value": 0.9342871830020563, "stage": "improve", "created_at": 1789638751.9131427}, {"event_id": "e6d6808c2a10445795128d144450801b", "step": 43, "value": 0.9384842960404273, "stage": "improve", "created_at": 1789639150.6818492}, {"event_id": "9c9e1d02bad64a709b1e85071876f16e", "step": 44, "value": 0.8929532213845099, "stage": "improve", "created_at": 1789639707.0781481}, {"event_id": "9b259859190e4c36a6768d81654e7066", "step": 45, "value": 0.9467704535277937, "stage": "improve", "created_at": 1789639952.929726}, {"event_id": "c811bd1d096d4ae39ea0e6a6d2cee310", "step": 46, "value": 0.9374536237446428, "stage": "improve", "created_at": 1789640442.588853}, {"event_id": "230da6d3929543868605543d0a268ba7", "step": 47, "value": 0.8166130940958228, "stage": "debug", "created_at": 1789637059.4901855}, {"event_id": "4b99221aced64670ba35c20c58110d07", "step": 48, "value": 0.9449953623744644, "stage": "improve", "created_at": 1789640699.2903244}, {"event_id": "92152f10d7984d379cac0bd7f03bf235", "step": 49, "value": 0.956782127550694, "stage": "improve", "created_at": 1789641252.4738674}, {"event_id": "3878f0a15e414e7286f11c7313369b7b", "step": 50, "value": 0.9293505725068766, "stage": "improve", "created_at": 1789641335.359553}, {"event_id": "9a50f8dc900f4743a5573fd1879f97fb", "step": 51, "value": 0.9135546600140728, "stage": "evolution", "created_at": 1789641379.389061}, {"event_id": "4164bf76f0cb480aa40b01d9d96a414f", "step": 52, "value": 0.939945148084181, "stage": "improve", "created_at": 1789642094.0788517}, {"event_id": "78ecb9c30cba4a428aa7a8f562a5f835", "step": 53, "value": 0.94339298279281, "stage": "improve", "created_at": 1789642115.5853748}, {"event_id": "ee58bc51278645568c87615a14aa692e", "step": 54, "value": 0.935099628989957, "stage": "improve", "created_at": 1789642248.5437999}, {"event_id": "fae4b03ee33a475c8ebca226665e6e8b", "step": 55, "value": 0.9472462099405103, "stage": "improve", "created_at": 1789642798.2855198}, {"event_id": "c0464a7246ac45098f9a436300b8fb1d", "step": 56, "value": 0.9381372737158575, "stage": "improve", "created_at": 1789642878.9484277}, {"event_id": "58fcc29e02024273b8f3b093a20ab50a", "step": 57, "value": 0.9511274227595471, "stage": "evolution", "created_at": 1789642886.9641154}, {"event_id": "8999c62ba81a44fb96a0a29f34065fe0", "step": 58, "value": 0.9595215249792106, "stage": "evolution", "created_at": 1789643509.5454059}, {"event_id": "11da486be0434ba28a34f59f987b0f6f", "step": 59, "value": 0.9340681571035631, "stage": "fusion", "created_at": 1789643592.1737423}, {"event_id": "f07683d8f73c4916931943aca3b63d9f", "step": 60, "value": 0.9511290219407664, "stage": "fusion", "created_at": 1789643619.6914299}, {"event_id": "d00c3165616d4cf6aaf26ac5beb686b7", "step": 61, "value": 0.956288780144566, "stage": "improve", "created_at": 1789644271.6174374}, {"event_id": "138d0781b7bd4ce5b8e26dc116ad2746", "step": 62, "value": 0.9046927972877886, "stage": "improve", "created_at": 1789644278.0717995}, {"event_id": "238d858028c14204a883f4c76fc3fc32", "step": 63, "value": 0.9567165611207061, "stage": "improve", "created_at": 1789644357.7072256}, {"event_id": "37c08019a6c44939b7205fc38eeba903", "step": 64, "value": 0.9510618563295592, "stage": "evolution", "created_at": 1789644969.2154496}, {"event_id": "270cbeb1680340c8bd832c94adfcdca9", "step": 65, "value": 0.906780528369475, "stage": "evolution", "created_at": 1789645091.9725046}, {"event_id": "98323715cc3b4ffda59dfff3f2f4a161", "step": 66, "value": 0.9427677029360967, "stage": "evolution", "created_at": 1789644987.6047776}, {"event_id": "a4762497a554445db9d2fd9841c6ee4d", "step": 67, "value": 0.9379877502718609, "stage": "evolution", "created_at": 1789645787.9752812}, {"event_id": "2de87bcf75d14798bd68f0077ae2b57f", "step": 68, "value": 0.9540339346254718, "stage": "fusion", "created_at": 1789645832.2752197}, {"event_id": "1e5763bd3e50466892cdbf07a1bf3800", "step": 69, "value": 0.9341769014264696, "stage": "fusion", "created_at": 1789645652.9300537}, {"event_id": "303a821b1d7842d3a8a2acd43b9664cf", "step": 70, "value": 0.9555363653809249, "stage": "evolution", "created_at": 1789646629.0672832}, {"event_id": "bb7b6aca130542eeba2f0ce67e8eec47", "step": 71, "value": 0.9392015288172456, "stage": "evolution", "created_at": 1789646627.6404033}, {"event_id": "e889b28e7b4443f48628247de34e348a", "step": 72, "value": 0.9557490564830806, "stage": "evolution", "created_at": 1789646632.113817}, {"event_id": "2c39fef80e994a84b58695decf3c0d4d", "step": 75, "value": 0.9573826200985095, "stage": "evolution", "created_at": 1789647444.8204875}, {"event_id": "7dc48192954f4004b794ada71e21d411", "step": 76, "value": 0.9553332693660846, "stage": "evolution", "created_at": 1789647637.7057424}, {"event_id": "21562417342c430ab6a8b1e759070007", "step": 77, "value": 0.8300965905456407, "stage": "debug", "created_at": 1789647757.8575878}, {"event_id": "b88037e4b38c498794b2e4a4952af40f", "step": 78, "value": 0.9074801701528817, "stage": "fusion", "created_at": 1789648192.6292408}, {"event_id": "e276031e57b444f9a7893b06b2b59281", "step": 79, "value": 0.9561808354122688, "stage": "fusion", "created_at": 1789648340.5071514}, {"event_id": "ffefd3e5ddd6446fb06647fa64c68dd2", "step": 80, "value": 0.9616388409134523, "stage": "fusion", "created_at": 1789648827.870253}, {"event_id": "bb147ee6db34432a85174e7500c82484", "step": 81, "value": 0.9314287085012474, "stage": "evolution", "created_at": 1789648902.853853}, {"event_id": "ab0d2b012fda4391bfa88b8aa4fe40f2", "step": 82, "value": 0.9574393910317915, "stage": "fusion", "created_at": 1789649069.4195526}, {"event_id": "89ad02fa7e5e4840aa8b9d60063fc8e0", "step": 83, "value": 0.9054236231049703, "stage": "improve", "created_at": 1789649550.036745}, {"event_id": "1de4515ea77a49cb9ee167579f3ad263", "step": 84, "value": 0.9350580502782574, "stage": "improve", "created_at": 1789649767.4599583}, {"event_id": "99eae20689e54357b04d4e1a2d88a91d", "step": 85, "value": 0.9482456982025202, "stage": "improve", "created_at": 1789649699.4889352}, {"event_id": "332535ad4ff84146be00ed49cf0e3f3f", "step": 88, "value": 0.9443764792426278, "stage": "evolution", "created_at": 1789650627.4332106}, {"event_id": "6d6a671da86546508f492f1b03b9c3c8", "step": 89, "value": 0.8352371585748097, "stage": "debug", "created_at": 1789650752.8966212}, {"event_id": "d6840f1d80a34ec0bd6161b63a8c8232", "step": 90, "value": 0.95703479818333, "stage": "improve", "created_at": 1789650740.8537223}, {"event_id": "4ce8039a8efa4049b2a07088468c0af8", "step": 91, "value": 0.9643942301541611, "stage": "evolution", "created_at": 1789651206.2961318}, {"event_id": "b4855fa276b64c4d8d5ca0fe609196ae", "step": 93, "value": 0.9837547175845966, "stage": "evolution", "created_at": 1789651515.4800901}, {"event_id": "e05e6a368bdd40328d92a10e03458492", "step": 94, "value": 0.9555211731593424, "stage": "improve", "created_at": 1789651943.5692291}, {"event_id": "04bb148fd31b448aaa14c3689593447d", "step": 95, "value": 0.9437791850572508, "stage": "improve", "created_at": 1789651975.2690039}, {"event_id": "5ea68e704a2e44358ba1cbef2a7c819d", "step": 97, "value": 0.9861734791786605, "stage": "improve", "created_at": 1789652296.8514771}, {"event_id": "252b99e4cf3147e4b48fd5bf24c1f4eb", "step": 98, "value": 0.9844791466769014, "stage": "improve", "created_at": 1789652765.2958288}, {"event_id": "f4b885439cc6403e87e2d079e5bacf70", "step": 99, "value": 0.9471542570204056, "stage": "improve", "created_at": 1789653151.1196492}, {"event_id": "e4e233d38a4c47dd8f1eedb16922b200", "step": 100, "value": 0.9864661293417771, "stage": "improve", "created_at": 1789653251.737468}, {"event_id": "fbb533d7de1a408ca6ed120e6fa27937", "step": 101, "value": 0.9858648372033518, "stage": "improve", "created_at": 1789653908.0749693}], "maximize": true, "elapsed_seconds": 28744.444864034653, "node_count": 102, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-hard14-20260917/xixian.gp7-ancestry-logei.mlsp-2013-birds.yaml", "note": ""}, {"id": "xixian.gp7-ancestry-logei.new-york-city-taxi-fare-prediction", "experiment_id": "mlebench-gp7-hard14-20260917", "family": "MLEBench", "method": "gp7_ancestry_logei", "dataset": "new-york-city-taxi-fare-prediction", "status": "archived", "official_score": 11.26417, "medal": "none", "valid_submission": true, "score_maximize": false, "thresholds": {"gold": 2.83377, "silver": 2.88191, "bronze": 2.92371}, "grading_policy": "ensemble", "artifacts": [{"bundle_id": "gp7-ancestry-logei-hard14-full-logs-20260917", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917/logs-77c0e49ab8d6.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917", "member": "results/official_private_grades.jsonl:14", "sha256": "77c0e49ab8d6df7268cefe20565a32eaa589661c5946ef2499c567afceab8104"}, {"bundle_id": "gp7-ancestry-logei-hard14-full-logs-20260917", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917/logs-77c0e49ab8d6.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917", "member": "gp7_ancestry_logei-hard14/runs/07_new-york-city-taxi-fare-prediction/logs/journal.json", "sha256": "77c0e49ab8d6df7268cefe20565a32eaa589661c5946ef2499c567afceab8104"}], "alternate_scores": [{"cohort": "09-17", "workflow_id": "09-17 gp7_ancestry_logei", "method": "gp7_ancestry_logei", "task": "new-york-city-taxi-fare-prediction", "policy": "best_node", "status": "graded", "valid_submission": true, "score": 11.94814, "medal": "none", "is_lower_better": true, "gold_threshold": 2.83377, "silver_threshold": 2.88191, "bronze_threshold": 2.92371, "submission_sha256": "1e5b53d12c253c80a2b56fb6f3d1fb7e4d1f607283bc1137040f3c163f449514", "source_archive": "gp7_ancestry_logei_hard14_full_logs_20260917.zip", "source_member": "results/official_private_grades.jsonl", "source_line": 13}], "journal_ref": "gp7-ancestry-logei-hard14-full-logs-20260917:gp7_ancestry_logei-hard14/runs/07_new-york-city-taxi-fare-prediction/logs/journal.json", "metrics": [{"event_id": "8b82743136ac467391ec7302b2ecd241", "step": 4, "value": 2.948396303343463, "stage": "debug", "created_at": 1789628359.0156596}, {"event_id": "1154d012dbf94bc183a44b933e654cf7", "step": 5, "value": 3.4425158500671387, "stage": "debug", "created_at": 1789629604.145115}, {"event_id": "00ca599905154468bb7331337de87725", "step": 6, "value": 2.671120214508534, "stage": "improve", "created_at": 1789631099.575341}, {"event_id": "5c0bfbdb42ad4d1196748c00eb092b46", "step": 7, "value": 2.629736424567353, "stage": "improve", "created_at": 1789635935.8502252}, {"event_id": "2491d4d96cc642a1b0e5a31cb1c781c1", "step": 8, "value": 2.6236958794208585, "stage": "improve", "created_at": 1789640122.7208328}, {"event_id": "4ff8c0665ab5440683f6fe6f5b27c1fa", "step": 9, "value": 2.627080959941338, "stage": "improve", "created_at": 1789630226.3477712}, {"event_id": "f671f8c272314c0ab19af759024342b2", "step": 12, "value": 2.6802683203774706, "stage": "debug", "created_at": 1789647675.2217224}], "maximize": false, "elapsed_seconds": 28750.232929944992, "node_count": 13, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-hard14-20260917/xixian.gp7-ancestry-logei.new-york-city-taxi-fare-prediction.yaml", "note": ""}, {"id": "xixian.gp7-ancestry-logei.nomad2018-predict-transparent-conductors", "experiment_id": "mlebench-gp7-hard14-20260917", "family": "MLEBench", "method": "gp7_ancestry_logei", "dataset": "nomad2018-predict-transparent-conductors", "status": "archived", "official_score": 0.06038, "medal": "silver", "valid_submission": true, "score_maximize": false, "thresholds": {"gold": 0.05589, "silver": 0.06229, "bronze": 0.06582}, "grading_policy": "ensemble", "artifacts": [{"bundle_id": "gp7-ancestry-logei-hard14-full-logs-20260917", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917/logs-77c0e49ab8d6.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917", "member": "results/official_private_grades.jsonl:16", "sha256": "77c0e49ab8d6df7268cefe20565a32eaa589661c5946ef2499c567afceab8104"}, {"bundle_id": "gp7-ancestry-logei-hard14-full-logs-20260917", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917/logs-77c0e49ab8d6.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917", "member": "gp7_ancestry_logei-hard14/runs/08_nomad2018-predict-transparent-conductors/logs/journal.json", "sha256": "77c0e49ab8d6df7268cefe20565a32eaa589661c5946ef2499c567afceab8104"}], "alternate_scores": [{"cohort": "09-17", "workflow_id": "09-17 gp7_ancestry_logei", "method": "gp7_ancestry_logei", "task": "nomad2018-predict-transparent-conductors", "policy": "best_node", "status": "graded", "valid_submission": true, "score": 0.06157, "medal": "silver", "is_lower_better": true, "gold_threshold": 0.05589, "silver_threshold": 0.06229, "bronze_threshold": 0.06582, "submission_sha256": "49a4267890fedd4f7fa919dad601be4e6c8f77c0ddd7fbb475b1efe2cc993332", "source_archive": "gp7_ancestry_logei_hard14_full_logs_20260917.zip", "source_member": "results/official_private_grades.jsonl", "source_line": 15}], "journal_ref": "gp7-ancestry-logei-hard14-full-logs-20260917:gp7_ancestry_logei-hard14/runs/08_nomad2018-predict-transparent-conductors/logs/journal.json", "metrics": [{"event_id": "c8f0537b92dd4d95a485b5b1a77c3aed", "step": 2, "value": 0.06236596154746952, "stage": "draft", "created_at": 1789626595.855881}, {"event_id": "f4fb15c9564a4ceca4331d2ed49eb2d8", "step": 4, "value": 0.05426923279366407, "stage": "debug", "created_at": 1789627362.7503316}, {"event_id": "77356fa03c084f18bc9041a63f560471", "step": 5, "value": 0.0519333707954191, "stage": "improve", "created_at": 1789627724.9334667}, {"event_id": "df68395f35644dbfb9b004f7d2bce308", "step": 6, "value": 0.053807466063340276, "stage": "improve", "created_at": 1789627998.9482214}, {"event_id": "6517b8d31f664ca3bfd8eec59fd32ec5", "step": 7, "value": 0.05329941292795806, "stage": "improve", "created_at": 1789628227.7817223}, {"event_id": "df776990199e494b8aacabbb30d4ae83", "step": 8, "value": 0.08414776143282644, "stage": "improve", "created_at": 1789628503.238166}, {"event_id": "866b9010bd7441f8887f2dbbbfa422a0", "step": 10, "value": 0.07737826514270357, "stage": "debug", "created_at": 1789630807.7450142}, {"event_id": "64d5c94384f94baa8473d550cb9f014e", "step": 11, "value": 0.06143924703284867, "stage": "improve", "created_at": 1789627370.160627}, {"event_id": "143d92a5be1c47dab41f4716129b657d", "step": 13, "value": 0.05375347098532236, "stage": "fusion", "created_at": 1789643038.419946}, {"event_id": "6df620140b7c40d1befd7fb6f2db6e94", "step": 14, "value": 0.06538847837522316, "stage": "draft", "created_at": 1789652986.4792678}, {"event_id": "1d480118ab9040f8a79e287b6cbde5fe", "step": 15, "value": 0.051674537986350584, "stage": "debug", "created_at": 1789650408.077251}], "maximize": false, "elapsed_seconds": 28749.27417898178, "node_count": 17, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-hard14-20260917/xixian.gp7-ancestry-logei.nomad2018-predict-transparent-conductors.yaml", "note": ""}, {"id": "xixian.gp7-ancestry-logei.random-acts-of-pizza", "experiment_id": "mlebench-gp7-hard14-20260917", "family": "MLEBench", "method": "gp7_ancestry_logei", "dataset": "random-acts-of-pizza", "status": "archived", "official_score": 0.67961, "medal": "none", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.97908, "silver": 0.76482, "bronze": 0.6921}, "grading_policy": "ensemble", "artifacts": [{"bundle_id": "gp7-ancestry-logei-hard14-full-logs-20260917", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917/logs-77c0e49ab8d6.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917", "member": "results/official_private_grades.jsonl:18", "sha256": "77c0e49ab8d6df7268cefe20565a32eaa589661c5946ef2499c567afceab8104"}, {"bundle_id": "gp7-ancestry-logei-hard14-full-logs-20260917", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917/logs-77c0e49ab8d6.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917", "member": "gp7_ancestry_logei-hard14/runs/09_random-acts-of-pizza/logs/journal.json", "sha256": "77c0e49ab8d6df7268cefe20565a32eaa589661c5946ef2499c567afceab8104"}], "alternate_scores": [{"cohort": "09-17", "workflow_id": "09-17 gp7_ancestry_logei", "method": "gp7_ancestry_logei", "task": "random-acts-of-pizza", "policy": "best_node", "status": "graded", "valid_submission": true, "score": 0.67463, "medal": "none", "is_lower_better": false, "gold_threshold": 0.97908, "silver_threshold": 0.76482, "bronze_threshold": 0.6921, "submission_sha256": "d2c61530456ee02fba463a4c99d575508e1f229d5ff8e13520bdbbe74ae53a71", "source_archive": "gp7_ancestry_logei_hard14_full_logs_20260917.zip", "source_member": "results/official_private_grades.jsonl", "source_line": 17}], "journal_ref": "gp7-ancestry-logei-hard14-full-logs-20260917:gp7_ancestry_logei-hard14/runs/09_random-acts-of-pizza/logs/journal.json", "metrics": [{"event_id": "c147a15c566e456aa1918d031fcefaee", "step": 3, "value": 0.5925569581280788, "stage": "draft", "created_at": 1789626541.201743}, {"event_id": "5d6c03d16bae48e6ae9761bca20c865c", "step": 5, "value": 0.6541610814128135, "stage": "debug", "created_at": 1789627343.1518474}, {"event_id": "2f54f8a1d94841b191a291e40200981a", "step": 6, "value": 0.6046605603448276, "stage": "improve", "created_at": 1789627400.846443}, {"event_id": "5f777df4ed9245f8b3952bbd40fe714f", "step": 7, "value": 0.6975887853486007, "stage": "improve", "created_at": 1789628128.2366893}, {"event_id": "a76bf20fb7b44aaebf37914e73edba51", "step": 9, "value": 0.690240475459875, "stage": "improve", "created_at": 1789628592.7828255}, {"event_id": "516c5385d8494885a16351737107b5cb", "step": 11, "value": 0.6722330786995914, "stage": "debug", "created_at": 1789628490.435572}, {"event_id": "7e492e35724c4c7b852712f4c13177ae", "step": 12, "value": 0.658602367609296, "stage": "improve", "created_at": 1789628983.2358162}, {"event_id": "01a31b7008444405b70ed6aa3cf010f9", "step": 13, "value": 0.699914404302395, "stage": "improve", "created_at": 1789629310.706308}, {"event_id": "5b94cdf284104aca985d6f433e191c73", "step": 14, "value": 0.6838773236001874, "stage": "improve", "created_at": 1789629742.3986585}, {"event_id": "1e19246d6b914d7d8705209131996c99", "step": 15, "value": 0.6771911691080282, "stage": "improve", "created_at": 1789630401.067052}, {"event_id": "993d4dd8663a425c972a4d2d8995e9cc", "step": 16, "value": 0.6954892682375361, "stage": "improve", "created_at": 1789631076.8859482}, {"event_id": "6719996f535b4e1eb50bc652de68bded", "step": 17, "value": 0.6646971201588877, "stage": "debug", "created_at": 1789629164.419106}, {"event_id": "649dbd1c08144a0eb74da61067bf4a61", "step": 18, "value": 0.6763352121319789, "stage": "evolution", "created_at": 1789632205.231424}, {"event_id": "2dbdd1afc08a49ac9ddbfb50b5623ad0", "step": 20, "value": 0.6977341365332127, "stage": "evolution", "created_at": 1789631426.6434493}, {"event_id": "633a3c6d64554bd683e5aabc6fd660c8", "step": 22, "value": 0.6890938161146013, "stage": "evolution", "created_at": 1789629648.715266}, {"event_id": "f737d0adeae441ff9a80e0e1f979f23d", "step": 23, "value": 0.6367091286945812, "stage": "debug", "created_at": 1789632967.8648052}, {"event_id": "5708e15f9fa04f808725e749039c759c", "step": 24, "value": 0.7020946720715774, "stage": "evolution", "created_at": 1789633509.9765587}, {"event_id": "ba694a456cd1473ea5b3958d6f99a3e3", "step": 25, "value": 0.6977341365332128, "stage": "evolution", "created_at": 1789633477.1296852}, {"event_id": "8b2db10e7b904a578db1207f60b80098", "step": 26, "value": 0.7035481839176989, "stage": "improve", "created_at": 1789634804.7732313}, {"event_id": "6fb88cc15b9749cbaab1b532834e7244", "step": 27, "value": 0.7033382322065925, "stage": "improve", "created_at": 1789635149.0986874}, {"event_id": "26526fc54e78478ab02a7d9d477114d7", "step": 28, "value": 0.7004958090408436, "stage": "evolution", "created_at": 1789632929.7223487}, {"event_id": "24f41def0dae4d3eb5e4befab3367cb9", "step": 29, "value": 0.6876080040052326, "stage": "improve", "created_at": 1789636117.7314787}, {"event_id": "49aed926fe034c0699ffd9613cf63ec3", "step": 30, "value": 0.703515883654452, "stage": "improve", "created_at": 1789636548.7118194}, {"event_id": "7b5d45b94d944c80a4250490df549c60", "step": 31, "value": 0.6829083157027729, "stage": "improve", "created_at": 1789637015.9750223}, {"event_id": "aa6ae10673e54dd0af5f01d4de4938ee", "step": 34, "value": 0.7046463928681019, "stage": "evolution", "created_at": 1789637471.9382093}, {"event_id": "db8add988c7d4642ba9a0a57ac1d5da7", "step": 35, "value": 0.613897013546798, "stage": "debug", "created_at": 1789638502.3653526}, {"event_id": "f6508db392744a1ebd2ca13462d2fdbc", "step": 36, "value": 0.6477252539608198, "stage": "improve", "created_at": 1789638683.0047736}, {"event_id": "4954711bab0248ba8000cf9f39a31138", "step": 39, "value": 0.6945202603401217, "stage": "improve", "created_at": 1789639069.663324}, {"event_id": "c0df282516404e0fb737226bb71cabab", "step": 40, "value": 0.6842730018249648, "stage": "evolution", "created_at": 1789638304.310931}, {"event_id": "df1636d558d54748b66155341daa7049", "step": 43, "value": 0.6937127537589431, "stage": "improve", "created_at": 1789641072.2904658}, {"event_id": "a275f6ffeccf49f28e5ed3bbfd8f674c", "step": 44, "value": 0.6996883024596652, "stage": "improve", "created_at": 1789641195.824271}, {"event_id": "efec0f4fe9e342c6b272edd2032879c9", "step": 45, "value": 0.6995914016699237, "stage": "evolution", "created_at": 1789642447.3498855}, {"event_id": "2500b5515d8f4dd9b83d77a54c978366", "step": 46, "value": 0.6904092671082963, "stage": "debug", "created_at": 1789641579.39882}, {"event_id": "14e4c2af51314535a111d179d2b8bc39", "step": 47, "value": 0.7000597554870072, "stage": "evolution", "created_at": 1789642968.1760912}, {"event_id": "098b058d63af47e49479afddd7dd4d65", "step": 48, "value": 0.7003666079878551, "stage": "fusion", "created_at": 1789643482.635535}, {"event_id": "7abe7613829a46e6878d0acf53756595", "step": 49, "value": 0.7072304139278736, "stage": "fusion", "created_at": 1789643735.2307768}, {"event_id": "c608f2702edd4dfdb33935ff1bdf6a73", "step": 52, "value": 0.7077633682714514, "stage": "improve", "created_at": 1789645952.7618167}, {"event_id": "571c82bad121491e8c7409a779415f35", "step": 54, "value": 0.7077472181398279, "stage": "improve", "created_at": 1789645889.8760087}, {"event_id": "59eef30597b349f5873740d69f71b3a5", "step": 55, "value": 0.7088292769586072, "stage": "debug", "created_at": 1789647870.0277855}, {"event_id": "bb86e46288524a21999e2d289550def4", "step": 56, "value": 0.7068589609005314, "stage": "improve", "created_at": 1789648328.7814987}, {"event_id": "69b71554f4004f34a51c17c2f500d34a", "step": 57, "value": 0.6995591014066765, "stage": "improve", "created_at": 1789649536.5716136}, {"event_id": "a3b6721b155f4cbf9ae16f6ba49e76ce", "step": 58, "value": 0.7075695666919686, "stage": "improve", "created_at": 1789649749.0509677}, {"event_id": "7e021843673e49368f5b3ed57d4d7664", "step": 59, "value": 0.7070043120851436, "stage": "debug", "created_at": 1789645947.4940875}, {"event_id": "b804937ff6de488393ba3a0441a3b189", "step": 60, "value": 0.7066328590578014, "stage": "improve", "created_at": 1789651166.997626}, {"event_id": "5388c3ce7f2f40fe90f58af391eb8280", "step": 63, "value": 0.704565642209984, "stage": "fusion", "created_at": 1789651516.0322614}, {"event_id": "76e2687691004f61a65e9500e3adc63c", "step": 65, "value": 0.6521513238916257, "stage": "debug", "created_at": 1789653114.288537}], "maximize": true, "elapsed_seconds": 28762.390697479248, "node_count": 67, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-hard14-20260917/xixian.gp7-ancestry-logei.random-acts-of-pizza.yaml", "note": ""}, {"id": "xixian.gp7-ancestry-logei.ranzcr-clip-catheter-line-classification", "experiment_id": "mlebench-gp7-hard14-20260917", "family": "MLEBench", "method": "gp7_ancestry_logei", "dataset": "ranzcr-clip-catheter-line-classification", "status": "archived", "official_score": 0.82588, "medal": "none", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.97357, "silver": 0.97152, "bronze": 0.9709}, "grading_policy": "ensemble", "artifacts": [{"bundle_id": "gp7-ancestry-logei-hard14-full-logs-20260917", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917/logs-77c0e49ab8d6.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917", "member": "results/official_private_grades.jsonl:20", "sha256": "77c0e49ab8d6df7268cefe20565a32eaa589661c5946ef2499c567afceab8104"}, {"bundle_id": "gp7-ancestry-logei-hard14-full-logs-20260917", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917/logs-77c0e49ab8d6.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917", "member": "gp7_ancestry_logei-hard14/runs/10_ranzcr-clip-catheter-line-classification/logs/journal.json", "sha256": "77c0e49ab8d6df7268cefe20565a32eaa589661c5946ef2499c567afceab8104"}], "alternate_scores": [{"cohort": "09-17", "workflow_id": "09-17 gp7_ancestry_logei", "method": "gp7_ancestry_logei", "task": "ranzcr-clip-catheter-line-classification", "policy": "best_node", "status": "graded", "valid_submission": true, "score": 0.81903, "medal": "none", "is_lower_better": false, "gold_threshold": 0.97357, "silver_threshold": 0.97152, "bronze_threshold": 0.9709, "submission_sha256": "ed46a7d1951a6c54687d4417dd26fda914bff6f13702e6182dd2c6cb26a60c50", "source_archive": "gp7_ancestry_logei_hard14_full_logs_20260917.zip", "source_member": "results/official_private_grades.jsonl", "source_line": 19}], "journal_ref": "gp7-ancestry-logei-hard14-full-logs-20260917:gp7_ancestry_logei-hard14/runs/10_ranzcr-clip-catheter-line-classification/logs/journal.json", "metrics": [{"event_id": "47fbfb55f24542e1a5c0ac1c550daa99", "step": 3, "value": 0.5, "stage": "draft", "created_at": 1789627007.4425764}, {"event_id": "16ed4f3dd0bd4cd9a3f8a5d35cc6328f", "step": 4, "value": 0.7320739380718011, "stage": "debug", "created_at": 1789628705.7878501}, {"event_id": "248ce6c9c09d4db9a173f923ff1d5ca4", "step": 6, "value": 0.7017711999501841, "stage": "draft", "created_at": 1789626603.8936443}, {"event_id": "85cb946cff2a4ee1bce2cb93f8388d4e", "step": 15, "value": 0.7891239731981006, "stage": "improve", "created_at": 1789632737.0038998}], "maximize": true, "elapsed_seconds": 28748.977032661438, "node_count": 16, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-hard14-20260917/xixian.gp7-ancestry-logei.ranzcr-clip-catheter-line-classification.yaml", "note": ""}, {"id": "xixian.gp7-ancestry-logei.siim-isic-melanoma-classification", "experiment_id": "mlebench-gp7-hard14-20260917", "family": "MLEBench", "method": "gp7_ancestry_logei", "dataset": "siim-isic-melanoma-classification", "status": "archived", "official_score": 0.88321, "medal": "none", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.9455, "silver": 0.9401, "bronze": 0.937}, "grading_policy": "ensemble", "artifacts": [{"bundle_id": "gp7-ancestry-logei-hard14-full-logs-20260917", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917/logs-77c0e49ab8d6.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917", "member": "results/official_private_grades.jsonl:22", "sha256": "77c0e49ab8d6df7268cefe20565a32eaa589661c5946ef2499c567afceab8104"}, {"bundle_id": "gp7-ancestry-logei-hard14-full-logs-20260917", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917/logs-77c0e49ab8d6.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917", "member": "gp7_ancestry_logei-hard14/runs/11_siim-isic-melanoma-classification/logs/journal.json", "sha256": "77c0e49ab8d6df7268cefe20565a32eaa589661c5946ef2499c567afceab8104"}], "alternate_scores": [{"cohort": "09-17", "workflow_id": "09-17 gp7_ancestry_logei", "method": "gp7_ancestry_logei", "task": "siim-isic-melanoma-classification", "policy": "best_node", "status": "graded", "valid_submission": true, "score": 0.87518, "medal": "none", "is_lower_better": false, "gold_threshold": 0.9455, "silver_threshold": 0.9401, "bronze_threshold": 0.937, "submission_sha256": "70267d1d2029e5143b65aac345753f45ff45f806edcb1cbe6adcd96200736db0", "source_archive": "gp7_ancestry_logei_hard14_full_logs_20260917.zip", "source_member": "results/official_private_grades.jsonl", "source_line": 21}], "journal_ref": "gp7-ancestry-logei-hard14-full-logs-20260917:gp7_ancestry_logei-hard14/runs/11_siim-isic-melanoma-classification/logs/journal.json", "metrics": [{"event_id": "f5543cd12139458ea3b25bf83b7f5c7c", "step": 7, "value": 0.8915298419810742, "stage": "debug", "created_at": 1789627025.1667004}, {"event_id": "76cb954bc72e4d098ee8604b983103b3", "step": 9, "value": 0.887213860226703, "stage": "improve", "created_at": 1789631275.3889725}, {"event_id": "aaeea6da9bed4816a62decaacdc3a39b", "step": 10, "value": 0.8057045638614537, "stage": "improve", "created_at": 1789631604.4773407}, {"event_id": "f4f811a881ba41ccad70393297ece8c4", "step": 11, "value": 0.887213860226703, "stage": "improve", "created_at": 1789632357.9537241}, {"event_id": "8d67d59833214aebbc0d664628923769", "step": 12, "value": 0.9025382210673246, "stage": "evolution", "created_at": 1789635505.207007}, {"event_id": "bb1062ff57e24387a40e989c450a509e", "step": 13, "value": 0.8601762143251267, "stage": "improve", "created_at": 1789637040.2898812}], "maximize": true, "elapsed_seconds": 28746.1677236557, "node_count": 18, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-hard14-20260917/xixian.gp7-ancestry-logei.siim-isic-melanoma-classification.yaml", "note": ""}, {"id": "xixian.gp7-ancestry-logei.tabular-playground-series-may-2022", "experiment_id": "mlebench-gp7-hard14-20260917", "family": "MLEBench", "method": "gp7_ancestry_logei", "dataset": "tabular-playground-series-may-2022", "status": "archived", "official_score": 0.99237, "medal": "none", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.99823, "silver": 0.99822, "bronze": 0.99818}, "grading_policy": "ensemble", "artifacts": [{"bundle_id": "gp7-ancestry-logei-hard14-full-logs-20260917", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917/logs-77c0e49ab8d6.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917", "member": "results/official_private_grades.jsonl:24", "sha256": "77c0e49ab8d6df7268cefe20565a32eaa589661c5946ef2499c567afceab8104"}, {"bundle_id": "gp7-ancestry-logei-hard14-full-logs-20260917", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917/logs-77c0e49ab8d6.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917", "member": "gp7_ancestry_logei-hard14/runs/12_tabular-playground-series-may-2022/logs/journal.json", "sha256": "77c0e49ab8d6df7268cefe20565a32eaa589661c5946ef2499c567afceab8104"}], "alternate_scores": [{"cohort": "09-17", "workflow_id": "09-17 gp7_ancestry_logei", "method": "gp7_ancestry_logei", "task": "tabular-playground-series-may-2022", "policy": "best_node", "status": "graded", "valid_submission": true, "score": 0.99224, "medal": "none", "is_lower_better": false, "gold_threshold": 0.99823, "silver_threshold": 0.99822, "bronze_threshold": 0.99818, "submission_sha256": "b493049e1d69a1ae0a06240ce89ad34ebed9ae733d8ca55b053b8a8908ed7598", "source_archive": "gp7_ancestry_logei_hard14_full_logs_20260917.zip", "source_member": "results/official_private_grades.jsonl", "source_line": 23}], "journal_ref": "gp7-ancestry-logei-hard14-full-logs-20260917:gp7_ancestry_logei-hard14/runs/12_tabular-playground-series-may-2022/logs/journal.json", "metrics": [{"event_id": "57bc4fdd10d2472e86c1c4794f01b9dd", "step": 2, "value": 0.9869677231497621, "stage": "draft", "created_at": 1789626832.9994147}, {"event_id": "d3fef6b244c642f19329b4b43a5ec19d", "step": 3, "value": 0.9885868342433037, "stage": "debug", "created_at": 1789627074.242529}, {"event_id": "b22347746f6f4fafa82fe5f2ff4a991e", "step": 4, "value": 0.9869138993015493, "stage": "improve", "created_at": 1789627272.9984963}, {"event_id": "f113aac6371e45cfab2e6187978bdcb2", "step": 5, "value": 0.9862972295143327, "stage": "improve", "created_at": 1789627698.4528947}, {"event_id": "a7a52b4103c54b888f076d33a3729412", "step": 6, "value": 0.9890953256551325, "stage": "improve", "created_at": 1789627582.7908623}, {"event_id": "9c8729669500406f9c73a62c76de1db4", "step": 8, "value": 0.9850864693338637, "stage": "debug", "created_at": 1789628267.013511}, {"event_id": "a91d3bf821a6439f86f705d6796e1101", "step": 9, "value": 0.992186417796066, "stage": "improve", "created_at": 1789628794.7381923}, {"event_id": "1c68b61053394a588609f9dfafc7776d", "step": 11, "value": 0.9917558303277564, "stage": "improve", "created_at": 1789628133.9494824}, {"event_id": "94a3c45994294f3b86af22b3a2074620", "step": 13, "value": 0.991828260927111, "stage": "debug", "created_at": 1789630869.021008}], "maximize": true, "elapsed_seconds": 28768.33899974823, "node_count": 15, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-hard14-20260917/xixian.gp7-ancestry-logei.tabular-playground-series-may-2022.yaml", "note": ""}, {"id": "xixian.gp7-ancestry-logei.text-normalization-challenge-english-language", "experiment_id": "mlebench-gp7-hard14-20260917", "family": "MLEBench", "method": "gp7_ancestry_logei", "dataset": "text-normalization-challenge-english-language", "status": "archived", "official_score": 0.99324, "medal": "silver", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.99724, "silver": 0.99135, "bronze": 0.99038}, "grading_policy": "ensemble", "artifacts": [{"bundle_id": "gp7-ancestry-logei-hard14-full-logs-20260917", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917/logs-77c0e49ab8d6.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917", "member": "results/official_private_grades.jsonl:26", "sha256": "77c0e49ab8d6df7268cefe20565a32eaa589661c5946ef2499c567afceab8104"}, {"bundle_id": "gp7-ancestry-logei-hard14-full-logs-20260917", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917/logs-77c0e49ab8d6.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917", "member": "gp7_ancestry_logei-hard14/runs/13_text-normalization-challenge-english-language/logs/journal.json", "sha256": "77c0e49ab8d6df7268cefe20565a32eaa589661c5946ef2499c567afceab8104"}], "alternate_scores": [{"cohort": "09-17", "workflow_id": "09-17 gp7_ancestry_logei", "method": "gp7_ancestry_logei", "task": "text-normalization-challenge-english-language", "policy": "best_node", "status": "graded", "valid_submission": true, "score": 0.98551, "medal": "none", "is_lower_better": false, "gold_threshold": 0.99724, "silver_threshold": 0.99135, "bronze_threshold": 0.99038, "submission_sha256": "047b7342be20456a005bb845f5769acd56ca6c3b4e28d95a598350fce376e07b", "source_archive": "gp7_ancestry_logei_hard14_full_logs_20260917.zip", "source_member": "results/official_private_grades.jsonl", "source_line": 25}], "journal_ref": "gp7-ancestry-logei-hard14-full-logs-20260917:gp7_ancestry_logei-hard14/runs/13_text-normalization-challenge-english-language/logs/journal.json", "metrics": [{"event_id": "edc254dfad0645408379cc8e1268610d", "step": 8, "value": 0.9622645743684113, "stage": "debug", "created_at": 1789627192.6518626}, {"event_id": "4a968754880e4902b905c73fd9ba8b96", "step": 9, "value": 0.3697592612332602, "stage": "debug", "created_at": 1789627914.9792292}, {"event_id": "1786352d323945c2af40eda619f37ee4", "step": 10, "value": 0.9899237549160967, "stage": "draft", "created_at": 1789628227.704318}, {"event_id": "add5cbb7a2c641e4950993c2bd6fe123", "step": 11, "value": 0.9899630275862455, "stage": "improve", "created_at": 1789629294.4445589}, {"event_id": "f8e596419b8f46a9bc92d2d56a895d66", "step": 12, "value": 0.986860486644487, "stage": "improve", "created_at": 1789630606.0602517}, {"event_id": "ac1aee24526c451c84e2f840c96400d8", "step": 13, "value": 0.9029404009178584, "stage": "improve", "created_at": 1789629260.4888318}, {"event_id": "54e020de31364c6ab4098c5097804184", "step": 14, "value": 0.515481847610819, "stage": "improve", "created_at": 1789628179.2777724}, {"event_id": "61549d77109245e9a805948f6dbbc515", "step": 15, "value": 0.9865070326131473, "stage": "improve", "created_at": 1789637983.5462093}], "maximize": true, "elapsed_seconds": 28767.29025554657, "node_count": 16, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-hard14-20260917/xixian.gp7-ancestry-logei.text-normalization-challenge-english-language.yaml", "note": ""}, {"id": "xixian.gp7-ancestry-logei.text-normalization-challenge-russian-language", "experiment_id": "mlebench-gp7-hard14-20260917", "family": "MLEBench", "method": "gp7_ancestry_logei", "dataset": "text-normalization-challenge-russian-language", "status": "archived", "official_score": 0.97335, "medal": "none", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.99012, "silver": 0.98232, "bronze": 0.97592}, "grading_policy": "ensemble", "artifacts": [{"bundle_id": "gp7-ancestry-logei-hard14-full-logs-20260917", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917/logs-77c0e49ab8d6.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917", "member": "results/official_private_grades.jsonl:28", "sha256": "77c0e49ab8d6df7268cefe20565a32eaa589661c5946ef2499c567afceab8104"}, {"bundle_id": "gp7-ancestry-logei-hard14-full-logs-20260917", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917/logs-77c0e49ab8d6.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917", "member": "gp7_ancestry_logei-hard14/runs/14_text-normalization-challenge-russian-language/logs/journal.json", "sha256": "77c0e49ab8d6df7268cefe20565a32eaa589661c5946ef2499c567afceab8104"}], "alternate_scores": [{"cohort": "09-17", "workflow_id": "09-17 gp7_ancestry_logei", "method": "gp7_ancestry_logei", "task": "text-normalization-challenge-russian-language", "policy": "best_node", "status": "graded", "valid_submission": true, "score": 0.97335, "medal": "none", "is_lower_better": false, "gold_threshold": 0.99012, "silver_threshold": 0.98232, "bronze_threshold": 0.97592, "submission_sha256": "e087c7a9ad763b6ef4b4b6e213f88c4fc73deef1e151950a52045bc50af90685", "source_archive": "gp7_ancestry_logei_hard14_full_logs_20260917.zip", "source_member": "results/official_private_grades.jsonl", "source_line": 27}], "journal_ref": "gp7-ancestry-logei-hard14-full-logs-20260917:gp7_ancestry_logei-hard14/runs/14_text-normalization-challenge-russian-language/logs/journal.json", "metrics": [{"event_id": "ae1f79bfc731427aba05c109d5e66331", "step": 4, "value": 0.9741997884525591, "stage": "draft", "created_at": 1789626220.1687984}, {"event_id": "80f19e399ac546eaa792b66dffc9b122", "step": 5, "value": 0.21413294147792938, "stage": "debug", "created_at": 1789627127.8531024}, {"event_id": "c5206d7ece9d462f9c82034bb605cd2c", "step": 6, "value": 0.9120417095912188, "stage": "improve", "created_at": 1789637425.7293458}, {"event_id": "e791e26f22e64511b3ba80f870a309b9", "step": 8, "value": 0.9524491669946216, "stage": "debug", "created_at": 1789627338.7454991}, {"event_id": "4a3429c9d5b8468ab9edba0d14840110", "step": 10, "value": 0.9323524647182703, "stage": "improve", "created_at": 1789634237.7781088}, {"event_id": "9a4bd687a623432bb7e1f4927edb01d2", "step": 11, "value": 0.9143426398991774, "stage": "debug", "created_at": 1789643505.7145457}, {"event_id": "d97382ff8a464cfd9f71c862a76d98e8", "step": 12, "value": 0.9248798548322151, "stage": "improve", "created_at": 1789647887.9440355}, {"event_id": "adf64d0f528e4245bc75a7c8d08bdc1b", "step": 13, "value": 0.847306036186551, "stage": "improve", "created_at": 1789648821.0951278}], "maximize": true, "elapsed_seconds": 28756.034727334976, "node_count": 14, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-hard14-20260917/xixian.gp7-ancestry-logei.text-normalization-challenge-russian-language.yaml", "note": ""}, {"id": "xixian.gp7-short-ucb-pibo.aerial-cactus-identification", "experiment_id": "mlebench-gp7-hard14-20260917", "family": "MLEBench", "method": "gp7_short_ucb_pibo", "dataset": "aerial-cactus-identification", "status": "archived", "official_score": 0.99998, "medal": "none", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 1.0, "silver": 1.0, "bronze": 1.0}, "grading_policy": "ensemble", "artifacts": [{"bundle_id": "gp7-ancestry-logei-hard14-full-logs-20260917", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917/logs-77c0e49ab8d6.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917", "member": "results/official_private_grades.jsonl:30", "sha256": "77c0e49ab8d6df7268cefe20565a32eaa589661c5946ef2499c567afceab8104"}, {"bundle_id": "gp7-short-ucb-pibo-hard14-full-logs-20260917", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-short-ucb-pibo-hard14-full-logs-20260917/logs-7d4a0bf30b9a.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-short-ucb-pibo-hard14-full-logs-20260917", "member": "gp7_short_ucb_pibo-hard14/runs/01_aerial-cactus-identification/logs/journal.json", "sha256": "7d4a0bf30b9a2ab2c851ec14cd1b35edcbf277be29c9cdffb309d38ba56f821d"}], "alternate_scores": [{"cohort": "09-17", "workflow_id": "09-17 gp7_short_ucb_pibo", "method": "gp7_short_ucb_pibo", "task": "aerial-cactus-identification", "policy": "best_node", "status": "graded", "valid_submission": true, "score": 0.99995, "medal": "none", "is_lower_better": false, "gold_threshold": 1.0, "silver_threshold": 1.0, "bronze_threshold": 1.0, "submission_sha256": "5174a0ca3bc57636122c934f27e6b3714be9a8f9d48f93726c26f6da9d5e5afc", "source_archive": "gp7_ancestry_logei_hard14_full_logs_20260917.zip", "source_member": "results/official_private_grades.jsonl", "source_line": 29}], "journal_ref": "gp7-short-ucb-pibo-hard14-full-logs-20260917:gp7_short_ucb_pibo-hard14/runs/01_aerial-cactus-identification/logs/journal.json", "metrics": [{"event_id": "2b189e15740a4fca80b35d69cf3c183f", "step": 1, "value": 0.9999151483724987, "stage": "draft", "created_at": 1789626351.7102454}, {"event_id": "bab17b15b88b4fcf9bfc84914572ff54", "step": 2, "value": 0.9998899745993084, "stage": "draft", "created_at": 1789626884.9640048}, {"event_id": "688a0e3f054d4e3598b7d86a16e43ef8", "step": 4, "value": 0.9999434322483325, "stage": "improve", "created_at": 1789627204.582716}, {"event_id": "916b0cd7bded4e7d99d33325627b5eca", "step": 5, "value": 0.9999715451549935, "stage": "improve", "created_at": 1789627406.7940168}, {"event_id": "63ef87d24013481c896251ea166e2c24", "step": 8, "value": 0.9999976430103472, "stage": "improve", "created_at": 1789627979.5881765}, {"event_id": "6e30490ac7a54f19968633e2e25035b3", "step": 12, "value": 0.9999895665568309, "stage": "improve", "created_at": 1789629541.3837605}, {"event_id": "0ae8dc1047eb44bd9d97d089e6a641d1", "step": 13, "value": 0.9999668026808257, "stage": "debug", "created_at": 1789629652.5697265}, {"event_id": "ab06d27e4a3249018d0c723c01a2db21", "step": 14, "value": 0.9999917505362153, "stage": "improve", "created_at": 1789630689.857667}, {"event_id": "5a2787c56f834c4382342c3a1df1d001", "step": 15, "value": 0.9999611117118246, "stage": "improve", "created_at": 1789630751.8818042}, {"event_id": "7730e31102984342add1f372e3321f6b", "step": 18, "value": 0.9999411933203199, "stage": "improve", "created_at": 1789632155.739165}, {"event_id": "9039868b8bd946fe9541554c46eb101e", "step": 20, "value": 0.9999624908972783, "stage": "debug", "created_at": 1789629433.873341}, {"event_id": "8866cfaf0a4c4239b75923e5a8efcb7c", "step": 21, "value": 0.9997360171588847, "stage": "debug", "created_at": 1789633145.7979555}, {"event_id": "e9751826086040fc9f3530cc18cf94dc", "step": 22, "value": 0.9999231719184827, "stage": "evolution", "created_at": 1789633131.471073}, {"event_id": "2a1bcfa371e44ab58989e1a0a9ba5973", "step": 23, "value": 0.9999530441228203, "stage": "evolution", "created_at": 1789633552.2637784}, {"event_id": "d84f40ebe06546aa94a758668b6674e6", "step": 24, "value": 0.999942253753506, "stage": "improve", "created_at": 1789635316.0059023}, {"event_id": "530d9f76698e4d8bafb4421f8b652762", "step": 25, "value": 0.9999971545154993, "stage": "evolution", "created_at": 1789633302.7480814}, {"event_id": "57befa4adfcc47d9913695c6c8d2d9d4", "step": 27, "value": 0.9999835010724303, "stage": "draft", "created_at": 1789635919.556077}, {"event_id": "e630f98e70af4fc0b4340ef818015b2d", "step": 28, "value": 0.9999402448254864, "stage": "improve", "created_at": 1789635880.915015}, {"event_id": "f72a5073d95d4da1a2714514470edbc6", "step": 30, "value": 0.9999060990114788, "stage": "debug", "created_at": 1789636040.3533924}, {"event_id": "01624350f21c4f5fae0a17f608e8a1be", "step": 31, "value": 0.9999387182690267, "stage": "improve", "created_at": 1789638294.4999144}, {"event_id": "6f07c585035e44e28447fd2d61716c9e", "step": 32, "value": 0.9999634666603814, "stage": "debug", "created_at": 1789637757.486982}, {"event_id": "54a1d1c0aa82437883103420a88da318", "step": 33, "value": 0.9999976430103472, "stage": "improve", "created_at": 1789638926.4994276}, {"event_id": "7a141d808dcb4857b8bde32d99ec8675", "step": 34, "value": 0.9999893935465624, "stage": "improve", "created_at": 1789638992.4140232}, {"event_id": "e72edd7c3c0c43a7835faf84ad29dde4", "step": 37, "value": 0.999974864886911, "stage": "improve", "created_at": 1789637038.9484859}, {"event_id": "dc417f93fddc4d768efceb6848a533ef", "step": 39, "value": 0.9999658236500342, "stage": "improve", "created_at": 1789639677.7600727}, {"event_id": "91cf62638edc49ba830d8871ebae0c27", "step": 40, "value": 0.9997407311381903, "stage": "debug", "created_at": 1789640197.545537}, {"event_id": "490bec23b50545c38a9054a31047617c", "step": 43, "value": 0.9999533656275919, "stage": "evolution", "created_at": 1789640631.7109249}, {"event_id": "e8b470ea4cee4c659cd76b56954d02ae", "step": 45, "value": 0.9999636050290422, "stage": "evolution", "created_at": 1789642468.323213}, {"event_id": "f6fd222cf77c48fd95537af6dea6d380", "step": 46, "value": 0.9999457258669244, "stage": "evolution", "created_at": 1789642333.6028202}, {"event_id": "0dcd8c92dbcf44189861d640ab93b421", "step": 49, "value": 0.9999871609577671, "stage": "fusion", "created_at": 1789644792.8626418}, {"event_id": "03e1383a22514974bc472525d0e14fe0", "step": 51, "value": 0.9999634458673616, "stage": "debug", "created_at": 1789646137.3441236}, {"event_id": "f52a07794f5a4d1b86e44ce85aa982b9", "step": 52, "value": 0.9999870017960865, "stage": "evolution", "created_at": 1789649089.000679}, {"event_id": "7d9ad0ee61ff4b349ba0b2e56c413055", "step": 54, "value": 0.9999857725774968, "stage": "fusion", "created_at": 1789647332.2195945}, {"event_id": "2de016fa53ec484ca50fcdb27287a0ea", "step": 56, "value": 0.9995118776526284, "stage": "debug", "created_at": 1789651688.718225}, {"event_id": "61204dda9a4743e2acc16e04b3bbbab7", "step": 57, "value": 0.9999587526810757, "stage": "debug", "created_at": 1789652222.0290236}, {"event_id": "315f5be34403458095a279ae00403c15", "step": 58, "value": 0.9999573177324903, "stage": "debug", "created_at": 1789649047.9887066}, {"event_id": "8fbb49fca8784a27b4f15e8f9ea149e2", "step": 59, "value": 0.9999618011966623, "stage": "evolution", "created_at": 1789652679.2125587}, {"event_id": "5754107bef2c4e1badb01c8e50a8ab35", "step": 60, "value": 0.9997804895155425, "stage": "fusion", "created_at": 1789652610.3070502}], "maximize": true, "elapsed_seconds": 28689.993500709534, "node_count": 61, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-hard14-20260917/xixian.gp7-short-ucb-pibo.aerial-cactus-identification.yaml", "note": ""}, {"id": "xixian.gp7-short-ucb-pibo.aptos2019-blindness-detection", "experiment_id": "mlebench-gp7-hard14-20260917", "family": "MLEBench", "method": "gp7_short_ucb_pibo", "dataset": "aptos2019-blindness-detection", "status": "archived", "official_score": 0.91021, "medal": "none", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.930508, "silver": 0.919654, "bronze": 0.914492}, "grading_policy": "ensemble", "artifacts": [{"bundle_id": "gp7-ancestry-logei-hard14-full-logs-20260917", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917/logs-77c0e49ab8d6.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917", "member": "results/official_private_grades.jsonl:32", "sha256": "77c0e49ab8d6df7268cefe20565a32eaa589661c5946ef2499c567afceab8104"}, {"bundle_id": "gp7-short-ucb-pibo-hard14-full-logs-20260917", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-short-ucb-pibo-hard14-full-logs-20260917/logs-7d4a0bf30b9a.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-short-ucb-pibo-hard14-full-logs-20260917", "member": "gp7_short_ucb_pibo-hard14/runs/02_aptos2019-blindness-detection/logs/journal.json", "sha256": "7d4a0bf30b9a2ab2c851ec14cd1b35edcbf277be29c9cdffb309d38ba56f821d"}], "alternate_scores": [{"cohort": "09-17", "workflow_id": "09-17 gp7_short_ucb_pibo", "method": "gp7_short_ucb_pibo", "task": "aptos2019-blindness-detection", "policy": "best_node", "status": "graded", "valid_submission": true, "score": 0.90383, "medal": "none", "is_lower_better": false, "gold_threshold": 0.930508, "silver_threshold": 0.919654, "bronze_threshold": 0.914492, "submission_sha256": "77a83a4f8aacc69bbcbc1918fbac5e15b0a85919ace425c9b177f98fe477bbf1", "source_archive": "gp7_ancestry_logei_hard14_full_logs_20260917.zip", "source_member": "results/official_private_grades.jsonl", "source_line": 31}], "journal_ref": "gp7-short-ucb-pibo-hard14-full-logs-20260917:gp7_short_ucb_pibo-hard14/runs/02_aptos2019-blindness-detection/logs/journal.json", "metrics": [{"event_id": "81a7dec8244a47d1bfbad7a00eb297d1", "step": 4, "value": 0.9348822622152146, "stage": "debug", "created_at": 1789629917.9317846}, {"event_id": "c78ab6976675422a869ba39fd1e2514a", "step": 8, "value": -0.41689043914772683, "stage": "debug", "created_at": 1789633054.9072354}, {"event_id": "f6542b55f456491f8789a0ea2f414b60", "step": 9, "value": 0.9179368635000609, "stage": "improve", "created_at": 1789639631.5239093}, {"event_id": "294cc69063b64881855102ad7969c8b6", "step": 11, "value": 0.9335294374335162, "stage": "improve", "created_at": 1789640618.1543667}, {"event_id": "40796041302240159017b8545e61ff29", "step": 13, "value": 0.9149388373890396, "stage": "improve", "created_at": 1789642617.9645982}, {"event_id": "326f1b4f59554d51bbe1b952ae0de7ca", "step": 14, "value": 0.9084453286196168, "stage": "improve", "created_at": 1789642327.6362562}, {"event_id": "3f99bab891e74da58cc1f1780491b5e4", "step": 16, "value": 0.892518474146899, "stage": "debug", "created_at": 1789642946.3279727}, {"event_id": "8e925c72f7aa455aa1fedc801c93d7b8", "step": 17, "value": 0.9214315337370362, "stage": "draft", "created_at": 1789646547.2749941}, {"event_id": "955ce94368bb4a51bbff6e322412f958", "step": 18, "value": 0.9202097554886238, "stage": "debug", "created_at": 1789647456.0663855}, {"event_id": "e4028be3202a441592265cee2424f840", "step": 20, "value": 0.9329656081434414, "stage": "evolution", "created_at": 1789649832.9537053}, {"event_id": "0b1e64c367e54dcc9275bbf438cd1ade", "step": 21, "value": 0.9215601244301765, "stage": "improve", "created_at": 1789649812.6872005}], "maximize": true, "elapsed_seconds": 28749.315964460373, "node_count": 26, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-hard14-20260917/xixian.gp7-short-ucb-pibo.aptos2019-blindness-detection.yaml", "note": ""}, {"id": "xixian.gp7-short-ucb-pibo.dog-breed-identification", "experiment_id": "mlebench-gp7-hard14-20260917", "family": "MLEBench", "method": "gp7_short_ucb_pibo", "dataset": "dog-breed-identification", "status": "archived", "official_score": 0.29923, "medal": "none", "valid_submission": true, "score_maximize": false, "thresholds": {"gold": 0.0005, "silver": 0.00539, "bronze": 0.04598}, "grading_policy": "ensemble", "artifacts": [{"bundle_id": "gp7-ancestry-logei-hard14-full-logs-20260917", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917/logs-77c0e49ab8d6.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917", "member": "results/official_private_grades.jsonl:34", "sha256": "77c0e49ab8d6df7268cefe20565a32eaa589661c5946ef2499c567afceab8104"}, {"bundle_id": "gp7-short-ucb-pibo-hard14-full-logs-20260917", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-short-ucb-pibo-hard14-full-logs-20260917/logs-7d4a0bf30b9a.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-short-ucb-pibo-hard14-full-logs-20260917", "member": "gp7_short_ucb_pibo-hard14/runs/03_dog-breed-identification/logs/journal.json", "sha256": "7d4a0bf30b9a2ab2c851ec14cd1b35edcbf277be29c9cdffb309d38ba56f821d"}], "alternate_scores": [{"cohort": "09-17", "workflow_id": "09-17 gp7_short_ucb_pibo", "method": "gp7_short_ucb_pibo", "task": "dog-breed-identification", "policy": "best_node", "status": "graded", "valid_submission": true, "score": 0.34504, "medal": "none", "is_lower_better": true, "gold_threshold": 0.0005, "silver_threshold": 0.00539, "bronze_threshold": 0.04598, "submission_sha256": "6d58dbfff53c9146d247670bc097ea632682f4c19598dc88d2a434350274cca0", "source_archive": "gp7_ancestry_logei_hard14_full_logs_20260917.zip", "source_member": "results/official_private_grades.jsonl", "source_line": 33}], "journal_ref": "gp7-short-ucb-pibo-hard14-full-logs-20260917:gp7_short_ucb_pibo-hard14/runs/03_dog-breed-identification/logs/journal.json", "metrics": [{"event_id": "58f98beea0a84bc5a078564bdce0f583", "step": 1, "value": 0.48578064525745074, "stage": "draft", "created_at": 1789626761.515688}, {"event_id": "d853b1f7c8c14744890a140ef1333b29", "step": 2, "value": 0.6931957040373731, "stage": "draft", "created_at": 1789626135.6335793}, {"event_id": "e780b9e46250483bbf9c6da8f3781180", "step": 3, "value": 0.36080129891918106, "stage": "draft", "created_at": 1789626507.1758206}, {"event_id": "ed5b320e73214dd49189c44e43aafc8a", "step": 4, "value": 0.5097501044482388, "stage": "improve", "created_at": 1789628296.33211}, {"event_id": "8953a2422e3f43d1826c17ad76cebfb3", "step": 5, "value": 0.4401314266315072, "stage": "improve", "created_at": 1789627686.2703445}, {"event_id": "3cbe704385c9474bbdcb529bf800f51a", "step": 6, "value": 0.31680494968217393, "stage": "improve", "created_at": 1789628642.6250494}, {"event_id": "98377c46df10424ba5724ca93f9e0459", "step": 8, "value": 0.3219276038728346, "stage": "improve", "created_at": 1789629917.93693}, {"event_id": "4631d7a64de647bbaf9f1bec36387b32", "step": 9, "value": 0.3903604516354257, "stage": "improve", "created_at": 1789632849.2962115}, {"event_id": "b5a7c9414b0d4610b7e9b13b9f78d2fd", "step": 11, "value": 0.3844013798381844, "stage": "debug", "created_at": 1789635828.7458436}, {"event_id": "d3ca3545723a4182bc5274d06dcf506b", "step": 13, "value": 0.32145512638013063, "stage": "improve", "created_at": 1789631779.4941432}, {"event_id": "0e5f799bf9b2476f9e76cfa0a9f26392", "step": 18, "value": 0.44057291927054204, "stage": "debug", "created_at": 1789632276.17732}, {"event_id": "ecd38f30db9c41ec8b037fd684a40030", "step": 20, "value": 0.2564500984678912, "stage": "debug", "created_at": 1789639396.6915162}, {"event_id": "6c249b6802264a29afed15da94826d17", "step": 21, "value": 0.17287234281250813, "stage": "improve", "created_at": 1789638534.5316043}, {"event_id": "5cb68faa85ac457b8ab645cc5d88c472", "step": 25, "value": 0.40102720966537825, "stage": "debug", "created_at": 1789648535.8868742}, {"event_id": "f1d2c54ebdae423f8fecaaf81dda3f56", "step": 26, "value": 0.24212577319493414, "stage": "improve", "created_at": 1789646385.9649136}], "maximize": false, "elapsed_seconds": 28772.26028752327, "node_count": 27, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-hard14-20260917/xixian.gp7-short-ucb-pibo.dog-breed-identification.yaml", "note": ""}, {"id": "xixian.gp7-short-ucb-pibo.jigsaw-toxic-comment-classification-challenge", "experiment_id": "mlebench-gp7-hard14-20260917", "family": "MLEBench", "method": "gp7_short_ucb_pibo", "dataset": "jigsaw-toxic-comment-classification-challenge", "status": "archived", "official_score": 0.98709, "medal": "silver", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.9874, "silver": 0.98668, "bronze": 0.98639}, "grading_policy": "ensemble", "artifacts": [{"bundle_id": "gp7-ancestry-logei-hard14-full-logs-20260917", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917/logs-77c0e49ab8d6.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917", "member": "results/official_private_grades.jsonl:36", "sha256": "77c0e49ab8d6df7268cefe20565a32eaa589661c5946ef2499c567afceab8104"}, {"bundle_id": "gp7-short-ucb-pibo-hard14-full-logs-20260917", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-short-ucb-pibo-hard14-full-logs-20260917/logs-7d4a0bf30b9a.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-short-ucb-pibo-hard14-full-logs-20260917", "member": "gp7_short_ucb_pibo-hard14/runs/04_jigsaw-toxic-comment-classification-challenge/logs/journal.json", "sha256": "7d4a0bf30b9a2ab2c851ec14cd1b35edcbf277be29c9cdffb309d38ba56f821d"}], "alternate_scores": [{"cohort": "09-17", "workflow_id": "09-17 gp7_short_ucb_pibo", "method": "gp7_short_ucb_pibo", "task": "jigsaw-toxic-comment-classification-challenge", "policy": "best_node", "status": "graded", "valid_submission": true, "score": 0.98615, "medal": "none", "is_lower_better": false, "gold_threshold": 0.9874, "silver_threshold": 0.98668, "bronze_threshold": 0.98639, "submission_sha256": "307948690f07c98367e9257c326f97d142e3a6ad1151261bf6a5bd4b420dfeeb", "source_archive": "gp7_ancestry_logei_hard14_full_logs_20260917.zip", "source_member": "results/official_private_grades.jsonl", "source_line": 35}], "journal_ref": "gp7-short-ucb-pibo-hard14-full-logs-20260917:gp7_short_ucb_pibo-hard14/runs/04_jigsaw-toxic-comment-classification-challenge/logs/journal.json", "metrics": [{"event_id": "a50baa2e5e184cb090f171abe261be66", "step": 5, "value": 0.990385819944516, "stage": "debug", "created_at": 1789627354.808754}, {"event_id": "80bdb30750014212be3479fa3fee5173", "step": 7, "value": 0.99268797101552, "stage": "debug", "created_at": 1789627219.6667728}, {"event_id": "a75e7782954b485c8aa9fa15f44d0d41", "step": 8, "value": 0.9890614185023999, "stage": "debug", "created_at": 1789627105.5475006}, {"event_id": "e0e6534f25db4cd68bc0ba52e8df00f2", "step": 9, "value": 0.9920953528317377, "stage": "debug", "created_at": 1789630848.3955731}], "maximize": true, "elapsed_seconds": 28760.31684613228, "node_count": 10, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-hard14-20260917/xixian.gp7-short-ucb-pibo.jigsaw-toxic-comment-classification-challenge.yaml", "note": ""}, {"id": "xixian.gp7-short-ucb-pibo.leaf-classification", "experiment_id": "mlebench-gp7-hard14-20260917", "family": "MLEBench", "method": "gp7_short_ucb_pibo", "dataset": "leaf-classification", "status": "archived", "official_score": 1.05397, "medal": "none", "valid_submission": true, "score_maximize": false, "thresholds": {"gold": 0.0, "silver": 0.00791, "bronze": 0.01526}, "grading_policy": "ensemble", "artifacts": [{"bundle_id": "gp7-ancestry-logei-hard14-full-logs-20260917", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917/logs-77c0e49ab8d6.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917", "member": "results/official_private_grades.jsonl:38", "sha256": "77c0e49ab8d6df7268cefe20565a32eaa589661c5946ef2499c567afceab8104"}, {"bundle_id": "gp7-short-ucb-pibo-hard14-full-logs-20260917", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-short-ucb-pibo-hard14-full-logs-20260917/logs-7d4a0bf30b9a.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-short-ucb-pibo-hard14-full-logs-20260917", "member": "gp7_short_ucb_pibo-hard14/runs/05_leaf-classification/logs/journal.json", "sha256": "7d4a0bf30b9a2ab2c851ec14cd1b35edcbf277be29c9cdffb309d38ba56f821d"}], "alternate_scores": [{"cohort": "09-17", "workflow_id": "09-17 gp7_short_ucb_pibo", "method": "gp7_short_ucb_pibo", "task": "leaf-classification", "policy": "best_node", "status": "graded", "valid_submission": true, "score": 9.03936, "medal": "none", "is_lower_better": true, "gold_threshold": 0.0, "silver_threshold": 0.00791, "bronze_threshold": 0.01526, "submission_sha256": "2001f33888b05dea49c10b6822aebc5c28853766b77de8c9720e6b6a255ed37e", "source_archive": "gp7_ancestry_logei_hard14_full_logs_20260917.zip", "source_member": "results/official_private_grades.jsonl", "source_line": 37}], "journal_ref": "gp7-short-ucb-pibo-hard14-full-logs-20260917:gp7_short_ucb_pibo-hard14/runs/05_leaf-classification/logs/journal.json", "metrics": [{"event_id": "c3d6a6fadb9b4a129ed1ecc130c1ca4b", "step": 2, "value": 2.09930135016915e-06, "stage": "draft", "created_at": 1789626243.942649}, {"event_id": "5e58a8bd5d3d40aca4fcf77643a25dab", "step": 3, "value": 9.652316396129952e-05, "stage": "draft", "created_at": 1789626860.018034}, {"event_id": "e0f4fa64e7594f56befa6034d2305efa", "step": 4, "value": 0.0017200134238626941, "stage": "improve", "created_at": 1789627130.046872}, {"event_id": "b083c89a059249c3b9a5a40a354ed9ea", "step": 6, "value": 0.02427290217637687, "stage": "improve", "created_at": 1789627441.6965115}, {"event_id": "c208470c304c456b89b884e0a28ed2fd", "step": 12, "value": 2.2846658382967557e-05, "stage": "debug", "created_at": 1789628441.5732217}, {"event_id": "403b761cb8354267b9b259195ceb2e85", "step": 13, "value": 0.001933706741769271, "stage": "improve", "created_at": 1789627539.7715173}, {"event_id": "49abcd6d833442e5989d182f64fdcd96", "step": 14, "value": 0.001656402322187167, "stage": "improve", "created_at": 1789628618.0474482}, {"event_id": "72ab9b41c3fd4b02b58db437232e6a15", "step": 15, "value": 0.006278485322582865, "stage": "improve", "created_at": 1789629228.4498782}, {"event_id": "64610da0ed7847b6adacc8b264d47526", "step": 16, "value": 0.014515424947598827, "stage": "evolution", "created_at": 1789629783.188266}, {"event_id": "bf9c3b0410734077952f09a9ca1aacdf", "step": 17, "value": 4.746166004010192e-07, "stage": "draft", "created_at": 1789631817.8854613}], "maximize": false, "elapsed_seconds": 28767.97395181656, "node_count": 19, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-hard14-20260917/xixian.gp7-short-ucb-pibo.leaf-classification.yaml", "note": ""}, {"id": "xixian.gp7-short-ucb-pibo.mlsp-2013-birds", "experiment_id": "mlebench-gp7-hard14-20260917", "family": "MLEBench", "method": "gp7_short_ucb_pibo", "dataset": "mlsp-2013-birds", "status": "archived", "official_score": 0.89125, "medal": "bronze", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.93527, "silver": 0.90038, "bronze": 0.87372}, "grading_policy": "ensemble", "artifacts": [{"bundle_id": "gp7-ancestry-logei-hard14-full-logs-20260917", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917/logs-77c0e49ab8d6.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917", "member": "results/official_private_grades.jsonl:40", "sha256": "77c0e49ab8d6df7268cefe20565a32eaa589661c5946ef2499c567afceab8104"}, {"bundle_id": "gp7-short-ucb-pibo-hard14-full-logs-20260917", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-short-ucb-pibo-hard14-full-logs-20260917/logs-7d4a0bf30b9a.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-short-ucb-pibo-hard14-full-logs-20260917", "member": "gp7_short_ucb_pibo-hard14/runs/06_mlsp-2013-birds/logs/journal.json", "sha256": "7d4a0bf30b9a2ab2c851ec14cd1b35edcbf277be29c9cdffb309d38ba56f821d"}], "alternate_scores": [{"cohort": "09-17", "workflow_id": "09-17 gp7_short_ucb_pibo", "method": "gp7_short_ucb_pibo", "task": "mlsp-2013-birds", "policy": "best_node", "status": "graded", "valid_submission": true, "score": 0.85904, "medal": "none", "is_lower_better": false, "gold_threshold": 0.93527, "silver_threshold": 0.90038, "bronze_threshold": 0.87372, "submission_sha256": "0cd9e1094e7e8bf02d199523c00a8d00473691b20b54059b7cc016426a76d875", "source_archive": "gp7_ancestry_logei_hard14_full_logs_20260917.zip", "source_member": "results/official_private_grades.jsonl", "source_line": 39}], "journal_ref": "gp7-short-ucb-pibo-hard14-full-logs-20260917:gp7_short_ucb_pibo-hard14/runs/06_mlsp-2013-birds/logs/journal.json", "metrics": [{"event_id": "dbf9d1a10b974ed097ec08c7c7bc8a64", "step": 6, "value": 0.47002143637303595, "stage": "debug", "created_at": 1789627384.488452}, {"event_id": "19dd06de772d47718c3aba9c4baf28e6", "step": 8, "value": 0.4512309401710315, "stage": "improve", "created_at": 1789627730.5425932}, {"event_id": "48659f3389034b348380d379f9e9540a", "step": 10, "value": 0.7453626569317686, "stage": "improve", "created_at": 1789628141.3618085}, {"event_id": "2daaf35107e0405b8d76deac1355a241", "step": 11, "value": 0.6805720474829893, "stage": "improve", "created_at": 1789628444.6067712}, {"event_id": "9387f8d6568e4196b186f7805f786c8f", "step": 12, "value": 0.732198979662337, "stage": "improve", "created_at": 1789628746.9710066}, {"event_id": "5f3f3e9dd22941b5b973203b2c9876d2", "step": 13, "value": 0.8228478287178166, "stage": "debug", "created_at": 1789628116.2375736}, {"event_id": "2e77b93a0aa64b2ea989e0af6c11cc37", "step": 16, "value": 0.7437518314695782, "stage": "debug", "created_at": 1789629194.077524}, {"event_id": "3b4a0826090c4054b2496a22e8e7ea25", "step": 18, "value": 0.7002472249053175, "stage": "debug", "created_at": 1789629589.7905786}, {"event_id": "97ce774271964b15b1bf6d1e7c0279f6", "step": 20, "value": 0.7294319073369492, "stage": "evolution", "created_at": 1789629494.25788}, {"event_id": "9e446bbd6f644ddc9908b6017af6fc8b", "step": 21, "value": 0.4915273764083027, "stage": "debug", "created_at": 1789627319.8358166}, {"event_id": "fefdf32146f94ee28ddd1025be60603a", "step": 22, "value": 0.85726113478471, "stage": "evolution", "created_at": 1789630644.0818183}, {"event_id": "6ff5cbb9e2654b5c898ba0407ac6a85d", "step": 23, "value": 0.7573176314488921, "stage": "debug", "created_at": 1789630203.2221053}, {"event_id": "5cc4672fa62743a4b086ba8aa5f621df", "step": 25, "value": 0.859941912716347, "stage": "improve", "created_at": 1789631228.09485}, {"event_id": "cf25917ab8c342daaf0aa942299f8889", "step": 26, "value": 0.85726113478471, "stage": "debug", "created_at": 1789631586.3578207}, {"event_id": "a89f3edbc04f4c30acc6c4cda751c274", "step": 27, "value": 0.846756404286725, "stage": "evolution", "created_at": 1789630995.482479}, {"event_id": "a407fad9352048d4921cd7823529fa77", "step": 28, "value": 0.8637715699639044, "stage": "improve", "created_at": 1789632239.11777}, {"event_id": "70b3947c243b42a0a412f1bba9b330df", "step": 29, "value": 0.85726113478471, "stage": "improve", "created_at": 1789632080.403761}, {"event_id": "dd8107ae5e994b36a1a8ac2a24abc4dc", "step": 32, "value": 0.846756404286725, "stage": "debug", "created_at": 1789633320.8142042}, {"event_id": "f591c691959d4790877d0d6577a84a93", "step": 33, "value": 0.846756404286725, "stage": "improve", "created_at": 1789632890.8954432}, {"event_id": "cc8247a61ea04252ac0f651c19891e25", "step": 34, "value": 0.846756404286725, "stage": "debug", "created_at": 1789633258.0218966}, {"event_id": "547a08814d534b00b022aed5b4f2fdf1", "step": 35, "value": 0.8597596405060647, "stage": "improve", "created_at": 1789635508.3786879}, {"event_id": "f363af08ed944c9786096dd7b4bee8c7", "step": 36, "value": 0.7230961136525967, "stage": "draft", "created_at": 1789636318.3250227}, {"event_id": "7a3b55e0d00e492984d93c8e476461ac", "step": 38, "value": 0.7056451467391608, "stage": "debug", "created_at": 1789637178.277556}, {"event_id": "b0f456c997c041838aaa8617814cfa24", "step": 39, "value": 0.8453873571241391, "stage": "evolution", "created_at": 1789635997.1713533}, {"event_id": "5fa0af2fa7bf41a39286942cc8f95a53", "step": 40, "value": 0.5483554751784618, "stage": "evolution", "created_at": 1789638855.9001153}, {"event_id": "d9e62d0b93594a5db05fb11d6dbba3f0", "step": 41, "value": 0.6420577966301412, "stage": "evolution", "created_at": 1789638984.0031495}, {"event_id": "685da41ba4184432bdbed8185d8cb01c", "step": 42, "value": 0.8533512124971091, "stage": "evolution", "created_at": 1789640415.789348}, {"event_id": "6904139e92934b68ac246d5386b0eec7", "step": 43, "value": 0.8718793358906527, "stage": "evolution", "created_at": 1789636827.666432}, {"event_id": "df8fc546cad4416eb6d0bc96d3b6d427", "step": 44, "value": 0.8730840858482893, "stage": "evolution", "created_at": 1789644351.773246}, {"event_id": "2a0d4f1393da4014b698bc88e90118bc", "step": 48, "value": 0.8798820003225933, "stage": "improve", "created_at": 1789645119.9308422}, {"event_id": "bef15de324924667bd0ff92e99d43ec1", "step": 49, "value": 0.8755871576202957, "stage": "improve", "created_at": 1789649143.8856819}], "maximize": true, "elapsed_seconds": 28750.803900957108, "node_count": 50, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-hard14-20260917/xixian.gp7-short-ucb-pibo.mlsp-2013-birds.yaml", "note": ""}, {"id": "xixian.gp7-short-ucb-pibo.new-york-city-taxi-fare-prediction", "experiment_id": "mlebench-gp7-hard14-20260917", "family": "MLEBench", "method": "gp7_short_ucb_pibo", "dataset": "new-york-city-taxi-fare-prediction", "status": "archived", "official_score": 4.92971, "medal": "none", "valid_submission": true, "score_maximize": false, "thresholds": {"gold": 2.83377, "silver": 2.88191, "bronze": 2.92371}, "grading_policy": "ensemble", "artifacts": [{"bundle_id": "gp7-ancestry-logei-hard14-full-logs-20260917", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917/logs-77c0e49ab8d6.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917", "member": "results/official_private_grades.jsonl:42", "sha256": "77c0e49ab8d6df7268cefe20565a32eaa589661c5946ef2499c567afceab8104"}, {"bundle_id": "gp7-short-ucb-pibo-hard14-full-logs-20260917", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-short-ucb-pibo-hard14-full-logs-20260917/logs-7d4a0bf30b9a.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-short-ucb-pibo-hard14-full-logs-20260917", "member": "gp7_short_ucb_pibo-hard14/runs/07_new-york-city-taxi-fare-prediction/logs/journal.json", "sha256": "7d4a0bf30b9a2ab2c851ec14cd1b35edcbf277be29c9cdffb309d38ba56f821d"}], "alternate_scores": [{"cohort": "09-17", "workflow_id": "09-17 gp7_short_ucb_pibo", "method": "gp7_short_ucb_pibo", "task": "new-york-city-taxi-fare-prediction", "policy": "best_node", "status": "graded", "valid_submission": true, "score": 5.0128, "medal": "none", "is_lower_better": true, "gold_threshold": 2.83377, "silver_threshold": 2.88191, "bronze_threshold": 2.92371, "submission_sha256": "c4623f165b667650dfec66368e6ed59e69f29332394c81fb8baf5afa8bcdc33e", "source_archive": "gp7_ancestry_logei_hard14_full_logs_20260917.zip", "source_member": "results/official_private_grades.jsonl", "source_line": 41}], "journal_ref": "gp7-short-ucb-pibo-hard14-full-logs-20260917:gp7_short_ucb_pibo-hard14/runs/07_new-york-city-taxi-fare-prediction/logs/journal.json", "metrics": [{"event_id": "0639bac47e28467797a383ea9d09fd6d", "step": 5, "value": 3.5636491989511394, "stage": "debug", "created_at": 1789629292.57248}, {"event_id": "3b1bf168abf143c4833e4bdd8847bfc8", "step": 6, "value": 3.7231542949164242, "stage": "draft", "created_at": 1789627316.6172237}, {"event_id": "18e8aaab20044cab914b3c26773f62c1", "step": 7, "value": 3.290425180219764, "stage": "improve", "created_at": 1789631453.920689}, {"event_id": "bc5bed0d5f474e2ca1e902de018ae743", "step": 8, "value": 2.562658665264617, "stage": "improve", "created_at": 1789631935.7771828}, {"event_id": "72bd8a8b68894efc92a9a13ac5e3c8f8", "step": 9, "value": 3.3533483737326923, "stage": "improve", "created_at": 1789634672.8887403}, {"event_id": "86f1d280c9bc443b80d83ab4dd7af13c", "step": 11, "value": 2.9943053316939494, "stage": "improve", "created_at": 1789638662.920518}, {"event_id": "72b91b6f87d74aedb36a94ae7646662c", "step": 12, "value": 2.4861289989442494, "stage": "improve", "created_at": 1789638687.0389867}, {"event_id": "281f9a093c3641f2b69f3c687e3ac692", "step": 13, "value": 2.3575670809517484, "stage": "improve", "created_at": 1789642177.2790143}, {"event_id": "28fe6daa1baa4e48aa30566d8c43b92a", "step": 15, "value": 2.4728432423155997, "stage": "improve", "created_at": 1789642815.721096}], "maximize": false, "elapsed_seconds": 28754.486837148666, "node_count": 16, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-hard14-20260917/xixian.gp7-short-ucb-pibo.new-york-city-taxi-fare-prediction.yaml", "note": ""}, {"id": "xixian.gp7-short-ucb-pibo.nomad2018-predict-transparent-conductors", "experiment_id": "mlebench-gp7-hard14-20260917", "family": "MLEBench", "method": "gp7_short_ucb_pibo", "dataset": "nomad2018-predict-transparent-conductors", "status": "archived", "official_score": 0.05923, "medal": "silver", "valid_submission": true, "score_maximize": false, "thresholds": {"gold": 0.05589, "silver": 0.06229, "bronze": 0.06582}, "grading_policy": "ensemble", "artifacts": [{"bundle_id": "gp7-ancestry-logei-hard14-full-logs-20260917", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917/logs-77c0e49ab8d6.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917", "member": "results/official_private_grades.jsonl:44", "sha256": "77c0e49ab8d6df7268cefe20565a32eaa589661c5946ef2499c567afceab8104"}, {"bundle_id": "gp7-short-ucb-pibo-hard14-full-logs-20260917", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-short-ucb-pibo-hard14-full-logs-20260917/logs-7d4a0bf30b9a.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-short-ucb-pibo-hard14-full-logs-20260917", "member": "gp7_short_ucb_pibo-hard14/runs/08_nomad2018-predict-transparent-conductors/logs/journal.json", "sha256": "7d4a0bf30b9a2ab2c851ec14cd1b35edcbf277be29c9cdffb309d38ba56f821d"}], "alternate_scores": [{"cohort": "09-17", "workflow_id": "09-17 gp7_short_ucb_pibo", "method": "gp7_short_ucb_pibo", "task": "nomad2018-predict-transparent-conductors", "policy": "best_node", "status": "graded", "valid_submission": true, "score": 0.05982, "medal": "silver", "is_lower_better": true, "gold_threshold": 0.05589, "silver_threshold": 0.06229, "bronze_threshold": 0.06582, "submission_sha256": "63781efe22890ce2f18ab133fa29d4faf97300ffb572a010f5beeaa065ee101a", "source_archive": "gp7_ancestry_logei_hard14_full_logs_20260917.zip", "source_member": "results/official_private_grades.jsonl", "source_line": 43}], "journal_ref": "gp7-short-ucb-pibo-hard14-full-logs-20260917:gp7_short_ucb_pibo-hard14/runs/08_nomad2018-predict-transparent-conductors/logs/journal.json", "metrics": [{"event_id": "276cf3ecdc594011b96ef61ccb71bf73", "step": 5, "value": 0.05883210004112412, "stage": "debug", "created_at": 1789627201.917896}, {"event_id": "891d9f91133a4b6d8abeb6f4da57ec08", "step": 6, "value": 0.06849828889908197, "stage": "debug", "created_at": 1789627205.83623}, {"event_id": "bffc1b0795114ebe8a2bbcd4f2c89579", "step": 8, "value": 0.060283460835861086, "stage": "improve", "created_at": 1789627507.3565705}, {"event_id": "4cc9577a97f84dd8998321bce3be7f2b", "step": 9, "value": 0.05926841737119989, "stage": "improve", "created_at": 1789627666.5701997}, {"event_id": "ca5467c9603f42caa7780d069acf95a6", "step": 10, "value": 0.05861046607764049, "stage": "improve", "created_at": 1789628024.9758444}, {"event_id": "13a6debbc9b34ac590d755409e595a8d", "step": 11, "value": 0.05890970228179133, "stage": "improve", "created_at": 1789628876.5354633}, {"event_id": "a8eba4b891f44417bb4734865072651c", "step": 12, "value": 0.05877365045366023, "stage": "improve", "created_at": 1789629604.7380269}, {"event_id": "d35d7093cca9486fabdc7413355a4578", "step": 13, "value": 0.05820900215798605, "stage": "improve", "created_at": 1789627848.80663}, {"event_id": "fb49f8b0c2e743509f6e045451c0e2d6", "step": 14, "value": 0.059830472519174366, "stage": "debug", "created_at": 1789627684.6272433}, {"event_id": "490ffec3f7284d94a9233f748ef3a9c3", "step": 15, "value": 0.058911173040245, "stage": "improve", "created_at": 1789630346.7547836}, {"event_id": "17b87bdccb0245748862f4479dfca9de", "step": 16, "value": 0.059830472519174366, "stage": "improve", "created_at": 1789630939.5221598}, {"event_id": "6d638a5e4c6745819d9bd19d7d44f1c2", "step": 17, "value": 0.05812379159186615, "stage": "improve", "created_at": 1789630416.3060863}, {"event_id": "4d1783b61d084fe1a76a32da0b24152c", "step": 18, "value": 0.059830472519174366, "stage": "improve", "created_at": 1789631052.9590766}, {"event_id": "63b8e5d18f334a54ba628cb100f7a40a", "step": 19, "value": 0.059830472519174366, "stage": "improve", "created_at": 1789632749.9008217}, {"event_id": "2a67fa3e6e0743f9bf6af4cd090f1c0a", "step": 20, "value": 0.059830472519174366, "stage": "improve", "created_at": 1789631108.1615386}, {"event_id": "6654f6172f6a43cda53f1ef45c0d8406", "step": 24, "value": 0.0574791185652713, "stage": "improve", "created_at": 1789639234.6119373}, {"event_id": "bc9b2170b5e64949a947a9d690199543", "step": 25, "value": 0.05741924470394315, "stage": "improve", "created_at": 1789646013.6405852}], "maximize": false, "elapsed_seconds": 28755.798612594604, "node_count": 26, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-hard14-20260917/xixian.gp7-short-ucb-pibo.nomad2018-predict-transparent-conductors.yaml", "note": ""}, {"id": "xixian.gp7-short-ucb-pibo.random-acts-of-pizza", "experiment_id": "mlebench-gp7-hard14-20260917", "family": "MLEBench", "method": "gp7_short_ucb_pibo", "dataset": "random-acts-of-pizza", "status": "archived", "official_score": 0.70344, "medal": "bronze", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.97908, "silver": 0.76482, "bronze": 0.6921}, "grading_policy": "ensemble", "artifacts": [{"bundle_id": "gp7-ancestry-logei-hard14-full-logs-20260917", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917/logs-77c0e49ab8d6.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917", "member": "results/official_private_grades.jsonl:46", "sha256": "77c0e49ab8d6df7268cefe20565a32eaa589661c5946ef2499c567afceab8104"}, {"bundle_id": "gp7-short-ucb-pibo-hard14-full-logs-20260917", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-short-ucb-pibo-hard14-full-logs-20260917/logs-7d4a0bf30b9a.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-short-ucb-pibo-hard14-full-logs-20260917", "member": "gp7_short_ucb_pibo-hard14/runs/09_random-acts-of-pizza/logs/journal.json", "sha256": "7d4a0bf30b9a2ab2c851ec14cd1b35edcbf277be29c9cdffb309d38ba56f821d"}], "alternate_scores": [{"cohort": "09-17", "workflow_id": "09-17 gp7_short_ucb_pibo", "method": "gp7_short_ucb_pibo", "task": "random-acts-of-pizza", "policy": "best_node", "status": "graded", "valid_submission": true, "score": 0.69567, "medal": "bronze", "is_lower_better": false, "gold_threshold": 0.97908, "silver_threshold": 0.76482, "bronze_threshold": 0.6921, "submission_sha256": "0147522570925e03bf4c1113fe8c6a4d1e4894756a0efa4d97051a89031c03b3", "source_archive": "gp7_ancestry_logei_hard14_full_logs_20260917.zip", "source_member": "results/official_private_grades.jsonl", "source_line": 45}], "journal_ref": "gp7-short-ucb-pibo-hard14-full-logs-20260917:gp7_short_ucb_pibo-hard14/runs/09_random-acts-of-pizza/logs/journal.json", "metrics": [{"event_id": "653dae8787ba45f49b95ad0649cff238", "step": 2, "value": 0.6334859913793104, "stage": "draft", "created_at": 1789626769.7703598}, {"event_id": "4413e1bb7a6f4732b0ef84ae3f0f746d", "step": 4, "value": 0.6508022215365628, "stage": "draft", "created_at": 1789626513.8268383}, {"event_id": "f5551f982feb436a81c6386bd7a54f37", "step": 5, "value": 0.6543493889288281, "stage": "debug", "created_at": 1789627011.2880096}, {"event_id": "9221cfa6b9a149509380ef9bc0e40620", "step": 6, "value": 0.6409920920201294, "stage": "improve", "created_at": 1789627327.1009085}, {"event_id": "74b3b8b26cf74c47975cee0ec706f20c", "step": 7, "value": 0.6473792810860846, "stage": "improve", "created_at": 1789627250.5291216}, {"event_id": "a747efb964b54718ac095f78319a1b42", "step": 8, "value": 0.6695470884255931, "stage": "improve", "created_at": 1789627707.9624906}, {"event_id": "6c3709ee8ca2450ca966faddbdd29302", "step": 9, "value": 0.650726096333573, "stage": "improve", "created_at": 1789627739.6570148}, {"event_id": "c2a3c1f107ad4997abeab9c3bc0eadfa", "step": 10, "value": 0.6353127246585191, "stage": "improve", "created_at": 1789628074.8740473}, {"event_id": "61dd8f9a17934154a8f52d1fa9fc2b55", "step": 11, "value": 0.624255930984903, "stage": "improve", "created_at": 1789628183.0040224}, {"event_id": "bcd2ac5ca66e4432a21e232a758244f0", "step": 12, "value": 0.6410290948275862, "stage": "improve", "created_at": 1789627022.9491456}, {"event_id": "b80d50c780ee4e59916dc031f9c1a443", "step": 14, "value": 0.6684092606422702, "stage": "debug", "created_at": 1789628790.7063105}, {"event_id": "0fae9e7db0d5427ca5bdabc94774decb", "step": 17, "value": 0.6422028940886699, "stage": "debug", "created_at": 1789630077.881177}, {"event_id": "7f0395cc348347399840c06e624a4b44", "step": 18, "value": 0.6927072927072928, "stage": "evolution", "created_at": 1789628731.5516794}, {"event_id": "ec08b41e0af94197a174d2ab10363897", "step": 19, "value": 0.6854013300615243, "stage": "evolution", "created_at": 1789628847.9485154}, {"event_id": "4547b572aeec4767a444ef4aa84708dc", "step": 20, "value": 0.6909561466570813, "stage": "evolution", "created_at": 1789630446.0619051}, {"event_id": "91697c2a31484eb3bae4efceb2f3af01", "step": 21, "value": 0.6932446194582117, "stage": "improve", "created_at": 1789634626.4942582}, {"event_id": "e119ff508eb84cc7868fcc6b5c1fdfbd", "step": 22, "value": 0.6997862978445503, "stage": "improve", "created_at": 1789636435.2878742}, {"event_id": "97050fc82fa94eb0a1251c9bb1b0a744", "step": 23, "value": 0.6919494744737462, "stage": "improve", "created_at": 1789634699.0512006}, {"event_id": "369bec453e4f4c878906ac2c77ec55f0", "step": 24, "value": 0.6920807347991814, "stage": "improve", "created_at": 1789641317.9361234}, {"event_id": "60f199274c6644e59756e0b91205b495", "step": 26, "value": 0.6878228567548956, "stage": "improve", "created_at": 1789642909.9428756}, {"event_id": "d3ab49808feb4bfe871d3113d254c605", "step": 27, "value": 0.6905702711527955, "stage": "improve", "created_at": 1789643398.3688438}, {"event_id": "3319a9ebf5c84e0ea7d6efeb41ccbd87", "step": 29, "value": 0.7079913613894196, "stage": "debug", "created_at": 1789647081.6453617}], "maximize": true, "elapsed_seconds": 28765.811678647995, "node_count": 31, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-hard14-20260917/xixian.gp7-short-ucb-pibo.random-acts-of-pizza.yaml", "note": ""}, {"id": "xixian.gp7-short-ucb-pibo.ranzcr-clip-catheter-line-classification", "experiment_id": "mlebench-gp7-hard14-20260917", "family": "MLEBench", "method": "gp7_short_ucb_pibo", "dataset": "ranzcr-clip-catheter-line-classification", "status": "archived", "official_score": 0.8599, "medal": "none", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.97357, "silver": 0.97152, "bronze": 0.9709}, "grading_policy": "ensemble", "artifacts": [{"bundle_id": "gp7-ancestry-logei-hard14-full-logs-20260917", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917/logs-77c0e49ab8d6.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917", "member": "results/official_private_grades.jsonl:48", "sha256": "77c0e49ab8d6df7268cefe20565a32eaa589661c5946ef2499c567afceab8104"}, {"bundle_id": "gp7-short-ucb-pibo-hard14-full-logs-20260917", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-short-ucb-pibo-hard14-full-logs-20260917/logs-7d4a0bf30b9a.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-short-ucb-pibo-hard14-full-logs-20260917", "member": "gp7_short_ucb_pibo-hard14/runs/10_ranzcr-clip-catheter-line-classification/logs/journal.json", "sha256": "7d4a0bf30b9a2ab2c851ec14cd1b35edcbf277be29c9cdffb309d38ba56f821d"}], "alternate_scores": [{"cohort": "09-17", "workflow_id": "09-17 gp7_short_ucb_pibo", "method": "gp7_short_ucb_pibo", "task": "ranzcr-clip-catheter-line-classification", "policy": "best_node", "status": "graded", "valid_submission": true, "score": 0.85035, "medal": "none", "is_lower_better": false, "gold_threshold": 0.97357, "silver_threshold": 0.97152, "bronze_threshold": 0.9709, "submission_sha256": "b27d66cd0478bd06453517ca67706ea0e9674ba6dbd5cbac391b80eeaf74c328", "source_archive": "gp7_ancestry_logei_hard14_full_logs_20260917.zip", "source_member": "results/official_private_grades.jsonl", "source_line": 47}], "journal_ref": "gp7-short-ucb-pibo-hard14-full-logs-20260917:gp7_short_ucb_pibo-hard14/runs/10_ranzcr-clip-catheter-line-classification/logs/journal.json", "metrics": [{"event_id": "9d51e30d3189426c8c0e1efdd29146b0", "step": 3, "value": 0.8227157930072581, "stage": "debug", "created_at": 1789627817.0120618}, {"event_id": "2d4efe0a18974fdfad41df58d9ec1f13", "step": 4, "value": 0.6546919148124908, "stage": "debug", "created_at": 1789627658.8787003}, {"event_id": "62e6cbd959c94bf984b3b24902918e58", "step": 6, "value": 0.8433940955626151, "stage": "improve", "created_at": 1789631354.6909344}, {"event_id": "3d1639b8fe554d51b40ab4070270020b", "step": 7, "value": 0.8410640036410133, "stage": "debug", "created_at": 1789632816.8213387}, {"event_id": "dc359287751e4bfea1031c9d71947559", "step": 9, "value": 0.8428759489785995, "stage": "improve", "created_at": 1789637851.4875858}, {"event_id": "826356e97d6c47319032420f12c14d17", "step": 10, "value": 0.8437395615411989, "stage": "improve", "created_at": 1789642103.7287147}], "maximize": true, "elapsed_seconds": 28735.2747733593, "node_count": 15, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-hard14-20260917/xixian.gp7-short-ucb-pibo.ranzcr-clip-catheter-line-classification.yaml", "note": ""}, {"id": "xixian.gp7-short-ucb-pibo.siim-isic-melanoma-classification", "experiment_id": "mlebench-gp7-hard14-20260917", "family": "MLEBench", "method": "gp7_short_ucb_pibo", "dataset": "siim-isic-melanoma-classification", "status": "archived", "official_score": 0.89676, "medal": "none", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.9455, "silver": 0.9401, "bronze": 0.937}, "grading_policy": "ensemble", "artifacts": [{"bundle_id": "gp7-ancestry-logei-hard14-full-logs-20260917", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917/logs-77c0e49ab8d6.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917", "member": "results/official_private_grades.jsonl:50", "sha256": "77c0e49ab8d6df7268cefe20565a32eaa589661c5946ef2499c567afceab8104"}, {"bundle_id": "gp7-short-ucb-pibo-hard14-full-logs-20260917", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-short-ucb-pibo-hard14-full-logs-20260917/logs-7d4a0bf30b9a.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-short-ucb-pibo-hard14-full-logs-20260917", "member": "gp7_short_ucb_pibo-hard14/runs/11_siim-isic-melanoma-classification/logs/journal.json", "sha256": "7d4a0bf30b9a2ab2c851ec14cd1b35edcbf277be29c9cdffb309d38ba56f821d"}], "alternate_scores": [{"cohort": "09-17", "workflow_id": "09-17 gp7_short_ucb_pibo", "method": "gp7_short_ucb_pibo", "task": "siim-isic-melanoma-classification", "policy": "best_node", "status": "graded", "valid_submission": true, "score": 0.87618, "medal": "none", "is_lower_better": false, "gold_threshold": 0.9455, "silver_threshold": 0.9401, "bronze_threshold": 0.937, "submission_sha256": "ea259236a236921ed023cdbc1807ebc69cd8a72dced59290413b9e2bada48ad0", "source_archive": "gp7_ancestry_logei_hard14_full_logs_20260917.zip", "source_member": "results/official_private_grades.jsonl", "source_line": 49}], "journal_ref": "gp7-short-ucb-pibo-hard14-full-logs-20260917:gp7_short_ucb_pibo-hard14/runs/11_siim-isic-melanoma-classification/logs/journal.json", "metrics": [{"event_id": "f02c85be1d734d2d8be36dee87a82d8a", "step": 2, "value": 0.8787458058544486, "stage": "draft", "created_at": 1789626233.8998995}, {"event_id": "bd541815eda8458bbb183267ddf717ec", "step": 3, "value": 0.8841995098503256, "stage": "improve", "created_at": 1789633283.8783736}, {"event_id": "3ffb6c6992374c8aa8dbb18dba976575", "step": 4, "value": 0.8821458247872688, "stage": "improve", "created_at": 1789633732.0260634}, {"event_id": "0ebd42b0ec1b4ff2bc1114e3247d9f27", "step": 5, "value": 0.9041719026972146, "stage": "draft", "created_at": 1789626777.7936084}, {"event_id": "014511cb854b44d9ab2eb4b9e6a70cc5", "step": 9, "value": 0.900749827315019, "stage": "debug", "created_at": 1789641683.9507642}], "maximize": true, "elapsed_seconds": 28753.472333669662, "node_count": 12, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-hard14-20260917/xixian.gp7-short-ucb-pibo.siim-isic-melanoma-classification.yaml", "note": ""}, {"id": "xixian.gp7-short-ucb-pibo.tabular-playground-series-may-2022", "experiment_id": "mlebench-gp7-hard14-20260917", "family": "MLEBench", "method": "gp7_short_ucb_pibo", "dataset": "tabular-playground-series-may-2022", "status": "archived", "official_score": 0.99453, "medal": "none", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.99823, "silver": 0.99822, "bronze": 0.99818}, "grading_policy": "ensemble", "artifacts": [{"bundle_id": "gp7-ancestry-logei-hard14-full-logs-20260917", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917/logs-77c0e49ab8d6.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917", "member": "results/official_private_grades.jsonl:52", "sha256": "77c0e49ab8d6df7268cefe20565a32eaa589661c5946ef2499c567afceab8104"}, {"bundle_id": "gp7-short-ucb-pibo-hard14-full-logs-20260917", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-short-ucb-pibo-hard14-full-logs-20260917/logs-7d4a0bf30b9a.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-short-ucb-pibo-hard14-full-logs-20260917", "member": "gp7_short_ucb_pibo-hard14/runs/12_tabular-playground-series-may-2022/logs/journal.json", "sha256": "7d4a0bf30b9a2ab2c851ec14cd1b35edcbf277be29c9cdffb309d38ba56f821d"}], "alternate_scores": [{"cohort": "09-17", "workflow_id": "09-17 gp7_short_ucb_pibo", "method": "gp7_short_ucb_pibo", "task": "tabular-playground-series-may-2022", "policy": "best_node", "status": "graded", "valid_submission": true, "score": 0.99379, "medal": "none", "is_lower_better": false, "gold_threshold": 0.99823, "silver_threshold": 0.99822, "bronze_threshold": 0.99818, "submission_sha256": "fcd1cc4be93cee92af2ce20c174f5144e21451fd73f5be4908a438c101d6f99c", "source_archive": "gp7_ancestry_logei_hard14_full_logs_20260917.zip", "source_member": "results/official_private_grades.jsonl", "source_line": 51}], "journal_ref": "gp7-short-ucb-pibo-hard14-full-logs-20260917:gp7_short_ucb_pibo-hard14/runs/12_tabular-playground-series-may-2022/logs/journal.json", "metrics": [{"event_id": "2e033fd6a7bf45ccbef594d4131e55c2", "step": 3, "value": 0.990231692902937, "stage": "debug", "created_at": 1789626946.2430003}, {"event_id": "c24311cfcb9642ee83813938de976b81", "step": 6, "value": 0.992967826414574, "stage": "debug", "created_at": 1789627423.2687511}, {"event_id": "b097bdb8ea314acf9f220af79efcf530", "step": 7, "value": 0.7734476309142166, "stage": "debug", "created_at": 1789627192.650084}, {"event_id": "603bf442433b4512b549115785ebe8df", "step": 8, "value": 0.9770995472827443, "stage": "improve", "created_at": 1789627794.1165695}, {"event_id": "f018e325a69c481daf17d96e9724859c", "step": 9, "value": 0.9921301600208353, "stage": "improve", "created_at": 1789627780.1563854}, {"event_id": "081061390e8c4c22b01716a9de2a46da", "step": 10, "value": 0.9921203820480167, "stage": "improve", "created_at": 1789634560.876996}, {"event_id": "49a5957eb9c24ff696b8dc894d5ec9d4", "step": 12, "value": 0.9917879347130045, "stage": "improve", "created_at": 1789638685.6010158}, {"event_id": "a89d0b57bfac4b0c8a24baa8c8b00cd5", "step": 13, "value": 0.9934470298446954, "stage": "improve", "created_at": 1789640786.542965}, {"event_id": "6dc87054f77c4a988af06b8eb20c6fc5", "step": 14, "value": 0.9917902309214275, "stage": "improve", "created_at": 1789642048.9482193}, {"event_id": "5f9c36f02f52469b9270a68290a21d26", "step": 15, "value": 0.9916272251426139, "stage": "improve", "created_at": 1789630895.8489063}], "maximize": true, "elapsed_seconds": 28739.82437825203, "node_count": 17, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-hard14-20260917/xixian.gp7-short-ucb-pibo.tabular-playground-series-may-2022.yaml", "note": ""}, {"id": "xixian.gp7-short-ucb-pibo.text-normalization-challenge-english-language", "experiment_id": "mlebench-gp7-hard14-20260917", "family": "MLEBench", "method": "gp7_short_ucb_pibo", "dataset": "text-normalization-challenge-english-language", "status": "archived", "official_score": 0.97099, "medal": "none", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.99724, "silver": 0.99135, "bronze": 0.99038}, "grading_policy": "ensemble", "artifacts": [{"bundle_id": "gp7-ancestry-logei-hard14-full-logs-20260917", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917/logs-77c0e49ab8d6.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917", "member": "results/official_private_grades.jsonl:54", "sha256": "77c0e49ab8d6df7268cefe20565a32eaa589661c5946ef2499c567afceab8104"}, {"bundle_id": "gp7-short-ucb-pibo-hard14-full-logs-20260917", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-short-ucb-pibo-hard14-full-logs-20260917/logs-7d4a0bf30b9a.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-short-ucb-pibo-hard14-full-logs-20260917", "member": "gp7_short_ucb_pibo-hard14/runs/13_text-normalization-challenge-english-language/logs/journal.json", "sha256": "7d4a0bf30b9a2ab2c851ec14cd1b35edcbf277be29c9cdffb309d38ba56f821d"}], "alternate_scores": [{"cohort": "09-17", "workflow_id": "09-17 gp7_short_ucb_pibo", "method": "gp7_short_ucb_pibo", "task": "text-normalization-challenge-english-language", "policy": "best_node", "status": "graded", "valid_submission": true, "score": 0.97099, "medal": "none", "is_lower_better": false, "gold_threshold": 0.99724, "silver_threshold": 0.99135, "bronze_threshold": 0.99038, "submission_sha256": "3699ef96723484d5414790c663fb84a262fb53ecb70b6ac5a7b0ef5213eaeaa6", "source_archive": "gp7_ancestry_logei_hard14_full_logs_20260917.zip", "source_member": "results/official_private_grades.jsonl", "source_line": 53}], "journal_ref": "gp7-short-ucb-pibo-hard14-full-logs-20260917:gp7_short_ucb_pibo-hard14/runs/13_text-normalization-challenge-english-language/logs/journal.json", "metrics": [{"event_id": "a149e2d8c27f46409b45a746bfb52704", "step": 5, "value": 0.7344830875051195, "stage": "debug", "created_at": 1789628175.0853827}, {"event_id": "1c18207768e14fbf9496cf7ee4cb3df2", "step": 6, "value": 0.9712580158324965, "stage": "debug", "created_at": 1789627330.5597348}, {"event_id": "2514c8d4af7743d387a9d15d1df18239", "step": 8, "value": 0.9310296271262815, "stage": "debug", "created_at": 1789641907.5309582}], "maximize": true, "elapsed_seconds": 28747.81075000763, "node_count": 9, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-hard14-20260917/xixian.gp7-short-ucb-pibo.text-normalization-challenge-english-language.yaml", "note": ""}, {"id": "xixian.gp7-short-ucb-pibo.text-normalization-challenge-russian-language", "experiment_id": "mlebench-gp7-hard14-20260917", "family": "MLEBench", "method": "gp7_short_ucb_pibo", "dataset": "text-normalization-challenge-russian-language", "status": "archived", "official_score": 0.98438, "medal": "silver", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.99012, "silver": 0.98232, "bronze": 0.97592}, "grading_policy": "ensemble", "artifacts": [{"bundle_id": "gp7-ancestry-logei-hard14-full-logs-20260917", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917/logs-77c0e49ab8d6.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917", "member": "results/official_private_grades.jsonl:56", "sha256": "77c0e49ab8d6df7268cefe20565a32eaa589661c5946ef2499c567afceab8104"}, {"bundle_id": "gp7-short-ucb-pibo-hard14-full-logs-20260917", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-short-ucb-pibo-hard14-full-logs-20260917/logs-7d4a0bf30b9a.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-short-ucb-pibo-hard14-full-logs-20260917", "member": "gp7_short_ucb_pibo-hard14/runs/14_text-normalization-challenge-russian-language/logs/journal.json", "sha256": "7d4a0bf30b9a2ab2c851ec14cd1b35edcbf277be29c9cdffb309d38ba56f821d"}], "alternate_scores": [{"cohort": "09-17", "workflow_id": "09-17 gp7_short_ucb_pibo", "method": "gp7_short_ucb_pibo", "task": "text-normalization-challenge-russian-language", "policy": "best_node", "status": "graded", "valid_submission": true, "score": 0.98388, "medal": "silver", "is_lower_better": false, "gold_threshold": 0.99012, "silver_threshold": 0.98232, "bronze_threshold": 0.97592, "submission_sha256": "979c775b71cc9322b1afbac72fd0d67646713424e515e3e6c6f8312b965be797", "source_archive": "gp7_ancestry_logei_hard14_full_logs_20260917.zip", "source_member": "results/official_private_grades.jsonl", "source_line": 55}], "journal_ref": "gp7-short-ucb-pibo-hard14-full-logs-20260917:gp7_short_ucb_pibo-hard14/runs/14_text-normalization-challenge-russian-language/logs/journal.json", "metrics": [{"event_id": "ebf03a65fe5e4d8388863048f2e759a2", "step": 5, "value": 0.9296639966161736, "stage": "debug", "created_at": 1789627373.2682374}, {"event_id": "6b3ddf1d98ff4a41bf2cff9db5ca569a", "step": 6, "value": 0.8887725698575092, "stage": "debug", "created_at": 1789626817.6721597}, {"event_id": "620ade1e237240aeb3976adcce3e76bf", "step": 7, "value": 0.89975, "stage": "draft", "created_at": 1789626467.3981647}, {"event_id": "ad2c82b31682443da0a0467dedab313e", "step": 8, "value": 0.9682607661194385, "stage": "improve", "created_at": 1789628964.9778507}, {"event_id": "3b06e72e9cda42218a9de35063f94ba0", "step": 10, "value": 0.9795807227641632, "stage": "improve", "created_at": 1789628918.9659147}, {"event_id": "15ea643a52ed4ef29cc6e3a1c48e3df9", "step": 11, "value": 0.9472387448119068, "stage": "improve", "created_at": 1789631988.4525502}, {"event_id": "a8f50e9f268b4e54a798ed4e74b3d5e8", "step": 12, "value": 0.983191899965633, "stage": "debug", "created_at": 1789632536.7684672}, {"event_id": "126a51d03f4c4ed4acb997802c5c9b0e", "step": 14, "value": 0.9718349327200148, "stage": "improve", "created_at": 1789637719.3023863}, {"event_id": "93c10113fd794589aacfb61d49e2dbd9", "step": 16, "value": 0.9801676051497608, "stage": "improve", "created_at": 1789635539.8365438}, {"event_id": "d606a220a88e4d2685cf8802a4d58c70", "step": 17, "value": 0.9835567187458694, "stage": "improve", "created_at": 1789641489.9212344}, {"event_id": "5915b95c7fa545d98a122324577ba732", "step": 18, "value": 0.9766410236074762, "stage": "improve", "created_at": 1789643379.4838047}, {"event_id": "bb3c4ba792e44147a50e9b01099b4643", "step": 19, "value": 0.9243661934596981, "stage": "improve", "created_at": 1789649947.0680158}, {"event_id": "fd322dda11ea4fafbba1af1232685a46", "step": 20, "value": 0.9756946096703413, "stage": "improve", "created_at": 1789642853.5698674}], "maximize": true, "elapsed_seconds": 28761.000586509705, "node_count": 21, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-hard14-20260917/xixian.gp7-short-ucb-pibo.text-normalization-challenge-russian-language.yaml", "note": ""}, {"id": "xixian.gp7-no-ancestry-logei.aerial-cactus-identification", "experiment_id": "mlebench-gp7-hard14-20260917", "family": "MLEBench", "method": "gp7_no_ancestry_logei", "dataset": "aerial-cactus-identification", "status": "archived", "official_score": 0.99999, "medal": "none", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 1.0, "silver": 1.0, "bronze": 1.0}, "grading_policy": "ensemble", "artifacts": [{"bundle_id": "gp7-ancestry-logei-hard14-full-logs-20260917", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917/logs-77c0e49ab8d6.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917", "member": "results/official_private_grades.jsonl:58", "sha256": "77c0e49ab8d6df7268cefe20565a32eaa589661c5946ef2499c567afceab8104"}, {"bundle_id": "gp7-no-ancestry-logei-hard14-full-logs-20260917", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-no-ancestry-logei-hard14-full-logs-20260917/logs-5cb1f19bf4da.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-no-ancestry-logei-hard14-full-logs-20260917", "member": "gp7_no_ancestry_logei-hard14/runs/01_aerial-cactus-identification/logs/journal.json", "sha256": "5cb1f19bf4da2d6fd6b6aea2a936a5ebe2ad2c67f0a46cbfeed510ddf38aef8d"}], "alternate_scores": [{"cohort": "09-17", "workflow_id": "09-17 gp7_no_ancestry_logei", "method": "gp7_no_ancestry_logei", "task": "aerial-cactus-identification", "policy": "best_node", "status": "graded", "valid_submission": true, "score": 1.0, "medal": "gold", "is_lower_better": false, "gold_threshold": 1.0, "silver_threshold": 1.0, "bronze_threshold": 1.0, "submission_sha256": "02325ac17da1fc612ba145e7fae1af8e68b6948f87c0727aae94d0335b42bc61", "source_archive": "gp7_ancestry_logei_hard14_full_logs_20260917.zip", "source_member": "results/official_private_grades.jsonl", "source_line": 57}], "journal_ref": "gp7-no-ancestry-logei-hard14-full-logs-20260917:gp7_no_ancestry_logei-hard14/runs/01_aerial-cactus-identification/logs/journal.json", "metrics": [{"event_id": "764cfd4b7f2449db969e4f71bb46e956", "step": 2, "value": 0.9998244042708653, "stage": "draft", "created_at": 1789626862.90027}, {"event_id": "ae42069c9f49442299086dd4f0c3664a", "step": 3, "value": 0.9997529537551029, "stage": "debug", "created_at": 1789627025.8995283}, {"event_id": "4bd3a2b2e14d42c3b8ebc868a8df186d", "step": 4, "value": 0.9998632946001367, "stage": "draft", "created_at": 1789626391.1754763}, {"event_id": "f217ff55f66e41d28a6c51ac019a5114", "step": 6, "value": 0.9998962924552761, "stage": "improve", "created_at": 1789627364.895574}, {"event_id": "1e566ef974a44f32adebb61255be2531", "step": 7, "value": 0.999853189731516, "stage": "debug", "created_at": 1789627930.5857816}, {"event_id": "4c2ad829e32d4c1da363240cfe68196a", "step": 8, "value": 0.9995156386263464, "stage": "improve", "created_at": 1789628033.1551816}, {"event_id": "0bd5db46183c42c6aaa68af735a24ff7", "step": 10, "value": 0.9998833290121856, "stage": "improve", "created_at": 1789628774.6441019}, {"event_id": "6f9e42190973469a846a6cd1cd982cac", "step": 11, "value": 0.999962288165555, "stage": "improve", "created_at": 1789627778.00361}, {"event_id": "c11c8b1db39f4c97ad5a6aaac66bc795", "step": 12, "value": 0.9998515022571658, "stage": "improve", "created_at": 1789630144.3412697}, {"event_id": "10481444967b4b389a8f921664357d3d", "step": 15, "value": 0.999734249416645, "stage": "debug", "created_at": 1789628866.4164104}, {"event_id": "1582fa27ab094bd2b077eda20a21d920", "step": 16, "value": 0.9999429456245265, "stage": "draft", "created_at": 1789633426.9671233}, {"event_id": "fb2fb3cb781b4690927acb1767082d0a", "step": 17, "value": 0.9998644340385716, "stage": "evolution", "created_at": 1789634079.1778862}, {"event_id": "2fb393601c424e0aa6fd4ff58ab48321", "step": 18, "value": 0.9999701459663219, "stage": "debug", "created_at": 1789631652.2588086}, {"event_id": "bc5e50f9cecb46028ae2ab90f561848b", "step": 21, "value": 0.9999360165401666, "stage": "debug", "created_at": 1789640584.5389607}, {"event_id": "33af32877c3b418ea464eadd611b0f80", "step": 22, "value": 0.9981976000752941, "stage": "debug", "created_at": 1789641051.5398772}, {"event_id": "509fce64fdb0408c93685d6302ff06a5", "step": 23, "value": 0.9999871609577671, "stage": "improve", "created_at": 1789643594.4333253}, {"event_id": "1db9ab7290454df8915d2712eff4ea57", "step": 24, "value": 0.9999847412716757, "stage": "improve", "created_at": 1789647783.9434118}, {"event_id": "b25490b1069b416aa3c7c776b93fbe28", "step": 25, "value": 0.9999525652576005, "stage": "improve", "created_at": 1789647162.823482}, {"event_id": "b6338a26bb9643dba825c8a18de1865c", "step": 26, "value": 0.998977094405902, "stage": "improve", "created_at": 1789648947.8346457}], "maximize": true, "elapsed_seconds": 28693.35284471512, "node_count": 28, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-hard14-20260917/xixian.gp7-no-ancestry-logei.aerial-cactus-identification.yaml", "note": ""}, {"id": "xixian.gp7-no-ancestry-logei.aptos2019-blindness-detection", "experiment_id": "mlebench-gp7-hard14-20260917", "family": "MLEBench", "method": "gp7_no_ancestry_logei", "dataset": "aptos2019-blindness-detection", "status": "archived", "official_score": 0.92976, "medal": "silver", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.930508, "silver": 0.919654, "bronze": 0.914492}, "grading_policy": "ensemble", "artifacts": [{"bundle_id": "gp7-ancestry-logei-hard14-full-logs-20260917", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917/logs-77c0e49ab8d6.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917", "member": "results/official_private_grades.jsonl:60", "sha256": "77c0e49ab8d6df7268cefe20565a32eaa589661c5946ef2499c567afceab8104"}, {"bundle_id": "gp7-no-ancestry-logei-hard14-full-logs-20260917", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-no-ancestry-logei-hard14-full-logs-20260917/logs-5cb1f19bf4da.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-no-ancestry-logei-hard14-full-logs-20260917", "member": "gp7_no_ancestry_logei-hard14/runs/02_aptos2019-blindness-detection/logs/journal.json", "sha256": "5cb1f19bf4da2d6fd6b6aea2a936a5ebe2ad2c67f0a46cbfeed510ddf38aef8d"}], "alternate_scores": [{"cohort": "09-17", "workflow_id": "09-17 gp7_no_ancestry_logei", "method": "gp7_no_ancestry_logei", "task": "aptos2019-blindness-detection", "policy": "best_node", "status": "graded", "valid_submission": true, "score": 0.93087, "medal": "gold", "is_lower_better": false, "gold_threshold": 0.930508, "silver_threshold": 0.919654, "bronze_threshold": 0.914492, "submission_sha256": "2d641d39d86c3b8a0f329897c28d289ab7234ea0db0c5b43b5a73aba1226fdca", "source_archive": "gp7_ancestry_logei_hard14_full_logs_20260917.zip", "source_member": "results/official_private_grades.jsonl", "source_line": 59}], "journal_ref": "gp7-no-ancestry-logei-hard14-full-logs-20260917:gp7_no_ancestry_logei-hard14/runs/02_aptos2019-blindness-detection/logs/journal.json", "metrics": [{"event_id": "bb3e39b59463482fa3110318718b7496", "step": 2, "value": 0.8970272488530215, "stage": "draft", "created_at": 1789626512.632246}, {"event_id": "57d553a2397b4f3dafd709ccfe1d9e3f", "step": 4, "value": 0.9153864101703502, "stage": "improve", "created_at": 1789628274.4514349}, {"event_id": "2d714549c3224913a90a5e0c06c2439e", "step": 5, "value": 0.9226685295144953, "stage": "improve", "created_at": 1789630101.237323}, {"event_id": "76e9ac6a420b42bf8c249ffd50aca4d5", "step": 6, "value": 0.8123637333277564, "stage": "debug", "created_at": 1789629558.8453412}, {"event_id": "2ad964056f414100991ab3032a970494", "step": 7, "value": 0.9203107594755934, "stage": "improve", "created_at": 1789632781.4175744}, {"event_id": "250e7526ddeb40efa521e7000d77085d", "step": 9, "value": 0.922364012262066, "stage": "improve", "created_at": 1789633699.8693218}, {"event_id": "d8a8380e24a74b2b815b9089223aef82", "step": 10, "value": 0.9254356873692573, "stage": "improve", "created_at": 1789634744.242544}, {"event_id": "d7c52bdb61c74d909045e659430e8a8d", "step": 11, "value": 0.9225647493620391, "stage": "improve", "created_at": 1789636905.8172681}, {"event_id": "faa2bc461cbe4348ba8e3b4c244d0b0f", "step": 13, "value": 0.9324538884446604, "stage": "improve", "created_at": 1789639551.2763827}, {"event_id": "810e992ce99841f8b9d362d2d40773c7", "step": 14, "value": 0.9121756487025948, "stage": "debug", "created_at": 1789634862.7141676}, {"event_id": "2bc8b012b3e64ca0abe1d061fa0f93f0", "step": 16, "value": 0.9219705810386042, "stage": "improve", "created_at": 1789642890.6781}, {"event_id": "24c4273fd7804e8891d619cad0c51045", "step": 17, "value": 0.9198097338556094, "stage": "debug", "created_at": 1789640784.1111565}, {"event_id": "afbeca4e1fce427e8a50147621f732ce", "step": 18, "value": 0.9191179642432775, "stage": "improve", "created_at": 1789645450.6299279}, {"event_id": "bd895423a9794610886369d317f27d37", "step": 19, "value": 0.9318955517211347, "stage": "improve", "created_at": 1789646370.5706966}, {"event_id": "48a813ac209f4ff08c4d11e097bbc726", "step": 20, "value": 0.9270102791267312, "stage": "debug", "created_at": 1789644962.082133}, {"event_id": "d2507ebdda63451883006dfe890e105b", "step": 21, "value": 0.9259970358790479, "stage": "fusion", "created_at": 1789648919.7670805}], "maximize": true, "elapsed_seconds": 28765.8975045681, "node_count": 23, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-hard14-20260917/xixian.gp7-no-ancestry-logei.aptos2019-blindness-detection.yaml", "note": ""}, {"id": "xixian.gp7-no-ancestry-logei.dog-breed-identification", "experiment_id": "mlebench-gp7-hard14-20260917", "family": "MLEBench", "method": "gp7_no_ancestry_logei", "dataset": "dog-breed-identification", "status": "archived", "official_score": 0.23281, "medal": "none", "valid_submission": true, "score_maximize": false, "thresholds": {"gold": 0.0005, "silver": 0.00539, "bronze": 0.04598}, "grading_policy": "ensemble", "artifacts": [{"bundle_id": "gp7-ancestry-logei-hard14-full-logs-20260917", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917/logs-77c0e49ab8d6.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917", "member": "results/official_private_grades.jsonl:62", "sha256": "77c0e49ab8d6df7268cefe20565a32eaa589661c5946ef2499c567afceab8104"}, {"bundle_id": "gp7-no-ancestry-logei-hard14-full-logs-20260917", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-no-ancestry-logei-hard14-full-logs-20260917/logs-5cb1f19bf4da.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-no-ancestry-logei-hard14-full-logs-20260917", "member": "gp7_no_ancestry_logei-hard14/runs/03_dog-breed-identification/logs/journal.json", "sha256": "5cb1f19bf4da2d6fd6b6aea2a936a5ebe2ad2c67f0a46cbfeed510ddf38aef8d"}], "alternate_scores": [{"cohort": "09-17", "workflow_id": "09-17 gp7_no_ancestry_logei", "method": "gp7_no_ancestry_logei", "task": "dog-breed-identification", "policy": "best_node", "status": "graded", "valid_submission": true, "score": 0.22435, "medal": "none", "is_lower_better": true, "gold_threshold": 0.0005, "silver_threshold": 0.00539, "bronze_threshold": 0.04598, "submission_sha256": "c4483b2383801f83580b754a76b87d4131af8108503f5cfc62391dfe059589f3", "source_archive": "gp7_ancestry_logei_hard14_full_logs_20260917.zip", "source_member": "results/official_private_grades.jsonl", "source_line": 61}], "journal_ref": "gp7-no-ancestry-logei-hard14-full-logs-20260917:gp7_no_ancestry_logei-hard14/runs/03_dog-breed-identification/logs/journal.json", "metrics": [{"event_id": "ae1663de60b245e48da00f30a4a9e1fb", "step": 2, "value": 0.6501351194145233, "stage": "debug", "created_at": 1789627098.8805165}, {"event_id": "2abc2da308ea4876ab682099df891e72", "step": 3, "value": 0.4361548343838565, "stage": "draft", "created_at": 1789626537.6597302}, {"event_id": "f069296e00b14e42b29e41d07de19c7c", "step": 5, "value": 0.650336506841776, "stage": "improve", "created_at": 1789627591.3587804}, {"event_id": "1f70d8fba7a94696b6ce042a5abb6094", "step": 6, "value": 0.4541585059031266, "stage": "draft", "created_at": 1789626207.4084318}, {"event_id": "287e4594acee4242abd3f22c1160ab35", "step": 7, "value": 0.4528119268183457, "stage": "improve", "created_at": 1789628304.0359077}, {"event_id": "9f9634e52b5a49a28fd222c8b3d5b611", "step": 8, "value": 0.5419310798295112, "stage": "improve", "created_at": 1789628117.1199043}, {"event_id": "4e06bc63d4cd4a6dbd73eee5f240aa1a", "step": 10, "value": 0.42430984305409025, "stage": "debug", "created_at": 1789627877.4483037}, {"event_id": "bdda676f94e04019a661b11a9a99e27a", "step": 11, "value": 0.5415822130556378, "stage": "improve", "created_at": 1789629380.769154}, {"event_id": "5b76d45968174e7b973d161aa47c1f80", "step": 12, "value": 0.40380395385015355, "stage": "debug", "created_at": 1789629559.616311}, {"event_id": "4b37a8585e1c48ad8eecf0901c129eea", "step": 13, "value": 0.8708563530218291, "stage": "improve", "created_at": 1789630589.773298}, {"event_id": "713bdaebb89a4fc4846c6e551745fb1c", "step": 15, "value": 0.42735350249030196, "stage": "improve", "created_at": 1789630895.39211}, {"event_id": "75ceeed3486f49ee8146615766be74e4", "step": 16, "value": 0.39767294824508576, "stage": "debug", "created_at": 1789631251.0217535}, {"event_id": "22a3418458b542a8b27c49b7ede54ce9", "step": 17, "value": 0.40250671085051, "stage": "improve", "created_at": 1789633248.2255187}, {"event_id": "115107f0467c463d8fd4445ad764132a", "step": 18, "value": 0.2968289552983826, "stage": "improve", "created_at": 1789632851.7781627}, {"event_id": "56fca299863d493d89c2355036c4b901", "step": 20, "value": 0.39380804442179695, "stage": "improve", "created_at": 1789634424.6080885}, {"event_id": "fafa64ca831f4a899c860e23359cba43", "step": 21, "value": 0.28006354267485245, "stage": "improve", "created_at": 1789630769.2258315}, {"event_id": "8d8171050051422982b58cbe41e45ae7", "step": 23, "value": 0.28923389563863344, "stage": "improve", "created_at": 1789636561.7752116}, {"event_id": "c855bff357f9470d895596bb0253d4f2", "step": 24, "value": 0.3354284995694812, "stage": "improve", "created_at": 1789638295.8907726}, {"event_id": "2e1afe0ab30d40edaeb1b292308f2d7b", "step": 25, "value": 0.20612030145669852, "stage": "improve", "created_at": 1789638631.4693515}, {"event_id": "b7452d6fbf3b4d3587b76cf98521ce5e", "step": 26, "value": 0.3317400206399675, "stage": "improve", "created_at": 1789638887.2440073}, {"event_id": "cd01aa53e66e4881834f436cc1f70178", "step": 27, "value": 0.19761734844924034, "stage": "improve", "created_at": 1789642053.5499897}, {"event_id": "8a533c4640c7486193b74e51002917b2", "step": 28, "value": 0.21456094357542516, "stage": "improve", "created_at": 1789646238.6930437}], "maximize": false, "elapsed_seconds": 28761.041182279587, "node_count": 30, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-hard14-20260917/xixian.gp7-no-ancestry-logei.dog-breed-identification.yaml", "note": ""}, {"id": "xixian.gp7-no-ancestry-logei.jigsaw-toxic-comment-classification-challenge", "experiment_id": "mlebench-gp7-hard14-20260917", "family": "MLEBench", "method": "gp7_no_ancestry_logei", "dataset": "jigsaw-toxic-comment-classification-challenge", "status": "archived", "official_score": 0.98538, "medal": "none", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.9874, "silver": 0.98668, "bronze": 0.98639}, "grading_policy": "ensemble", "artifacts": [{"bundle_id": "gp7-ancestry-logei-hard14-full-logs-20260917", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917/logs-77c0e49ab8d6.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917", "member": "results/official_private_grades.jsonl:64", "sha256": "77c0e49ab8d6df7268cefe20565a32eaa589661c5946ef2499c567afceab8104"}, {"bundle_id": "gp7-no-ancestry-logei-hard14-full-logs-20260917", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-no-ancestry-logei-hard14-full-logs-20260917/logs-5cb1f19bf4da.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-no-ancestry-logei-hard14-full-logs-20260917", "member": "gp7_no_ancestry_logei-hard14/runs/04_jigsaw-toxic-comment-classification-challenge/logs/journal.json", "sha256": "5cb1f19bf4da2d6fd6b6aea2a936a5ebe2ad2c67f0a46cbfeed510ddf38aef8d"}], "alternate_scores": [{"cohort": "09-17", "workflow_id": "09-17 gp7_no_ancestry_logei", "method": "gp7_no_ancestry_logei", "task": "jigsaw-toxic-comment-classification-challenge", "policy": "best_node", "status": "graded", "valid_submission": true, "score": 0.97978, "medal": "none", "is_lower_better": false, "gold_threshold": 0.9874, "silver_threshold": 0.98668, "bronze_threshold": 0.98639, "submission_sha256": "b88b3c29755bfb55c41fa398d21434adebaa56351168306c99448608fc93c36f", "source_archive": "gp7_ancestry_logei_hard14_full_logs_20260917.zip", "source_member": "results/official_private_grades.jsonl", "source_line": 63}], "journal_ref": "gp7-no-ancestry-logei-hard14-full-logs-20260917:gp7_no_ancestry_logei-hard14/runs/04_jigsaw-toxic-comment-classification-challenge/logs/journal.json", "metrics": [{"event_id": "04ab4e0b1c384207b75063a1820d00fd", "step": 5, "value": 0.9892279881214879, "stage": "draft", "created_at": 1789626201.177507}, {"event_id": "e87241422fa54246b59fdded2dbd85c9", "step": 6, "value": 0.9159230174591295, "stage": "debug", "created_at": 1789627352.9813333}, {"event_id": "78ee1b60cda34f61a9c0aeb700d33baf", "step": 7, "value": 0.9922905087791315, "stage": "debug", "created_at": 1789627028.910935}, {"event_id": "774c837c20c744439c423c42fbfe4a5d", "step": 9, "value": 0.9697739048341235, "stage": "improve", "created_at": 1789631189.4284194}, {"event_id": "1a17ab11d6724b5cb6fd0feecd886d09", "step": 11, "value": 0.9924968987198356, "stage": "debug", "created_at": 1789640374.8858483}, {"event_id": "cc2f630837cc4a84b33c25c86a50aabf", "step": 12, "value": 0.9921699946676914, "stage": "improve", "created_at": 1789631188.7867408}, {"event_id": "06ed798b91f94248938a994ddfd40842", "step": 14, "value": 0.9901503768010403, "stage": "fusion_draft", "created_at": 1789649502.7033272}], "maximize": true, "elapsed_seconds": 28759.99180006981, "node_count": 16, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-hard14-20260917/xixian.gp7-no-ancestry-logei.jigsaw-toxic-comment-classification-challenge.yaml", "note": ""}, {"id": "xixian.gp7-no-ancestry-logei.leaf-classification", "experiment_id": "mlebench-gp7-hard14-20260917", "family": "MLEBench", "method": "gp7_no_ancestry_logei", "dataset": "leaf-classification", "status": "archived", "official_score": 3.6436, "medal": "none", "valid_submission": true, "score_maximize": false, "thresholds": {"gold": 0.0, "silver": 0.00791, "bronze": 0.01526}, "grading_policy": "ensemble", "artifacts": [{"bundle_id": "gp7-ancestry-logei-hard14-full-logs-20260917", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917/logs-77c0e49ab8d6.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917", "member": "results/official_private_grades.jsonl:66", "sha256": "77c0e49ab8d6df7268cefe20565a32eaa589661c5946ef2499c567afceab8104"}, {"bundle_id": "gp7-no-ancestry-logei-hard14-full-logs-20260917", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-no-ancestry-logei-hard14-full-logs-20260917/logs-5cb1f19bf4da.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-no-ancestry-logei-hard14-full-logs-20260917", "member": "gp7_no_ancestry_logei-hard14/runs/05_leaf-classification/logs/journal.json", "sha256": "5cb1f19bf4da2d6fd6b6aea2a936a5ebe2ad2c67f0a46cbfeed510ddf38aef8d"}], "alternate_scores": [{"cohort": "09-17", "workflow_id": "09-17 gp7_no_ancestry_logei", "method": "gp7_no_ancestry_logei", "task": "leaf-classification", "policy": "best_node", "status": "graded", "valid_submission": true, "score": 7.89896, "medal": "none", "is_lower_better": true, "gold_threshold": 0.0, "silver_threshold": 0.00791, "bronze_threshold": 0.01526, "submission_sha256": "cb5793e687dbb302d915d60a1ff7e34de6d1f70ce07e42668bd0d056da8525c2", "source_archive": "gp7_ancestry_logei_hard14_full_logs_20260917.zip", "source_member": "results/official_private_grades.jsonl", "source_line": 65}], "journal_ref": "gp7-no-ancestry-logei-hard14-full-logs-20260917:gp7_no_ancestry_logei-hard14/runs/05_leaf-classification/logs/journal.json", "metrics": [{"event_id": "8349c18427ed454f966efb60e59a62eb", "step": 2, "value": 0.057425744305750814, "stage": "draft", "created_at": 1789626509.1869037}, {"event_id": "c5979a7b4dff4a52b5cdcb0f7133791e", "step": 5, "value": 0.0441080486329071, "stage": "draft", "created_at": 1789626239.8145342}, {"event_id": "64103920ebcd43ae99353994db55a396", "step": 6, "value": 0.010546497576285823, "stage": "debug", "created_at": 1789627530.8962557}, {"event_id": "800cfe808047437283a108f36b5af035", "step": 8, "value": 0.04913842679246766, "stage": "improve", "created_at": 1789627680.9300454}, {"event_id": "4ac3183d01174c0d95304fcbcf585195", "step": 9, "value": 0.19712389275222925, "stage": "debug", "created_at": 1789627998.2969854}, {"event_id": "9ea63f4ac87045d0af2a4dddf4b32cd3", "step": 10, "value": 0.007472834773347772, "stage": "improve", "created_at": 1789628101.2351563}, {"event_id": "1030192d7f984720abf5b8a6987940e8", "step": 11, "value": 0.016951733564178298, "stage": "improve", "created_at": 1789628240.7798216}, {"event_id": "090cafe32bfc4bb293509912625b0a06", "step": 13, "value": 0.20829075203604894, "stage": "improve", "created_at": 1789628575.5043685}, {"event_id": "c434514efd1848718ff997b21c05ee37", "step": 14, "value": 0.005602246144466607, "stage": "improve", "created_at": 1789629161.3750608}, {"event_id": "97cc9165e397496aafaffca8e727a713", "step": 15, "value": 0.01051161215444736, "stage": "debug", "created_at": 1789629522.059797}, {"event_id": "b6ac7be84041425f8ac3db65e663ae32", "step": 18, "value": 2.175922429435348, "stage": "debug", "created_at": 1789631092.6872203}, {"event_id": "6bfb67dfd95045eab0e307987918dd18", "step": 19, "value": 0.129306080998364, "stage": "improve", "created_at": 1789633599.2186823}, {"event_id": "df0cb17b19284837ab639b0905c88a64", "step": 21, "value": 0.03497101284978537, "stage": "fusion_draft", "created_at": 1789651954.8647556}], "maximize": false, "elapsed_seconds": 28764.95996904373, "node_count": 23, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-hard14-20260917/xixian.gp7-no-ancestry-logei.leaf-classification.yaml", "note": ""}, {"id": "xixian.gp7-no-ancestry-logei.mlsp-2013-birds", "experiment_id": "mlebench-gp7-hard14-20260917", "family": "MLEBench", "method": "gp7_no_ancestry_logei", "dataset": "mlsp-2013-birds", "status": "archived", "official_score": 0.88053, "medal": "bronze", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.93527, "silver": 0.90038, "bronze": 0.87372}, "grading_policy": "ensemble", "artifacts": [{"bundle_id": "gp7-ancestry-logei-hard14-full-logs-20260917", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917/logs-77c0e49ab8d6.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917", "member": "results/official_private_grades.jsonl:68", "sha256": "77c0e49ab8d6df7268cefe20565a32eaa589661c5946ef2499c567afceab8104"}, {"bundle_id": "gp7-no-ancestry-logei-hard14-full-logs-20260917", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-no-ancestry-logei-hard14-full-logs-20260917/logs-5cb1f19bf4da.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-no-ancestry-logei-hard14-full-logs-20260917", "member": "gp7_no_ancestry_logei-hard14/runs/06_mlsp-2013-birds/logs/journal.json", "sha256": "5cb1f19bf4da2d6fd6b6aea2a936a5ebe2ad2c67f0a46cbfeed510ddf38aef8d"}], "alternate_scores": [{"cohort": "09-17", "workflow_id": "09-17 gp7_no_ancestry_logei", "method": "gp7_no_ancestry_logei", "task": "mlsp-2013-birds", "policy": "best_node", "status": "graded", "valid_submission": true, "score": 0.87852, "medal": "bronze", "is_lower_better": false, "gold_threshold": 0.93527, "silver_threshold": 0.90038, "bronze_threshold": 0.87372, "submission_sha256": "63cdbff00570fb82c9fa0395ae51b7727e12126b277320c0542f59de787de52e", "source_archive": "gp7_ancestry_logei_hard14_full_logs_20260917.zip", "source_member": "results/official_private_grades.jsonl", "source_line": 67}], "journal_ref": "gp7-no-ancestry-logei-hard14-full-logs-20260917:gp7_no_ancestry_logei-hard14/runs/06_mlsp-2013-birds/logs/journal.json", "metrics": [{"event_id": "e6d7f4f0a36745ecb06709dca7b548db", "step": 10, "value": 0.7800491533542999, "stage": "debug", "created_at": 1789627692.857995}, {"event_id": "f8b103298e324c5cb141cbdf3224ec61", "step": 11, "value": 0.758670322138451, "stage": "debug", "created_at": 1789627659.6452863}, {"event_id": "30ac056bbe714f10886485b21d1f2e46", "step": 13, "value": 0.79202507654177, "stage": "improve", "created_at": 1789628103.473164}, {"event_id": "bbb9541ac170445baf3dad2817c8d21d", "step": 14, "value": 0.814810572136713, "stage": "improve", "created_at": 1789628107.820161}, {"event_id": "47360fea907445f8a009db95969d77ef", "step": 15, "value": 0.767347732211415, "stage": "improve", "created_at": 1789628180.0751767}, {"event_id": "90dd14ff51ec4fdc845d3940d362a4a7", "step": 16, "value": 0.7900915724213581, "stage": "improve", "created_at": 1789628468.419938}, {"event_id": "5aee378a0f2046c2aa9b869fdb5ad627", "step": 17, "value": 0.8047091412742382, "stage": "improve", "created_at": 1789628479.2767575}, {"event_id": "a3c3b6e56acf4c6f8c064bfa81361646", "step": 18, "value": 0.8240164122216899, "stage": "improve", "created_at": 1789628558.0411174}, {"event_id": "0d79a8fdcdc7432dbd08a510af6fad2b", "step": 19, "value": 0.7818229784988786, "stage": "improve", "created_at": 1789628893.5870793}, {"event_id": "776afff1090742109d68204fcf7012f4", "step": 20, "value": 0.8749019362811461, "stage": "evolution", "created_at": 1789628849.4182038}, {"event_id": "4d735886bfca4ebfba7652458b199084", "step": 21, "value": 0.7862072077701178, "stage": "improve", "created_at": 1789629275.3672035}, {"event_id": "c9f865e5f8b249ef95af13153bd7cc11", "step": 22, "value": 0.8594875423783024, "stage": "improve", "created_at": 1789628811.354344}, {"event_id": "b253690d700143fe9c5d385f489b85aa", "step": 25, "value": 0.8747214296128132, "stage": "improve", "created_at": 1789629597.2184894}, {"event_id": "9e6551b0052a4f078c9e1de17556ea29", "step": 27, "value": 0.8785259547761369, "stage": "improve", "created_at": 1789629650.777972}, {"event_id": "83e3170fc75f4d75bd8eab1b2c46c762", "step": 28, "value": 0.8808517137719645, "stage": "debug", "created_at": 1789630247.0879183}, {"event_id": "bbd9f79e454a4f90b2ff620f47dcccb3", "step": 30, "value": 0.8571567422711904, "stage": "debug", "created_at": 1789630584.6442106}, {"event_id": "29d5c4484e574bfe869da8391254ca85", "step": 32, "value": 0.8505404786203736, "stage": "improve", "created_at": 1789631140.4605193}, {"event_id": "38d9ec17311545cd8e2b9f34f85a2a80", "step": 35, "value": 0.8434035226570581, "stage": "debug", "created_at": 1789631145.6730044}, {"event_id": "115bbcea6abc4ca7841ca0847cf3e04b", "step": 37, "value": 0.8823235373752941, "stage": "debug", "created_at": 1789632098.2704413}, {"event_id": "7855401cf8164a24a2bdb42d3fbf0921", "step": 38, "value": 0.8045529335804885, "stage": "debug", "created_at": 1789632457.373849}, {"event_id": "1f4bb570fd3a4521b64075c4446b5617", "step": 39, "value": 0.8780052624636383, "stage": "debug", "created_at": 1789632940.971991}, {"event_id": "1f050eb9c8ac429b8c999d405746fd76", "step": 40, "value": 0.8815043148036296, "stage": "improve", "created_at": 1789633166.593032}, {"event_id": "79eb8347aa4042ddb1f0f7c269509669", "step": 42, "value": 0.8864265927977839, "stage": "improve", "created_at": 1789633467.2523103}, {"event_id": "7f67691e80e14ce983de66441c664aee", "step": 43, "value": 0.884684009191955, "stage": "improve", "created_at": 1789634066.9589097}, {"event_id": "88202c65bfb94cd684c5b60249f369dd", "step": 44, "value": 0.8838578440561238, "stage": "improve", "created_at": 1789634665.8302972}, {"event_id": "c1923bdc5fa9454895cf1dfe849af40d", "step": 45, "value": 0.8925430179747968, "stage": "debug", "created_at": 1789634455.473946}, {"event_id": "104a5e9a89a34cc286dc1f88bb1da492", "step": 47, "value": 0.8828372871236262, "stage": "improve", "created_at": 1789635497.18209}, {"event_id": "7b556c8857ae4b79a6220fc8058d51d7", "step": 48, "value": 0.8856559681752858, "stage": "improve", "created_at": 1789635226.2975912}, {"event_id": "2ca9b2668bfd446ca191b2b9a1d5e305", "step": 52, "value": 0.8927661037548776, "stage": "improve", "created_at": 1789636482.754864}, {"event_id": "9468681173f64b6d89347067a1cb24e3", "step": 53, "value": 0.8914299878462228, "stage": "debug", "created_at": 1789637425.5537927}, {"event_id": "d70f6109846d4644ade26f630dffd417", "step": 54, "value": 0.8861103115205015, "stage": "debug", "created_at": 1789636891.1651406}, {"event_id": "1ea15c9c0091409a934e102174b1a44b", "step": 56, "value": 0.9040955031024116, "stage": "improve", "created_at": 1789637605.612648}, {"event_id": "44683b1c0eb944daa6e329944bf481b2", "step": 58, "value": 0.8980801829463316, "stage": "improve", "created_at": 1789638508.4749482}, {"event_id": "c646b8dc43d84bd7991cc0576440b941", "step": 59, "value": 0.8915491268470543, "stage": "improve", "created_at": 1789639378.674954}, {"event_id": "364a5eddeb6740de9663fbafad9defa0", "step": 61, "value": 0.8934641463570652, "stage": "improve", "created_at": 1789639580.662243}, {"event_id": "ad4a61b9b8434c4eae088a6723257dc3", "step": 63, "value": 0.8819620354378559, "stage": "debug", "created_at": 1789641140.8261707}, {"event_id": "eec23e72a5f24641831b58cc72037ee2", "step": 65, "value": 0.7773989033584646, "stage": "debug", "created_at": 1789642663.8872006}, {"event_id": "bd3e61efe2c5443a828d31a91c810347", "step": 67, "value": 0.9007931938847311, "stage": "debug", "created_at": 1789641534.895649}, {"event_id": "6757f80c845541d2b4dcad2c404975b8", "step": 71, "value": 0.8632068380988933, "stage": "fusion", "created_at": 1789643519.5142477}, {"event_id": "78cb7123c9ae4224ad579e9a83580042", "step": 72, "value": 0.8982432994306915, "stage": "fusion", "created_at": 1789644281.8087142}, {"event_id": "68dd533a8e15409793ddfcd971dd29d9", "step": 73, "value": 0.8972414123968528, "stage": "debug", "created_at": 1789643892.5227442}, {"event_id": "f9657f24e0394220b99d0fd8dccf7081", "step": 75, "value": 0.9040955031024116, "stage": "fusion", "created_at": 1789645421.7085435}, {"event_id": "bbe658e1549b45659c136020d550f588", "step": 76, "value": 0.8992443868739206, "stage": "fusion", "created_at": 1789646452.7689266}, {"event_id": "8a26bf3bc0b3440dac92684e77598eac", "step": 79, "value": 0.8935225164715667, "stage": "improve", "created_at": 1789647688.155523}, {"event_id": "4d96ae67f2454aa2bbc18eb40ac09d7e", "step": 80, "value": 0.8863022132668074, "stage": "debug", "created_at": 1789648742.8918662}, {"event_id": "962efb164c8c461c92d91bb9acac53d5", "step": 81, "value": 0.8905384443165099, "stage": "improve", "created_at": 1789649436.040295}, {"event_id": "be9f5a5deeca409ca3a40ec6884f53ff", "step": 82, "value": 0.744131254283756, "stage": "debug", "created_at": 1789646861.8815844}, {"event_id": "d2b11b91ffed40269f0210b36e440126", "step": 83, "value": 0.9392958805091792, "stage": "evolution", "created_at": 1789650103.902654}, {"event_id": "682538e4e4d349e087907f1939bc77e5", "step": 84, "value": 0.8836443740804708, "stage": "fusion", "created_at": 1789650990.6837056}, {"event_id": "12be6a45dea24f2cbeef85a43366cbc3", "step": 85, "value": 0.8949202008571612, "stage": "evolution", "created_at": 1789651908.2544177}, {"event_id": "7b7062cf551f4d6bbae46ec8c8a80e2f", "step": 86, "value": 0.9381092880445213, "stage": "improve", "created_at": 1789652143.5731318}], "maximize": true, "elapsed_seconds": 28742.096148967743, "node_count": 88, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-hard14-20260917/xixian.gp7-no-ancestry-logei.mlsp-2013-birds.yaml", "note": ""}, {"id": "xixian.gp7-no-ancestry-logei.new-york-city-taxi-fare-prediction", "experiment_id": "mlebench-gp7-hard14-20260917", "family": "MLEBench", "method": "gp7_no_ancestry_logei", "dataset": "new-york-city-taxi-fare-prediction", "status": "archived", "official_score": 5.72698, "medal": "none", "valid_submission": true, "score_maximize": false, "thresholds": {"gold": 2.83377, "silver": 2.88191, "bronze": 2.92371}, "grading_policy": "ensemble", "artifacts": [{"bundle_id": "gp7-ancestry-logei-hard14-full-logs-20260917", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917/logs-77c0e49ab8d6.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917", "member": "results/official_private_grades.jsonl:70", "sha256": "77c0e49ab8d6df7268cefe20565a32eaa589661c5946ef2499c567afceab8104"}, {"bundle_id": "gp7-no-ancestry-logei-hard14-full-logs-20260917", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-no-ancestry-logei-hard14-full-logs-20260917/logs-5cb1f19bf4da.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-no-ancestry-logei-hard14-full-logs-20260917", "member": "gp7_no_ancestry_logei-hard14/runs/07_new-york-city-taxi-fare-prediction/logs/journal.json", "sha256": "5cb1f19bf4da2d6fd6b6aea2a936a5ebe2ad2c67f0a46cbfeed510ddf38aef8d"}], "alternate_scores": [{"cohort": "09-17", "workflow_id": "09-17 gp7_no_ancestry_logei", "method": "gp7_no_ancestry_logei", "task": "new-york-city-taxi-fare-prediction", "policy": "best_node", "status": "graded", "valid_submission": true, "score": 6.35423, "medal": "none", "is_lower_better": true, "gold_threshold": 2.83377, "silver_threshold": 2.88191, "bronze_threshold": 2.92371, "submission_sha256": "3fc0a1c582b7babd0619c6b9acc0bc1e6bb19f1e967f3d7cb59e23bc565cd686", "source_archive": "gp7_ancestry_logei_hard14_full_logs_20260917.zip", "source_member": "results/official_private_grades.jsonl", "source_line": 69}], "journal_ref": "gp7-no-ancestry-logei-hard14-full-logs-20260917:gp7_no_ancestry_logei-hard14/runs/07_new-york-city-taxi-fare-prediction/logs/journal.json", "metrics": [{"event_id": "63fe7c134fca4a3f89bc777510c47e5a", "step": 2, "value": 10.673357613428898, "stage": "draft", "created_at": 1789626633.2105653}, {"event_id": "cdbe397bbf0c4d1aa2d466c3ba0ce677", "step": 6, "value": 3.6850381165478, "stage": "debug", "created_at": 1789628275.6039174}, {"event_id": "66d00efa468c4dbb82abfd26eeb7764a", "step": 7, "value": 3.355474524434123, "stage": "debug", "created_at": 1789628430.7069113}, {"event_id": "33c1f2359dd9452ba6f6e3f51d8f634d", "step": 8, "value": 3.412328449073833, "stage": "improve", "created_at": 1789629023.322533}, {"event_id": "52514843486f4a65922d8d11ff08bbca", "step": 9, "value": 3.028243982542668, "stage": "improve", "created_at": 1789630077.9344823}, {"event_id": "8f34db54723645bd850516a33871e2a9", "step": 10, "value": 3.094722271575528, "stage": "improve", "created_at": 1789630687.4383404}, {"event_id": "aafc5fb056984487aef76c4dc29450b3", "step": 11, "value": 2.777295344538999, "stage": "improve", "created_at": 1789631052.1154935}, {"event_id": "66894575cf624d4abaa96d214b812845", "step": 12, "value": 3.0369173699574725, "stage": "improve", "created_at": 1789632405.9956403}, {"event_id": "f2b3797486d84ea1994f6f48c18b2064", "step": 14, "value": 3.922649641733437, "stage": "debug", "created_at": 1789634170.021788}, {"event_id": "3140f7c1280241bfae3bab79fdaf61d9", "step": 15, "value": 3.0945760489389853, "stage": "improve", "created_at": 1789632506.1978261}, {"event_id": "35d307698d45470596ca8d2cfe8f545b", "step": 16, "value": 3.2196948444549878, "stage": "improve", "created_at": 1789636365.0802386}, {"event_id": "cda97e269fe5478fb9d20ed61de05285", "step": 18, "value": 4.494452344795448, "stage": "debug", "created_at": 1789638762.3714721}, {"event_id": "73dc651465a941b1a096ec921bd368f5", "step": 19, "value": 2.6882224919051145, "stage": "evolution", "created_at": 1789636293.022221}, {"event_id": "31bb2b1b3e9e48238fee2d7493bd1206", "step": 21, "value": 3.307060687435014, "stage": "debug", "created_at": 1789645920.498025}, {"event_id": "0088ea2ea9ed40ef8854289115b8e433", "step": 23, "value": 3.1439579787967205, "stage": "improve", "created_at": 1789647291.9598398}, {"event_id": "97a4877d57044e4080ac565c9b14d9fb", "step": 24, "value": 2.736402289654783, "stage": "evolution", "created_at": 1789639432.538587}, {"event_id": "2531a52aa53c44169c815d0b7ffe3ec1", "step": 25, "value": 3.1697281526983505, "stage": "improve", "created_at": 1789649740.6096053}], "maximize": false, "elapsed_seconds": 28742.165578842163, "node_count": 27, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-hard14-20260917/xixian.gp7-no-ancestry-logei.new-york-city-taxi-fare-prediction.yaml", "note": ""}, {"id": "xixian.gp7-no-ancestry-logei.nomad2018-predict-transparent-conductors", "experiment_id": "mlebench-gp7-hard14-20260917", "family": "MLEBench", "method": "gp7_no_ancestry_logei", "dataset": "nomad2018-predict-transparent-conductors", "status": "archived", "official_score": 0.0651, "medal": "bronze", "valid_submission": true, "score_maximize": false, "thresholds": {"gold": 0.05589, "silver": 0.06229, "bronze": 0.06582}, "grading_policy": "ensemble", "artifacts": [{"bundle_id": "gp7-ancestry-logei-hard14-full-logs-20260917", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917/logs-77c0e49ab8d6.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917", "member": "results/official_private_grades.jsonl:72", "sha256": "77c0e49ab8d6df7268cefe20565a32eaa589661c5946ef2499c567afceab8104"}, {"bundle_id": "gp7-no-ancestry-logei-hard14-full-logs-20260917", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-no-ancestry-logei-hard14-full-logs-20260917/logs-5cb1f19bf4da.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-no-ancestry-logei-hard14-full-logs-20260917", "member": "gp7_no_ancestry_logei-hard14/runs/08_nomad2018-predict-transparent-conductors/logs/journal.json", "sha256": "5cb1f19bf4da2d6fd6b6aea2a936a5ebe2ad2c67f0a46cbfeed510ddf38aef8d"}], "alternate_scores": [{"cohort": "09-17", "workflow_id": "09-17 gp7_no_ancestry_logei", "method": "gp7_no_ancestry_logei", "task": "nomad2018-predict-transparent-conductors", "policy": "best_node", "status": "graded", "valid_submission": true, "score": 0.06475, "medal": "bronze", "is_lower_better": true, "gold_threshold": 0.05589, "silver_threshold": 0.06229, "bronze_threshold": 0.06582, "submission_sha256": "b2136807186ed61044236fcde77c17dd5a068d2987d4e756a4d60b6139572bfc", "source_archive": "gp7_ancestry_logei_hard14_full_logs_20260917.zip", "source_member": "results/official_private_grades.jsonl", "source_line": 71}], "journal_ref": "gp7-no-ancestry-logei-hard14-full-logs-20260917:gp7_no_ancestry_logei-hard14/runs/08_nomad2018-predict-transparent-conductors/logs/journal.json", "metrics": [{"event_id": "add4d870043f4e65824c5a3771e79afc", "step": 4, "value": 0.18525067214109953, "stage": "debug", "created_at": 1789626971.0808814}, {"event_id": "83095dee3d1f45f58ac3123d5f507839", "step": 5, "value": 0.07477027820589001, "stage": "debug", "created_at": 1789626982.737499}, {"event_id": "5d3c2b030f4b4872a045bcaf60399874", "step": 6, "value": 0.18617167237621268, "stage": "debug", "created_at": 1789626978.7436726}, {"event_id": "d4d4d9199d6448e599dca1050ac29a91", "step": 7, "value": 0.18507380609054197, "stage": "improve", "created_at": 1789627340.9557962}, {"event_id": "5b0cd3b288974103886d85391f81df92", "step": 8, "value": 0.0638304915724407, "stage": "improve", "created_at": 1789627408.5748768}, {"event_id": "7403ddcb4f2346fe8a77cc2a2bd12f28", "step": 9, "value": 0.06375519761443378, "stage": "improve", "created_at": 1789627676.6128962}, {"event_id": "c97e70792a134495b9ec791c2dd6725e", "step": 10, "value": 0.07209612092254547, "stage": "improve", "created_at": 1789627404.6933885}, {"event_id": "eaecc940bebd4d809d1c3869ea6c450f", "step": 11, "value": 0.06375519761443378, "stage": "improve", "created_at": 1789629400.0522783}, {"event_id": "59f28b7ed2cb4671a935bf766e8f6f4f", "step": 12, "value": 0.06375519761443378, "stage": "improve", "created_at": 1789629711.1773288}, {"event_id": "5cc5ea7d2093465fb1a394b5e53435a9", "step": 13, "value": 0.06442393940022924, "stage": "improve", "created_at": 1789627832.6682148}, {"event_id": "d3f28e1dd06d452ebe71599ecb37e010", "step": 14, "value": 0.18547024359552194, "stage": "draft", "created_at": 1789633241.4759068}], "maximize": false, "elapsed_seconds": 28749.135685920715, "node_count": 16, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-hard14-20260917/xixian.gp7-no-ancestry-logei.nomad2018-predict-transparent-conductors.yaml", "note": ""}, {"id": "xixian.gp7-no-ancestry-logei.random-acts-of-pizza", "experiment_id": "mlebench-gp7-hard14-20260917", "family": "MLEBench", "method": "gp7_no_ancestry_logei", "dataset": "random-acts-of-pizza", "status": "archived", "official_score": 0.65906, "medal": "none", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.97908, "silver": 0.76482, "bronze": 0.6921}, "grading_policy": "ensemble", "artifacts": [{"bundle_id": "gp7-ancestry-logei-hard14-full-logs-20260917", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917/logs-77c0e49ab8d6.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917", "member": "results/official_private_grades.jsonl:74", "sha256": "77c0e49ab8d6df7268cefe20565a32eaa589661c5946ef2499c567afceab8104"}, {"bundle_id": "gp7-no-ancestry-logei-hard14-full-logs-20260917", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-no-ancestry-logei-hard14-full-logs-20260917/logs-5cb1f19bf4da.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-no-ancestry-logei-hard14-full-logs-20260917", "member": "gp7_no_ancestry_logei-hard14/runs/09_random-acts-of-pizza/logs/journal.json", "sha256": "5cb1f19bf4da2d6fd6b6aea2a936a5ebe2ad2c67f0a46cbfeed510ddf38aef8d"}], "alternate_scores": [{"cohort": "09-17", "workflow_id": "09-17 gp7_no_ancestry_logei", "method": "gp7_no_ancestry_logei", "task": "random-acts-of-pizza", "policy": "best_node", "status": "graded", "valid_submission": true, "score": 0.65695, "medal": "none", "is_lower_better": false, "gold_threshold": 0.97908, "silver_threshold": 0.76482, "bronze_threshold": 0.6921, "submission_sha256": "518d278b0244dad2443f3e7b9b217fc49f09f465abf430947633d3039239906b", "source_archive": "gp7_ancestry_logei_hard14_full_logs_20260917.zip", "source_member": "results/official_private_grades.jsonl", "source_line": 73}], "journal_ref": "gp7-no-ancestry-logei-hard14-full-logs-20260917:gp7_no_ancestry_logei-hard14/runs/09_random-acts-of-pizza/logs/journal.json", "metrics": [{"event_id": "5c752d29f30f4f4283f34a3ad65070fa", "step": 3, "value": 0.6816141787015574, "stage": "draft", "created_at": 1789626268.5750954}, {"event_id": "dc5300fd879c4aadb1bfffda74cbcb13", "step": 5, "value": 0.6663302055911755, "stage": "debug", "created_at": 1789627015.2408214}, {"event_id": "27230a1214864e40b478e32dad9c759d", "step": 6, "value": 0.6973602449330605, "stage": "improve", "created_at": 1789627196.4747667}, {"event_id": "45d8ff2a1eb24a239c9d213232dca588", "step": 7, "value": 0.6198180350722724, "stage": "debug", "created_at": 1789627169.7228804}, {"event_id": "b584a6c727ab457a8b0e15c86f92dcd0", "step": 8, "value": 0.6554530919426994, "stage": "improve", "created_at": 1789627314.9307153}, {"event_id": "4da37613f21e44bd8313333082be49bf", "step": 9, "value": 0.6655616228431762, "stage": "improve", "created_at": 1789627462.5252924}, {"event_id": "4774d43b029e4854a01b29d26ad06ea6", "step": 14, "value": 0.6939229055733911, "stage": "improve", "created_at": 1789627547.8004363}, {"event_id": "e2e50f15e7a54ba7addfeb3efa92e83c", "step": 15, "value": 0.68671199350811, "stage": "improve", "created_at": 1789627748.083013}, {"event_id": "e980f737622143fd81c2cb25de443a73", "step": 16, "value": 0.6930745629774756, "stage": "improve", "created_at": 1789628134.617976}, {"event_id": "4ebf8f04d5cd4756a296cac073caa80f", "step": 17, "value": 0.7015961384893423, "stage": "improve", "created_at": 1789628308.6722486}, {"event_id": "8737a47464084729aef7319f2ec2ce7a", "step": 19, "value": 0.7069881574735944, "stage": "evolution", "created_at": 1789628284.4534457}, {"event_id": "7d3c65e049394b7ea91f3047f0f0b7c8", "step": 20, "value": 0.6974061537168333, "stage": "improve", "created_at": 1789628795.2467623}, {"event_id": "c975eb6179194f75ae7ffc44d8f61b6b", "step": 21, "value": 0.7031932468825672, "stage": "improve", "created_at": 1789629548.6369512}, {"event_id": "379c6a128cbe4574b1ba3413ef780514", "step": 22, "value": 0.7132737812349463, "stage": "improve", "created_at": 1789630033.7968473}, {"event_id": "16dd82e9018b4978953e26b9d61ed509", "step": 23, "value": 0.7119747566349508, "stage": "improve", "created_at": 1789629283.27353}, {"event_id": "e3556ed362894ecb95b24122ab7c2265", "step": 24, "value": 0.7184103921968, "stage": "improve", "created_at": 1789630516.0410888}, {"event_id": "1687d0acce7e4ddbaa84e5c3d1e7acc2", "step": 25, "value": 0.7134606493829794, "stage": "improve", "created_at": 1789630691.2243533}, {"event_id": "d5a9b4046d534450877e2a477e6918aa", "step": 26, "value": 0.7114290240503832, "stage": "improve", "created_at": 1789631053.7678013}, {"event_id": "3de29a63cc724902acbd99100421f3f8", "step": 27, "value": 0.7170085577852567, "stage": "improve", "created_at": 1789631331.2974179}, {"event_id": "9e7c31a19582453fb44869563e16a088", "step": 28, "value": 0.691930722998684, "stage": "improve", "created_at": 1789631596.2170103}, {"event_id": "358ffe23fe1042b4b712c1dc63e8d7d2", "step": 29, "value": 0.7105412386965785, "stage": "evolution", "created_at": 1789632174.7265172}, {"event_id": "00e0e450de22458aa5aa0493a7864942", "step": 30, "value": 0.7100524071397858, "stage": "evolution", "created_at": 1789632428.9141774}, {"event_id": "adc2b07005864cc099983186edc10ce7", "step": 31, "value": 0.7045937880889337, "stage": "evolution", "created_at": 1789633543.9614654}, {"event_id": "a2abc3fd4b81412798ada1236e6be2b1", "step": 32, "value": 0.6956318762144005, "stage": "evolution", "created_at": 1789633861.1272447}, {"event_id": "5eecc95f80474c378c22c6e67cd01426", "step": 33, "value": 0.7058190999938573, "stage": "evolution", "created_at": 1789635948.3138893}, {"event_id": "a9c8d6f05bbb42da9c6ef8625adf2581", "step": 34, "value": 0.8215357458075907, "stage": "evolution", "created_at": 1789636297.8929644}, {"event_id": "31fd84c00b3e407182cb433272e1d8c2", "step": 35, "value": 0.8190599044967977, "stage": "improve", "created_at": 1789638572.1570935}, {"event_id": "f02d92c7cb0a459395a5c3fd6e6de266", "step": 36, "value": 0.8224299971872787, "stage": "improve", "created_at": 1789640072.3124127}, {"event_id": "dbe1da6e9cd14ec987c0dbcc9be34a7b", "step": 37, "value": 0.822133206599226, "stage": "improve", "created_at": 1789641361.5478125}, {"event_id": "13b424cb6b8344e587fdf15fd6b781c5", "step": 38, "value": 0.7143933736166747, "stage": "evolution", "created_at": 1789632573.2584004}, {"event_id": "7727814a904745e58861ce2e8b3c3136", "step": 40, "value": 0.8228425296386461, "stage": "improve", "created_at": 1789643558.3108766}, {"event_id": "0b99363793c049f98dfa66b809deb5af", "step": 41, "value": 0.8244034282869235, "stage": "debug", "created_at": 1789644769.4864922}, {"event_id": "5ec303449ad746a1a855e6360ecffc08", "step": 42, "value": 0.8068478447119223, "stage": "improve", "created_at": 1789646627.7354808}, {"event_id": "7ba4b970cef24c3ca090193861cd43fd", "step": 43, "value": 0.82170838869868, "stage": "improve", "created_at": 1789646455.0489733}, {"event_id": "2d8becda1a0c42b1b8ce313599e63f07", "step": 45, "value": 0.6654044984142072, "stage": "improve", "created_at": 1789648656.5413592}, {"event_id": "c03fab29e9e240ef89305d84bb874a0c", "step": 49, "value": 0.6820538684616354, "stage": "fusion_draft", "created_at": 1789650162.2968326}, {"event_id": "b014127fcdc84073b12c515e1871c7f1", "step": 51, "value": 0.8325341766305878, "stage": "evolution", "created_at": 1789650146.798634}, {"event_id": "a7e84c0616de40f39d1fb76adcb9abb9", "step": 52, "value": 0.8223071426954922, "stage": "improve", "created_at": 1789650972.9364264}, {"event_id": "42f7afd6ef914cac9ed0476d373756ad", "step": 53, "value": 0.6901700241506067, "stage": "improve", "created_at": 1789651222.91279}], "maximize": true, "elapsed_seconds": 28756.875290632248, "node_count": 54, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-hard14-20260917/xixian.gp7-no-ancestry-logei.random-acts-of-pizza.yaml", "note": ""}, {"id": "xixian.gp7-no-ancestry-logei.ranzcr-clip-catheter-line-classification", "experiment_id": "mlebench-gp7-hard14-20260917", "family": "MLEBench", "method": "gp7_no_ancestry_logei", "dataset": "ranzcr-clip-catheter-line-classification", "status": "archived", "official_score": 0.74469, "medal": "none", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.97357, "silver": 0.97152, "bronze": 0.9709}, "grading_policy": "ensemble", "artifacts": [{"bundle_id": "gp7-ancestry-logei-hard14-full-logs-20260917", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917/logs-77c0e49ab8d6.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917", "member": "results/official_private_grades.jsonl:76", "sha256": "77c0e49ab8d6df7268cefe20565a32eaa589661c5946ef2499c567afceab8104"}, {"bundle_id": "gp7-no-ancestry-logei-hard14-full-logs-20260917", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-no-ancestry-logei-hard14-full-logs-20260917/logs-5cb1f19bf4da.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-no-ancestry-logei-hard14-full-logs-20260917", "member": "gp7_no_ancestry_logei-hard14/runs/10_ranzcr-clip-catheter-line-classification/logs/journal.json", "sha256": "5cb1f19bf4da2d6fd6b6aea2a936a5ebe2ad2c67f0a46cbfeed510ddf38aef8d"}], "alternate_scores": [{"cohort": "09-17", "workflow_id": "09-17 gp7_no_ancestry_logei", "method": "gp7_no_ancestry_logei", "task": "ranzcr-clip-catheter-line-classification", "policy": "best_node", "status": "graded", "valid_submission": true, "score": 0.72563, "medal": "none", "is_lower_better": false, "gold_threshold": 0.97357, "silver_threshold": 0.97152, "bronze_threshold": 0.9709, "submission_sha256": "c1f0fade34329d35b1027529e4d4d006474c3e5ef624c6987b20c13704c20e4e", "source_archive": "gp7_ancestry_logei_hard14_full_logs_20260917.zip", "source_member": "results/official_private_grades.jsonl", "source_line": 75}], "journal_ref": "gp7-no-ancestry-logei-hard14-full-logs-20260917:gp7_no_ancestry_logei-hard14/runs/10_ranzcr-clip-catheter-line-classification/logs/journal.json", "metrics": [{"event_id": "d3ce3807238c471698ef4afbc41b89b6", "step": 2, "value": 0.6877594310287356, "stage": "draft", "created_at": 1789626572.1432047}, {"event_id": "7234044ae9434d11a316cdc6780a5562", "step": 3, "value": 0.6807067239244673, "stage": "draft", "created_at": 1789626259.2737508}, {"event_id": "741659b86af64f269d431980854c4443", "step": 5, "value": 0.6877594310287356, "stage": "improve", "created_at": 1789631894.8538468}, {"event_id": "8d40f90a661c40e9a32ee762a758efdc", "step": 7, "value": 0.7384269588607014, "stage": "debug", "created_at": 1789628282.2924454}, {"event_id": "89c2b97bf4bd4b48ba6b7df023e7e0ae", "step": 9, "value": 0.7601575440086192, "stage": "debug", "created_at": 1789637953.4498556}], "maximize": true, "elapsed_seconds": 28742.542182207108, "node_count": 11, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-hard14-20260917/xixian.gp7-no-ancestry-logei.ranzcr-clip-catheter-line-classification.yaml", "note": ""}, {"id": "xixian.gp7-no-ancestry-logei.siim-isic-melanoma-classification", "experiment_id": "mlebench-gp7-hard14-20260917", "family": "MLEBench", "method": "gp7_no_ancestry_logei", "dataset": "siim-isic-melanoma-classification", "status": "archived", "official_score": 0.8373, "medal": "none", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.9455, "silver": 0.9401, "bronze": 0.937}, "grading_policy": "ensemble", "artifacts": [{"bundle_id": "gp7-ancestry-logei-hard14-full-logs-20260917", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917/logs-77c0e49ab8d6.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917", "member": "results/official_private_grades.jsonl:78", "sha256": "77c0e49ab8d6df7268cefe20565a32eaa589661c5946ef2499c567afceab8104"}, {"bundle_id": "gp7-no-ancestry-logei-hard14-full-logs-20260917", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-no-ancestry-logei-hard14-full-logs-20260917/logs-5cb1f19bf4da.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-no-ancestry-logei-hard14-full-logs-20260917", "member": "gp7_no_ancestry_logei-hard14/runs/11_siim-isic-melanoma-classification/logs/journal.json", "sha256": "5cb1f19bf4da2d6fd6b6aea2a936a5ebe2ad2c67f0a46cbfeed510ddf38aef8d"}], "alternate_scores": [{"cohort": "09-17", "workflow_id": "09-17 gp7_no_ancestry_logei", "method": "gp7_no_ancestry_logei", "task": "siim-isic-melanoma-classification", "policy": "best_node", "status": "graded", "valid_submission": true, "score": 0.83738, "medal": "none", "is_lower_better": false, "gold_threshold": 0.9455, "silver_threshold": 0.9401, "bronze_threshold": 0.937, "submission_sha256": "ccbe82405905ffae7ad241b781add448c23d389edc296b2c608e7b897721a337", "source_archive": "gp7_ancestry_logei_hard14_full_logs_20260917.zip", "source_member": "results/official_private_grades.jsonl", "source_line": 77}], "journal_ref": "gp7-no-ancestry-logei-hard14-full-logs-20260917:gp7_no_ancestry_logei-hard14/runs/11_siim-isic-melanoma-classification/logs/journal.json", "metrics": [{"event_id": "f8f32c4545054fafaf6813e706827f6b", "step": 3, "value": 0.8419024766947982, "stage": "debug", "created_at": 1789626946.2993088}, {"event_id": "dd3bb2b8d9fa44798c13472dd80ee8ad", "step": 5, "value": 0.5293651544953176, "stage": "debug", "created_at": 1789630419.4577882}], "maximize": true, "elapsed_seconds": 28743.184767007828, "node_count": 8, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-hard14-20260917/xixian.gp7-no-ancestry-logei.siim-isic-melanoma-classification.yaml", "note": ""}, {"id": "xixian.gp7-no-ancestry-logei.tabular-playground-series-may-2022", "experiment_id": "mlebench-gp7-hard14-20260917", "family": "MLEBench", "method": "gp7_no_ancestry_logei", "dataset": "tabular-playground-series-may-2022", "status": "archived", "official_score": 0.99124, "medal": "none", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.99823, "silver": 0.99822, "bronze": 0.99818}, "grading_policy": "ensemble", "artifacts": [{"bundle_id": "gp7-ancestry-logei-hard14-full-logs-20260917", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917/logs-77c0e49ab8d6.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917", "member": "results/official_private_grades.jsonl:80", "sha256": "77c0e49ab8d6df7268cefe20565a32eaa589661c5946ef2499c567afceab8104"}, {"bundle_id": "gp7-no-ancestry-logei-hard14-full-logs-20260917", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-no-ancestry-logei-hard14-full-logs-20260917/logs-5cb1f19bf4da.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-no-ancestry-logei-hard14-full-logs-20260917", "member": "gp7_no_ancestry_logei-hard14/runs/12_tabular-playground-series-may-2022/logs/journal.json", "sha256": "5cb1f19bf4da2d6fd6b6aea2a936a5ebe2ad2c67f0a46cbfeed510ddf38aef8d"}], "alternate_scores": [{"cohort": "09-17", "workflow_id": "09-17 gp7_no_ancestry_logei", "method": "gp7_no_ancestry_logei", "task": "tabular-playground-series-may-2022", "policy": "best_node", "status": "graded", "valid_submission": true, "score": 0.99247, "medal": "none", "is_lower_better": false, "gold_threshold": 0.99823, "silver_threshold": 0.99822, "bronze_threshold": 0.99818, "submission_sha256": "a8a42ed4245e38372d2978f9fb816f1a1bd65d8b20566dc02edb9544d3393580", "source_archive": "gp7_ancestry_logei_hard14_full_logs_20260917.zip", "source_member": "results/official_private_grades.jsonl", "source_line": 79}], "journal_ref": "gp7-no-ancestry-logei-hard14-full-logs-20260917:gp7_no_ancestry_logei-hard14/runs/12_tabular-playground-series-may-2022/logs/journal.json", "metrics": [{"event_id": "4c177056fbae4363b7fd10b703c71684", "step": 1, "value": 0.898383623327526, "stage": "draft", "created_at": 1789626258.9864275}, {"event_id": "b5f133da827f4108a63ee70c76ec4385", "step": 2, "value": 0.9196673488917797, "stage": "draft", "created_at": 1789626783.613945}, {"event_id": "9bdf1995b9284e24a75ffe142ffffcc1", "step": 3, "value": 0.9197068099007085, "stage": "improve", "created_at": 1789627218.8417206}, {"event_id": "c75365995b2a486eb617409a2da97984", "step": 4, "value": 0.9487700537635602, "stage": "improve", "created_at": 1789627692.7594588}, {"event_id": "043464bf88034db89ab17019059cfa11", "step": 5, "value": 0.9919152551411926, "stage": "improve", "created_at": 1789627070.1124766}, {"event_id": "e90898508d6340fbac933a374399a156", "step": 6, "value": 0.9837144711795404, "stage": "improve", "created_at": 1789628219.951732}, {"event_id": "afd353ef8d8145b5b1d34175ec14d3a5", "step": 7, "value": 0.9923228531393387, "stage": "improve", "created_at": 1789630930.0891607}, {"event_id": "8d94e5a56ea34b79837e9f72a227b605", "step": 8, "value": 0.9922902810707334, "stage": "improve", "created_at": 1789636315.2960715}], "maximize": true, "elapsed_seconds": 28758.91709136963, "node_count": 11, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-hard14-20260917/xixian.gp7-no-ancestry-logei.tabular-playground-series-may-2022.yaml", "note": ""}, {"id": "xixian.gp7-no-ancestry-logei.text-normalization-challenge-english-language", "experiment_id": "mlebench-gp7-hard14-20260917", "family": "MLEBench", "method": "gp7_no_ancestry_logei", "dataset": "text-normalization-challenge-english-language", "status": "archived", "official_score": 0.9928, "medal": "silver", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.99724, "silver": 0.99135, "bronze": 0.99038}, "grading_policy": "ensemble", "artifacts": [{"bundle_id": "gp7-ancestry-logei-hard14-full-logs-20260917", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917/logs-77c0e49ab8d6.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917", "member": "results/official_private_grades.jsonl:82", "sha256": "77c0e49ab8d6df7268cefe20565a32eaa589661c5946ef2499c567afceab8104"}, {"bundle_id": "gp7-no-ancestry-logei-hard14-full-logs-20260917", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-no-ancestry-logei-hard14-full-logs-20260917/logs-5cb1f19bf4da.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-no-ancestry-logei-hard14-full-logs-20260917", "member": "gp7_no_ancestry_logei-hard14/runs/13_text-normalization-challenge-english-language/logs/journal.json", "sha256": "5cb1f19bf4da2d6fd6b6aea2a936a5ebe2ad2c67f0a46cbfeed510ddf38aef8d"}], "alternate_scores": [{"cohort": "09-17", "workflow_id": "09-17 gp7_no_ancestry_logei", "method": "gp7_no_ancestry_logei", "task": "text-normalization-challenge-english-language", "policy": "best_node", "status": "graded", "valid_submission": true, "score": 0.99263, "medal": "silver", "is_lower_better": false, "gold_threshold": 0.99724, "silver_threshold": 0.99135, "bronze_threshold": 0.99038, "submission_sha256": "d8059a1207251cd9ed65ff7cf653b9bb2955dc745a1367fe38301d43e09fb245", "source_archive": "gp7_ancestry_logei_hard14_full_logs_20260917.zip", "source_member": "results/official_private_grades.jsonl", "source_line": 81}], "journal_ref": "gp7-no-ancestry-logei-hard14-full-logs-20260917:gp7_no_ancestry_logei-hard14/runs/13_text-normalization-challenge-english-language/logs/journal.json", "metrics": [{"event_id": "417ccfcf3d134b93a328e1db3d47b979", "step": 6, "value": 0.658641951066253, "stage": "debug", "created_at": 1789627161.8138068}, {"event_id": "b83b215d34a24cc0938df341ba9448e8", "step": 7, "value": 0.9671063335596187, "stage": "draft", "created_at": 1789626637.0616975}, {"event_id": "7d3c0e2674b74a419e4c4dc2917bd4e9", "step": 8, "value": 0.9926143757710963, "stage": "debug", "created_at": 1789628171.9425526}, {"event_id": "042e3f63a52b4605a00a86de65eb418e", "step": 10, "value": 0.7951649732665323, "stage": "improve", "created_at": 1789629503.1745818}, {"event_id": "95450c1a2e8944c4b0906d49cae83b66", "step": 11, "value": 0.9757192674091726, "stage": "improve", "created_at": 1789632588.1252818}, {"event_id": "73b9ffa2827c4d039908b7db8d6acfee", "step": 12, "value": 0.9299319460730135, "stage": "debug", "created_at": 1789632451.7723286}, {"event_id": "7874ac14b84c4ac6af3d95a6649af35c", "step": 13, "value": 0.9859949185102559, "stage": "improve", "created_at": 1789632705.699719}, {"event_id": "51eddaf3382149acb63016a596f79553", "step": 14, "value": 0.9761361523770894, "stage": "improve", "created_at": 1789639573.5308495}, {"event_id": "a4abcb5037f444278c3fde171affbff1", "step": 15, "value": 0.9730771180854839, "stage": "improve", "created_at": 1789642961.7737103}, {"event_id": "d7f8080b988a482b8d95c7c47a6f5e4c", "step": 18, "value": 0.9920115826418113, "stage": "improve", "created_at": 1789642480.5879924}, {"event_id": "5b7b49ccc05a4c7c92d9ff78a6ac5d4b", "step": 20, "value": 0.9771, "stage": "fusion_draft", "created_at": 1789648093.4796832}, {"event_id": "a37112f8636d4bb3a293787222f676ea", "step": 21, "value": 0.9860906893812639, "stage": "fusion", "created_at": 1789644107.8560529}, {"event_id": "11097746135d42ef8dc5f45ddd578318", "step": 23, "value": 0.9926819787388667, "stage": "fusion", "created_at": 1789649864.0447543}], "maximize": true, "elapsed_seconds": 28763.897820711136, "node_count": 25, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-hard14-20260917/xixian.gp7-no-ancestry-logei.text-normalization-challenge-english-language.yaml", "note": ""}, {"id": "xixian.gp7-no-ancestry-logei.text-normalization-challenge-russian-language", "experiment_id": "mlebench-gp7-hard14-20260917", "family": "MLEBench", "method": "gp7_no_ancestry_logei", "dataset": "text-normalization-challenge-russian-language", "status": "archived", "official_score": 0.9707, "medal": "none", "valid_submission": true, "score_maximize": true, "thresholds": {"gold": 0.99012, "silver": 0.98232, "bronze": 0.97592}, "grading_policy": "ensemble", "artifacts": [{"bundle_id": "gp7-ancestry-logei-hard14-full-logs-20260917", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917/logs-77c0e49ab8d6.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917", "member": "results/official_private_grades.jsonl:84", "sha256": "77c0e49ab8d6df7268cefe20565a32eaa589661c5946ef2499c567afceab8104"}, {"bundle_id": "gp7-no-ancestry-logei-hard14-full-logs-20260917", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-no-ancestry-logei-hard14-full-logs-20260917/logs-5cb1f19bf4da.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-no-ancestry-logei-hard14-full-logs-20260917", "member": "gp7_no_ancestry_logei-hard14/runs/14_text-normalization-challenge-russian-language/logs/journal.json", "sha256": "5cb1f19bf4da2d6fd6b6aea2a936a5ebe2ad2c67f0a46cbfeed510ddf38aef8d"}], "alternate_scores": [{"cohort": "09-17", "workflow_id": "09-17 gp7_no_ancestry_logei", "method": "gp7_no_ancestry_logei", "task": "text-normalization-challenge-russian-language", "policy": "best_node", "status": "graded", "valid_submission": true, "score": 0.9707, "medal": "none", "is_lower_better": false, "gold_threshold": 0.99012, "silver_threshold": 0.98232, "bronze_threshold": 0.97592, "submission_sha256": "f370230771ddc823550b6820f2d3bebfcb7ea6ff21cf4d36abf893f4197efeeb", "source_archive": "gp7_ancestry_logei_hard14_full_logs_20260917.zip", "source_member": "results/official_private_grades.jsonl", "source_line": 83}], "journal_ref": "gp7-no-ancestry-logei-hard14-full-logs-20260917:gp7_no_ancestry_logei-hard14/runs/14_text-normalization-challenge-russian-language/logs/journal.json", "metrics": [{"event_id": "67aae35290c6451dbc559acdfcd3d2bf", "step": 3, "value": 0.9707722015826039, "stage": "draft", "created_at": 1789626755.4139354}, {"event_id": "8da3636d01344544aaccd4979ddb10c0", "step": 4, "value": 0.9707722015826039, "stage": "improve", "created_at": 1789627170.7795622}, {"event_id": "c8ee8e3da9394dbb968eace697447184", "step": 6, "value": 0.9386688495686669, "stage": "debug", "created_at": 1789626877.0766943}, {"event_id": "c8590183cb854d4cb2f84e249ac1dbe3", "step": 7, "value": 0.8919886859730115, "stage": "debug", "created_at": 1789628448.9756155}, {"event_id": "63a03904a48e4a8f8c949ada5a8acee8", "step": 9, "value": 0.9253510484226434, "stage": "improve", "created_at": 1789627558.702099}, {"event_id": "6217a97fbfe64aac8544c9e904f09c51", "step": 10, "value": 0.9150767164116449, "stage": "improve", "created_at": 1789640911.7841299}], "maximize": true, "elapsed_seconds": 28760.06722998619, "node_count": 12, "metric_name": "native validation metric", "curve_scope": "原始 journal 中非 buggy 的有限验证指标；不含官方 private score。", "config_url": "configs/mlebench-gp7-hard14-20260917/xixian.gp7-no-ancestry-logei.text-normalization-challenge-russian-language.yaml", "note": ""}, {"id": "xixian.bo-study-mcgs.seed42", "experiment_id": "nanogpt-development-r1-v1-20260917", "family": "nanoGPT", "method": "bo_study_mcgs", "dataset": "nanoGPT", "seed": "42", "status": "completed", "best_valid_bpb": 1.1989174764383868, "elapsed_seconds": 21600.0, "budget_seconds": 21600.0, "comparison_eligible": true, "note": "user_amended_6h_current_action_completed", "artifacts": [{"bundle_id": "01-read-first-and-final-states", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/01-read-first-and-final-states/logs-c828e9f97191.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/01-read-first-and-final-states", "member": "MLEvolve_BO/research/nanogpt_bo_20260917/analysis/final_closeout_20260918/all_runs_final.csv", "sha256": "c828e9f97191ffc3f6f4fa6f39045e6be494d2ab2ea3337eff18dfd2830908ba"}, {"bundle_id": "02-study-run-logs", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/02-study-run-logs/logs-50a9df8a8a5a.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/02-study-run-logs", "member": "MLEvolve_BO/research/nanogpt_bo_20260917/development_r1_v1/bo_study_mcgs/runs/20260917_041214_bo_study_mcgs/logs/journal.json", "sha256": "50a9df8a8a5acb631814aa5ea6a0f2e8b7d47ec05bff989ffaa975aa9ca71d25"}], "ledger": {"campaign": "development_r1_v1", "stage": "development", "method": "bo_study_mcgs", "version": "development_r1_v1", "seed": "42", "training_seed": "42", "state": "finished", "complete_budget": "True", "launch_allowed": "", "not_launched_reason": "", "complete_8h": "False", "active_seconds": "21600", "budget_seconds": "21600", "source_duration_seconds": "28800", "budget_amended": "True", "raw_active_seconds": "22672.567658901215", "post_budget_active_seconds": "1072.5676589012146", "comparison_eligible": "True", "protocol_invalid_results": "0", "raw_reported_valid": "33", "raw_reported_best_bpb": "1.1989174764383868", "validity_audit": "", "comparison_exclusion_reason": "", "policy_contamination_started_at": "", "active_gpu_hours": "6.0", "actual_elapsed_seconds": "22689.622069835663", "segment_gpu_hours_including_cleanup": "6.297935460805893", "between_segment_seconds": "17.054410934448242", "completed": "35", "raw_completed": "37", "unverified_commit_time_count": "0", "post_budget_completed": "2", "valid": "32", "failure_fraction": "0.08571428571428574", "best_bpb_so_far": "1.1989174764383868", "final_bpb": "1.1989174764383868", "best_node_id": "eff9ee4f40e2439684ad4e2fb4348cad", "llm_attempts": "155", "llm_cli_reported_tokens_known": "3003258", "llm_attempts_unknown_tokens": "0", "llm_measured_wall_seconds": "6583.681753873825", "llm_unfinished_attempts": "0", "llm_failed_or_interrupted_attempts": "0", "allocated_gpu_hours": "6.378055555555556", "allocated_gpu_hours_accounting_final": "True", "resource_records": "[\"10826467.3\", \"10833302\"]", "resource_accounting_captured_at": "[\"2026-09-18T07:57:20.346825+00:00\"]", "gpu_models": "[\"NVIDIA A100-SXM4-80GB\"]", "completed_proposal_wall_seconds": "21286.332087486517", "raw_completed_proposal_wall_seconds": "22209.475793194957", "diagnostic_feedback_scope": "Only results committed within the registered budget; later DEBUG repairs and mature labels excluded", "diagnostic_excluded_late_transitions": "2", "closed_proposals": "32", "unclosed_proposals": "0", "unknown_closure_proposals": "0", "closed_proposal_failure_fraction": "0.0", "raw_reported_closed_proposal_failure_fraction": "0.0", "debug_repaired_proposals": "3", "raw_serial_actions": "41", "raw_actions_with_error_logs": "0", "raw_training_launches": "38", "interrupted_actions": "1", "interrupted_action_active_seconds_upper_bound": "338.4340000152588", "gpu_uuid": "GPU-78b4ce31-d115-7b9a-f22e-d0ed70044433", "job_id": "10833302", "node": "cn-g027.server.mila.quebec", "started_at": "2026-09-17T08:11:39.986931+00:00", "finished_at": "2026-09-17T14:29:49.609001+00:00", "stop_reason": "user_amended_6h_current_action_completed", "training_rows": "", "incomplete_windows": "", "current_label_diagnostics": "{}", "threshold_active_seconds": "{\"1.2\": 14511.193069458008, \"1.15\": null, \"1.1\": null}", "log_dir": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r1_v1/bo_study_mcgs/runs/20260917_041214_bo_study_mcgs/logs", "committed_evidence": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r1_v1/bo_study_mcgs/checkpoints/boundary-1789655386497441286/logs", "final_solution": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r1_v1/bo_study_mcgs/runs/20260917_041214_bo_study_mcgs/workspace/trials/eff9ee4f40e2439684ad4e2fb4348cad/candidate.py"}, "journal_ref": "02-study-run-logs:MLEvolve_BO/research/nanogpt_bo_20260917/development_r1_v1/bo_study_mcgs/runs/20260917_041214_bo_study_mcgs/logs/journal.json", "metrics": [{"event_id": "add74218bd584ede9aaa2335918b4277", "step": 1, "value": 1.4791708585686136, "stage": "draft", "created_at": 1789632756.2703915}, {"event_id": "927d30d98ec144778049a6a471609479", "step": 4, "value": 1.8046494364664434, "stage": "improve", "created_at": 1789634756.531641}, {"event_id": "06e966eb439a4acfb1587a9d4143efa5", "step": 5, "value": 3.0788264797840057, "stage": "debug", "created_at": 1789635540.0906658}, {"event_id": "b27478a9510943cfbb0135646f079bd3", "step": 6, "value": 3.2889695169250026, "stage": "debug", "created_at": 1789636051.0271797}, {"event_id": "6517795fd2e349deb2c7e40096b293b4", "step": 7, "value": 1.9289052029101972, "stage": "improve", "created_at": 1789636835.0617096}, {"event_id": "70148fe223ed4df79146f9062586aacd", "step": 8, "value": 3.179844351392588, "stage": "improve", "created_at": 1789637453.4635704}, {"event_id": "a08c64cc3ca54d0eb3f877142704bcfb", "step": 9, "value": 4.918838379654888, "stage": "improve", "created_at": 1789638008.5044675}, {"event_id": "549f7f703f18437cbe839094af271bf5", "step": 10, "value": 1.8379492613087494, "stage": "improve", "created_at": 1789638637.7027183}, {"event_id": "eb4b01c5eee0499db1ddeeb64c0ca036", "step": 11, "value": 3.1754638940446878, "stage": "improve", "created_at": 1789639273.5479612}, {"event_id": "9bbdd0067f2142b18a33c0f42f25bb15", "step": 12, "value": 5.333843082616155, "stage": "improve", "created_at": 1789639873.8278642}, {"event_id": "a49fffa8124242c189181ad787b51e35", "step": 13, "value": 1.4296640344490648, "stage": "evolution", "created_at": 1789640438.7638495}, {"event_id": "4658f0c166244a13944ce41cfa160629", "step": 14, "value": 3.1575653730546067, "stage": "improve", "created_at": 1789641017.492815}, {"event_id": "8ad23d3e42034cd29f51e8e665c1ee2e", "step": 15, "value": 3.1737853239925613, "stage": "improve", "created_at": 1789641712.300991}, {"event_id": "6604b484b4ba4542be1dcacec2299773", "step": 17, "value": 1.2035442636063765, "stage": "evolution", "created_at": 1789642541.1647213}, {"event_id": "17c83bf6f958425f904ca0c860d93a78", "step": 18, "value": 3.152213801267461, "stage": "improve", "created_at": 1789643130.032639}, {"event_id": "8e90006ce8c742d09ba7c49c5ad79211", "step": 19, "value": 1.4140657256857738, "stage": "debug", "created_at": 1789643617.6669886}, {"event_id": "d3cb022d089b40cfa1659ef882bc2817", "step": 20, "value": 1.2134339606471714, "stage": "improve", "created_at": 1789644231.5920582}, {"event_id": "d41e568a655442a0b84650189cd4b856", "step": 21, "value": 1.3292655644925913, "stage": "improve", "created_at": 1789644821.0944788}, {"event_id": "32a3fc31c2d34d6ba85e0ce08f826df8", "step": 22, "value": 1.5473831613357416, "stage": "improve", "created_at": 1789645433.6625075}, {"event_id": "c81c57efe4814e249f002d63f77d55c5", "step": 23, "value": 1.4520190530421846, "stage": "improve", "created_at": 1789646078.3200731}, {"event_id": "eff9ee4f40e2439684ad4e2fb4348cad", "step": 24, "value": 1.1989174764383868, "stage": "improve", "created_at": 1789646778.392011}, {"event_id": "a881c770e03e4f48a887ad012f1ea67f", "step": 25, "value": 1.5336845204413612, "stage": "improve", "created_at": 1789647338.6634872}, {"event_id": "5436e3ee90634aacac0aa8606463ada4", "step": 26, "value": 1.426288115807903, "stage": "improve", "created_at": 1789648014.6467497}, {"event_id": "725a2bf3f9144dcc8f0afe46e740d964", "step": 27, "value": 1.202248716282949, "stage": "improve", "created_at": 1789648615.6578307}, {"event_id": "e0126fff49b1401bb91908c7aab87f08", "step": 28, "value": 1.3192711877181005, "stage": "draft", "created_at": 1789649076.3096778}, {"event_id": "bddd7b99feb7404388b291f70e712351", "step": 29, "value": 1.2018283971270471, "stage": "improve", "created_at": 1789649952.5356603}, {"event_id": "9ee3865914a847048e9a3de308d588b2", "step": 30, "value": 1.2096119526474862, "stage": "improve", "created_at": 1789650462.407726}, {"event_id": "f72a6ba5998a4cd0939bcee78e9f32f2", "step": 31, "value": 1.3903523383442349, "stage": "improve", "created_at": 1789651037.1275811}, {"event_id": "01c84f5284b34eb8a6fd4f849574e21a", "step": 32, "value": 1.2904099143670726, "stage": "improve", "created_at": 1789651609.795686}, {"event_id": "efc8c377418a4019be2deae5f7789856", "step": 33, "value": 1.3734613188860658, "stage": "improve", "created_at": 1789652285.0592377}, {"event_id": "a06cad1e9aaf437781b8a24245cb7c4a", "step": 34, "value": 1.615555878830987, "stage": "improve", "created_at": 1789652914.782197}, {"event_id": "e8db3be33b35422dbd4f4ea11e95dfe3", "step": 35, "value": 1.3135434853283852, "stage": "improve", "created_at": 1789653518.6298966}, {"event_id": "25bfd092e1334628a1f763c58a070e70", "step": 36, "value": 1.2923360648904325, "stage": "evolution", "created_at": 1789654521.894558}], "maximize": false, "node_count": 38, "metric_name": "BPB", "curve_scope": "原始候选验证 BPB（可能含回滚或预算后记录），不作为预算内最终成绩。最终成绩以 all_runs_final.csv 为准。", "official_score": null}, {"id": "xixian.bo-study-gp7-ucb.seed42", "experiment_id": "nanogpt-development-r1-v1-20260917", "family": "nanoGPT", "method": "bo_study_gp7_ucb", "dataset": "nanoGPT", "seed": "42", "status": "completed", "best_valid_bpb": 1.1135677786001326, "elapsed_seconds": 21600.0, "budget_seconds": 21600.0, "comparison_eligible": true, "note": "user_amended_6h_current_action_completed", "artifacts": [{"bundle_id": "01-read-first-and-final-states", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/01-read-first-and-final-states/logs-c828e9f97191.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/01-read-first-and-final-states", "member": "MLEvolve_BO/research/nanogpt_bo_20260917/analysis/final_closeout_20260918/all_runs_final.csv", "sha256": "c828e9f97191ffc3f6f4fa6f39045e6be494d2ab2ea3337eff18dfd2830908ba"}, {"bundle_id": "02-study-run-logs", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/02-study-run-logs/logs-50a9df8a8a5a.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/02-study-run-logs", "member": "MLEvolve_BO/research/nanogpt_bo_20260917/development_r1_v1/bo_study_gp7_ucb/runs/20260917_041214_bo_study_gp7_ucb/logs/journal.json", "sha256": "50a9df8a8a5acb631814aa5ea6a0f2e8b7d47ec05bff989ffaa975aa9ca71d25"}], "ledger": {"campaign": "development_r1_v1", "stage": "development", "method": "bo_study_gp7_ucb", "version": "development_r1_v1", "seed": "42", "training_seed": "42", "state": "finished", "complete_budget": "True", "launch_allowed": "", "not_launched_reason": "", "complete_8h": "False", "active_seconds": "21600", "budget_seconds": "21600", "source_duration_seconds": "28800", "budget_amended": "True", "raw_active_seconds": "22893.708297014236", "post_budget_active_seconds": "1293.7082970142365", "comparison_eligible": "True", "protocol_invalid_results": "0", "raw_reported_valid": "33", "raw_reported_best_bpb": "1.0949444618089161", "validity_audit": "", "comparison_exclusion_reason": "", "policy_contamination_started_at": "", "active_gpu_hours": "6.0", "actual_elapsed_seconds": "22907.10657811165", "segment_gpu_hours_including_cleanup": "6.359363415837288", "between_segment_seconds": "13.39828109741211", "completed": "40", "raw_completed": "42", "unverified_commit_time_count": "0", "post_budget_completed": "2", "valid": "31", "failure_fraction": "0.22499999999999998", "best_bpb_so_far": "1.1135677786001326", "final_bpb": "1.1135677786001326", "best_node_id": "4dcdf07339fc4742bf84b93c8111abbf", "llm_attempts": "161", "llm_cli_reported_tokens_known": "3322638", "llm_attempts_unknown_tokens": "1", "llm_measured_wall_seconds": "6741.789593696594", "llm_unfinished_attempts": "0", "llm_failed_or_interrupted_attempts": "1", "allocated_gpu_hours": "6.378055555555556", "allocated_gpu_hours_accounting_final": "True", "resource_records": "[\"10826467.3\", \"10833302\"]", "resource_accounting_captured_at": "[\"2026-09-18T07:57:20.346825+00:00\"]", "gpu_models": "[\"NVIDIA A100-SXM4-80GB\"]", "completed_proposal_wall_seconds": "20958.850675242487", "raw_completed_proposal_wall_seconds": "22085.75050272001", "diagnostic_feedback_scope": "Only results committed within the registered budget; later DEBUG repairs and mature labels excluded", "diagnostic_excluded_late_transitions": "2", "closed_proposals": "31", "unclosed_proposals": "3", "unknown_closure_proposals": "0", "closed_proposal_failure_fraction": "0.0", "raw_reported_closed_proposal_failure_fraction": "0.0", "debug_repaired_proposals": "4", "raw_serial_actions": "46", "raw_actions_with_error_logs": "0", "raw_training_launches": "39", "interrupted_actions": "1", "interrupted_action_active_seconds_upper_bound": "628.8600866794586", "gpu_uuid": "GPU-247a5d9f-faae-6e91-b78b-f0e0c4015b0a", "job_id": "10833302", "node": "cn-g027.server.mila.quebec", "started_at": "2026-09-17T08:11:39.986256+00:00", "finished_at": "2026-09-17T14:33:27.092834+00:00", "stop_reason": "user_amended_6h_current_action_completed", "training_rows": "26", "incomplete_windows": "", "current_label_diagnostics": "{}", "threshold_active_seconds": "{\"1.2\": 6638.894744157791, \"1.15\": 8452.925744056702, \"1.1\": null}", "log_dir": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r1_v1/bo_study_gp7_ucb/runs/20260917_041214_bo_study_gp7_ucb/logs", "committed_evidence": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r1_v1/bo_study_gp7_ucb/checkpoints/boundary-1789655604369616208/logs", "final_solution": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r1_v1/bo_study_gp7_ucb/runs/20260917_041214_bo_study_gp7_ucb/workspace/trials/4dcdf07339fc4742bf84b93c8111abbf/candidate.py"}, "journal_ref": "02-study-run-logs:MLEvolve_BO/research/nanogpt_bo_20260917/development_r1_v1/bo_study_gp7_ucb/runs/20260917_041214_bo_study_gp7_ucb/logs/journal.json", "metrics": [{"event_id": "5e0297879bfc47099a42411f114a964b", "step": 1, "value": 1.4742080209723625, "stage": "draft", "created_at": 1789632756.3420749}, {"event_id": "4072a9d073b9436e841d4f8f0f7e09ee", "step": 4, "value": 1.4523255614796915, "stage": "improve", "created_at": 1789634677.3631783}, {"event_id": "a56ae98ffc16463e93a121db6ade9fbb", "step": 5, "value": 1.4644650429489796, "stage": "debug", "created_at": 1789635187.190945}, {"event_id": "b75df9bf5b7e46f78bb254b325dec180", "step": 6, "value": 1.953460417048203, "stage": "debug", "created_at": 1789635705.1580887}, {"event_id": "3930ea5eb6fc45efb3123163a3aab173", "step": 7, "value": 1.2549802103927754, "stage": "improve", "created_at": 1789636452.1819034}, {"event_id": "7cee0b9a2ea143ec8518e1339a9f3f80", "step": 8, "value": 1.4769433805915166, "stage": "improve", "created_at": 1789637085.7191641}, {"event_id": "579970ef8eb24b3aad14a36da868f6fd", "step": 9, "value": 1.2863566490567617, "stage": "improve", "created_at": 1789637716.2954848}, {"event_id": "a8c18b3b57f94ce6a24fb1eba745948b", "step": 10, "value": 1.3425410325633136, "stage": "improve", "created_at": 1789638335.1440556}, {"event_id": "f84f84c63db04ecab4e01605f488a5a7", "step": 11, "value": 1.170547142799338, "stage": "evolution", "created_at": 1789638882.5881438}, {"event_id": "41f80c8894e1408cbb45cf7bf652e8c4", "step": 12, "value": 1.2287069108181314, "stage": "improve", "created_at": 1789639457.2112136}, {"event_id": "c976f829ba0949a5b67998a4fa2b578f", "step": 13, "value": 1.4722508075759362, "stage": "improve", "created_at": 1789640038.2088294}, {"event_id": "09a476a664ed470c9c7dd3da30b5315d", "step": 14, "value": 1.122378334095873, "stage": "improve", "created_at": 1789640656.5786946}, {"event_id": "db6a11805a7442d18d7f14ec88d0df52", "step": 16, "value": 1.1477665022628427, "stage": "improve", "created_at": 1789641494.1518002}, {"event_id": "8441f629fd6644369031e480d135a6d2", "step": 17, "value": 1.1598243612731534, "stage": "improve", "created_at": 1789642033.8969567}, {"event_id": "b95806b3f2b94f699460291b95de2d8c", "step": 18, "value": 1.2353955672546983, "stage": "debug", "created_at": 1789642543.1040103}, {"event_id": "c9ea4889ac5a4a468a073ef4e2dc1028", "step": 19, "value": 1.1378336791231536, "stage": "evolution", "created_at": 1789643102.3686018}, {"event_id": "33429fd6a4c14426a417a41f716067b0", "step": 20, "value": 1.3254758049220223, "stage": "draft", "created_at": 1789643562.1315312}, {"event_id": "138084f8378b45d0881d7d7b1f0e9659", "step": 21, "value": 1.1432998150811127, "stage": "evolution", "created_at": 1789644454.6786997}, {"event_id": "9237805e45424236bc5174020c059de5", "step": 24, "value": 1.153947102538603, "stage": "evolution", "created_at": 1789645350.8208613}, {"event_id": "ff41f3417f9342128e60e01ab206de1c", "step": 25, "value": 1.1521369910092627, "stage": "evolution", "created_at": 1789645951.827389}, {"event_id": "843fbf8af9b24dd0a4e364db76f9a278", "step": 27, "value": 1.1427158902553034, "stage": "evolution", "created_at": 1789646777.2343538}, {"event_id": "2e9760a09a71466ab6a3b696c4a1e0aa", "step": 30, "value": 1.1491114564964757, "stage": "evolution", "created_at": 1789647812.8891633}, {"event_id": "39c105c5a6824b96ad09346944b2b057", "step": 31, "value": 1.2991380686588447, "stage": "debug", "created_at": 1789648325.6322992}, {"event_id": "d3783580ba63438cad4abe2c7347ca87", "step": 32, "value": 1.1619949216441232, "stage": "fusion", "created_at": 1789648882.4453025}, {"event_id": "948e7d96eb824abdb6547870d9f933fe", "step": 33, "value": 1.1245287811477078, "stage": "fusion", "created_at": 1789649451.36604}, {"event_id": "d37bda22b9874bbbad2332372b1d7907", "step": 34, "value": 1.1136067400773093, "stage": "fusion", "created_at": 1789650000.3976786}, {"event_id": "c8b2031e428c4f6a9eb79c91ec0f105e", "step": 35, "value": 1.12541850488781, "stage": "improve", "created_at": 1789650644.5965958}, {"event_id": "6c3780e064594f34acd25328587ae0f2", "step": 36, "value": 1.1401868318987458, "stage": "improve", "created_at": 1789651259.7694428}, {"event_id": "4dcdf07339fc4742bf84b93c8111abbf", "step": 37, "value": 1.1135677786001326, "stage": "improve", "created_at": 1789651802.6875148}, {"event_id": "f5b1162a7f36421e9962515a5b52fb8a", "step": 38, "value": 1.1263901218505326, "stage": "improve", "created_at": 1789652411.7621186}, {"event_id": "faff0a73265a454f89818f21d0a411f6", "step": 39, "value": 1.136116157178404, "stage": "improve", "created_at": 1789652989.1122334}, {"event_id": "aa08f8187cf34c528863eba8f4b6122c", "step": 41, "value": 1.1300954030313481, "stage": "improve", "created_at": 1789654549.828515}, {"event_id": "620aa553c2a5430daacd7a6583ed71f3", "step": 42, "value": 1.0949444618089161, "stage": "evolution", "created_at": 1789655086.766954}], "maximize": false, "node_count": 43, "metric_name": "BPB", "curve_scope": "原始候选验证 BPB（可能含回滚或预算后记录），不作为预算内最终成绩。最终成绩以 all_runs_final.csv 为准。", "official_score": null}, {"id": "xixian.bo-study-parent-greedy.seed42", "experiment_id": "nanogpt-development-r1-v1-20260917", "family": "nanoGPT", "method": "bo_study_parent_greedy", "dataset": "nanoGPT", "seed": "42", "status": "completed", "best_valid_bpb": 1.1284544681937752, "elapsed_seconds": 21600.0, "budget_seconds": 21600.0, "comparison_eligible": true, "note": "user_amended_6h_current_action_completed", "artifacts": [{"bundle_id": "01-read-first-and-final-states", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/01-read-first-and-final-states/logs-c828e9f97191.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/01-read-first-and-final-states", "member": "MLEvolve_BO/research/nanogpt_bo_20260917/analysis/final_closeout_20260918/all_runs_final.csv", "sha256": "c828e9f97191ffc3f6f4fa6f39045e6be494d2ab2ea3337eff18dfd2830908ba"}, {"bundle_id": "02-study-run-logs", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/02-study-run-logs/logs-50a9df8a8a5a.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/02-study-run-logs", "member": "MLEvolve_BO/research/nanogpt_bo_20260917/development_r1_v1/bo_study_parent_greedy/runs/20260917_041220_bo_study_parent_greedy/logs/journal.json", "sha256": "50a9df8a8a5acb631814aa5ea6a0f2e8b7d47ec05bff989ffaa975aa9ca71d25"}], "ledger": {"campaign": "development_r1_v1", "stage": "development", "method": "bo_study_parent_greedy", "version": "development_r1_v1", "seed": "42", "training_seed": "42", "state": "finished", "complete_budget": "True", "launch_allowed": "", "not_launched_reason": "", "complete_8h": "False", "active_seconds": "21600", "budget_seconds": "21600", "source_duration_seconds": "28800", "budget_amended": "True", "raw_active_seconds": "22802.057672977448", "post_budget_active_seconds": "1202.0576729774475", "comparison_eligible": "True", "protocol_invalid_results": "0", "raw_reported_valid": "33", "raw_reported_best_bpb": "1.1284544681937752", "validity_audit": "", "comparison_exclusion_reason": "", "policy_contamination_started_at": "", "active_gpu_hours": "6.0", "actual_elapsed_seconds": "22802.057672977448", "segment_gpu_hours_including_cleanup": "6.3339049091604025", "between_segment_seconds": "0.0", "completed": "36", "raw_completed": "39", "unverified_commit_time_count": "0", "post_budget_completed": "3", "valid": "31", "failure_fraction": "0.13888888888888884", "best_bpb_so_far": "1.1284544681937752", "final_bpb": "1.1284544681937752", "best_node_id": "1daa1c1acaa546cfbf849540fbab51d7", "llm_attempts": "153", "llm_cli_reported_tokens_known": "2985951", "llm_attempts_unknown_tokens": "0", "llm_measured_wall_seconds": "6319.231840848923", "llm_unfinished_attempts": "0", "llm_failed_or_interrupted_attempts": "0", "allocated_gpu_hours": "6.344166666666666", "allocated_gpu_hours_accounting_final": "True", "resource_records": "[\"10829749\"]", "resource_accounting_captured_at": "[\"2026-09-18T07:57:20.346825+00:00\"]", "gpu_models": "[\"NVIDIA A100-SXM4-80GB\"]", "completed_proposal_wall_seconds": "21409.102831666358", "raw_completed_proposal_wall_seconds": "22718.907928129658", "diagnostic_feedback_scope": "Only results committed within the registered budget; later DEBUG repairs and mature labels excluded", "diagnostic_excluded_late_transitions": "3", "closed_proposals": "31", "unclosed_proposals": "0", "unknown_closure_proposals": "1", "closed_proposal_failure_fraction": "", "raw_reported_closed_proposal_failure_fraction": "", "debug_repaired_proposals": "4", "raw_serial_actions": "42", "raw_actions_with_error_logs": "0", "raw_training_launches": "39", "interrupted_actions": "0", "interrupted_action_active_seconds_upper_bound": "0", "gpu_uuid": "GPU-8e27f2b8-b621-cdc7-e21a-23be3000f119", "job_id": "10829749", "node": "cn-g007.server.mila.quebec", "started_at": "2026-09-17T08:11:45.723308+00:00", "finished_at": "2026-09-17T14:31:47.780981+00:00", "stop_reason": "user_amended_6h_current_action_completed", "training_rows": "", "incomplete_windows": "", "current_label_diagnostics": "{}", "threshold_active_seconds": "{\"1.2\": 16266.987691879272, \"1.15\": 16834.13769197464, \"1.1\": null}", "log_dir": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r1_v1/bo_study_parent_greedy/runs/20260917_041220_bo_study_parent_greedy/logs", "committed_evidence": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r1_v1/bo_study_parent_greedy/checkpoints/boundary-1789655506231693594/logs", "final_solution": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r1_v1/bo_study_parent_greedy/runs/20260917_041220_bo_study_parent_greedy/workspace/trials/1daa1c1acaa546cfbf849540fbab51d7/candidate.py"}, "journal_ref": "02-study-run-logs:MLEvolve_BO/research/nanogpt_bo_20260917/development_r1_v1/bo_study_parent_greedy/runs/20260917_041220_bo_study_parent_greedy/logs/journal.json", "metrics": [{"event_id": "cf2298d850cd4715bd1c1615dcf3be14", "step": 1, "value": 1.4898474547927174, "stage": "draft", "created_at": 1789632764.0270517}, {"event_id": "719f0d9b336f4a489355c67d7f8b1f08", "step": 4, "value": 1.8521795488792958, "stage": "improve", "created_at": 1789634762.9833033}, {"event_id": "0b0ff807b73345869903ac9b97ce9503", "step": 5, "value": 3.0850047203958835, "stage": "debug", "created_at": 1789635442.3961368}, {"event_id": "62d9ccf7928d4ab5860d0e4389cbb2e9", "step": 6, "value": 3.28802810022551, "stage": "debug", "created_at": 1789636054.1096117}, {"event_id": "c73d8722826e466a95bd91f8d301e38c", "step": 7, "value": 1.8611099009134773, "stage": "improve", "created_at": 1789636817.9064586}, {"event_id": "5e3ffb02af78474ab2bd400f649fd52e", "step": 9, "value": 1.7207859674533552, "stage": "improve", "created_at": 1789638136.3002203}, {"event_id": "e8e1534052e24555b78ab01188881972", "step": 10, "value": 1.4756432499877397, "stage": "evolution", "created_at": 1789638775.0994575}, {"event_id": "087cdfacaaaa4ea6b4bfe46dd3e8e01c", "step": 11, "value": 1.76041911178571, "stage": "debug", "created_at": 1789639298.048266}, {"event_id": "d5b6406b051b4f6d8774f9ce7a03aa66", "step": 12, "value": 1.3238254201138213, "stage": "improve", "created_at": 1789639905.1320734}, {"event_id": "810de84be61b4711b45d55d1989fc68e", "step": 13, "value": 1.5611241443923918, "stage": "improve", "created_at": 1789640486.6156785}, {"event_id": "a06b5e7649554754b28de0c520b3fa3d", "step": 14, "value": 1.4140841412077094, "stage": "improve", "created_at": 1789641129.0365064}, {"event_id": "3bee75c8ca284edaade109eb125cb1dd", "step": 15, "value": 1.4708491109205193, "stage": "improve", "created_at": 1789641684.4054375}, {"event_id": "facac132aa4c43599d1c6477f3bc25e0", "step": 16, "value": 1.3478530733910477, "stage": "evolution", "created_at": 1789642250.2922544}, {"event_id": "a201787915f543429cf8dc27d13d2f0d", "step": 17, "value": 1.8838411876541692, "stage": "evolution", "created_at": 1789642796.8780706}, {"event_id": "2f6d54eaa4df4823858157331fc62c58", "step": 18, "value": 1.3895387925041123, "stage": "evolution", "created_at": 1789643334.747668}, {"event_id": "c494025dfa5e4ba9993ac07dd81c1f37", "step": 19, "value": 1.403379350288245, "stage": "evolution", "created_at": 1789643874.718153}, {"event_id": "7b21f738d398444990ffa690c88b95a6", "step": 20, "value": 1.319891010857616, "stage": "evolution", "created_at": 1789644433.7662914}, {"event_id": "7d289e0a442041888859b70297a86405", "step": 21, "value": 1.6056514896011456, "stage": "improve", "created_at": 1789645020.2704906}, {"event_id": "e4dcb4d850074623bcd596a7fd5d38e2", "step": 22, "value": 1.3292730121567604, "stage": "draft", "created_at": 1789645527.3590596}, {"event_id": "429efb839e6042b9bcbbebaf7cd87883", "step": 23, "value": 1.3992181955169665, "stage": "improve", "created_at": 1789646416.4371457}, {"event_id": "a8a6b16adee5492a8d5b849e0e2e226d", "step": 24, "value": 1.9179611614285281, "stage": "improve", "created_at": 1789647001.0940528}, {"event_id": "8b95d3e5e0a248e6b4e321ce2dda67fd", "step": 25, "value": 1.2273679944539961, "stage": "improve", "created_at": 1789647543.9814687}, {"event_id": "8cde29daff234d3b986e5381f8434d9d", "step": 27, "value": 1.1641304970627664, "stage": "improve", "created_at": 1789648548.3959277}, {"event_id": "a09d88b30abd45c298a9d4f76ee7b245", "step": 28, "value": 1.1317125526007548, "stage": "improve", "created_at": 1789649087.73547}, {"event_id": "e453a976f7284a879f4c3bfb82523c90", "step": 29, "value": 1.1785625699071143, "stage": "debug", "created_at": 1789649568.865647}, {"event_id": "6ed2c2b04238450c9e1a7d891b3c8b2f", "step": 30, "value": 1.1873410764522636, "stage": "improve", "created_at": 1789650214.2193677}, {"event_id": "8d809e86848b44348b2266d0571c216a", "step": 31, "value": 1.1908879261578826, "stage": "improve", "created_at": 1789650821.0630202}, {"event_id": "1daa1c1acaa546cfbf849540fbab51d7", "step": 32, "value": 1.1284544681937752, "stage": "improve", "created_at": 1789651374.8597028}, {"event_id": "8c3f2b71abab4167bf00d888d3c43f84", "step": 33, "value": 1.208884170725387, "stage": "improve", "created_at": 1789651946.3540592}, {"event_id": "a43ea3decbaf4052859885703a43c201", "step": 34, "value": 1.1800557862047514, "stage": "improve", "created_at": 1789652564.808339}, {"event_id": "d4c8d54b3a234fea8140f0eab310c0ee", "step": 36, "value": 1.1382860874980842, "stage": "improve", "created_at": 1789653749.6895676}, {"event_id": "9f2acf8a5e0a45dd90d77de42cca1d36", "step": 37, "value": 1.1668299735770375, "stage": "improve", "created_at": 1789654299.0240662}, {"event_id": "f7aacbd14ee14fc0b77d836eca948cf5", "step": 39, "value": 1.1349731715897222, "stage": "improve", "created_at": 1789655039.2052536}], "maximize": false, "node_count": 40, "metric_name": "BPB", "curve_scope": "原始候选验证 BPB（可能含回滚或预算后记录），不作为预算内最终成绩。最终成绩以 all_runs_final.csv 为准。", "official_score": null}, {"id": "xixian.bo-study-gp7-logei.seed42", "experiment_id": "nanogpt-development-r1-v1-20260917", "family": "nanoGPT", "method": "bo_study_gp7_logei", "dataset": "nanoGPT", "seed": "42", "status": "completed", "best_valid_bpb": 1.1242429564434022, "elapsed_seconds": 21600.0, "budget_seconds": 21600.0, "comparison_eligible": true, "note": "user_amended_6h_current_action_completed", "artifacts": [{"bundle_id": "01-read-first-and-final-states", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/01-read-first-and-final-states/logs-c828e9f97191.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/01-read-first-and-final-states", "member": "MLEvolve_BO/research/nanogpt_bo_20260917/analysis/final_closeout_20260918/all_runs_final.csv", "sha256": "c828e9f97191ffc3f6f4fa6f39045e6be494d2ab2ea3337eff18dfd2830908ba"}, {"bundle_id": "02-study-run-logs", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/02-study-run-logs/logs-50a9df8a8a5a.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/02-study-run-logs", "member": "MLEvolve_BO/research/nanogpt_bo_20260917/development_r1_v1/bo_study_gp7_logei/runs/20260917_041227_bo_study_gp7_logei/logs/journal.json", "sha256": "50a9df8a8a5acb631814aa5ea6a0f2e8b7d47ec05bff989ffaa975aa9ca71d25"}], "ledger": {"campaign": "development_r1_v1", "stage": "development", "method": "bo_study_gp7_logei", "version": "development_r1_v1", "seed": "42", "training_seed": "42", "state": "finished", "complete_budget": "True", "launch_allowed": "", "not_launched_reason": "", "complete_8h": "False", "active_seconds": "21600", "budget_seconds": "21600", "source_duration_seconds": "28800", "budget_amended": "True", "raw_active_seconds": "22729.42967772484", "post_budget_active_seconds": "1129.4296777248383", "comparison_eligible": "True", "protocol_invalid_results": "0", "raw_reported_valid": "32", "raw_reported_best_bpb": "1.0956682943624008", "validity_audit": "", "comparison_exclusion_reason": "", "policy_contamination_started_at": "", "active_gpu_hours": "6.0", "actual_elapsed_seconds": "23194.40518093109", "segment_gpu_hours_including_cleanup": "6.313730466034677", "between_segment_seconds": "464.97550320625305", "completed": "38", "raw_completed": "40", "unverified_commit_time_count": "0", "post_budget_completed": "2", "valid": "30", "failure_fraction": "0.21052631578947367", "best_bpb_so_far": "1.1242429564434022", "final_bpb": "1.1242429564434022", "best_node_id": "9b830a4902934fde89df0097dd6c0915", "llm_attempts": "156", "llm_cli_reported_tokens_known": "3086308", "llm_attempts_unknown_tokens": "0", "llm_measured_wall_seconds": "6521.564327478409", "llm_unfinished_attempts": "0", "llm_failed_or_interrupted_attempts": "0", "allocated_gpu_hours": "6.430555555555555", "allocated_gpu_hours_accounting_final": "True", "resource_records": "[\"10829750\", \"10832308\", \"10833227\"]", "resource_accounting_captured_at": "[\"2026-09-18T07:57:20.346825+00:00\"]", "gpu_models": "[\"NVIDIA A100-SXM4-80GB\"]", "completed_proposal_wall_seconds": "21338.079143378884", "raw_completed_proposal_wall_seconds": "22463.558650666848", "diagnostic_feedback_scope": "Only results committed within the registered budget; later DEBUG repairs and mature labels excluded", "diagnostic_excluded_late_transitions": "2", "closed_proposals": "30", "unclosed_proposals": "2", "unknown_closure_proposals": "0", "closed_proposal_failure_fraction": "0.0", "raw_reported_closed_proposal_failure_fraction": "0.0", "debug_repaired_proposals": "5", "raw_serial_actions": "43", "raw_actions_with_error_logs": "0", "raw_training_launches": "38", "interrupted_actions": "0", "interrupted_action_active_seconds_upper_bound": "0", "gpu_uuid": "GPU-e27f237e-7e81-8bb7-b62a-dcb4172c4550", "job_id": "10833227", "node": "cn-g026.server.mila.quebec", "started_at": "2026-09-17T08:11:49.414297+00:00", "finished_at": "2026-09-17T14:38:23.819478+00:00", "stop_reason": "user_amended_6h_current_action_completed", "training_rows": "24", "incomplete_windows": "", "current_label_diagnostics": "{}", "threshold_active_seconds": "{\"1.2\": 4701.779703140259, \"1.15\": 9437.871703147888, \"1.1\": null}", "log_dir": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r1_v1/bo_study_gp7_logei/runs/20260917_041227_bo_study_gp7_logei/logs", "committed_evidence": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r1_v1/bo_study_gp7_logei/checkpoints/boundary-1789655901060439294/logs", "final_solution": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r1_v1/bo_study_gp7_logei/runs/20260917_041227_bo_study_gp7_logei/workspace/trials/9b830a4902934fde89df0097dd6c0915/candidate.py"}, "journal_ref": "02-study-run-logs:MLEvolve_BO/research/nanogpt_bo_20260917/development_r1_v1/bo_study_gp7_logei/runs/20260917_041227_bo_study_gp7_logei/logs/journal.json", "metrics": [{"event_id": "8d70b9bbca644911b3e15dc8d6f6733c", "step": 1, "value": 1.492807688409709, "stage": "draft", "created_at": 1789632777.9663095}, {"event_id": "970b07f93af649f692eea0619ac27936", "step": 4, "value": 1.445368923849263, "stage": "improve", "created_at": 1789634779.3633277}, {"event_id": "72b941916f9d46a8831bb4dbf5a8474c", "step": 5, "value": 1.4547396533804162, "stage": "debug", "created_at": 1789635397.913103}, {"event_id": "716925b2afc24d8ba0fd5746bf834f4d", "step": 6, "value": 3.285944688474341, "stage": "debug", "created_at": 1789635919.5389497}, {"event_id": "99754e285eaa44a4a4bbe81f5df9668d", "step": 8, "value": 1.150213878922556, "stage": "improve", "created_at": 1789636900.9407759}, {"event_id": "633fb68953744cb3be1e57349ea34413", "step": 10, "value": 1.2524390749660346, "stage": "debug", "created_at": 1789637615.0571315}, {"event_id": "7fadea949cb34048a248f72c85753cda", "step": 11, "value": 1.157838231144985, "stage": "improve", "created_at": 1789638194.4836087}, {"event_id": "a72bb208cbb645ad805a92eef9a2b9b2", "step": 13, "value": 1.30191681582222, "stage": "improve", "created_at": 1789638959.367436}, {"event_id": "61388841ba864b4781f82544d9cdc1e7", "step": 14, "value": 1.1733584249966098, "stage": "evolution", "created_at": 1789639556.316379}, {"event_id": "20e2a19b45d0450190a521f84f65fd54", "step": 15, "value": 1.2172727618499533, "stage": "debug", "created_at": 1789640208.9161499}, {"event_id": "fdd40372e54246649e63d97588766b7e", "step": 16, "value": 1.317073626161668, "stage": "draft", "created_at": 1789640710.2071874}, {"event_id": "421a4dd324534226b615175f457a9fed", "step": 17, "value": 1.142093887594924, "stage": "evolution", "created_at": 1789641595.7275145}, {"event_id": "ed0fc79d94af42cc804f1a3e2920e2bc", "step": 18, "value": 1.230374695851166, "stage": "improve", "created_at": 1789642241.5046031}, {"event_id": "da5e1b71f7994a01ad69d11c691d4d83", "step": 19, "value": 1.2292003936649816, "stage": "improve", "created_at": 1789642861.9023628}, {"event_id": "74cccc397c1d4c14b877aa59ae9c91bb", "step": 20, "value": 1.130509268587734, "stage": "improve", "created_at": 1789643602.923057}, {"event_id": "5d00308ba331437299fc8424013da9ce", "step": 21, "value": 1.2887869276713217, "stage": "improve", "created_at": 1789644281.280422}, {"event_id": "d582145fdd594949b8979903de2205bb", "step": 22, "value": 1.1575858134027284, "stage": "improve", "created_at": 1789644931.3486233}, {"event_id": "47540cb9f1674cd4bc5313055c2af324", "step": 23, "value": 1.237446855309069, "stage": "improve", "created_at": 1789645537.27911}, {"event_id": "257ada59f0a74249a9a44769939f86b4", "step": 25, "value": 1.1316191849367672, "stage": "evolution", "created_at": 1789646693.881162}, {"event_id": "98f141cade3b4436881b0e1d90ffe84c", "step": 27, "value": 1.1954376157080902, "stage": "evolution", "created_at": 1789647698.9573252}, {"event_id": "492913dcd23d4bb9bd1f27ef844769fc", "step": 28, "value": 1.1562710021912406, "stage": "fusion", "created_at": 1789648280.320208}, {"event_id": "2b8353ca053d4a1e82931749bf8bccd1", "step": 29, "value": 1.180954550442047, "stage": "debug", "created_at": 1789648855.5678747}, {"event_id": "68bd17a4d47c440983dfe6574e5d7ba8", "step": 30, "value": 1.144761338254716, "stage": "improve", "created_at": 1789649416.934106}, {"event_id": "357efe44341b4bc484fefa3759b431d0", "step": 31, "value": 1.1333588763536662, "stage": "improve", "created_at": 1789650006.068987}, {"event_id": "4ce1ff2cd9d041778bde2bbcc3677f38", "step": 32, "value": 1.1875273286921064, "stage": "improve", "created_at": 1789650607.3213508}, {"event_id": "a26c4d1263574e8f92797e541235bb9c", "step": 33, "value": 1.2238042446508823, "stage": "fusion", "created_at": 1789651131.3248804}, {"event_id": "12740737f2d9438d974a07afe2e78869", "step": 34, "value": 1.1339334220280501, "stage": "improve", "created_at": 1789651738.7652273}, {"event_id": "9b830a4902934fde89df0097dd6c0915", "step": 35, "value": 1.1242429564434022, "stage": "improve", "created_at": 1789652272.5794632}, {"event_id": "d09e3da3cfb34065ba98b75a46e11c05", "step": 37, "value": 1.1326570777573903, "stage": "improve", "created_at": 1789653113.7191129}, {"event_id": "56ea9dcf33474212aa43c3a3093ed160", "step": 38, "value": 1.1266044244849547, "stage": "improve", "created_at": 1789654245.6109614}, {"event_id": "21f9a39a572f459a8a09f1b4dfd0b389", "step": 39, "value": 1.0956682943624008, "stage": "debug", "created_at": 1789654785.1800313}, {"event_id": "cf339afdbc20430f9155f91350ca6862", "step": 40, "value": 1.2581336390607227, "stage": "improve", "created_at": 1789655415.9768245}], "maximize": false, "node_count": 41, "metric_name": "BPB", "curve_scope": "原始候选验证 BPB（可能含回滚或预算后记录），不作为预算内最终成绩。最终成绩以 all_runs_final.csv 为准。", "official_score": null}, {"id": "xixian.bo-study-gp7-mean.seed42", "experiment_id": "nanogpt-development-r1-v1-20260917", "family": "nanoGPT", "method": "bo_study_gp7_mean", "dataset": "nanoGPT", "seed": "42", "status": "completed", "best_valid_bpb": 1.1196253269171514, "elapsed_seconds": 21600.0, "budget_seconds": 21600.0, "comparison_eligible": true, "note": "user_amended_6h_current_action_completed", "artifacts": [{"bundle_id": "01-read-first-and-final-states", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/01-read-first-and-final-states/logs-c828e9f97191.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/01-read-first-and-final-states", "member": "MLEvolve_BO/research/nanogpt_bo_20260917/analysis/final_closeout_20260918/all_runs_final.csv", "sha256": "c828e9f97191ffc3f6f4fa6f39045e6be494d2ab2ea3337eff18dfd2830908ba"}, {"bundle_id": "02-study-run-logs", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/02-study-run-logs/logs-50a9df8a8a5a.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/02-study-run-logs", "member": "MLEvolve_BO/research/nanogpt_bo_20260917/development_r1_v1/bo_study_gp7_mean/runs/20260917_041227_bo_study_gp7_mean/logs/journal.json", "sha256": "50a9df8a8a5acb631814aa5ea6a0f2e8b7d47ec05bff989ffaa975aa9ca71d25"}], "ledger": {"campaign": "development_r1_v1", "stage": "development", "method": "bo_study_gp7_mean", "version": "development_r1_v1", "seed": "42", "training_seed": "42", "state": "finished", "complete_budget": "True", "launch_allowed": "", "not_launched_reason": "", "complete_8h": "False", "active_seconds": "21600", "budget_seconds": "21600", "source_duration_seconds": "28800", "budget_amended": "True", "raw_active_seconds": "22591.667818307877", "post_budget_active_seconds": "991.6678183078766", "comparison_eligible": "True", "protocol_invalid_results": "0", "raw_reported_valid": "32", "raw_reported_best_bpb": "1.112076033864291", "validity_audit": "", "comparison_exclusion_reason": "", "policy_contamination_started_at": "", "active_gpu_hours": "6.0", "actual_elapsed_seconds": "23146.080447912216", "segment_gpu_hours_including_cleanup": "6.275463282863299", "between_segment_seconds": "554.4126296043396", "completed": "41", "raw_completed": "43", "unverified_commit_time_count": "0", "post_budget_completed": "2", "valid": "30", "failure_fraction": "0.2682926829268293", "best_bpb_so_far": "1.1196253269171514", "final_bpb": "1.1196253269171514", "best_node_id": "9585a3c506b4464eafbbe0d94d30ef0d", "llm_attempts": "155", "llm_cli_reported_tokens_known": "3085213", "llm_attempts_unknown_tokens": "0", "llm_measured_wall_seconds": "6123.455632925034", "llm_unfinished_attempts": "0", "llm_failed_or_interrupted_attempts": "0", "allocated_gpu_hours": "6.430555555555555", "allocated_gpu_hours_accounting_final": "True", "resource_records": "[\"10829750\", \"10832308\", \"10833227\"]", "resource_accounting_captured_at": "[\"2026-09-18T07:57:20.346825+00:00\"]", "gpu_models": "[\"NVIDIA A100-SXM4-80GB\"]", "completed_proposal_wall_seconds": "21059.69546472002", "raw_completed_proposal_wall_seconds": "22338.85715072276", "diagnostic_feedback_scope": "Only results committed within the registered budget; later DEBUG repairs and mature labels excluded", "diagnostic_excluded_late_transitions": "2", "closed_proposals": "30", "unclosed_proposals": "1", "unknown_closure_proposals": "0", "closed_proposal_failure_fraction": "0.0", "raw_reported_closed_proposal_failure_fraction": "0.0", "debug_repaired_proposals": "9", "raw_serial_actions": "46", "raw_actions_with_error_logs": "0", "raw_training_launches": "43", "interrupted_actions": "0", "interrupted_action_active_seconds_upper_bound": "0", "gpu_uuid": "GPU-d643eb43-635f-a053-e2f5-aaf1fa80f917", "job_id": "10833227", "node": "cn-g026.server.mila.quebec", "started_at": "2026-09-17T08:11:49.424627+00:00", "finished_at": "2026-09-17T14:37:35.505075+00:00", "stop_reason": "user_amended_6h_current_action_completed", "training_rows": "25", "incomplete_windows": "", "current_label_diagnostics": "{}", "threshold_active_seconds": "{\"1.2\": 5898.722373485565, \"1.15\": 9669.020373344421, \"1.1\": null}", "log_dir": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r1_v1/bo_study_gp7_mean/runs/20260917_041227_bo_study_gp7_mean/logs", "committed_evidence": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r1_v1/bo_study_gp7_mean/checkpoints/boundary-1789655852895727744/logs", "final_solution": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r1_v1/bo_study_gp7_mean/runs/20260917_041227_bo_study_gp7_mean/workspace/trials/9585a3c506b4464eafbbe0d94d30ef0d/candidate.py"}, "journal_ref": "02-study-run-logs:MLEvolve_BO/research/nanogpt_bo_20260917/development_r1_v1/bo_study_gp7_mean/runs/20260917_041227_bo_study_gp7_mean/logs/journal.json", "metrics": [{"event_id": "6f25b08975ef4a2eae8252a093b137af", "step": 1, "value": 1.5007289501390777, "stage": "draft", "created_at": 1789632777.9819043}, {"event_id": "ea515594be1840aa88795101da37e657", "step": 4, "value": 1.850219678032227, "stage": "improve", "created_at": 1789634736.6528602}, {"event_id": "b95dd3b8a54e4e1cb64bdbfb722efd5c", "step": 5, "value": 1.4964610098610556, "stage": "debug", "created_at": 1789635546.9073403}, {"event_id": "07ff5b1636eb4c2fa1d5db1341e2800a", "step": 6, "value": 3.285304288529302, "stage": "debug", "created_at": 1789636135.2250805}, {"event_id": "22ef91119e2540119dc3f63810c8976b", "step": 9, "value": 1.5382821981215837, "stage": "improve", "created_at": 1789637603.54498}, {"event_id": "a13ea8fa99654627b06f53d2de9d320a", "step": 10, "value": 1.161750315845637, "stage": "debug", "created_at": 1789638079.8528101}, {"event_id": "4c99bd3b88594f56944263c586f9c566", "step": 11, "value": 1.2897427961473047, "stage": "debug", "created_at": 1789638637.702637}, {"event_id": "30ed169174e74cf581d5e67ec4080147", "step": 13, "value": 1.2102797966309622, "stage": "improve", "created_at": 1789639480.7047386}, {"event_id": "3ccda040ea8f4f1aa33560b0b89a1a77", "step": 14, "value": 1.1689657667780406, "stage": "improve", "created_at": 1789640043.1524794}, {"event_id": "0928659dba434703b695972f03f1e07d", "step": 15, "value": 1.1715024553712041, "stage": "debug", "created_at": 1789640557.5357559}, {"event_id": "24bbaba77daf45d89fa7a69fed6dda1c", "step": 16, "value": 1.3170297000187745, "stage": "draft", "created_at": 1789641028.6432602}, {"event_id": "155ab3d39a734f66a3eb2dcf273d08df", "step": 17, "value": 1.142704492490366, "stage": "evolution", "created_at": 1789641898.6171873}, {"event_id": "9f6d42feeab54e6abca5ce50158450f7", "step": 18, "value": 1.2164712109457134, "stage": "improve", "created_at": 1789642459.7170906}, {"event_id": "1e57d5e1f2874689a28805673658759c", "step": 19, "value": 1.1898640350390806, "stage": "improve", "created_at": 1789643557.930968}, {"event_id": "433d497f007a46998e83b28d5e7995d0", "step": 22, "value": 1.3206954931709924, "stage": "improve", "created_at": 1789644396.3561525}, {"event_id": "db5c539e4d284d9bb369f6cdd3af4534", "step": 23, "value": 1.2285900104123446, "stage": "debug", "created_at": 1789644858.6766798}, {"event_id": "8d69bc2244c145bba9b0388fec94ebd6", "step": 24, "value": 1.225966791136859, "stage": "debug", "created_at": 1789645366.474992}, {"event_id": "e33fdb30da2a420c93253ba6431f6a6c", "step": 26, "value": 1.1971741836254215, "stage": "evolution", "created_at": 1789646354.0258944}, {"event_id": "e7b0de884e7c4673b66273253013f7a3", "step": 27, "value": 1.1650535198055691, "stage": "evolution", "created_at": 1789646955.7564468}, {"event_id": "4087f08789c742a7878d21510ec5c6e5", "step": 28, "value": 1.2913272946697787, "stage": "debug", "created_at": 1789647418.309448}, {"event_id": "a469dfa53ead4870bd23efe5efc1248c", "step": 29, "value": 1.1516497636811514, "stage": "evolution", "created_at": 1789647894.3763008}, {"event_id": "ee3b1dacc0f74a61aeb0bfbd423b16d2", "step": 30, "value": 1.1452041628746228, "stage": "fusion", "created_at": 1789648393.6479857}, {"event_id": "29b2784c38f647cb9fd1f23ddf5838da", "step": 31, "value": 1.13443392915472, "stage": "fusion", "created_at": 1789648894.5154269}, {"event_id": "98e0c6ac349c4ba995cf2cf43786b5d6", "step": 32, "value": 1.2733498432156916, "stage": "improve", "created_at": 1789649497.2413025}, {"event_id": "e294cca7d05b4445a1516429b761b0f8", "step": 33, "value": 1.1461064710006623, "stage": "improve", "created_at": 1789650056.7243464}, {"event_id": "9585a3c506b4464eafbbe0d94d30ef0d", "step": 35, "value": 1.1196253269171514, "stage": "improve", "created_at": 1789651111.059367}, {"event_id": "6856ebdb4de64173887bee8e8a0ccffc", "step": 36, "value": 1.1453543770592973, "stage": "improve", "created_at": 1789651672.5479548}, {"event_id": "05e44da9f0e04cc5b6a258a182b838cc", "step": 38, "value": 1.1238430052629036, "stage": "improve", "created_at": 1789652665.3313005}, {"event_id": "6a80536fc9384fb89a3b865fce2ddf22", "step": 40, "value": 1.134514996108937, "stage": "debug", "created_at": 1789653471.9690955}, {"event_id": "a84075bbe7b74cab9354cdae70c7ff04", "step": 41, "value": 1.1270261292744654, "stage": "fusion", "created_at": 1789654083.8556914}, {"event_id": "b121c4bbdb744066a1cbc2156a21949d", "step": 42, "value": 1.1208459111827855, "stage": "evolution", "created_at": 1789654681.7112}, {"event_id": "390a848214134e349c38d13adb809ea0", "step": 43, "value": 1.112076033864291, "stage": "evolution", "created_at": 1789655324.7585392}], "maximize": false, "node_count": 44, "metric_name": "BPB", "curve_scope": "原始候选验证 BPB（可能含回滚或预算后记录），不作为预算内最终成绩。最终成绩以 all_runs_final.csv 为准。", "official_score": null}, {"id": "xixian.bo-study-gp7-no-ancestry-ucb.seed42", "experiment_id": "nanogpt-development-r1-v1-20260917", "family": "nanoGPT", "method": "bo_study_gp7_no_ancestry_ucb", "dataset": "nanoGPT", "seed": "42", "status": "stopped", "best_valid_bpb": null, "elapsed_seconds": 12935.75233745575, "budget_seconds": 21600.0, "comparison_eligible": false, "note": "A non-causal candidate was admitted and changed subsequent selector state; no posthoc repair can turn this trajectory into the originally registered valid run.", "artifacts": [{"bundle_id": "01-read-first-and-final-states", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/01-read-first-and-final-states/logs-c828e9f97191.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/01-read-first-and-final-states", "member": "MLEvolve_BO/research/nanogpt_bo_20260917/analysis/final_closeout_20260918/all_runs_final.csv", "sha256": "c828e9f97191ffc3f6f4fa6f39045e6be494d2ab2ea3337eff18dfd2830908ba"}, {"bundle_id": "02-study-run-logs", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/02-study-run-logs/logs-50a9df8a8a5a.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/02-study-run-logs", "member": "MLEvolve_BO/research/nanogpt_bo_20260917/development_r1_v1/bo_study_gp7_no_ancestry_ucb/runs/20260917_041228_bo_study_gp7_no_ancestry_ucb/logs/journal.json", "sha256": "50a9df8a8a5acb631814aa5ea6a0f2e8b7d47ec05bff989ffaa975aa9ca71d25"}], "ledger": {"campaign": "development_r1_v1", "stage": "development", "method": "bo_study_gp7_no_ancestry_ucb", "version": "development_r1_v1", "seed": "42", "training_seed": "42", "state": "early_stopped", "complete_budget": "False", "launch_allowed": "", "not_launched_reason": "", "complete_8h": "False", "active_seconds": "12935.75233745575", "budget_seconds": "21600", "source_duration_seconds": "28800", "budget_amended": "True", "raw_active_seconds": "12935.75233745575", "post_budget_active_seconds": "0.0", "comparison_eligible": "False", "protocol_invalid_results": "1", "raw_reported_valid": "17", "raw_reported_best_bpb": "0.00835988795802198", "validity_audit": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r1_v1/bo_study_gp7_no_ancestry_ucb/validity_audit.json", "comparison_exclusion_reason": "A non-causal candidate was admitted and changed subsequent selector state; no posthoc repair can turn this trajectory into the originally registered valid run.", "policy_contamination_started_at": "2026-09-17T11:34:05.131988+00:00", "active_gpu_hours": "3.5932645381821526", "actual_elapsed_seconds": "13495.37416100502", "segment_gpu_hours_including_cleanup": "3.5932645381821526", "between_segment_seconds": "559.6218235492706", "completed": "24", "raw_completed": "24", "unverified_commit_time_count": "0", "post_budget_completed": "0", "valid": "16", "failure_fraction": "0.33333333333333337", "best_bpb_so_far": "1.1132253923824948", "final_bpb": "", "best_node_id": "c7f5dcca33b144eaafa5d4eba9ced73a", "llm_attempts": "92", "llm_cli_reported_tokens_known": "1777045", "llm_attempts_unknown_tokens": "0", "llm_measured_wall_seconds": "3924.1680765151978", "llm_unfinished_attempts": "0", "llm_failed_or_interrupted_attempts": "0", "allocated_gpu_hours": "4.5956204937564", "allocated_gpu_hours_accounting_final": "True", "resource_records": "[\"10829750\", \"10832308\", \"10833227\"]", "resource_accounting_captured_at": "[\"2026-09-18T07:57:20.346825+00:00\"]", "gpu_models": "[\"NVIDIA A100-SXM4-80GB\"]", "completed_proposal_wall_seconds": "12770.928102182224", "raw_completed_proposal_wall_seconds": "12770.928102182224", "diagnostic_feedback_scope": "Only results committed within the registered budget; later DEBUG repairs and mature labels excluded", "diagnostic_excluded_late_transitions": "0", "closed_proposals": "17", "unclosed_proposals": "2", "unknown_closure_proposals": "0", "closed_proposal_failure_fraction": "0.058823529411764705", "raw_reported_closed_proposal_failure_fraction": "0.0", "debug_repaired_proposals": "2", "raw_serial_actions": "27", "raw_actions_with_error_logs": "0", "raw_training_launches": "20", "interrupted_actions": "0", "interrupted_action_active_seconds_upper_bound": "0", "gpu_uuid": "GPU-06c12867-49f5-9c50-ffee-2bb91574fb7c", "job_id": "10832308", "node": "cn-g017.server.mila.quebec", "started_at": "2026-09-17T08:11:49.418432+00:00", "finished_at": "2026-09-17T11:56:44.792593+00:00", "stop_reason": "protocol_invalid_noncausal_admitted_result", "training_rows": "13", "incomplete_windows": "", "current_label_diagnostics": "{}", "threshold_active_seconds": "{\"1.2\": 6982.296568155289, \"1.15\": 8730.36156821251, \"1.1\": null}", "log_dir": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r1_v1/bo_study_gp7_no_ancestry_ucb/runs/20260917_041228_bo_study_gp7_no_ancestry_ucb/logs", "committed_evidence": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r1_v1/bo_study_gp7_no_ancestry_ucb/checkpoints/boundary-1789646202526097005/logs", "final_solution": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r1_v1/bo_study_gp7_no_ancestry_ucb/runs/20260917_041228_bo_study_gp7_no_ancestry_ucb/workspace/trials/c7f5dcca33b144eaafa5d4eba9ced73a/candidate.py"}, "journal_ref": "02-study-run-logs:MLEvolve_BO/research/nanogpt_bo_20260917/development_r1_v1/bo_study_gp7_no_ancestry_ucb/runs/20260917_041228_bo_study_gp7_no_ancestry_ucb/logs/journal.json", "metrics": [{"event_id": "e26dfe8bca4c4463967da006aaab4290", "step": 1, "value": 1.4915872244834718, "stage": "draft", "created_at": 1789632778.130228}, {"event_id": "2ea03a58686e47cdbe2d90b8eb1e98d9", "step": 4, "value": 1.4976662766786304, "stage": "improve", "created_at": 1789634741.7297003}, {"event_id": "66e054c8b389400aaeacf9a52ef28153", "step": 5, "value": 1.4461247164965387, "stage": "debug", "created_at": 1789635631.4024231}, {"event_id": "a9f2220191974961beae6cbd0395979b", "step": 7, "value": 1.5588119988637241, "stage": "improve", "created_at": 1789636859.2150712}, {"event_id": "5360adfc56934973b5828d094c779f20", "step": 8, "value": 1.2481360885010369, "stage": "improve", "created_at": 1789637426.834062}, {"event_id": "1cf999a34d8942e08dd34e71ffd9ce88", "step": 9, "value": 2.5505333601641533, "stage": "debug", "created_at": 1789638020.8988807}, {"event_id": "3e7125937cd64f15b80e366007209f94", "step": 10, "value": 1.2537540041207809, "stage": "improve", "created_at": 1789638593.3913841}, {"event_id": "182e86065932431fb8bd38ffffab005a", "step": 11, "value": 1.1691453270025933, "stage": "improve", "created_at": 1789639248.8350146}, {"event_id": "24834e825a134b8da3060be33629edab", "step": 12, "value": 1.1734443940507067, "stage": "improve", "created_at": 1789639827.988103}, {"event_id": "f7e7b02593b945759e712548770baf7c", "step": 13, "value": 1.1792528343582405, "stage": "improve", "created_at": 1789640388.0139873}, {"event_id": "25b4f563ad194fa09cc95107c9aa5df7", "step": 14, "value": 1.1305266681469734, "stage": "improve", "created_at": 1789640981.1431549}, {"event_id": "c7f5dcca33b144eaafa5d4eba9ced73a", "step": 15, "value": 1.1132253923824948, "stage": "improve", "created_at": 1789641580.7620103}, {"event_id": "fb7b68977ea44faba4e7d2d8dccbedb5", "step": 17, "value": 1.1306510670017524, "stage": "improve", "created_at": 1789642348.6772277}, {"event_id": "6333588b9d9449fe98c74b52411f734d", "step": 18, "value": 1.1596680542409161, "stage": "improve", "created_at": 1789643560.4528816}, {"event_id": "ff2859aac8804fb6842c617094a5285a", "step": 20, "value": 0.00835988795802198, "stage": "improve", "created_at": 1789644249.7334008}, {"event_id": "9491587464134f868f5f7fa130d6472e", "step": 21, "value": 1.2592811106199098, "stage": "improve", "created_at": 1789644966.591484}, {"event_id": "d44854a0a0a14eeea9b6b9864831b37a", "step": 24, "value": 1.1931534148776732, "stage": "improve", "created_at": 1789645722.1654627}], "maximize": false, "node_count": 25, "metric_name": "BPB", "curve_scope": "原始候选验证 BPB（可能含回滚或预算后记录），不作为预算内最终成绩。最终成绩以 all_runs_final.csv 为准。", "official_score": null}, {"id": "xixian.bo-study-gp7-long-ucb.seed42", "experiment_id": "nanogpt-development-r1-v1-20260917", "family": "nanoGPT", "method": "bo_study_gp7_long_ucb", "dataset": "nanoGPT", "seed": "42", "status": "completed", "best_valid_bpb": 1.1331051971776425, "elapsed_seconds": 21600.0, "budget_seconds": 21600.0, "comparison_eligible": true, "note": "user_amended_6h_current_action_completed", "artifacts": [{"bundle_id": "01-read-first-and-final-states", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/01-read-first-and-final-states/logs-c828e9f97191.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/01-read-first-and-final-states", "member": "MLEvolve_BO/research/nanogpt_bo_20260917/analysis/final_closeout_20260918/all_runs_final.csv", "sha256": "c828e9f97191ffc3f6f4fa6f39045e6be494d2ab2ea3337eff18dfd2830908ba"}, {"bundle_id": "02-study-run-logs", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/02-study-run-logs/logs-50a9df8a8a5a.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/02-study-run-logs", "member": "MLEvolve_BO/research/nanogpt_bo_20260917/development_r1_v1/bo_study_gp7_long_ucb/runs/20260917_041228_bo_study_gp7_long_ucb/logs/journal.json", "sha256": "50a9df8a8a5acb631814aa5ea6a0f2e8b7d47ec05bff989ffaa975aa9ca71d25"}], "ledger": {"campaign": "development_r1_v1", "stage": "development", "method": "bo_study_gp7_long_ucb", "version": "development_r1_v1", "seed": "42", "training_seed": "42", "state": "finished", "complete_budget": "True", "launch_allowed": "", "not_launched_reason": "", "complete_8h": "False", "active_seconds": "21600", "budget_seconds": "21600", "source_duration_seconds": "28800", "budget_amended": "True", "raw_active_seconds": "22402.323688983917", "post_budget_active_seconds": "802.3236889839172", "comparison_eligible": "True", "protocol_invalid_results": "0", "raw_reported_valid": "32", "raw_reported_best_bpb": "1.1331051971776425", "validity_audit": "", "comparison_exclusion_reason": "", "policy_contamination_started_at": "", "active_gpu_hours": "6.0", "actual_elapsed_seconds": "22890.400906085968", "segment_gpu_hours_including_cleanup": "6.222867691384422", "between_segment_seconds": "488.0772171020508", "completed": "36", "raw_completed": "38", "unverified_commit_time_count": "0", "post_budget_completed": "2", "valid": "31", "failure_fraction": "0.13888888888888884", "best_bpb_so_far": "1.1331051971776425", "final_bpb": "1.1331051971776425", "best_node_id": "b1f1f4de7f364a4aa1fbacc3b2f59b67", "llm_attempts": "151", "llm_cli_reported_tokens_known": "2994614", "llm_attempts_unknown_tokens": "0", "llm_measured_wall_seconds": "6387.7907807827", "llm_unfinished_attempts": "0", "llm_failed_or_interrupted_attempts": "0", "allocated_gpu_hours": "6.430555555555555", "allocated_gpu_hours_accounting_final": "True", "resource_records": "[\"10829750\", \"10832308\", \"10833227\"]", "resource_accounting_captured_at": "[\"2026-09-18T07:57:20.346825+00:00\"]", "gpu_models": "[\"NVIDIA A100-SXM4-80GB\"]", "completed_proposal_wall_seconds": "21214.002198183443", "raw_completed_proposal_wall_seconds": "22161.07341492921", "diagnostic_feedback_scope": "Only results committed within the registered budget; later DEBUG repairs and mature labels excluded", "diagnostic_excluded_late_transitions": "2", "closed_proposals": "31", "unclosed_proposals": "2", "unknown_closure_proposals": "0", "closed_proposal_failure_fraction": "0.0", "raw_reported_closed_proposal_failure_fraction": "0.0", "debug_repaired_proposals": "2", "raw_serial_actions": "41", "raw_actions_with_error_logs": "0", "raw_training_launches": "38", "interrupted_actions": "0", "interrupted_action_active_seconds_upper_bound": "0", "gpu_uuid": "GPU-8dd659f6-d359-7105-c089-3f532d8b9df7", "job_id": "10833227", "node": "cn-g026.server.mila.quebec", "started_at": "2026-09-17T08:11:49.422350+00:00", "finished_at": "2026-09-17T14:33:19.823256+00:00", "stop_reason": "user_amended_6h_current_action_completed", "training_rows": "11", "incomplete_windows": "8", "current_label_diagnostics": "{\"long_horizon_contract\": \"primary_direction_budget_nonoverlap_v1\", \"horizon\": 2, \"horizon_is_feature\": false, \"window_policy\": \"observed_policy; pauses_and_parallelism_allowed; no_forced_continuation\", \"ordinary_proposal_count\": 29, \"pending_ordinary_count\": 0, \"complete_window_count\": 20, \"blocked_window_count\": 2, \"incomplete_window_count\": 9, \"overlap_excluded_count\": 9, \"training_count\": 11, \"training_windows\": [{\"horizon\": 2, \"contract\": \"primary_direction_budget_nonoverlap_v1\", \"origin_transition_id\": \"3d7b8e686ab84bb38b1600d5d48c3fac\", \"origin_decision_index\": 6, \"member_transition_ids\": [\"3d7b8e686ab84bb38b1600d5d48c3fac\", \"033d022c52d04f74ae40cf95b10449a7\"], \"member_decision_ids\": [\"1afb2ac818d64228aa7a21a7c3a5e80b\", \"defaec193b6a4a76b9159772e6535351\"], \"outcome_transition_id\": \"033d022c52d04f74ae40cf95b10449a7\", \"available_at\": \"2026-09-17T09:36:38.903111+00:00\", \"best_utility\": -1.2121463076680525, \"parent_utility\": -1.4464990758536103, \"gain\": 0.23435276818555772, \"failed_attempts\": 0, \"total_wall_time_sec\": 1121.119845659472}, {\"horizon\": 2, \"contract\": \"primary_direction_budget_nonoverlap_v1\", \"origin_transition_id\": \"10ffa8bfef254b11ba5c939f32fe943c\", \"origin_decision_index\": 8, \"member_transition_ids\": [\"10ffa8bfef254b11ba5c939f32fe943c\", \"8e30a5e7f19240ebb30799dd40c470e6\"], \"member_decision_ids\": [\"5f2cd3999461410b854558ead1f6b95f\", \"8fac9c5ea0604534b7ba1b4a481dc554\"], \"outcome_transition_id\": \"8e30a5e7f19240ebb30799dd40c470e6\", \"available_at\": \"2026-09-17T09:56:27.390068+00:00\", \"best_utility\": -1.2133336239476669, \"parent_utility\": -1.2133336239476669, \"gain\": 0.0, \"failed_attempts\": 0, \"total_wall_time_sec\": 1187.4543714178726}, {\"horizon\": 2, \"contract\": \"primary_direction_budget_nonoverlap_v1\", \"origin_transition_id\": \"7e31626fccfc434a84c8cfeec49db6c2\", \"origin_decision_index\": 10, \"member_transition_ids\": [\"7e31626fccfc434a84c8cfeec49db6c2\", \"61df03239aa641ef8d63a4ccc4a9fc1f\"], \"member_decision_ids\": [\"e2d201bf0bb24151b43dec3566452345\", \"47946707d6374ff295a4a6e6cb88b0b2\"], \"outcome_transition_id\": \"61df03239aa641ef8d63a4ccc4a9fc1f\", \"available_at\": \"2026-09-17T10:16:46.096868+00:00\", \"best_utility\": -1.2076129821459245, \"parent_utility\": -1.2121463076680525, \"gain\": 0.00453332552212804, \"failed_attempts\": 0, \"total_wall_time_sec\": 1217.4736954448745}, {\"horizon\": 2, \"contract\": \"primary_direction_budget_nonoverlap_v1\", \"origin_transition_id\": \"1a025e5854834589824075d8d9becc6e\", \"origin_decision_index\": 12, \"member_transition_ids\": [\"1a025e5854834589824075d8d9becc6e\", \"43740350d97b41b0890081104dada54c\"], \"member_decision_ids\": [\"53b1020702244dfcb3d4e2b7e4c1990b\", \"2ba667ca4bf944dfaa801c590fc09ea1\"], \"outcome_transition_id\": \"43740350d97b41b0890081104dada54c\", \"available_at\": \"2026-09-17T10:38:07.783721+00:00\", \"best_utility\": -1.1765658144358566, \"parent_utility\": -1.2076129821459245, \"gain\": 0.03104716771006788, \"failed_attempts\": 0, \"total_wall_time_sec\": 1279.084790554829}, {\"horizon\": 2, \"contract\": \"primary_direction_budget_nonoverlap_v1\", \"origin_transition_id\": \"c93ceef20fea4a92ae883fb110a4f40f\", \"origin_decision_index\": 15, \"member_transition_ids\": [\"c93ceef20fea4a92ae883fb110a4f40f\", \"962f297e40ee47988ae16927711dfcad\"], \"member_decision_ids\": [\"7418278167f7423cb3293d3aa367d025\", \"3c7e87d039f34df49bcf63aea01bdc27\"], \"outcome_transition_id\": \"962f297e40ee47988ae16927711dfcad\", \"available_at\": \"2026-09-17T11:08:33.138586+00:00\", \"best_utility\": -1.1760414802417165, \"parent_utility\": -1.1765658144358566, \"gain\": 0.0005243341941401081, \"failed_attempts\": 0, \"total_wall_time_sec\": 1249.5121225118637}, {\"horizon\": 2, \"contract\": \"primary_direction_budget_nonoverlap_v1\", \"origin_transition_id\": \"2caf48a44788473db4949ab8504c6a2e\", \"origin_decision_index\": 19, \"member_transition_ids\": [\"2caf48a44788473db4949ab8504c6a2e\", \"74518c2407104cdbb3c3340c5dc1e647\"], \"member_decision_ids\": [\"c9202571e48a48a8908cb9dffa1f5e57\", \"92218c5e8114476892307ad0735353cd\"], \"outcome_transition_id\": \"74518c2407104cdbb3c3340c5dc1e647\", \"available_at\": \"2026-09-17T11:53:05.016039+00:00\", \"best_utility\": -1.173311129749959, \"parent_utility\": -1.2133336239476669, \"gain\": 0.04002249419770787, \"failed_attempts\": 0, \"total_wall_time_sec\": 1171.624491641298}, {\"horizon\": 2, \"contract\": \"primary_direction_budget_nonoverlap_v1\", \"origin_transition_id\": \"de4c4a1f7309490491d4e8e797113a25\", \"origin_decision_index\": 22, \"member_transition_ids\": [\"de4c4a1f7309490491d4e8e797113a25\", \"38adedc065ea496793747dde265ac154\"], \"member_decision_ids\": [\"75549403e00449f288c84f494105a45b\", \"b99b378f48a0425c8164285b5dec8d0e\"], \"outcome_transition_id\": \"38adedc065ea496793747dde265ac154\", \"available_at\": \"2026-09-17T12:11:48.705826+00:00\", \"best_utility\": -1.173311129749959, \"parent_utility\": -1.173311129749959, \"gain\": 0.0, \"failed_attempts\": 0, \"total_wall_time_sec\": 1121.4235241832212}, {\"horizon\": 2, \"contract\": \"primary_direction_budget_nonoverlap_v1\", \"origin_transition_id\": \"4ead22bbdde64573a6f20643d429afd4\", \"origin_decision_index\": 24, \"member_transition_ids\": [\"4ead22bbdde64573a6f20643d429afd4\", \"444a6a2a43b44b94979adc7623ced315\"], \"member_decision_ids\": [\"e19665554399437b82ed2fa8a388de21\", \"d688a292f2aa46e8b04c91a9f47c5159\"], \"outcome_transition_id\": \"444a6a2a43b44b94979adc7623ced315\", \"available_at\": \"2026-09-17T12:44:14.028358+00:00\", \"best_utility\": -1.1546098926667647, \"parent_utility\": -1.1760414802417165, \"gain\": 0.021431587574951783, \"failed_attempts\": 0, \"total_wall_time_sec\": 1167.49027904775}, {\"horizon\": 2, \"contract\": \"primary_direction_budget_nonoverlap_v1\", \"origin_transition_id\": \"d085a2ecf479452b86cbb1dc45ed078d\", \"origin_decision_index\": 27, \"member_transition_ids\": [\"d085a2ecf479452b86cbb1dc45ed078d\", \"75f3714e37dc44f6b4f9cb7d810570b6\"], \"member_decision_ids\": [\"e241dcef4a364fe9ba4a6dbc57fa7b6c\", \"2c4406bd05274459b204e74cca724bd3\"], \"outcome_transition_id\": \"75f3714e37dc44f6b4f9cb7d810570b6\", \"available_at\": \"2026-09-17T13:13:25.568455+00:00\", \"best_utility\": -1.1457650727907722, \"parent_utility\": -1.1546098926667647, \"gain\": 0.008844819875992505, \"failed_attempts\": 0, \"total_wall_time_sec\": 1154.5177271747962}, {\"horizon\": 2, \"contract\": \"primary_direction_budget_nonoverlap_v1\", \"origin_transition_id\": \"7bec453fef494b16ab5cc33c7d95db8c\", \"origin_decision_index\": 30, \"member_transition_ids\": [\"7bec453fef494b16ab5cc33c7d95db8c\", \"9bc79813cecf484cbce82814385b6af6\"], \"member_decision_ids\": [\"c875efad989c4778bbe9647908f1b93f\", \"334c2e4156654fd78876d3fce06c9c1a\"], \"outcome_transition_id\": \"9bc79813cecf484cbce82814385b6af6\", \"available_at\": \"2026-09-17T13:35:14.003661+00:00\", \"best_utility\": -1.1331051971776425, \"parent_utility\": -1.1457650727907722, \"gain\": 0.012659875613129756, \"failed_attempts\": 0, \"total_wall_time_sec\": 1304.1806090958416}, {\"horizon\": 2, \"contract\": \"primary_direction_budget_nonoverlap_v1\", \"origin_transition_id\": \"d3a626e4e3894aeb951dcc0d9d8b01b1\", \"origin_decision_index\": 32, \"member_transition_ids\": [\"d3a626e4e3894aeb951dcc0d9d8b01b1\", \"bad657a740d14766b9d3b7c7ca5767c1\"], \"member_decision_ids\": [\"af8d095960e7485e9dffc6dd9f65d0c8\", \"e8159238eb694654b12533aff2584d52\"], \"outcome_transition_id\": \"bad657a740d14766b9d3b7c7ca5767c1\", \"available_at\": \"2026-09-17T13:56:27.586079+00:00\", \"best_utility\": -1.1331051971776425, \"parent_utility\": -1.1331051971776425, \"gain\": 0.0, \"failed_attempts\": 0, \"total_wall_time_sec\": 1270.2013330431655}]}", "threshold_active_seconds": "{\"1.2\": 8124.973649978638, \"1.15\": 17967.238345861435, \"1.1\": null}", "log_dir": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r1_v1/bo_study_gp7_long_ucb/runs/20260917_041228_bo_study_gp7_long_ucb/logs", "committed_evidence": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r1_v1/bo_study_gp7_long_ucb/checkpoints/boundary-1789655597357346834/logs", "final_solution": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r1_v1/bo_study_gp7_long_ucb/runs/20260917_041228_bo_study_gp7_long_ucb/workspace/trials/b1f1f4de7f364a4aa1fbacc3b2f59b67/candidate.py"}, "journal_ref": "02-study-run-logs:MLEvolve_BO/research/nanogpt_bo_20260917/development_r1_v1/bo_study_gp7_long_ucb/runs/20260917_041228_bo_study_gp7_long_ucb/logs/journal.json", "metrics": [{"event_id": "a48581e669ae45ce8ccecc01077d14de", "step": 1, "value": 1.4801891582983795, "stage": "draft", "created_at": 1789632778.112468}, {"event_id": "9c6b4e7cc0034a7eb2ca937fcc055f83", "step": 4, "value": 1.87266096945655, "stage": "improve", "created_at": 1789634746.1378028}, {"event_id": "975ef6dede38400ab0236a4720a0d015", "step": 5, "value": 1.4464990758536103, "stage": "debug", "created_at": 1789635574.04101}, {"event_id": "387359e302da4d199c648da385928020", "step": 6, "value": 1.9534360913177007, "stage": "debug", "created_at": 1789636094.6250312}, {"event_id": "064adf61aa7e4173a6f0621eaeeeb1cf", "step": 7, "value": 1.2121463076680525, "stage": "improve", "created_at": 1789636761.2202637}, {"event_id": "647e45fa38eb4a2a8d347c0cb9ea4f01", "step": 8, "value": 1.2133336239476669, "stage": "improve", "created_at": 1789637345.2311485}, {"event_id": "773a4f6525484da498381d97221e0f63", "step": 9, "value": 1.2864703487540758, "stage": "improve", "created_at": 1789637920.388236}, {"event_id": "c0661ca125704a728ca66a65be9b4941", "step": 10, "value": 1.2882100132809766, "stage": "improve", "created_at": 1789638534.6738307}, {"event_id": "d6792d7ed4c84305a366160a3ad99dd4", "step": 11, "value": 1.2076129821459245, "stage": "evolution", "created_at": 1789639057.7842584}, {"event_id": "9ed4df2f368f4f85857b6f056325c7b0", "step": 12, "value": 1.4122425098084561, "stage": "improve", "created_at": 1789639672.0311341}, {"event_id": "f98bc83dfe2f4fea8719f8683a8c097b", "step": 13, "value": 1.1765658144358566, "stage": "improve", "created_at": 1789640311.8813303}, {"event_id": "c1840716a2ed43e7a7818c38af54a27b", "step": 14, "value": 1.2963952487957946, "stage": "improve", "created_at": 1789640927.1143317}, {"event_id": "46138cc870be4bdd8fd8b29b2cd13bc9", "step": 15, "value": 1.2813916767674032, "stage": "improve", "created_at": 1789641582.4900563}, {"event_id": "f7c13d8231cb404f8332c79f94b2fc64", "step": 16, "value": 1.1760414802417165, "stage": "improve", "created_at": 1789642142.3237243}, {"event_id": "665e68979de6429697c9381782ac21ac", "step": 17, "value": 1.3164177823722674, "stage": "improve", "created_at": 1789642742.5845215}, {"event_id": "4c155acb29534db2b80dbbce815303bd", "step": 19, "value": 1.217967789757727, "stage": "improve", "created_at": 1789643854.0222125}, {"event_id": "5c677f5189194608b0fa4e9543f57ff8", "step": 20, "value": 1.173311129749959, "stage": "improve", "created_at": 1789644440.9273875}, {"event_id": "34f291f2549643b5b59dacfe5bc5af54", "step": 22, "value": 1.2521386087909459, "stage": "improve", "created_at": 1789645485.5722792}, {"event_id": "2e192d15054240faaa313fa45e8b0ed1", "step": 23, "value": 1.1844334859966703, "stage": "improve", "created_at": 1789646066.9559677}, {"event_id": "349fcfe4d241459e87ff50cc4140adae", "step": 24, "value": 1.2350250060432826, "stage": "improve", "created_at": 1789646623.2763832}, {"event_id": "2764d78ff60b43a3948d67028f7c00ab", "step": 25, "value": 1.1757664325693749, "stage": "evolution", "created_at": 1789647231.0884173}, {"event_id": "ae96f68cb93843d4a5f813ce31e1094a", "step": 26, "value": 1.3190938167653636, "stage": "draft", "created_at": 1789647712.7361958}, {"event_id": "74906fbcf0e047938a52019fc1323b0a", "step": 27, "value": 1.1546098926667647, "stage": "evolution", "created_at": 1789648563.1620505}, {"event_id": "7f5a96d7c9014bb6ad7e7d0537faeef1", "step": 28, "value": 1.2194683916861715, "stage": "improve", "created_at": 1789649135.8203042}, {"event_id": "7cfd491dfa6647c9a26618ec115478df", "step": 29, "value": 1.1698179550095718, "stage": "improve", "created_at": 1789649708.6990457}, {"event_id": "ddaf7a0d78ec472e9001b22b2b76f5bd", "step": 30, "value": 1.1457650727907722, "stage": "improve", "created_at": 1789650301.5310254}, {"event_id": "b1f1f4de7f364a4aa1fbacc3b2f59b67", "step": 31, "value": 1.1331051971776425, "stage": "improve", "created_at": 1789650917.7053285}, {"event_id": "e51fd7c740564853bd846aaace7a77c1", "step": 32, "value": 1.2547435801410673, "stage": "improve", "created_at": 1789651546.6412187}, {"event_id": "24bb698fcdfb48d98b1d1c9fc7ec8129", "step": 33, "value": 1.1710660308370548, "stage": "improve", "created_at": 1789652200.4305174}, {"event_id": "1767fb39d13f4a4fbfde7666fd9ea876", "step": 34, "value": 1.1568896734204834, "stage": "improve", "created_at": 1789652843.7464006}, {"event_id": "e0bc26029cf142dcb84eb864241a3a13", "step": 36, "value": 1.155883564311239, "stage": "fusion", "created_at": 1789654106.8909593}, {"event_id": "e6791ee79c684fdcaf768fc67ad5940a", "step": 38, "value": 1.1366271384917634, "stage": "debug", "created_at": 1789655094.374522}], "maximize": false, "node_count": 39, "metric_name": "BPB", "curve_scope": "原始候选验证 BPB（可能含回滚或预算后记录），不作为预算内最终成绩。最终成绩以 all_runs_final.csv 为准。", "official_score": null}, {"id": "xixian.bo-study-mcgs.seed47", "experiment_id": "nanogpt-development-r2-v1-20260917", "family": "nanoGPT", "method": "bo_study_mcgs", "dataset": "nanoGPT", "seed": "47", "status": "not_launched", "best_valid_bpb": null, "elapsed_seconds": 0.0, "budget_seconds": 28800.0, "comparison_eligible": false, "note": "Strict shared draft protocol identity rejected old pool after common validator change", "artifacts": [{"bundle_id": "01-read-first-and-final-states", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/01-read-first-and-final-states/logs-c828e9f97191.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/01-read-first-and-final-states", "member": "MLEvolve_BO/research/nanogpt_bo_20260917/analysis/final_closeout_20260918/all_runs_final.csv", "sha256": "c828e9f97191ffc3f6f4fa6f39045e6be494d2ab2ea3337eff18dfd2830908ba"}], "ledger": {"campaign": "development_r2_v1", "stage": "development", "method": "bo_study_mcgs", "version": "r2_value_models_v1_common_causality_v2", "seed": "47", "training_seed": "42", "state": "not_launched", "complete_budget": "False", "launch_allowed": "", "not_launched_reason": "", "complete_8h": "False", "active_seconds": "0.0", "budget_seconds": "28800", "source_duration_seconds": "28800", "budget_amended": "False", "raw_active_seconds": "0.0", "post_budget_active_seconds": "0.0", "comparison_eligible": "False", "protocol_invalid_results": "0", "raw_reported_valid": "0", "raw_reported_best_bpb": "", "validity_audit": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r2_v1/bo_study_mcgs/validity_audit.json", "comparison_exclusion_reason": "Strict shared draft protocol identity rejected old pool after common validator change", "policy_contamination_started_at": "", "active_gpu_hours": "0.0", "actual_elapsed_seconds": "", "segment_gpu_hours_including_cleanup": "0.0", "between_segment_seconds": "", "completed": "0", "raw_completed": "0", "unverified_commit_time_count": "0", "post_budget_completed": "0", "valid": "0", "failure_fraction": "", "best_bpb_so_far": "", "final_bpb": "", "best_node_id": "", "llm_attempts": "0", "llm_cli_reported_tokens_known": "0", "llm_attempts_unknown_tokens": "0", "llm_measured_wall_seconds": "0", "llm_unfinished_attempts": "0", "llm_failed_or_interrupted_attempts": "0", "allocated_gpu_hours": "", "allocated_gpu_hours_accounting_final": "False", "resource_records": "[]", "resource_accounting_captured_at": "[]", "gpu_models": "[]", "completed_proposal_wall_seconds": "0", "raw_completed_proposal_wall_seconds": "0", "diagnostic_feedback_scope": "Only results committed within the registered budget; later DEBUG repairs and mature labels excluded", "diagnostic_excluded_late_transitions": "0", "closed_proposals": "0", "unclosed_proposals": "0", "unknown_closure_proposals": "0", "closed_proposal_failure_fraction": "", "raw_reported_closed_proposal_failure_fraction": "", "debug_repaired_proposals": "0", "raw_serial_actions": "0", "raw_actions_with_error_logs": "0", "raw_training_launches": "0", "interrupted_actions": "0", "interrupted_action_active_seconds_upper_bound": "0", "gpu_uuid": "", "job_id": "", "node": "", "started_at": "", "finished_at": "", "stop_reason": "", "training_rows": "", "incomplete_windows": "", "current_label_diagnostics": "{}", "threshold_active_seconds": "{\"1.2\": null, \"1.15\": null, \"1.1\": null}", "log_dir": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r2_v1/bo_study_mcgs/unstarted_logs", "committed_evidence": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r2_v1/bo_study_mcgs/checkpoints/not-yet-committed/logs", "final_solution": ""}, "curve_scope": "原始候选验证 BPB（可能含回滚或预算后记录），不作为预算内最终成绩。最终成绩以 all_runs_final.csv 为准。", "metrics": [], "maximize": null, "official_score": null, "metric_name": "validation"}, {"id": "xixian.bo-study-gp7-ucb.seed47", "experiment_id": "nanogpt-development-r2-v1-20260917", "family": "nanoGPT", "method": "bo_study_gp7_ucb", "dataset": "nanoGPT", "seed": "47", "status": "not_launched", "best_valid_bpb": null, "elapsed_seconds": 0.0, "budget_seconds": 28800.0, "comparison_eligible": false, "note": "Strict shared draft protocol identity rejected old pool after common validator change", "artifacts": [{"bundle_id": "01-read-first-and-final-states", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/01-read-first-and-final-states/logs-c828e9f97191.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/01-read-first-and-final-states", "member": "MLEvolve_BO/research/nanogpt_bo_20260917/analysis/final_closeout_20260918/all_runs_final.csv", "sha256": "c828e9f97191ffc3f6f4fa6f39045e6be494d2ab2ea3337eff18dfd2830908ba"}], "ledger": {"campaign": "development_r2_v1", "stage": "development", "method": "bo_study_gp7_ucb", "version": "r2_value_models_v1_common_causality_v2", "seed": "47", "training_seed": "42", "state": "not_launched", "complete_budget": "False", "launch_allowed": "", "not_launched_reason": "", "complete_8h": "False", "active_seconds": "0.0", "budget_seconds": "28800", "source_duration_seconds": "28800", "budget_amended": "False", "raw_active_seconds": "0.0", "post_budget_active_seconds": "0.0", "comparison_eligible": "False", "protocol_invalid_results": "0", "raw_reported_valid": "0", "raw_reported_best_bpb": "", "validity_audit": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r2_v1/bo_study_gp7_ucb/validity_audit.json", "comparison_exclusion_reason": "Strict shared draft protocol identity rejected old pool after common validator change", "policy_contamination_started_at": "", "active_gpu_hours": "0.0", "actual_elapsed_seconds": "", "segment_gpu_hours_including_cleanup": "0.0", "between_segment_seconds": "", "completed": "0", "raw_completed": "0", "unverified_commit_time_count": "0", "post_budget_completed": "0", "valid": "0", "failure_fraction": "", "best_bpb_so_far": "", "final_bpb": "", "best_node_id": "", "llm_attempts": "0", "llm_cli_reported_tokens_known": "0", "llm_attempts_unknown_tokens": "0", "llm_measured_wall_seconds": "0", "llm_unfinished_attempts": "0", "llm_failed_or_interrupted_attempts": "0", "allocated_gpu_hours": "", "allocated_gpu_hours_accounting_final": "False", "resource_records": "[]", "resource_accounting_captured_at": "[]", "gpu_models": "[]", "completed_proposal_wall_seconds": "0", "raw_completed_proposal_wall_seconds": "0", "diagnostic_feedback_scope": "Only results committed within the registered budget; later DEBUG repairs and mature labels excluded", "diagnostic_excluded_late_transitions": "0", "closed_proposals": "0", "unclosed_proposals": "0", "unknown_closure_proposals": "0", "closed_proposal_failure_fraction": "", "raw_reported_closed_proposal_failure_fraction": "", "debug_repaired_proposals": "0", "raw_serial_actions": "0", "raw_actions_with_error_logs": "0", "raw_training_launches": "0", "interrupted_actions": "0", "interrupted_action_active_seconds_upper_bound": "0", "gpu_uuid": "", "job_id": "", "node": "", "started_at": "", "finished_at": "", "stop_reason": "", "training_rows": "", "incomplete_windows": "", "current_label_diagnostics": "{}", "threshold_active_seconds": "{\"1.2\": null, \"1.15\": null, \"1.1\": null}", "log_dir": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r2_v1/bo_study_gp7_ucb/unstarted_logs", "committed_evidence": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r2_v1/bo_study_gp7_ucb/checkpoints/not-yet-committed/logs", "final_solution": ""}, "curve_scope": "原始候选验证 BPB（可能含回滚或预算后记录），不作为预算内最终成绩。最终成绩以 all_runs_final.csv 为准。", "metrics": [], "maximize": null, "official_score": null, "metric_name": "validation"}, {"id": "xixian.bo-study-parent-coefficient-ucb.seed47", "experiment_id": "nanogpt-development-r2-v1-20260917", "family": "nanoGPT", "method": "bo_study_parent_coefficient_ucb", "dataset": "nanoGPT", "seed": "47", "status": "not_launched", "best_valid_bpb": null, "elapsed_seconds": 0.0, "budget_seconds": 28800.0, "comparison_eligible": false, "note": "Strict shared draft protocol identity rejected old pool after common validator change", "artifacts": [{"bundle_id": "01-read-first-and-final-states", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/01-read-first-and-final-states/logs-c828e9f97191.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/01-read-first-and-final-states", "member": "MLEvolve_BO/research/nanogpt_bo_20260917/analysis/final_closeout_20260918/all_runs_final.csv", "sha256": "c828e9f97191ffc3f6f4fa6f39045e6be494d2ab2ea3337eff18dfd2830908ba"}], "ledger": {"campaign": "development_r2_v1", "stage": "development", "method": "bo_study_parent_coefficient_ucb", "version": "r2_value_models_v1_common_causality_v2", "seed": "47", "training_seed": "42", "state": "not_launched", "complete_budget": "False", "launch_allowed": "", "not_launched_reason": "", "complete_8h": "False", "active_seconds": "0.0", "budget_seconds": "28800", "source_duration_seconds": "28800", "budget_amended": "False", "raw_active_seconds": "0.0", "post_budget_active_seconds": "0.0", "comparison_eligible": "False", "protocol_invalid_results": "0", "raw_reported_valid": "0", "raw_reported_best_bpb": "", "validity_audit": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r2_v1/bo_study_parent_coefficient_ucb/validity_audit.json", "comparison_exclusion_reason": "Strict shared draft protocol identity rejected old pool after common validator change", "policy_contamination_started_at": "", "active_gpu_hours": "0.0", "actual_elapsed_seconds": "", "segment_gpu_hours_including_cleanup": "0.0", "between_segment_seconds": "", "completed": "0", "raw_completed": "0", "unverified_commit_time_count": "0", "post_budget_completed": "0", "valid": "0", "failure_fraction": "", "best_bpb_so_far": "", "final_bpb": "", "best_node_id": "", "llm_attempts": "0", "llm_cli_reported_tokens_known": "0", "llm_attempts_unknown_tokens": "0", "llm_measured_wall_seconds": "0", "llm_unfinished_attempts": "0", "llm_failed_or_interrupted_attempts": "0", "allocated_gpu_hours": "", "allocated_gpu_hours_accounting_final": "False", "resource_records": "[]", "resource_accounting_captured_at": "[]", "gpu_models": "[]", "completed_proposal_wall_seconds": "0", "raw_completed_proposal_wall_seconds": "0", "diagnostic_feedback_scope": "Only results committed within the registered budget; later DEBUG repairs and mature labels excluded", "diagnostic_excluded_late_transitions": "0", "closed_proposals": "0", "unclosed_proposals": "0", "unknown_closure_proposals": "0", "closed_proposal_failure_fraction": "", "raw_reported_closed_proposal_failure_fraction": "", "debug_repaired_proposals": "0", "raw_serial_actions": "0", "raw_actions_with_error_logs": "0", "raw_training_launches": "0", "interrupted_actions": "0", "interrupted_action_active_seconds_upper_bound": "0", "gpu_uuid": "", "job_id": "", "node": "", "started_at": "", "finished_at": "", "stop_reason": "", "training_rows": "", "incomplete_windows": "", "current_label_diagnostics": "{}", "threshold_active_seconds": "{\"1.2\": null, \"1.15\": null, \"1.1\": null}", "log_dir": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r2_v1/bo_study_parent_coefficient_ucb/unstarted_logs", "committed_evidence": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r2_v1/bo_study_parent_coefficient_ucb/checkpoints/not-yet-committed/logs", "final_solution": ""}, "curve_scope": "原始候选验证 BPB（可能含回滚或预算后记录），不作为预算内最终成绩。最终成绩以 all_runs_final.csv 为准。", "metrics": [], "maximize": null, "official_score": null, "metric_name": "validation"}, {"id": "xixian.bo-study-gp7-long-ucb.seed47", "experiment_id": "nanogpt-development-r2-v1-20260917", "family": "nanoGPT", "method": "bo_study_gp7_long_ucb", "dataset": "nanoGPT", "seed": "47", "status": "not_launched", "best_valid_bpb": null, "elapsed_seconds": 0.0, "budget_seconds": 28800.0, "comparison_eligible": false, "note": "Strict shared draft protocol identity rejected old pool after common validator change", "artifacts": [{"bundle_id": "01-read-first-and-final-states", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/01-read-first-and-final-states/logs-c828e9f97191.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/01-read-first-and-final-states", "member": "MLEvolve_BO/research/nanogpt_bo_20260917/analysis/final_closeout_20260918/all_runs_final.csv", "sha256": "c828e9f97191ffc3f6f4fa6f39045e6be494d2ab2ea3337eff18dfd2830908ba"}], "ledger": {"campaign": "development_r2_v1", "stage": "development", "method": "bo_study_gp7_long_ucb", "version": "r2_value_models_v1_common_causality_v2", "seed": "47", "training_seed": "42", "state": "not_launched", "complete_budget": "False", "launch_allowed": "", "not_launched_reason": "", "complete_8h": "False", "active_seconds": "0.0", "budget_seconds": "28800", "source_duration_seconds": "28800", "budget_amended": "False", "raw_active_seconds": "0.0", "post_budget_active_seconds": "0.0", "comparison_eligible": "False", "protocol_invalid_results": "0", "raw_reported_valid": "0", "raw_reported_best_bpb": "", "validity_audit": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r2_v1/bo_study_gp7_long_ucb/validity_audit.json", "comparison_exclusion_reason": "Strict shared draft protocol identity rejected old pool after common validator change", "policy_contamination_started_at": "", "active_gpu_hours": "0.0", "actual_elapsed_seconds": "", "segment_gpu_hours_including_cleanup": "0.0", "between_segment_seconds": "", "completed": "0", "raw_completed": "0", "unverified_commit_time_count": "0", "post_budget_completed": "0", "valid": "0", "failure_fraction": "", "best_bpb_so_far": "", "final_bpb": "", "best_node_id": "", "llm_attempts": "0", "llm_cli_reported_tokens_known": "0", "llm_attempts_unknown_tokens": "0", "llm_measured_wall_seconds": "0", "llm_unfinished_attempts": "0", "llm_failed_or_interrupted_attempts": "0", "allocated_gpu_hours": "", "allocated_gpu_hours_accounting_final": "False", "resource_records": "[]", "resource_accounting_captured_at": "[]", "gpu_models": "[]", "completed_proposal_wall_seconds": "0", "raw_completed_proposal_wall_seconds": "0", "diagnostic_feedback_scope": "Only results committed within the registered budget; later DEBUG repairs and mature labels excluded", "diagnostic_excluded_late_transitions": "0", "closed_proposals": "0", "unclosed_proposals": "0", "unknown_closure_proposals": "0", "closed_proposal_failure_fraction": "", "raw_reported_closed_proposal_failure_fraction": "", "debug_repaired_proposals": "0", "raw_serial_actions": "0", "raw_actions_with_error_logs": "0", "raw_training_launches": "0", "interrupted_actions": "0", "interrupted_action_active_seconds_upper_bound": "0", "gpu_uuid": "", "job_id": "", "node": "", "started_at": "", "finished_at": "", "stop_reason": "", "training_rows": "", "incomplete_windows": "", "current_label_diagnostics": "{}", "threshold_active_seconds": "{\"1.2\": null, \"1.15\": null, \"1.1\": null}", "log_dir": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r2_v1/bo_study_gp7_long_ucb/unstarted_logs", "committed_evidence": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r2_v1/bo_study_gp7_long_ucb/checkpoints/not-yet-committed/logs", "final_solution": ""}, "curve_scope": "原始候选验证 BPB（可能含回滚或预算后记录），不作为预算内最终成绩。最终成绩以 all_runs_final.csv 为准。", "metrics": [], "maximize": null, "official_score": null, "metric_name": "validation"}, {"id": "xixian.bo-study-absolute-mean.seed47", "experiment_id": "nanogpt-development-r2-v1-20260917", "family": "nanoGPT", "method": "bo_study_absolute_mean", "dataset": "nanoGPT", "seed": "47", "status": "not_launched", "best_valid_bpb": null, "elapsed_seconds": 0.0, "budget_seconds": 28800.0, "comparison_eligible": false, "note": "Strict shared draft protocol identity rejected old pool after common validator change", "artifacts": [{"bundle_id": "01-read-first-and-final-states", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/01-read-first-and-final-states/logs-c828e9f97191.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/01-read-first-and-final-states", "member": "MLEvolve_BO/research/nanogpt_bo_20260917/analysis/final_closeout_20260918/all_runs_final.csv", "sha256": "c828e9f97191ffc3f6f4fa6f39045e6be494d2ab2ea3337eff18dfd2830908ba"}], "ledger": {"campaign": "development_r2_v1", "stage": "development", "method": "bo_study_absolute_mean", "version": "r2_value_models_v1_common_causality_v2", "seed": "47", "training_seed": "42", "state": "not_launched", "complete_budget": "False", "launch_allowed": "", "not_launched_reason": "", "complete_8h": "False", "active_seconds": "0.0", "budget_seconds": "28800", "source_duration_seconds": "28800", "budget_amended": "False", "raw_active_seconds": "0.0", "post_budget_active_seconds": "0.0", "comparison_eligible": "False", "protocol_invalid_results": "0", "raw_reported_valid": "0", "raw_reported_best_bpb": "", "validity_audit": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r2_v1/bo_study_absolute_mean/validity_audit.json", "comparison_exclusion_reason": "Strict shared draft protocol identity rejected old pool after common validator change", "policy_contamination_started_at": "", "active_gpu_hours": "0.0", "actual_elapsed_seconds": "", "segment_gpu_hours_including_cleanup": "0.0", "between_segment_seconds": "", "completed": "0", "raw_completed": "0", "unverified_commit_time_count": "0", "post_budget_completed": "0", "valid": "0", "failure_fraction": "", "best_bpb_so_far": "", "final_bpb": "", "best_node_id": "", "llm_attempts": "0", "llm_cli_reported_tokens_known": "0", "llm_attempts_unknown_tokens": "0", "llm_measured_wall_seconds": "0", "llm_unfinished_attempts": "0", "llm_failed_or_interrupted_attempts": "0", "allocated_gpu_hours": "", "allocated_gpu_hours_accounting_final": "False", "resource_records": "[]", "resource_accounting_captured_at": "[]", "gpu_models": "[]", "completed_proposal_wall_seconds": "0", "raw_completed_proposal_wall_seconds": "0", "diagnostic_feedback_scope": "Only results committed within the registered budget; later DEBUG repairs and mature labels excluded", "diagnostic_excluded_late_transitions": "0", "closed_proposals": "0", "unclosed_proposals": "0", "unknown_closure_proposals": "0", "closed_proposal_failure_fraction": "", "raw_reported_closed_proposal_failure_fraction": "", "debug_repaired_proposals": "0", "raw_serial_actions": "0", "raw_actions_with_error_logs": "0", "raw_training_launches": "0", "interrupted_actions": "0", "interrupted_action_active_seconds_upper_bound": "0", "gpu_uuid": "", "job_id": "", "node": "", "started_at": "", "finished_at": "", "stop_reason": "", "training_rows": "", "incomplete_windows": "", "current_label_diagnostics": "{}", "threshold_active_seconds": "{\"1.2\": null, \"1.15\": null, \"1.1\": null}", "log_dir": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r2_v1/bo_study_absolute_mean/unstarted_logs", "committed_evidence": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r2_v1/bo_study_absolute_mean/checkpoints/not-yet-committed/logs", "final_solution": ""}, "curve_scope": "原始候选验证 BPB（可能含回滚或预算后记录），不作为预算内最终成绩。最终成绩以 all_runs_final.csv 为准。", "metrics": [], "maximize": null, "official_score": null, "metric_name": "validation"}, {"id": "xixian.bo-study-absolute-ucb.seed47", "experiment_id": "nanogpt-development-r2-v1-20260917", "family": "nanoGPT", "method": "bo_study_absolute_ucb", "dataset": "nanoGPT", "seed": "47", "status": "failed", "best_valid_bpb": null, "elapsed_seconds": 38.149444580078125, "budget_seconds": 28800.0, "comparison_eligible": false, "note": "Strict shared draft protocol identity rejected old pool after common validator change", "artifacts": [{"bundle_id": "01-read-first-and-final-states", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/01-read-first-and-final-states/logs-c828e9f97191.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/01-read-first-and-final-states", "member": "MLEvolve_BO/research/nanogpt_bo_20260917/analysis/final_closeout_20260918/all_runs_final.csv", "sha256": "c828e9f97191ffc3f6f4fa6f39045e6be494d2ab2ea3337eff18dfd2830908ba"}], "ledger": {"campaign": "development_r2_v1", "stage": "development", "method": "bo_study_absolute_ucb", "version": "r2_value_models_v1_common_causality_v2", "seed": "47", "training_seed": "42", "state": "failed", "complete_budget": "False", "launch_allowed": "", "not_launched_reason": "", "complete_8h": "False", "active_seconds": "38.149444580078125", "budget_seconds": "28800", "source_duration_seconds": "28800", "budget_amended": "False", "raw_active_seconds": "38.149444580078125", "post_budget_active_seconds": "0.0", "comparison_eligible": "False", "protocol_invalid_results": "0", "raw_reported_valid": "0", "raw_reported_best_bpb": "", "validity_audit": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r2_v1/bo_study_absolute_ucb/validity_audit.json", "comparison_exclusion_reason": "Strict shared draft protocol identity rejected old pool after common validator change", "policy_contamination_started_at": "", "active_gpu_hours": "0.01059706793891059", "actual_elapsed_seconds": "38.14944386482239", "segment_gpu_hours_including_cleanup": "0.01059706793891059", "between_segment_seconds": "0.0", "completed": "0", "raw_completed": "0", "unverified_commit_time_count": "0", "post_budget_completed": "0", "valid": "0", "failure_fraction": "", "best_bpb_so_far": "", "final_bpb": "", "best_node_id": "", "llm_attempts": "0", "llm_cli_reported_tokens_known": "0", "llm_attempts_unknown_tokens": "0", "llm_measured_wall_seconds": "0", "llm_unfinished_attempts": "0", "llm_failed_or_interrupted_attempts": "0", "allocated_gpu_hours": "0.14201894481976826", "allocated_gpu_hours_accounting_final": "True", "resource_records": "[\"10832308\"]", "resource_accounting_captured_at": "[\"2026-09-18T07:57:53.779869+00:00\"]", "gpu_models": "[\"NVIDIA A100-SXM4-80GB\"]", "completed_proposal_wall_seconds": "0", "raw_completed_proposal_wall_seconds": "0", "diagnostic_feedback_scope": "Only results committed within the registered budget; later DEBUG repairs and mature labels excluded", "diagnostic_excluded_late_transitions": "0", "closed_proposals": "0", "unclosed_proposals": "0", "unknown_closure_proposals": "0", "closed_proposal_failure_fraction": "", "raw_reported_closed_proposal_failure_fraction": "", "debug_repaired_proposals": "0", "raw_serial_actions": "0", "raw_actions_with_error_logs": "0", "raw_training_launches": "0", "interrupted_actions": "0", "interrupted_action_active_seconds_upper_bound": "0", "gpu_uuid": "GPU-06c12867-49f5-9c50-ffee-2bb91574fb7c", "job_id": "10832308", "node": "cn-g017.server.mila.quebec", "started_at": "2026-09-17T12:47:22.435676+00:00", "finished_at": "", "stop_reason": "process_exit", "training_rows": "", "incomplete_windows": "", "current_label_diagnostics": "{}", "threshold_active_seconds": "{\"1.2\": null, \"1.15\": null, \"1.1\": null}", "log_dir": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r2_v1/bo_study_absolute_ucb/runs/20260917_084758_bo_study_absolute_ucb/logs", "committed_evidence": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r2_v1/bo_study_absolute_ucb/checkpoints/not-yet-committed/logs", "final_solution": ""}, "curve_scope": "原始候选验证 BPB（可能含回滚或预算后记录），不作为预算内最终成绩。最终成绩以 all_runs_final.csv 为准。", "metrics": [], "maximize": null, "official_score": null, "metric_name": "validation"}, {"id": "xixian.bo-study-parent-coefficient-mean.seed47", "experiment_id": "nanogpt-development-r2-v1-20260917", "family": "nanoGPT", "method": "bo_study_parent_coefficient_mean", "dataset": "nanoGPT", "seed": "47", "status": "not_launched", "best_valid_bpb": null, "elapsed_seconds": 0.0, "budget_seconds": 28800.0, "comparison_eligible": false, "note": "Strict shared draft protocol identity rejected old pool after common validator change", "artifacts": [{"bundle_id": "01-read-first-and-final-states", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/01-read-first-and-final-states/logs-c828e9f97191.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/01-read-first-and-final-states", "member": "MLEvolve_BO/research/nanogpt_bo_20260917/analysis/final_closeout_20260918/all_runs_final.csv", "sha256": "c828e9f97191ffc3f6f4fa6f39045e6be494d2ab2ea3337eff18dfd2830908ba"}], "ledger": {"campaign": "development_r2_v1", "stage": "development", "method": "bo_study_parent_coefficient_mean", "version": "r2_value_models_v1_common_causality_v2", "seed": "47", "training_seed": "42", "state": "not_launched", "complete_budget": "False", "launch_allowed": "", "not_launched_reason": "", "complete_8h": "False", "active_seconds": "0.0", "budget_seconds": "28800", "source_duration_seconds": "28800", "budget_amended": "False", "raw_active_seconds": "0.0", "post_budget_active_seconds": "0.0", "comparison_eligible": "False", "protocol_invalid_results": "0", "raw_reported_valid": "0", "raw_reported_best_bpb": "", "validity_audit": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r2_v1/bo_study_parent_coefficient_mean/validity_audit.json", "comparison_exclusion_reason": "Strict shared draft protocol identity rejected old pool after common validator change", "policy_contamination_started_at": "", "active_gpu_hours": "0.0", "actual_elapsed_seconds": "", "segment_gpu_hours_including_cleanup": "0.0", "between_segment_seconds": "", "completed": "0", "raw_completed": "0", "unverified_commit_time_count": "0", "post_budget_completed": "0", "valid": "0", "failure_fraction": "", "best_bpb_so_far": "", "final_bpb": "", "best_node_id": "", "llm_attempts": "0", "llm_cli_reported_tokens_known": "0", "llm_attempts_unknown_tokens": "0", "llm_measured_wall_seconds": "0", "llm_unfinished_attempts": "0", "llm_failed_or_interrupted_attempts": "0", "allocated_gpu_hours": "", "allocated_gpu_hours_accounting_final": "False", "resource_records": "[]", "resource_accounting_captured_at": "[]", "gpu_models": "[]", "completed_proposal_wall_seconds": "0", "raw_completed_proposal_wall_seconds": "0", "diagnostic_feedback_scope": "Only results committed within the registered budget; later DEBUG repairs and mature labels excluded", "diagnostic_excluded_late_transitions": "0", "closed_proposals": "0", "unclosed_proposals": "0", "unknown_closure_proposals": "0", "closed_proposal_failure_fraction": "", "raw_reported_closed_proposal_failure_fraction": "", "debug_repaired_proposals": "0", "raw_serial_actions": "0", "raw_actions_with_error_logs": "0", "raw_training_launches": "0", "interrupted_actions": "0", "interrupted_action_active_seconds_upper_bound": "0", "gpu_uuid": "", "job_id": "", "node": "", "started_at": "", "finished_at": "", "stop_reason": "", "training_rows": "", "incomplete_windows": "", "current_label_diagnostics": "{}", "threshold_active_seconds": "{\"1.2\": null, \"1.15\": null, \"1.1\": null}", "log_dir": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r2_v1/bo_study_parent_coefficient_mean/unstarted_logs", "committed_evidence": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r2_v1/bo_study_parent_coefficient_mean/checkpoints/not-yet-committed/logs", "final_solution": ""}, "curve_scope": "原始候选验证 BPB（可能含回滚或预算后记录），不作为预算内最终成绩。最终成绩以 all_runs_final.csv 为准。", "metrics": [], "maximize": null, "official_score": null, "metric_name": "validation"}, {"id": "xixian.bo-study-mcgs.seed47", "experiment_id": "nanogpt-development-r2-v2-20260917", "family": "nanoGPT", "method": "bo_study_mcgs", "dataset": "nanoGPT", "seed": "47", "status": "stopped", "best_valid_bpb": null, "elapsed_seconds": 5177.648926019669, "budget_seconds": 21600.0, "comparison_eligible": true, "note": "user_reallocated_duplicate_control", "artifacts": [{"bundle_id": "01-read-first-and-final-states", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/01-read-first-and-final-states/logs-c828e9f97191.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/01-read-first-and-final-states", "member": "MLEvolve_BO/research/nanogpt_bo_20260917/analysis/final_closeout_20260918/all_runs_final.csv", "sha256": "c828e9f97191ffc3f6f4fa6f39045e6be494d2ab2ea3337eff18dfd2830908ba"}, {"bundle_id": "02-study-run-logs", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/02-study-run-logs/logs-50a9df8a8a5a.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/02-study-run-logs", "member": "MLEvolve_BO/research/nanogpt_bo_20260917/development_r2_v2/bo_study_mcgs/runs/20260917_103611_bo_study_mcgs/logs/journal.json", "sha256": "50a9df8a8a5acb631814aa5ea6a0f2e8b7d47ec05bff989ffaa975aa9ca71d25"}], "ledger": {"campaign": "development_r2_v2", "stage": "development", "method": "bo_study_mcgs", "version": "r2_value_models_v1_common_causality_v2_pool2", "seed": "47", "training_seed": "42", "state": "early_stopped", "complete_budget": "False", "launch_allowed": "", "not_launched_reason": "", "complete_8h": "False", "active_seconds": "5177.648926019669", "budget_seconds": "21600", "source_duration_seconds": "28800", "budget_amended": "True", "raw_active_seconds": "5177.648926019669", "post_budget_active_seconds": "0.0", "comparison_eligible": "True", "protocol_invalid_results": "0", "raw_reported_valid": "7", "raw_reported_best_bpb": "1.2584124597192667", "validity_audit": "", "comparison_exclusion_reason": "", "policy_contamination_started_at": "", "active_gpu_hours": "1.4382358127832413", "actual_elapsed_seconds": "62554.473170518875", "segment_gpu_hours_including_cleanup": "1.4382358127832413", "between_segment_seconds": "57376.82424449921", "completed": "9", "raw_completed": "9", "unverified_commit_time_count": "0", "post_budget_completed": "0", "valid": "7", "failure_fraction": "0.2222222222222222", "best_bpb_so_far": "1.2584124597192667", "final_bpb": "", "best_node_id": "ce9c3e10eed840f9bdf09566a5edc76e", "llm_attempts": "27", "llm_cli_reported_tokens_known": "536413", "llm_attempts_unknown_tokens": "0", "llm_measured_wall_seconds": "835.0260672569275", "llm_unfinished_attempts": "0", "llm_failed_or_interrupted_attempts": "0", "allocated_gpu_hours": "1.4416666666666667", "allocated_gpu_hours_accounting_final": "True", "resource_records": "[\"10833519\"]", "resource_accounting_captured_at": "[\"2026-09-18T07:58:09.907083+00:00\"]", "gpu_models": "[\"NVIDIA A100-SXM4-80GB\"]", "completed_proposal_wall_seconds": "5117.57428808976", "raw_completed_proposal_wall_seconds": "5117.57428808976", "diagnostic_feedback_scope": "Only results committed within the registered budget; later DEBUG repairs and mature labels excluded", "diagnostic_excluded_late_transitions": "0", "closed_proposals": "7", "unclosed_proposals": "0", "unknown_closure_proposals": "0", "closed_proposal_failure_fraction": "0.0", "raw_reported_closed_proposal_failure_fraction": "0.0", "debug_repaired_proposals": "2", "raw_serial_actions": "12", "raw_actions_with_error_logs": "0", "raw_training_launches": "9", "interrupted_actions": "0", "interrupted_action_active_seconds_upper_bound": "0", "gpu_uuid": "GPU-78b4ce31-d115-7b9a-f22e-d0ed70044433", "job_id": "10833519", "node": "cn-g027.server.mila.quebec", "started_at": "2026-09-17T14:35:35.962906+00:00", "finished_at": "", "stop_reason": "user_reallocated_duplicate_control", "training_rows": "", "incomplete_windows": "", "current_label_diagnostics": "{}", "threshold_active_seconds": "{\"1.2\": null, \"1.15\": null, \"1.1\": null}", "log_dir": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r2_v2/bo_study_mcgs/runs/20260917_103611_bo_study_mcgs/logs", "committed_evidence": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r2_v2/bo_study_mcgs/checkpoints/boundary-1789660910632978604/logs", "final_solution": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r2_v2/bo_study_mcgs/runs/20260917_103611_bo_study_mcgs/workspace/trials/ce9c3e10eed840f9bdf09566a5edc76e/candidate.py"}, "journal_ref": "02-study-run-logs:MLEvolve_BO/research/nanogpt_bo_20260917/development_r2_v2/bo_study_mcgs/runs/20260917_103611_bo_study_mcgs/logs/journal.json", "metrics": [{"event_id": "f03a9433038f4933b8c4f07aed0253a6", "step": 1, "value": 1.4819746773271383, "stage": "draft", "created_at": 1789655791.507841}, {"event_id": "a3fc52c663334575837cd4105017bfe6", "step": 4, "value": 1.6203323298705241, "stage": "improve", "created_at": 1789657684.1402142}, {"event_id": "f2c86e1a710348b399997fa9f010c6e6", "step": 5, "value": 1.4585375812537884, "stage": "debug", "created_at": 1789658254.1270604}, {"event_id": "5a979b55faad4a5c913d75b2655fc356", "step": 6, "value": 3.287458185887363, "stage": "debug", "created_at": 1789658713.7554553}, {"event_id": "197d97eb8ba44b8bbba794a74405a7aa", "step": 7, "value": 1.8059255782634056, "stage": "improve", "created_at": 1789659356.8964756}, {"event_id": "ce9c3e10eed840f9bdf09566a5edc76e", "step": 8, "value": 1.2584124597192667, "stage": "improve", "created_at": 1789659919.789962}, {"event_id": "ea0bc2e17bba4fdf81252fdaa2824eed", "step": 9, "value": 3.3776522132403106, "stage": "improve", "created_at": 1789660456.7020411}], "maximize": false, "node_count": 10, "metric_name": "BPB", "curve_scope": "原始候选验证 BPB（可能含回滚或预算后记录），不作为预算内最终成绩。最终成绩以 all_runs_final.csv 为准。", "official_score": null}, {"id": "xixian.bo-study-gp7-ucb.seed47", "experiment_id": "nanogpt-development-r2-v2-20260917", "family": "nanoGPT", "method": "bo_study_gp7_ucb", "dataset": "nanoGPT", "seed": "47", "status": "stopped", "best_valid_bpb": null, "elapsed_seconds": 5153.639761686325, "budget_seconds": 21600.0, "comparison_eligible": true, "note": "user_reallocated_duplicate_control", "artifacts": [{"bundle_id": "01-read-first-and-final-states", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/01-read-first-and-final-states/logs-c828e9f97191.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/01-read-first-and-final-states", "member": "MLEvolve_BO/research/nanogpt_bo_20260917/analysis/final_closeout_20260918/all_runs_final.csv", "sha256": "c828e9f97191ffc3f6f4fa6f39045e6be494d2ab2ea3337eff18dfd2830908ba"}, {"bundle_id": "02-study-run-logs", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/02-study-run-logs/logs-50a9df8a8a5a.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/02-study-run-logs", "member": "MLEvolve_BO/research/nanogpt_bo_20260917/development_r2_v2/bo_study_gp7_ucb/runs/20260917_103612_bo_study_gp7_ucb/logs/journal.json", "sha256": "50a9df8a8a5acb631814aa5ea6a0f2e8b7d47ec05bff989ffaa975aa9ca71d25"}], "ledger": {"campaign": "development_r2_v2", "stage": "development", "method": "bo_study_gp7_ucb", "version": "r2_value_models_v1_common_causality_v2_pool2", "seed": "47", "training_seed": "42", "state": "early_stopped", "complete_budget": "False", "launch_allowed": "", "not_launched_reason": "", "complete_8h": "False", "active_seconds": "5153.639761686325", "budget_seconds": "21600", "source_duration_seconds": "28800", "budget_amended": "True", "raw_active_seconds": "5153.639761686325", "post_budget_active_seconds": "0.0", "comparison_eligible": "True", "protocol_invalid_results": "0", "raw_reported_valid": "7", "raw_reported_best_bpb": "1.4139500539665284", "validity_audit": "", "comparison_exclusion_reason": "", "policy_contamination_started_at": "", "active_gpu_hours": "1.4315666004684235", "actual_elapsed_seconds": "62554.62464642525", "segment_gpu_hours_including_cleanup": "1.4315666004684235", "between_segment_seconds": "57400.98488473892", "completed": "9", "raw_completed": "9", "unverified_commit_time_count": "0", "post_budget_completed": "0", "valid": "7", "failure_fraction": "0.2222222222222222", "best_bpb_so_far": "1.4139500539665284", "final_bpb": "", "best_node_id": "555ffa6c902e4f2783db6ba56745875a", "llm_attempts": "26", "llm_cli_reported_tokens_known": "477186", "llm_attempts_unknown_tokens": "0", "llm_measured_wall_seconds": "772.991959810257", "llm_unfinished_attempts": "0", "llm_failed_or_interrupted_attempts": "0", "allocated_gpu_hours": "1.4416666666666667", "allocated_gpu_hours_accounting_final": "True", "resource_records": "[\"10833519\"]", "resource_accounting_captured_at": "[\"2026-09-18T07:58:09.907083+00:00\"]", "gpu_models": "[\"NVIDIA A100-SXM4-80GB\"]", "completed_proposal_wall_seconds": "5088.752829650883", "raw_completed_proposal_wall_seconds": "5088.752829650883", "diagnostic_feedback_scope": "Only results committed within the registered budget; later DEBUG repairs and mature labels excluded", "diagnostic_excluded_late_transitions": "0", "closed_proposals": "7", "unclosed_proposals": "0", "unknown_closure_proposals": "0", "closed_proposal_failure_fraction": "0.0", "raw_reported_closed_proposal_failure_fraction": "0.0", "debug_repaired_proposals": "2", "raw_serial_actions": "12", "raw_actions_with_error_logs": "0", "raw_training_launches": "9", "interrupted_actions": "0", "interrupted_action_active_seconds_upper_bound": "0", "gpu_uuid": "GPU-247a5d9f-faae-6e91-b78b-f0e0c4015b0a", "job_id": "10833519", "node": "cn-g027.server.mila.quebec", "started_at": "2026-09-17T14:35:35.956683+00:00", "finished_at": "", "stop_reason": "user_reallocated_duplicate_control", "training_rows": "3", "incomplete_windows": "", "current_label_diagnostics": "{}", "threshold_active_seconds": "{\"1.2\": null, \"1.15\": null, \"1.1\": null}", "log_dir": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r2_v2/bo_study_gp7_ucb/runs/20260917_103612_bo_study_gp7_ucb/logs", "committed_evidence": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r2_v2/bo_study_gp7_ucb/checkpoints/boundary-1789660886514637275/logs", "final_solution": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r2_v2/bo_study_gp7_ucb/runs/20260917_103612_bo_study_gp7_ucb/workspace/trials/555ffa6c902e4f2783db6ba56745875a/candidate.py"}, "journal_ref": "02-study-run-logs:MLEvolve_BO/research/nanogpt_bo_20260917/development_r2_v2/bo_study_gp7_ucb/runs/20260917_103612_bo_study_gp7_ucb/logs/journal.json", "metrics": [{"event_id": "3b2408e50d8a425087f71e17c2bf64b3", "step": 1, "value": 1.4886947394176864, "stage": "draft", "created_at": 1789655793.0211282}, {"event_id": "6a46ce90b9a24bf2ad493b2538ad69a3", "step": 4, "value": 1.672125261347971, "stage": "improve", "created_at": 1789657681.2656832}, {"event_id": "f866736d3c804d32a71cab11af14ccb2", "step": 5, "value": 3.0760604004720564, "stage": "debug", "created_at": 1789658197.198019}, {"event_id": "39f34c0d77df498a8ad18c7ef789e2fb", "step": 6, "value": 3.285775532282869, "stage": "debug", "created_at": 1789658662.1619065}, {"event_id": "f638ceb1c8e84b51847acf18c5c62528", "step": 7, "value": 1.5855672649114283, "stage": "improve", "created_at": 1789659302.3729382}, {"event_id": "b7b2eb80d4d945b794a0069d095ed8c9", "step": 8, "value": 1.7617775950162986, "stage": "improve", "created_at": 1789659831.6687315}, {"event_id": "555ffa6c902e4f2783db6ba56745875a", "step": 9, "value": 1.4139500539665284, "stage": "evolution", "created_at": 1789660437.2523277}], "maximize": false, "node_count": 10, "metric_name": "BPB", "curve_scope": "原始候选验证 BPB（可能含回滚或预算后记录），不作为预算内最终成绩。最终成绩以 all_runs_final.csv 为准。", "official_score": null}, {"id": "xixian.bo-study-parent-coefficient-ucb.seed47", "experiment_id": "nanogpt-development-r2-v2-20260917", "family": "nanoGPT", "method": "bo_study_parent_coefficient_ucb", "dataset": "nanoGPT", "seed": "47", "status": "completed", "best_valid_bpb": 1.1301181460458554, "elapsed_seconds": 21600.0, "budget_seconds": 21600.0, "comparison_eligible": true, "note": "time_budget", "artifacts": [{"bundle_id": "01-read-first-and-final-states", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/01-read-first-and-final-states/logs-c828e9f97191.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/01-read-first-and-final-states", "member": "MLEvolve_BO/research/nanogpt_bo_20260917/analysis/final_closeout_20260918/all_runs_final.csv", "sha256": "c828e9f97191ffc3f6f4fa6f39045e6be494d2ab2ea3337eff18dfd2830908ba"}, {"bundle_id": "02-study-run-logs", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/02-study-run-logs/logs-50a9df8a8a5a.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/02-study-run-logs", "member": "MLEvolve_BO/research/nanogpt_bo_20260917/development_r2_v2/bo_study_parent_coefficient_ucb/runs/20260917_103608_bo_study_parent_coefficient_ucb/logs/journal.json", "sha256": "50a9df8a8a5acb631814aa5ea6a0f2e8b7d47ec05bff989ffaa975aa9ca71d25"}], "ledger": {"campaign": "development_r2_v2", "stage": "development", "method": "bo_study_parent_coefficient_ucb", "version": "r2_value_models_v1_common_causality_v2_pool2", "seed": "47", "training_seed": "42", "state": "finished", "complete_budget": "True", "launch_allowed": "", "not_launched_reason": "", "complete_8h": "False", "active_seconds": "21600", "budget_seconds": "21600", "source_duration_seconds": "28800", "budget_amended": "True", "raw_active_seconds": "21600.0", "post_budget_active_seconds": "0.0", "comparison_eligible": "True", "protocol_invalid_results": "0", "raw_reported_valid": "31", "raw_reported_best_bpb": "1.1301181460458554", "validity_audit": "", "comparison_exclusion_reason": "", "policy_contamination_started_at": "", "active_gpu_hours": "6.0", "actual_elapsed_seconds": "21603.065371990204", "segment_gpu_hours_including_cleanup": "6.000851492219501", "between_segment_seconds": "0.0", "completed": "36", "raw_completed": "36", "unverified_commit_time_count": "0", "post_budget_completed": "0", "valid": "31", "failure_fraction": "0.13888888888888884", "best_bpb_so_far": "1.1301181460458554", "final_bpb": "1.1301181460458554", "best_node_id": "1f968c3f66c64715b8ca3a12e8ba39b1", "llm_attempts": "144", "llm_cli_reported_tokens_known": "2740053", "llm_attempts_unknown_tokens": "2", "llm_measured_wall_seconds": "6595.137183904648", "llm_unfinished_attempts": "0", "llm_failed_or_interrupted_attempts": "2", "allocated_gpu_hours": "6.004722222222222", "allocated_gpu_hours_accounting_final": "True", "resource_records": "[\"10833520\"]", "resource_accounting_captured_at": "[\"2026-09-18T07:58:09.907083+00:00\"]", "gpu_models": "[\"NVIDIA A100-SXM4-80GB\"]", "completed_proposal_wall_seconds": "21378.122940789443", "raw_completed_proposal_wall_seconds": "21378.122940789443", "diagnostic_feedback_scope": "Only results committed within the registered budget; later DEBUG repairs and mature labels excluded", "diagnostic_excluded_late_transitions": "0", "closed_proposals": "31", "unclosed_proposals": "0", "unknown_closure_proposals": "0", "closed_proposal_failure_fraction": "0.0", "raw_reported_closed_proposal_failure_fraction": "0.0", "debug_repaired_proposals": "5", "raw_serial_actions": "40", "raw_actions_with_error_logs": "0", "raw_training_launches": "36", "interrupted_actions": "1", "interrupted_action_active_seconds_upper_bound": "122.4758574962616", "gpu_uuid": "GPU-cbb955ed-a480-9c12-d6ed-5bb03c810dcf", "job_id": "10833520", "node": "cn-g019.server.mila.quebec", "started_at": "2026-09-17T14:35:35.976857+00:00", "finished_at": "2026-09-17T20:35:39.042229+00:00", "stop_reason": "time_budget", "training_rows": "25", "incomplete_windows": "", "current_label_diagnostics": "{}", "threshold_active_seconds": "{\"1.2\": 14591.19014263153, \"1.15\": 16542.364142656326, \"1.1\": null}", "log_dir": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r2_v2/bo_study_parent_coefficient_ucb/runs/20260917_103608_bo_study_parent_coefficient_ucb/logs", "committed_evidence": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r2_v2/bo_study_parent_coefficient_ucb/checkpoints/boundary-1789677213288252432/logs", "final_solution": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r2_v2/bo_study_parent_coefficient_ucb/runs/20260917_103608_bo_study_parent_coefficient_ucb/workspace/trials/1f968c3f66c64715b8ca3a12e8ba39b1/candidate.py"}, "journal_ref": "02-study-run-logs:MLEvolve_BO/research/nanogpt_bo_20260917/development_r2_v2/bo_study_parent_coefficient_ucb/runs/20260917_103608_bo_study_parent_coefficient_ucb/logs/journal.json", "metrics": [{"event_id": "560dd3071fec47bb987628ff23c520ab", "step": 1, "value": 1.4845777526661643, "stage": "draft", "created_at": 1789655787.5646608}, {"event_id": "b6f6b1b739874bd599fb392720612c6b", "step": 4, "value": 1.538832924981863, "stage": "improve", "created_at": 1789657748.394721}, {"event_id": "799e3875c6464f1281b2bca05ba6d971", "step": 5, "value": 3.0884102017943325, "stage": "debug", "created_at": 1789658791.3797965}, {"event_id": "52184fc47fad405ca37af4cd4252b1e2", "step": 6, "value": 3.3048791498315775, "stage": "debug", "created_at": 1789659323.3594558}, {"event_id": "0665c9a716ea45db83aeec68c857010b", "step": 7, "value": 3.0678686006028792, "stage": "improve", "created_at": 1789660110.7078922}, {"event_id": "f7d4d06cebcf4c0691fecacf8288c482", "step": 8, "value": 1.630530099494748, "stage": "improve", "created_at": 1789660717.5147634}, {"event_id": "e6f8a792c9a542ea9ff690354a5356f3", "step": 9, "value": 1.6234567989424753, "stage": "improve", "created_at": 1789661297.5118234}, {"event_id": "622441920c394c0f8289060cd4069ad8", "step": 10, "value": 1.5820937089538272, "stage": "evolution", "created_at": 1789661878.2058554}, {"event_id": "c4c2c38e23f340e99e5fb41800343be7", "step": 11, "value": 1.3227557789581412, "stage": "draft", "created_at": 1789662352.4109879}, {"event_id": "eff7e5179af44e3a9ef6d0f1db8ef10f", "step": 12, "value": 1.5845656653347169, "stage": "evolution", "created_at": 1789663200.2627099}, {"event_id": "a49bbb85d1b44f938392c4fe27ac79e0", "step": 13, "value": 1.5343283248997588, "stage": "evolution", "created_at": 1789663741.3194957}, {"event_id": "1e1ea354ef1c41958703169413bd45af", "step": 14, "value": 1.3062458363645846, "stage": "improve", "created_at": 1789664364.771709}, {"event_id": "09f1f60440de4bb68de9eb4ffd1d24c6", "step": 15, "value": 1.881093170699974, "stage": "improve", "created_at": 1789665038.0955951}, {"event_id": "e1b911c46d0e42cbb830c34115f24007", "step": 16, "value": 1.3356648725036067, "stage": "improve", "created_at": 1789665639.567891}, {"event_id": "719b72b070094542a38832c1836f41f2", "step": 18, "value": 1.683870431747278, "stage": "improve", "created_at": 1789666503.662833}, {"event_id": "8bb33e5e5e474693bfa3c45b0a060de2", "step": 19, "value": 1.3631732644296282, "stage": "evolution", "created_at": 1789667053.6641252}, {"event_id": "3f29ac4ef43e47d6ac41137103a2804f", "step": 20, "value": 1.5904545779547796, "stage": "debug", "created_at": 1789667570.0340283}, {"event_id": "2991a2013cf54d2baddab7b3f1d2dc1f", "step": 22, "value": 1.2623393730557373, "stage": "evolution", "created_at": 1789668548.5327542}, {"event_id": "515ff023b7b440938fb4f961d3e84d58", "step": 23, "value": 1.7788957922262905, "stage": "improve", "created_at": 1789669207.9833238}, {"event_id": "2f5d40903e514758bcb3a75ef374f16a", "step": 24, "value": 1.1823602286808286, "stage": "debug", "created_at": 1789669782.9269075}, {"event_id": "becad6a55d8e4f2f9a985dd590551c93", "step": 25, "value": 1.2328919654063057, "stage": "improve", "created_at": 1789670526.0933807}, {"event_id": "6f8982b37fe142f7bff88bc0c256abd3", "step": 26, "value": 1.211915791296678, "stage": "improve", "created_at": 1789671172.819513}, {"event_id": "aacfd8490d4844fea3e0d7bfe77b409c", "step": 27, "value": 1.1475035592828358, "stage": "improve", "created_at": 1789671760.4925735}, {"event_id": "d128e73b4b0a4b1097122cbf8c67b862", "step": 28, "value": 1.2160178463784286, "stage": "improve", "created_at": 1789672402.2593303}, {"event_id": "80c41e4da9064998a62207779d4cdb2b", "step": 29, "value": 1.1462060038622814, "stage": "improve", "created_at": 1789673087.3815472}, {"event_id": "bec5c2f6500d44e9ac1b1cc1e64a20d7", "step": 30, "value": 1.1583891522255965, "stage": "improve", "created_at": 1789673664.314666}, {"event_id": "9a47958ac0204e019282da47bdeb57da", "step": 32, "value": 1.1745293267295591, "stage": "improve", "created_at": 1789674478.0311651}, {"event_id": "029417fefa7842a39b3622a71b651b90", "step": 33, "value": 1.147741265267582, "stage": "improve", "created_at": 1789675054.3404737}, {"event_id": "5dc850bd16c04630a69561b8f9e815ee", "step": 34, "value": 1.1603389417861192, "stage": "debug", "created_at": 1789675556.4688723}, {"event_id": "1f968c3f66c64715b8ca3a12e8ba39b1", "step": 35, "value": 1.1301181460458554, "stage": "evolution", "created_at": 1789676092.9442327}, {"event_id": "027470bebf7f4f64932f6420b73193a8", "step": 36, "value": 1.1487250231975128, "stage": "improve", "created_at": 1789676692.440109}], "maximize": false, "node_count": 37, "metric_name": "BPB", "curve_scope": "原始候选验证 BPB（可能含回滚或预算后记录），不作为预算内最终成绩。最终成绩以 all_runs_final.csv 为准。", "official_score": null}, {"id": "xixian.bo-study-gp7-long-ucb.seed47", "experiment_id": "nanogpt-development-r2-v2-20260917", "family": "nanoGPT", "method": "bo_study_gp7_long_ucb", "dataset": "nanoGPT", "seed": "47", "status": "stopped", "best_valid_bpb": null, "elapsed_seconds": 5109.1724643707275, "budget_seconds": 21600.0, "comparison_eligible": true, "note": "user_reallocated_duplicate_control", "artifacts": [{"bundle_id": "01-read-first-and-final-states", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/01-read-first-and-final-states/logs-c828e9f97191.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/01-read-first-and-final-states", "member": "MLEvolve_BO/research/nanogpt_bo_20260917/analysis/final_closeout_20260918/all_runs_final.csv", "sha256": "c828e9f97191ffc3f6f4fa6f39045e6be494d2ab2ea3337eff18dfd2830908ba"}, {"bundle_id": "02-study-run-logs", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/02-study-run-logs/logs-50a9df8a8a5a.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/02-study-run-logs", "member": "MLEvolve_BO/research/nanogpt_bo_20260917/development_r2_v2/bo_study_gp7_long_ucb/runs/20260917_104102_bo_study_gp7_long_ucb/logs/journal.json", "sha256": "50a9df8a8a5acb631814aa5ea6a0f2e8b7d47ec05bff989ffaa975aa9ca71d25"}], "ledger": {"campaign": "development_r2_v2", "stage": "development", "method": "bo_study_gp7_long_ucb", "version": "r2_value_models_v1_common_causality_v2_pool2", "seed": "47", "training_seed": "42", "state": "early_stopped", "complete_budget": "False", "launch_allowed": "", "not_launched_reason": "", "complete_8h": "False", "active_seconds": "5109.1724643707275", "budget_seconds": "21600", "source_duration_seconds": "28800", "budget_amended": "True", "raw_active_seconds": "5109.1724643707275", "post_budget_active_seconds": "0.0", "comparison_eligible": "True", "protocol_invalid_results": "0", "raw_reported_valid": "6", "raw_reported_best_bpb": "1.4978199008345343", "validity_audit": "", "comparison_exclusion_reason": "", "policy_contamination_started_at": "", "active_gpu_hours": "1.4192145734363133", "actual_elapsed_seconds": "62268.8477127552", "segment_gpu_hours_including_cleanup": "1.4192145734363133", "between_segment_seconds": "57159.675248384476", "completed": "8", "raw_completed": "8", "unverified_commit_time_count": "0", "post_budget_completed": "0", "valid": "6", "failure_fraction": "0.25", "best_bpb_so_far": "1.4978199008345343", "final_bpb": "", "best_node_id": "a7ae7cd4f6ec4891aaed6eacc8d44cce", "llm_attempts": "24", "llm_cli_reported_tokens_known": "453792", "llm_attempts_unknown_tokens": "0", "llm_measured_wall_seconds": "1170.4256043434143", "llm_unfinished_attempts": "0", "llm_failed_or_interrupted_attempts": "0", "allocated_gpu_hours": "3.2696558766232595", "allocated_gpu_hours_accounting_final": "True", "resource_records": "[\"10833543\", \"10835358\", \"10836530\", \"10838575\", \"10841315\", \"10842805\"]", "resource_accounting_captured_at": "[\"2026-09-18T07:58:09.907083+00:00\"]", "gpu_models": "[\"NVIDIA A100-SXM4-80GB\"]", "completed_proposal_wall_seconds": "5033.884025304578", "raw_completed_proposal_wall_seconds": "5033.884025304578", "diagnostic_feedback_scope": "Only results committed within the registered budget; later DEBUG repairs and mature labels excluded", "diagnostic_excluded_late_transitions": "0", "closed_proposals": "6", "unclosed_proposals": "0", "unknown_closure_proposals": "0", "closed_proposal_failure_fraction": "0.0", "raw_reported_closed_proposal_failure_fraction": "0.0", "debug_repaired_proposals": "2", "raw_serial_actions": "11", "raw_actions_with_error_logs": "0", "raw_training_launches": "8", "interrupted_actions": "0", "interrupted_action_active_seconds_upper_bound": "0", "gpu_uuid": "GPU-72dc27f5-0fa1-0bc5-1ef2-0657d9e0357e", "job_id": "10833543", "node": "cn-g013.server.mila.quebec", "started_at": "2026-09-17T14:40:22.561548+00:00", "finished_at": "", "stop_reason": "user_reallocated_duplicate_control", "training_rows": "1", "incomplete_windows": "1", "current_label_diagnostics": "{\"long_horizon_contract\": \"primary_direction_budget_nonoverlap_v1\", \"horizon\": 2, \"horizon_is_feature\": false, \"window_policy\": \"observed_policy; pauses_and_parallelism_allowed; no_forced_continuation\", \"ordinary_proposal_count\": 3, \"pending_ordinary_count\": 0, \"complete_window_count\": 2, \"blocked_window_count\": 0, \"incomplete_window_count\": 1, \"overlap_excluded_count\": 1, \"training_count\": 1, \"training_windows\": [{\"horizon\": 2, \"contract\": \"primary_direction_budget_nonoverlap_v1\", \"origin_transition_id\": \"b6175334556f4cf1904c9d41ff831103\", \"origin_decision_index\": 3, \"member_transition_ids\": [\"b6175334556f4cf1904c9d41ff831103\", \"046fa8a87b024d3e91e589025654539f\"], \"member_decision_ids\": [\"6c190dd8302744e0bf56814cd8e98b8b\", \"12e6f2534106423589692b98237c235f\"], \"outcome_transition_id\": \"046fa8a87b024d3e91e589025654539f\", \"available_at\": \"2026-09-17T15:55:41.506917+00:00\", \"best_utility\": -1.4978199008345343, \"parent_utility\": -1.4978199008345343, \"gain\": 0.0, \"failed_attempts\": 0, \"total_wall_time_sec\": 1321.3392144944519}]}", "threshold_active_seconds": "{\"1.2\": null, \"1.15\": null, \"1.1\": null}", "log_dir": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r2_v2/bo_study_gp7_long_ucb/runs/20260917_104102_bo_study_gp7_long_ucb/logs", "committed_evidence": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r2_v2/bo_study_gp7_long_ucb/checkpoints/boundary-1789661130046672002/logs", "final_solution": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r2_v2/bo_study_gp7_long_ucb/runs/20260917_104102_bo_study_gp7_long_ucb/workspace/trials/a7ae7cd4f6ec4891aaed6eacc8d44cce/candidate.py"}, "journal_ref": "02-study-run-logs:MLEvolve_BO/research/nanogpt_bo_20260917/development_r2_v2/bo_study_gp7_long_ucb/runs/20260917_104102_bo_study_gp7_long_ucb/logs/journal.json", "metrics": [{"event_id": "a7ae7cd4f6ec4891aaed6eacc8d44cce", "step": 1, "value": 1.4978199008345343, "stage": "draft", "created_at": 1789656090.4942305}, {"event_id": "9117bd2610634d7fb2e7b1b5edf45824", "step": 4, "value": 1.5068260625620895, "stage": "improve", "created_at": 1789658204.996022}, {"event_id": "2f9af5cb19134fd6863a69f78a048f71", "step": 5, "value": 3.094636335356282, "stage": "debug", "created_at": 1789658785.2229617}, {"event_id": "cd736d77c7b849a4b8a463ae8af1c298", "step": 6, "value": 3.28962299446114, "stage": "debug", "created_at": 1789659320.0311065}, {"event_id": "331a432834414b5caa767b1261bb6a4c", "step": 7, "value": 1.6109769243102514, "stage": "improve", "created_at": 1789660073.608669}, {"event_id": "205cf870e6f9440983ce74f98dcdf50b", "step": 8, "value": 1.5384148086758953, "stage": "improve", "created_at": 1789660659.233375}], "maximize": false, "node_count": 9, "metric_name": "BPB", "curve_scope": "原始候选验证 BPB（可能含回滚或预算后记录），不作为预算内最终成绩。最终成绩以 all_runs_final.csv 为准。", "official_score": null}, {"id": "xixian.bo-study-absolute-mean.seed47", "experiment_id": "nanogpt-development-r2-v2-20260917", "family": "nanoGPT", "method": "bo_study_absolute_mean", "dataset": "nanoGPT", "seed": "47", "status": "completed", "best_valid_bpb": 1.098516707919561, "elapsed_seconds": 21600.0, "budget_seconds": 21600.0, "comparison_eligible": true, "note": "time_budget", "artifacts": [{"bundle_id": "01-read-first-and-final-states", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/01-read-first-and-final-states/logs-c828e9f97191.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/01-read-first-and-final-states", "member": "MLEvolve_BO/research/nanogpt_bo_20260917/analysis/final_closeout_20260918/all_runs_final.csv", "sha256": "c828e9f97191ffc3f6f4fa6f39045e6be494d2ab2ea3337eff18dfd2830908ba"}, {"bundle_id": "02-study-run-logs", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/02-study-run-logs/logs-50a9df8a8a5a.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/02-study-run-logs", "member": "MLEvolve_BO/research/nanogpt_bo_20260917/development_r2_v2/bo_study_absolute_mean/runs/20260917_104102_bo_study_absolute_mean/logs/journal.json", "sha256": "50a9df8a8a5acb631814aa5ea6a0f2e8b7d47ec05bff989ffaa975aa9ca71d25"}], "ledger": {"campaign": "development_r2_v2", "stage": "development", "method": "bo_study_absolute_mean", "version": "r2_value_models_v1_common_causality_v2_pool2", "seed": "47", "training_seed": "42", "state": "finished", "complete_budget": "True", "launch_allowed": "", "not_launched_reason": "", "complete_8h": "False", "active_seconds": "21600", "budget_seconds": "21600", "source_duration_seconds": "28800", "budget_amended": "True", "raw_active_seconds": "21600.0", "post_budget_active_seconds": "0.0", "comparison_eligible": "True", "protocol_invalid_results": "0", "raw_reported_valid": "34", "raw_reported_best_bpb": "1.098516707919561", "validity_audit": "", "comparison_exclusion_reason": "", "policy_contamination_started_at": "", "active_gpu_hours": "6.0", "actual_elapsed_seconds": "21742.168462991714", "segment_gpu_hours_including_cleanup": "6.000894874864154", "between_segment_seconds": "138.94691348075867", "completed": "37", "raw_completed": "37", "unverified_commit_time_count": "0", "post_budget_completed": "0", "valid": "34", "failure_fraction": "0.08108108108108103", "best_bpb_so_far": "1.098516707919561", "final_bpb": "1.098516707919561", "best_node_id": "4158282fc3c04e27a8d14e69f77793f4", "llm_attempts": "149", "llm_cli_reported_tokens_known": "2814939", "llm_attempts_unknown_tokens": "1", "llm_measured_wall_seconds": "5315.612068891525", "llm_unfinished_attempts": "0", "llm_failed_or_interrupted_attempts": "1", "allocated_gpu_hours": "10.873686695430015", "allocated_gpu_hours_accounting_final": "True", "resource_records": "[\"10833543\", \"10835358\", \"10836530\", \"10838575\", \"10841315\", \"10842805\"]", "resource_accounting_captured_at": "[\"2026-09-18T07:58:09.907083+00:00\"]", "gpu_models": "[\"NVIDIA A100-SXM4-80GB\"]", "completed_proposal_wall_seconds": "21274.882440459915", "raw_completed_proposal_wall_seconds": "21274.882440459915", "diagnostic_feedback_scope": "Only results committed within the registered budget; later DEBUG repairs and mature labels excluded", "diagnostic_excluded_late_transitions": "0", "closed_proposals": "34", "unclosed_proposals": "0", "unknown_closure_proposals": "0", "closed_proposal_failure_fraction": "0.0", "raw_reported_closed_proposal_failure_fraction": "0.0", "debug_repaired_proposals": "3", "raw_serial_actions": "41", "raw_actions_with_error_logs": "0", "raw_training_launches": "37", "interrupted_actions": "1", "interrupted_action_active_seconds_upper_bound": "38.63611817359924", "gpu_uuid": "GPU-053e685d-e2d3-4984-989a-9d5c28cdce77", "job_id": "10836530", "node": "cn-g013.server.mila.quebec", "started_at": "2026-09-17T14:40:22.568205+00:00", "finished_at": "2026-09-17T20:42:44.736668+00:00", "stop_reason": "time_budget", "training_rows": "28", "incomplete_windows": "", "current_label_diagnostics": "{}", "threshold_active_seconds": "{\"1.2\": 6382.826795101166, \"1.15\": 20391.37686896324, \"1.1\": 20391.37686896324}", "log_dir": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r2_v2/bo_study_absolute_mean/runs/20260917_104102_bo_study_absolute_mean/logs", "committed_evidence": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r2_v2/bo_study_absolute_mean/checkpoints/boundary-1789677722630474711/logs", "final_solution": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r2_v2/bo_study_absolute_mean/runs/20260917_104102_bo_study_absolute_mean/workspace/trials/4158282fc3c04e27a8d14e69f77793f4/candidate.py"}, "journal_ref": "02-study-run-logs:MLEvolve_BO/research/nanogpt_bo_20260917/development_r2_v2/bo_study_absolute_mean/runs/20260917_104102_bo_study_absolute_mean/logs/journal.json", "metrics": [{"event_id": "bd7c5dc99c3041bcbba18badc272b2f6", "step": 1, "value": 1.4910669405619983, "stage": "draft", "created_at": 1789656090.5061562}, {"event_id": "daf6f8c156c44bf39a8ee95f30f0bbd8", "step": 4, "value": 1.4732042112241832, "stage": "improve", "created_at": 1789658027.2917893}, {"event_id": "21dc772c1bdb44999d0ada47b5e27c52", "step": 5, "value": 1.4483997520974452, "stage": "debug", "created_at": 1789658826.4954357}, {"event_id": "f465691822ac4241a66bfc409fdc5c89", "step": 6, "value": 1.9533901582757496, "stage": "debug", "created_at": 1789659367.6438494}, {"event_id": "0c466fd1d5d94ab2bbdac4d3f9277bfa", "step": 7, "value": 1.472753118196134, "stage": "improve", "created_at": 1789660128.5218}, {"event_id": "eea0238acf6b4e34b92b98d8843b3710", "step": 8, "value": 1.7893384020712106, "stage": "improve", "created_at": 1789660712.03158}, {"event_id": "5a046354fe804bf7882c5ecdab7ae7fc", "step": 9, "value": 1.246707091043014, "stage": "improve", "created_at": 1789661266.9715357}, {"event_id": "6b3e7b68eb8d424282b43c1ba6b6f32f", "step": 10, "value": 1.181640358009126, "stage": "improve", "created_at": 1789661931.1061656}, {"event_id": "c0bfcde47a1e42c18f994aae10c9288d", "step": 11, "value": 1.2400634978501468, "stage": "improve", "created_at": 1789662495.3443694}, {"event_id": "1d415a86c0aa4bbd929f0e6342b8e418", "step": 12, "value": 1.1698249764938966, "stage": "improve", "created_at": 1789663143.6422613}, {"event_id": "3d20ee3a0dba44e684b016c297eab1f9", "step": 13, "value": 1.2832583217220084, "stage": "improve", "created_at": 1789663744.0511324}, {"event_id": "70bd2bca94874589bb042b1cf34403bf", "step": 14, "value": 1.307768859992028, "stage": "improve", "created_at": 1789664342.7233458}, {"event_id": "2ac4596ec81b43379aff4a23dc59d2c5", "step": 15, "value": 1.1727614828825192, "stage": "improve", "created_at": 1789664945.5710495}, {"event_id": "b6ee7567ddb84b95b492e6f188af1cfd", "step": 16, "value": 1.1635507903724327, "stage": "evolution", "created_at": 1789665481.2729106}, {"event_id": "2b17e501c2c848d2ad8afcc5724f262b", "step": 17, "value": 3.0804488279088638, "stage": "improve", "created_at": 1789666040.847507}, {"event_id": "ea146f11896b4566abca73c2ffd28a73", "step": 18, "value": 1.8772330868625013, "stage": "improve", "created_at": 1789666812.956657}, {"event_id": "f898fbfe57e347949d07af11fc589c12", "step": 19, "value": 1.4054574111960532, "stage": "improve", "created_at": 1789667348.1877005}, {"event_id": "b28089738c64481ca09be1ab151910c3", "step": 20, "value": 1.180642640709153, "stage": "improve", "created_at": 1789667900.3864148}, {"event_id": "adb93dc59b4044e5aab081fb7db13a9f", "step": 21, "value": 1.244276914530575, "stage": "improve", "created_at": 1789668439.5722396}, {"event_id": "daa1238a3b3b48189576266702f0cf3b", "step": 22, "value": 1.2419180026362564, "stage": "evolution", "created_at": 1789668970.2575495}, {"event_id": "35c831061e31418781c1e2f81edc3244", "step": 23, "value": 1.3177142490141411, "stage": "draft", "created_at": 1789669452.5243204}, {"event_id": "983b8e05e5bb46d1aabc4b4077f571db", "step": 24, "value": 1.18880555140218, "stage": "evolution", "created_at": 1789670266.093278}, {"event_id": "b0c7138081bc4b808d00f274447ebdf9", "step": 25, "value": 1.2058555487882274, "stage": "evolution", "created_at": 1789670812.817583}, {"event_id": "47be7ade84b741acb5a4dbc6636c610a", "step": 26, "value": 1.2075817780338094, "stage": "evolution", "created_at": 1789671363.8949754}, {"event_id": "758bf2c69eb94cd4af7a66e41e8ffbc9", "step": 27, "value": 1.2749022332834696, "stage": "evolution", "created_at": 1789671878.5025218}, {"event_id": "0b08e3cea85741429592c3353f14abac", "step": 29, "value": 1.3565651654350641, "stage": "evolution", "created_at": 1789672812.772745}, {"event_id": "3f8f9efeda964961982d23d68cf4e018", "step": 30, "value": 1.1774137660283988, "stage": "evolution", "created_at": 1789673393.1054885}, {"event_id": "abfe411e0d6149a081835c253e6d4466", "step": 31, "value": 1.1805718646370356, "stage": "debug", "created_at": 1789673891.9495258}, {"event_id": "7714cda4c4eb4b85a6b16a163c28f94d", "step": 32, "value": 1.1784149634532095, "stage": "evolution", "created_at": 1789674392.539223}, {"event_id": "7614395121334c55828b5761707a34ce", "step": 33, "value": 1.1572893824578814, "stage": "improve", "created_at": 1789674939.5897987}, {"event_id": "469ef09656a242eb94ffe1a89e22516c", "step": 34, "value": 1.193963896788892, "stage": "improve", "created_at": 1789675481.9134471}, {"event_id": "4158282fc3c04e27a8d14e69f77793f4", "step": 35, "value": 1.098516707919561, "stage": "improve", "created_at": 1789676077.266544}, {"event_id": "484cfecd2c57410c9b15bfd8435b066c", "step": 36, "value": 1.185998809754122, "stage": "improve", "created_at": 1789676592.9214628}, {"event_id": "aeb729756a564e27bb5642f527b6542d", "step": 37, "value": 1.1943913793337613, "stage": "improve", "created_at": 1789677230.5071025}], "maximize": false, "node_count": 38, "metric_name": "BPB", "curve_scope": "原始候选验证 BPB（可能含回滚或预算后记录），不作为预算内最终成绩。最终成绩以 all_runs_final.csv 为准。", "official_score": null}, {"id": "xixian.bo-study-absolute-ucb.seed47", "experiment_id": "nanogpt-development-r2-v2-20260917", "family": "nanoGPT", "method": "bo_study_absolute_ucb", "dataset": "nanoGPT", "seed": "47", "status": "completed", "best_valid_bpb": 1.1798174851124013, "elapsed_seconds": 21600.0, "budget_seconds": 21600.0, "comparison_eligible": true, "note": "time_budget", "artifacts": [{"bundle_id": "01-read-first-and-final-states", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/01-read-first-and-final-states/logs-c828e9f97191.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/01-read-first-and-final-states", "member": "MLEvolve_BO/research/nanogpt_bo_20260917/analysis/final_closeout_20260918/all_runs_final.csv", "sha256": "c828e9f97191ffc3f6f4fa6f39045e6be494d2ab2ea3337eff18dfd2830908ba"}, {"bundle_id": "02-study-run-logs", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/02-study-run-logs/logs-50a9df8a8a5a.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/02-study-run-logs", "member": "MLEvolve_BO/research/nanogpt_bo_20260917/development_r2_v2/bo_study_absolute_ucb/runs/20260917_085629_bo_study_absolute_ucb/logs/journal.json", "sha256": "50a9df8a8a5acb631814aa5ea6a0f2e8b7d47ec05bff989ffaa975aa9ca71d25"}], "ledger": {"campaign": "development_r2_v2", "stage": "development", "method": "bo_study_absolute_ucb", "version": "r2_value_models_v1_common_causality_v2_pool2", "seed": "47", "training_seed": "42", "state": "finished", "complete_budget": "True", "launch_allowed": "", "not_launched_reason": "", "complete_8h": "False", "active_seconds": "21600", "budget_seconds": "21600", "source_duration_seconds": "28800", "budget_amended": "True", "raw_active_seconds": "21600.0", "post_budget_active_seconds": "0.0", "comparison_eligible": "True", "protocol_invalid_results": "0", "raw_reported_valid": "32", "raw_reported_best_bpb": "1.1798174851124013", "validity_audit": "", "comparison_exclusion_reason": "", "policy_contamination_started_at": "", "active_gpu_hours": "6.0", "actual_elapsed_seconds": "23213.4130859375", "segment_gpu_hours_including_cleanup": "6.009016833040449", "between_segment_seconds": "1580.9524869918823", "completed": "45", "raw_completed": "45", "unverified_commit_time_count": "0", "post_budget_completed": "0", "valid": "32", "failure_fraction": "0.28888888888888886", "best_bpb_so_far": "1.1798174851124013", "final_bpb": "1.1798174851124013", "best_node_id": "a695f078764e41a088ac07d66062a2f1", "llm_attempts": "161", "llm_cli_reported_tokens_known": "3391243", "llm_attempts_unknown_tokens": "0", "llm_measured_wall_seconds": "5097.428945302963", "llm_unfinished_attempts": "0", "llm_failed_or_interrupted_attempts": "0", "allocated_gpu_hours": "6.495171102484068", "allocated_gpu_hours_accounting_final": "True", "resource_records": "[\"10832308\", \"10833227\", \"10833543\", \"10835358\", \"10836530\", \"10838575\", \"10841315\", \"10842805\"]", "resource_accounting_captured_at": "[\"2026-09-18T07:58:09.907083+00:00\"]", "gpu_models": "[\"NVIDIA A100-SXM4-80GB\"]", "completed_proposal_wall_seconds": "21088.993854320608", "raw_completed_proposal_wall_seconds": "21088.993854320608", "diagnostic_feedback_scope": "Only results committed within the registered budget; later DEBUG repairs and mature labels excluded", "diagnostic_excluded_late_transitions": "0", "closed_proposals": "32", "unclosed_proposals": "3", "unknown_closure_proposals": "0", "closed_proposal_failure_fraction": "0.0", "raw_reported_closed_proposal_failure_fraction": "0.0", "debug_repaired_proposals": "5", "raw_serial_actions": "49", "raw_actions_with_error_logs": "0", "raw_training_launches": "42", "interrupted_actions": "1", "interrupted_action_active_seconds_upper_bound": "191.07398796081543", "gpu_uuid": "GPU-8f494385-0f3d-9f70-4382-4c33d153f5c2", "job_id": "10835358", "node": "cn-g013.server.mila.quebec", "started_at": "2026-09-17T12:55:54.080501+00:00", "finished_at": "2026-09-17T19:22:47.493587+00:00", "stop_reason": "time_budget", "training_rows": "27", "incomplete_windows": "", "current_label_diagnostics": "{}", "threshold_active_seconds": "{\"1.2\": 16506.65501189232, \"1.15\": null, \"1.1\": null}", "log_dir": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r2_v2/bo_study_absolute_ucb/runs/20260917_085629_bo_study_absolute_ucb/logs", "committed_evidence": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r2_v2/bo_study_absolute_ucb/checkpoints/boundary-1789672743661061079/logs", "final_solution": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r2_v2/bo_study_absolute_ucb/runs/20260917_085629_bo_study_absolute_ucb/workspace/trials/a695f078764e41a088ac07d66062a2f1/candidate.py"}, "journal_ref": "02-study-run-logs:MLEvolve_BO/research/nanogpt_bo_20260917/development_r2_v2/bo_study_absolute_ucb/runs/20260917_085629_bo_study_absolute_ucb/logs/journal.json", "metrics": [{"event_id": "46f046deed194810ad2a4c3a6840aa66", "step": 1, "value": 1.4898603605274425, "stage": "draft", "created_at": 1789649816.9425895}, {"event_id": "57c63fece6fb47c2b14a2ba7555c8b46", "step": 4, "value": 1.5607632201835206, "stage": "improve", "created_at": 1789651734.313345}, {"event_id": "302b88d87ab348b6bff76f8a140edeaf", "step": 5, "value": 3.077384567805417, "stage": "debug", "created_at": 1789652358.3666198}, {"event_id": "ddccacd99e13467cbff0ccfe62b3b715", "step": 6, "value": 3.2868812849420164, "stage": "debug", "created_at": 1789652844.9905794}, {"event_id": "c7f15f034152407099015b10c45122cf", "step": 7, "value": 3.214975747713169, "stage": "improve", "created_at": 1789654174.1375237}, {"event_id": "75545215351b402b8cb27227526f6a6c", "step": 8, "value": 1.5841885084860237, "stage": "improve", "created_at": 1789654783.980346}, {"event_id": "d6520668f88f4050b3ff32aeef34e945", "step": 10, "value": 1.5879655162072024, "stage": "improve", "created_at": 1789656318.1419544}, {"event_id": "509af8b6d7d34894a01c57e76f763758", "step": 14, "value": 2.2568054363859567, "stage": "debug", "created_at": 1789657569.1371017}, {"event_id": "a316fdcb11ed457ab243a2a53ee675cb", "step": 16, "value": 1.5067035527296688, "stage": "debug", "created_at": 1789658142.9388638}, {"event_id": "5326832d53fe45219b4ee19ef8ade339", "step": 17, "value": 1.3196720470017858, "stage": "draft", "created_at": 1789658576.969914}, {"event_id": "c1a465196f334a308e5774645f59bf73", "step": 19, "value": 1.504342239039367, "stage": "evolution", "created_at": 1789659539.6479976}, {"event_id": "e3f2151620bd4f758384a8ef7f5a309b", "step": 20, "value": 1.5492614340845736, "stage": "evolution", "created_at": 1789660068.9327762}, {"event_id": "5eaa4e06ad464457bab69d9cd41f17a3", "step": 21, "value": 1.4857998429048043, "stage": "evolution", "created_at": 1789660606.5580378}, {"event_id": "e7fa60994e8c4c0991bb1cb0ce41cf45", "step": 22, "value": 1.4569298390569931, "stage": "improve", "created_at": 1789661130.4658406}, {"event_id": "2421f947026c4fdeb76dca264319826c", "step": 23, "value": 1.451919724451367, "stage": "improve", "created_at": 1789661673.1294832}, {"event_id": "81cb363a939647958238b6b60edfb9ed", "step": 24, "value": 1.4521285356689735, "stage": "improve", "created_at": 1789662251.298893}, {"event_id": "f3b2324f68b64209a58b378c75d195d4", "step": 25, "value": 1.4116025982763012, "stage": "improve", "created_at": 1789662792.6024365}, {"event_id": "fe9c242735f24e579ec953199fd281f9", "step": 26, "value": 1.6934645561932604, "stage": "improve", "created_at": 1789663330.3296812}, {"event_id": "d8630a6ec0ab45f3b5e2563d992b9cc9", "step": 27, "value": 1.4205431699740232, "stage": "improve", "created_at": 1789663968.859037}, {"event_id": "789b26043e2342e9aea06e8bacfd2ab1", "step": 28, "value": 1.4858071087952496, "stage": "improve", "created_at": 1789664462.1969013}, {"event_id": "4cfc3c5ef12840c3973d11f69ef01058", "step": 29, "value": 2.625648969176106, "stage": "evolution", "created_at": 1789664957.4254067}, {"event_id": "67b79c9750ed402b8a772cbc6ade6bfa", "step": 31, "value": 1.5590632342447825, "stage": "evolution", "created_at": 1789665896.2444675}, {"event_id": "69af36104c374ba894e5925b0bbee2b5", "step": 32, "value": 1.6198460475527876, "stage": "evolution", "created_at": 1789666777.799568}, {"event_id": "a695f078764e41a088ac07d66062a2f1", "step": 33, "value": 1.1798174851124013, "stage": "debug", "created_at": 1789667367.7148476}, {"event_id": "ef656fdc0526418eb2b061580f2c5bf9", "step": 34, "value": 1.4291490771433302, "stage": "evolution", "created_at": 1789667883.6760862}, {"event_id": "ec00d39b196e477bb7fc48ff9fffc3a6", "step": 35, "value": 2.625481686498652, "stage": "evolution", "created_at": 1789668416.7064774}, {"event_id": "21927ad258824b7b920f794810de2aa2", "step": 36, "value": 1.4187701334953182, "stage": "evolution", "created_at": 1789668934.0490565}, {"event_id": "f4083418c7e8405e9d3ea4531b965957", "step": 38, "value": 1.4667134047368369, "stage": "fusion", "created_at": 1789669593.3801205}, {"event_id": "9d1142e2d4884b6e810a809a47cef51f", "step": 39, "value": 1.4201417267979928, "stage": "evolution", "created_at": 1789670152.0708866}, {"event_id": "f7b5cf995ffe48ff9aa30aa7c541b641", "step": 41, "value": 1.4022211783735241, "stage": "fusion", "created_at": 1789670803.2259035}, {"event_id": "dc71142bd01145a391244b58d0563dea", "step": 42, "value": 1.4607951939996648, "stage": "improve", "created_at": 1789671333.257888}, {"event_id": "2ab50815a7a6497a897c6842a142d751", "step": 44, "value": 1.449904011997447, "stage": "improve", "created_at": 1789671947.9946866}], "maximize": false, "node_count": 46, "metric_name": "BPB", "curve_scope": "原始候选验证 BPB（可能含回滚或预算后记录），不作为预算内最终成绩。最终成绩以 all_runs_final.csv 为准。", "official_score": null}, {"id": "xixian.bo-study-parent-coefficient-mean.seed47", "experiment_id": "nanogpt-development-r2-v2-20260917", "family": "nanoGPT", "method": "bo_study_parent_coefficient_mean", "dataset": "nanoGPT", "seed": "47", "status": "completed", "best_valid_bpb": 1.093027368156362, "elapsed_seconds": 21600.0, "budget_seconds": 21600.0, "comparison_eligible": true, "note": "time_budget", "artifacts": [{"bundle_id": "01-read-first-and-final-states", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/01-read-first-and-final-states/logs-c828e9f97191.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/01-read-first-and-final-states", "member": "MLEvolve_BO/research/nanogpt_bo_20260917/analysis/final_closeout_20260918/all_runs_final.csv", "sha256": "c828e9f97191ffc3f6f4fa6f39045e6be494d2ab2ea3337eff18dfd2830908ba"}, {"bundle_id": "02-study-run-logs", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/02-study-run-logs/logs-50a9df8a8a5a.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/02-study-run-logs", "member": "MLEvolve_BO/research/nanogpt_bo_20260917/development_r2_v2/bo_study_parent_coefficient_mean/runs/20260917_104103_bo_study_parent_coefficient_mean/logs/journal.json", "sha256": "50a9df8a8a5acb631814aa5ea6a0f2e8b7d47ec05bff989ffaa975aa9ca71d25"}], "ledger": {"campaign": "development_r2_v2", "stage": "development", "method": "bo_study_parent_coefficient_mean", "version": "r2_value_models_v1_common_causality_v2_pool2", "seed": "47", "training_seed": "42", "state": "finished", "complete_budget": "True", "launch_allowed": "", "not_launched_reason": "", "complete_8h": "False", "active_seconds": "21600", "budget_seconds": "21600", "source_duration_seconds": "28800", "budget_amended": "True", "raw_active_seconds": "21600.0", "post_budget_active_seconds": "0.0", "comparison_eligible": "True", "protocol_invalid_results": "0", "raw_reported_valid": "34", "raw_reported_best_bpb": "1.093027368156362", "validity_audit": "", "comparison_exclusion_reason": "", "policy_contamination_started_at": "", "active_gpu_hours": "6.0", "actual_elapsed_seconds": "21730.15146279335", "segment_gpu_hours_including_cleanup": "6.000696686440044", "between_segment_seconds": "127.6433916091919", "completed": "39", "raw_completed": "39", "unverified_commit_time_count": "0", "post_budget_completed": "0", "valid": "34", "failure_fraction": "0.1282051282051282", "best_bpb_so_far": "1.093027368156362", "final_bpb": "1.093027368156362", "best_node_id": "b2ced301d89a44c786d571a61489ed03", "llm_attempts": "146", "llm_cli_reported_tokens_known": "3085414", "llm_attempts_unknown_tokens": "1", "llm_measured_wall_seconds": "5155.973767518997", "llm_unfinished_attempts": "0", "llm_failed_or_interrupted_attempts": "1", "allocated_gpu_hours": "10.896372605363528", "allocated_gpu_hours_accounting_final": "True", "resource_records": "[\"10833543\", \"10835358\", \"10836530\", \"10838575\", \"10841315\", \"10842805\"]", "resource_accounting_captured_at": "[\"2026-09-18T07:58:09.907083+00:00\"]", "gpu_models": "[\"NVIDIA A100-SXM4-80GB\"]", "completed_proposal_wall_seconds": "21241.311650053598", "raw_completed_proposal_wall_seconds": "21241.311650053598", "diagnostic_feedback_scope": "Only results committed within the registered budget; later DEBUG repairs and mature labels excluded", "diagnostic_excluded_late_transitions": "0", "closed_proposals": "34", "unclosed_proposals": "0", "unknown_closure_proposals": "0", "closed_proposal_failure_fraction": "0.0", "raw_reported_closed_proposal_failure_fraction": "0.0", "debug_repaired_proposals": "4", "raw_serial_actions": "43", "raw_actions_with_error_logs": "0", "raw_training_launches": "39", "interrupted_actions": "1", "interrupted_action_active_seconds_upper_bound": "62.704554080963135", "gpu_uuid": "GPU-2350c43b-be72-b655-14bc-880ddd378c4d", "job_id": "10836530", "node": "cn-g013.server.mila.quebec", "started_at": "2026-09-17T14:40:22.576162+00:00", "finished_at": "2026-09-17T20:42:32.727625+00:00", "stop_reason": "time_budget", "training_rows": "28", "incomplete_windows": "", "current_label_diagnostics": "{}", "threshold_active_seconds": "{\"1.2\": 7441.36083817482, \"1.15\": 9007.118838071823, \"1.1\": 19654.451560735703}", "log_dir": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r2_v2/bo_study_parent_coefficient_mean/runs/20260917_104103_bo_study_parent_coefficient_mean/logs", "committed_evidence": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r2_v2/bo_study_parent_coefficient_mean/checkpoints/boundary-1789677687194925497/logs", "final_solution": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r2_v2/bo_study_parent_coefficient_mean/runs/20260917_104103_bo_study_parent_coefficient_mean/workspace/trials/b2ced301d89a44c786d571a61489ed03/candidate.py"}, "journal_ref": "02-study-run-logs:MLEvolve_BO/research/nanogpt_bo_20260917/development_r2_v2/bo_study_parent_coefficient_mean/runs/20260917_104103_bo_study_parent_coefficient_mean/logs/journal.json", "metrics": [{"event_id": "0e83b289804e4b2fa923280fa79c6baf", "step": 1, "value": 1.500926207576511, "stage": "draft", "created_at": 1789656090.6363382}, {"event_id": "b99e7470afe04b08af7f0c36841a1288", "step": 4, "value": 1.8564951310453288, "stage": "improve", "created_at": 1789657999.990069}, {"event_id": "d7d5c1a4a4184e0aa9c2b8f1a08e5723", "step": 6, "value": 3.2892863244979744, "stage": "debug", "created_at": 1789658716.4068017}, {"event_id": "4e389b846e6242ef84f91d828b2073bd", "step": 7, "value": 1.5370908679107358, "stage": "improve", "created_at": 1789659370.6075914}, {"event_id": "ac04a9141bcc430a9d992233efd66284", "step": 8, "value": 3.176168916778346, "stage": "debug", "created_at": 1789659873.6404052}, {"event_id": "70aa8e4775dc43cdb6655727bde4191b", "step": 9, "value": 1.7267439337213575, "stage": "improve", "created_at": 1789660387.4987266}, {"event_id": "49f739b508744d5fad55ca28efa2d87a", "step": 10, "value": 1.6348569301995415, "stage": "evolution", "created_at": 1789660958.8606489}, {"event_id": "68dfc680c64e43dc9d9184e80e62a3b3", "step": 11, "value": 1.3161976816818692, "stage": "draft", "created_at": 1789661481.6005015}, {"event_id": "78a4e402645f4a4ca8fcf99807e760ff", "step": 13, "value": 1.651316620112585, "stage": "improve", "created_at": 1789662497.6812384}, {"event_id": "87d510c51f0742ad854c91915088ab1a", "step": 14, "value": 1.1693127530489966, "stage": "evolution", "created_at": 1789662993.6190379}, {"event_id": "09d526a9d7754e8a85c006ee9bd46864", "step": 15, "value": 1.480447101802103, "stage": "debug", "created_at": 1789663483.4332147}, {"event_id": "51d3736658a5416889f6fbf7c8c29e5f", "step": 16, "value": 3.9361467089633684, "stage": "improve", "created_at": 1789664024.3113909}, {"event_id": "76ac8085d0a742ae8123d060ae9f6518", "step": 17, "value": 1.1231179717115882, "stage": "improve", "created_at": 1789664570.2032547}, {"event_id": "4150c0eeb09d4b4fbee61f9c2aed48d5", "step": 18, "value": 1.1772066045521041, "stage": "improve", "created_at": 1789665104.8733284}, {"event_id": "372b69db2a074232bcd7de52831ded3c", "step": 19, "value": 1.1917395973559872, "stage": "improve", "created_at": 1789665626.662857}, {"event_id": "df406c5eee1b44498958c9f3a7bc57a7", "step": 20, "value": 1.1465926456252882, "stage": "improve", "created_at": 1789666159.036139}, {"event_id": "c4587c12660f47d595b4ee50704b2548", "step": 21, "value": 1.1846398448997082, "stage": "evolution", "created_at": 1789666819.7518475}, {"event_id": "9dd01c6028ff4641a895893284260099", "step": 23, "value": 1.148916087482366, "stage": "evolution", "created_at": 1789667833.8813856}, {"event_id": "c47da0529c7344d2aaa5850171a708e0", "step": 24, "value": 1.300671374815183, "stage": "evolution", "created_at": 1789668465.2935736}, {"event_id": "7995b932f2424a549ca07d57271bdd89", "step": 25, "value": 1.179305835675775, "stage": "debug", "created_at": 1789669005.022945}, {"event_id": "3130a3ea3744472bb92488f99eb47211", "step": 26, "value": 1.2013758247497526, "stage": "evolution", "created_at": 1789669554.2891536}, {"event_id": "61fce84532bb4363b05001e4e2a4bb6d", "step": 27, "value": 1.130629879547005, "stage": "evolution", "created_at": 1789670124.1007469}, {"event_id": "01c2bff4a0004afb8266b7b792a4a6a9", "step": 28, "value": 1.136419073138804, "stage": "evolution", "created_at": 1789670702.2306342}, {"event_id": "21d1c23c47ba43d294ddf097efe4ed55", "step": 29, "value": 1.1318144720828136, "stage": "evolution", "created_at": 1789671226.432329}, {"event_id": "027626341bcf44f3b6bce0888a7fec3d", "step": 30, "value": 1.1318447527498001, "stage": "evolution", "created_at": 1789671803.8445098}, {"event_id": "dce203efb63e400782f9c3a44d19d744", "step": 31, "value": 3.023286527059814, "stage": "evolution", "created_at": 1789672329.8907385}, {"event_id": "50fb09e1c5f84d778bd1b38063b1d56e", "step": 32, "value": 1.1421010199672108, "stage": "evolution", "created_at": 1789672942.372203}, {"event_id": "1719a008a3454e48a627932e849e47dc", "step": 33, "value": 1.4988199471810653, "stage": "evolution", "created_at": 1789673545.869183}, {"event_id": "5a36c0fa12904128b6167b06e3fe69fc", "step": 34, "value": 1.1573931134205966, "stage": "fusion", "created_at": 1789674100.6369503}, {"event_id": "7723a2c65cac49a29b2598f2584d3e65", "step": 35, "value": 1.2457837038209318, "stage": "evolution", "created_at": 1789674661.009257}, {"event_id": "5bf512c251fe40af9e485869ad690ad9", "step": 36, "value": 1.0945599107432527, "stage": "fusion", "created_at": 1789675223.403768}, {"event_id": "2ba6d55e917149f8b7f09e8e86778ca7", "step": 37, "value": 1.176088949075285, "stage": "improve", "created_at": 1789675866.7830815}, {"event_id": "1bafd39c42184783b9ecaad1eb3a1145", "step": 38, "value": 1.1352251549653283, "stage": "improve", "created_at": 1789676476.5955868}, {"event_id": "b2ced301d89a44c786d571a61489ed03", "step": 39, "value": 1.093027368156362, "stage": "improve", "created_at": 1789677221.9966052}], "maximize": false, "node_count": 40, "metric_name": "BPB", "curve_scope": "原始候选验证 BPB（可能含回滚或预算后记录），不作为预算内最终成绩。最终成绩以 all_runs_final.csv 为准。", "official_score": null}, {"id": "xixian.bo-study-residual-scale-ucb.seed47", "experiment_id": "nanogpt-development-r3-v1-20260917", "family": "nanoGPT", "method": "bo_study_residual_scale_ucb", "dataset": "nanoGPT", "seed": "47", "status": "completed", "best_valid_bpb": 1.0888324608466247, "elapsed_seconds": 21600.0, "budget_seconds": 21600.0, "comparison_eligible": true, "note": "time_budget", "artifacts": [{"bundle_id": "01-read-first-and-final-states", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/01-read-first-and-final-states/logs-c828e9f97191.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/01-read-first-and-final-states", "member": "MLEvolve_BO/research/nanogpt_bo_20260917/analysis/final_closeout_20260918/all_runs_final.csv", "sha256": "c828e9f97191ffc3f6f4fa6f39045e6be494d2ab2ea3337eff18dfd2830908ba"}, {"bundle_id": "02-study-run-logs", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/02-study-run-logs/logs-50a9df8a8a5a.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/02-study-run-logs", "member": "MLEvolve_BO/research/nanogpt_bo_20260917/development_r3_v1/bo_study_residual_scale_ucb/runs/20260917_120354_bo_study_residual_scale_ucb/logs/journal.json", "sha256": "50a9df8a8a5acb631814aa5ea6a0f2e8b7d47ec05bff989ffaa975aa9ca71d25"}], "ledger": {"campaign": "development_r3_v1", "stage": "development", "method": "bo_study_residual_scale_ucb", "version": "r3_scale_linear_joint_ts_v1", "seed": "47", "training_seed": "42", "state": "finished", "complete_budget": "True", "launch_allowed": "", "not_launched_reason": "", "complete_8h": "False", "active_seconds": "21600", "budget_seconds": "21600", "source_duration_seconds": "21600", "budget_amended": "False", "raw_active_seconds": "21600.0", "post_budget_active_seconds": "0.0", "comparison_eligible": "True", "protocol_invalid_results": "0", "raw_reported_valid": "36", "raw_reported_best_bpb": "1.0888324608466247", "validity_audit": "", "comparison_exclusion_reason": "", "policy_contamination_started_at": "", "active_gpu_hours": "6.0", "actual_elapsed_seconds": "21636.094362020493", "segment_gpu_hours_including_cleanup": "6.010026211606132", "between_segment_seconds": "2.384185791015625e-07", "completed": "42", "raw_completed": "42", "unverified_commit_time_count": "0", "post_budget_completed": "0", "valid": "36", "failure_fraction": "0.1428571428571429", "best_bpb_so_far": "1.0888324608466247", "final_bpb": "1.0888324608466247", "best_node_id": "859b72ae78ea492db6c42aec83e5147f", "llm_attempts": "164", "llm_cli_reported_tokens_known": "3280787", "llm_attempts_unknown_tokens": "0", "llm_measured_wall_seconds": "4798.219171524048", "llm_unfinished_attempts": "0", "llm_failed_or_interrupted_attempts": "0", "allocated_gpu_hours": "6.016388888888889", "allocated_gpu_hours_accounting_final": "True", "resource_records": "[\"10834041\"]", "resource_accounting_captured_at": "[\"2026-09-18T07:58:41.254237+00:00\"]", "gpu_models": "[\"NVIDIA A100-SXM4-80GB\"]", "completed_proposal_wall_seconds": "21380.670722373296", "raw_completed_proposal_wall_seconds": "21380.670722373296", "diagnostic_feedback_scope": "Only results committed within the registered budget; later DEBUG repairs and mature labels excluded", "diagnostic_excluded_late_transitions": "0", "closed_proposals": "36", "unclosed_proposals": "2", "unknown_closure_proposals": "0", "closed_proposal_failure_fraction": "0.0", "raw_reported_closed_proposal_failure_fraction": "0.0", "debug_repaired_proposals": "4", "raw_serial_actions": "46", "raw_actions_with_error_logs": "0", "raw_training_launches": "43", "interrupted_actions": "1", "interrupted_action_active_seconds_upper_bound": "91.4330735206604", "gpu_uuid": "GPU-78b4ce31-d115-7b9a-f22e-d0ed70044433", "job_id": "10834041", "node": "cn-g027.server.mila.quebec", "started_at": "2026-09-17T16:03:17.553073+00:00", "finished_at": "2026-09-17T22:03:53.647435+00:00", "stop_reason": "time_budget", "training_rows": "30", "incomplete_windows": "", "current_label_diagnostics": "{}", "threshold_active_seconds": "{\"1.2\": 10909.241926670074, \"1.15\": 13058.044926643372, \"1.1\": 19175.522926568985}", "log_dir": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r3_v1/bo_study_residual_scale_ucb/runs/20260917_120354_bo_study_residual_scale_ucb/logs", "committed_evidence": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r3_v1/bo_study_residual_scale_ucb/checkpoints/boundary-1789682505790052687/logs", "final_solution": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r3_v1/bo_study_residual_scale_ucb/runs/20260917_120354_bo_study_residual_scale_ucb/workspace/trials/859b72ae78ea492db6c42aec83e5147f/candidate.py"}, "journal_ref": "02-study-run-logs:MLEvolve_BO/research/nanogpt_bo_20260917/development_r3_v1/bo_study_residual_scale_ucb/runs/20260917_120354_bo_study_residual_scale_ucb/logs/journal.json", "metrics": [{"event_id": "a4822512df704e37ac9bbfdc3c151181", "step": 1, "value": 1.4914079785524104, "stage": "draft", "created_at": 1789661057.5770373}, {"event_id": "60a6f92e360045978ec620ac65c7f2fe", "step": 4, "value": 1.8600254311552584, "stage": "improve", "created_at": 1789662960.1208496}, {"event_id": "b00ef15f310245dab90da3a099283be8", "step": 5, "value": 3.0912152630837544, "stage": "debug", "created_at": 1789663524.3091724}, {"event_id": "87607ca57e27421c93c9ffd2740f0f46", "step": 6, "value": 3.312520723100933, "stage": "debug", "created_at": 1789663993.9190474}, {"event_id": "91a828793b564deaa7e2c767cdae228c", "step": 7, "value": 1.2472463967094471, "stage": "improve", "created_at": 1789664630.0350864}, {"event_id": "fe028eabb2c249cda425528edf74a8a0", "step": 8, "value": 1.326269022855501, "stage": "improve", "created_at": 1789665135.7726512}, {"event_id": "569c6fd696524e399f5f63e977fdf86f", "step": 9, "value": 1.2793151986421496, "stage": "improve", "created_at": 1789665593.2774167}, {"event_id": "fefdf44b80ac47278962dc8a04b5cd17", "step": 10, "value": 1.7340526961416143, "stage": "improve", "created_at": 1789666136.5272777}, {"event_id": "2725950fd583469d9fd66a48bce35705", "step": 11, "value": 1.5593733233118228, "stage": "evolution", "created_at": 1789666732.2543104}, {"event_id": "636c7f8089aa4041a22d9ea8c3048735", "step": 12, "value": 1.3178563732364272, "stage": "draft", "created_at": 1789667212.1443553}, {"event_id": "19fada1aef2a4197bbbb77d381101d1c", "step": 13, "value": 1.686968224343804, "stage": "improve", "created_at": 1789668052.6864247}, {"event_id": "999faca2b7ee4a2dbd4c0d1305d52f64", "step": 14, "value": 1.3095508994284242, "stage": "evolution", "created_at": 1789668566.3890796}, {"event_id": "7bd1084ffe004dbf9870b0b69d76b593", "step": 15, "value": 1.3885941908041657, "stage": "evolution", "created_at": 1789669098.0631363}, {"event_id": "eeaca322a738472f8f01abf645104e76", "step": 16, "value": 1.4059421812842003, "stage": "evolution", "created_at": 1789669596.0191514}, {"event_id": "61f17b04eedd4fbe89947073bc42fb35", "step": 18, "value": 1.4721961420736995, "stage": "evolution", "created_at": 1789670456.2733314}, {"event_id": "27df666e7e094495b81230ce779944f1", "step": 19, "value": 1.2960960452525419, "stage": "evolution", "created_at": 1789671000.1151915}, {"event_id": "675ec6864f444784b87e540da45648e8", "step": 20, "value": 1.175645081403006, "stage": "debug", "created_at": 1789671461.3563156}, {"event_id": "958758f4bd254690b5d7fa4ff2f0f88a", "step": 21, "value": 1.2132064475690862, "stage": "improve", "created_at": 1789672007.0483587}, {"event_id": "4a6688e9a5864c8293f4ef8774188011", "step": 22, "value": 1.8716063594436658, "stage": "improve", "created_at": 1789672550.4349}, {"event_id": "0bb68be3bdf74025980e9d4ee1df3799", "step": 23, "value": 1.260455712057161, "stage": "improve", "created_at": 1789673085.682409}, {"event_id": "ca0154e4901a4546a97e983c3fef7d11", "step": 24, "value": 1.120320095509499, "stage": "evolution", "created_at": 1789673591.0460587}, {"event_id": "809a992638cb4ebcb495dda8acf41811", "step": 25, "value": 1.1924182006666264, "stage": "improve", "created_at": 1789674130.413504}, {"event_id": "ea31466685ec400aa945361d5770eaa7", "step": 26, "value": 1.1263276026052214, "stage": "improve", "created_at": 1789674639.607361}, {"event_id": "0b6080c6ceb9420bba29b0864d710e2b", "step": 28, "value": 1.165427423896338, "stage": "improve", "created_at": 1789675422.8310308}, {"event_id": "85ed25766e0340e8aa21a8036bf2ce9a", "step": 29, "value": 1.1239401324680942, "stage": "evolution", "created_at": 1789675918.7980866}, {"event_id": "54cc2da9168e427b857ce5a683257163", "step": 30, "value": 1.1745153855302335, "stage": "debug", "created_at": 1789676428.3368492}, {"event_id": "f1cdbb55013b41edb00057c88b0aba66", "step": 31, "value": 1.1834029643634647, "stage": "evolution", "created_at": 1789676921.214978}, {"event_id": "c2e1d4d44fa8496eb115cf9c667fc555", "step": 32, "value": 1.172993948645629, "stage": "evolution", "created_at": 1789677436.5522985}, {"event_id": "2d1af606ff1c4eebb7d9acc27206e427", "step": 33, "value": 1.182170110937216, "stage": "evolution", "created_at": 1789678115.9036212}, {"event_id": "55b0ec049f01432ba3d79cd53668b7b3", "step": 34, "value": 1.1389391418495505, "stage": "evolution", "created_at": 1789678587.6278267}, {"event_id": "59361d2d20134df0abb039c6ef94aef7", "step": 35, "value": 1.245567467502793, "stage": "fusion", "created_at": 1789679095.4885638}, {"event_id": "859b72ae78ea492db6c42aec83e5147f", "step": 37, "value": 1.0888324608466247, "stage": "fusion", "created_at": 1789679759.247343}, {"event_id": "31a3515f9da346f88ba01a6e674e9c90", "step": 38, "value": 1.1009575787971881, "stage": "improve", "created_at": 1789680238.1139529}, {"event_id": "c24f00be1b2e46b5a44a483bf9c30d03", "step": 39, "value": 1.1744538601498975, "stage": "improve", "created_at": 1789680801.000351}, {"event_id": "500d77f8531a4fcd8c837575b401516e", "step": 40, "value": 1.3049733300088224, "stage": "improve", "created_at": 1789681324.3544948}, {"event_id": "71e0e7f8b1784bdfbccda3cec075a603", "step": 42, "value": 1.0928389707070265, "stage": "evolution", "created_at": 1789682003.5649636}], "maximize": false, "node_count": 43, "metric_name": "BPB", "curve_scope": "原始候选验证 BPB（可能含回滚或预算后记录），不作为预算内最终成绩。最终成绩以 all_runs_final.csv 为准。", "official_score": null}, {"id": "xixian.bo-study-linear-ucb.seed47", "experiment_id": "nanogpt-development-r3-v1-20260917", "family": "nanoGPT", "method": "bo_study_linear_ucb", "dataset": "nanoGPT", "seed": "47", "status": "completed", "best_valid_bpb": 1.0990259698704752, "elapsed_seconds": 21600.0, "budget_seconds": 21600.0, "comparison_eligible": true, "note": "time_budget", "artifacts": [{"bundle_id": "01-read-first-and-final-states", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/01-read-first-and-final-states/logs-c828e9f97191.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/01-read-first-and-final-states", "member": "MLEvolve_BO/research/nanogpt_bo_20260917/analysis/final_closeout_20260918/all_runs_final.csv", "sha256": "c828e9f97191ffc3f6f4fa6f39045e6be494d2ab2ea3337eff18dfd2830908ba"}, {"bundle_id": "02-study-run-logs", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/02-study-run-logs/logs-50a9df8a8a5a.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/02-study-run-logs", "member": "MLEvolve_BO/research/nanogpt_bo_20260917/development_r3_v1/bo_study_linear_ucb/runs/20260917_120355_bo_study_linear_ucb/logs/journal.json", "sha256": "50a9df8a8a5acb631814aa5ea6a0f2e8b7d47ec05bff989ffaa975aa9ca71d25"}], "ledger": {"campaign": "development_r3_v1", "stage": "development", "method": "bo_study_linear_ucb", "version": "r3_scale_linear_joint_ts_v1", "seed": "47", "training_seed": "42", "state": "finished", "complete_budget": "True", "launch_allowed": "", "not_launched_reason": "", "complete_8h": "False", "active_seconds": "21600", "budget_seconds": "21600", "source_duration_seconds": "21600", "budget_amended": "False", "raw_active_seconds": "21600.0", "post_budget_active_seconds": "0.0", "comparison_eligible": "True", "protocol_invalid_results": "0", "raw_reported_valid": "36", "raw_reported_best_bpb": "1.0990259698704752", "validity_audit": "", "comparison_exclusion_reason": "", "policy_contamination_started_at": "", "active_gpu_hours": "6.0", "actual_elapsed_seconds": "21611.231537103653", "segment_gpu_hours_including_cleanup": "6.003119871417681", "between_segment_seconds": "0.0", "completed": "42", "raw_completed": "42", "unverified_commit_time_count": "0", "post_budget_completed": "0", "valid": "36", "failure_fraction": "0.1428571428571429", "best_bpb_so_far": "1.0990259698704752", "final_bpb": "1.0990259698704752", "best_node_id": "0b5aad6f28634508941f0376965e466c", "llm_attempts": "172", "llm_cli_reported_tokens_known": "3293294", "llm_attempts_unknown_tokens": "1", "llm_measured_wall_seconds": "4454.49192404747", "llm_unfinished_attempts": "0", "llm_failed_or_interrupted_attempts": "1", "allocated_gpu_hours": "6.016388888888889", "allocated_gpu_hours_accounting_final": "True", "resource_records": "[\"10834041\"]", "resource_accounting_captured_at": "[\"2026-09-18T07:58:41.254237+00:00\"]", "gpu_models": "[\"NVIDIA A100-SXM4-80GB\"]", "completed_proposal_wall_seconds": "21382.068144667894", "raw_completed_proposal_wall_seconds": "21382.068144667894", "diagnostic_feedback_scope": "Only results committed within the registered budget; later DEBUG repairs and mature labels excluded", "diagnostic_excluded_late_transitions": "0", "closed_proposals": "36", "unclosed_proposals": "3", "unknown_closure_proposals": "0", "closed_proposal_failure_fraction": "0.0", "raw_reported_closed_proposal_failure_fraction": "0.0", "debug_repaired_proposals": "3", "raw_serial_actions": "46", "raw_actions_with_error_logs": "0", "raw_training_launches": "42", "interrupted_actions": "1", "interrupted_action_active_seconds_upper_bound": "97.03946208953857", "gpu_uuid": "GPU-82331c40-6f70-3d2f-b8ad-f8c17706acde", "job_id": "10834041", "node": "cn-g027.server.mila.quebec", "started_at": "2026-09-17T16:03:17.555462+00:00", "finished_at": "2026-09-17T22:03:28.786999+00:00", "stop_reason": "time_budget", "training_rows": "30", "incomplete_windows": "", "current_label_diagnostics": "{}", "threshold_active_seconds": "{\"1.2\": 13220.589537858963, \"1.15\": 13755.696537971497, \"1.1\": 19040.752537965775}", "log_dir": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r3_v1/bo_study_linear_ucb/runs/20260917_120355_bo_study_linear_ucb/logs", "committed_evidence": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r3_v1/bo_study_linear_ucb/checkpoints/boundary-1789682500189976065/logs", "final_solution": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r3_v1/bo_study_linear_ucb/runs/20260917_120355_bo_study_linear_ucb/workspace/trials/0b5aad6f28634508941f0376965e466c/candidate.py"}, "journal_ref": "02-study-run-logs:MLEvolve_BO/research/nanogpt_bo_20260917/development_r3_v1/bo_study_linear_ucb/runs/20260917_120355_bo_study_linear_ucb/logs/journal.json", "metrics": [{"event_id": "3f1bb6be5d0d4b54986a20ee7d5cff83", "step": 1, "value": 1.483517840930757, "stage": "draft", "created_at": 1789661057.5969694}, {"event_id": "56e7d258654a4e8db38208f8231ec338", "step": 4, "value": 1.832719343866044, "stage": "improve", "created_at": 1789662960.9779692}, {"event_id": "a19cb331761241c9b612f175822a22e6", "step": 5, "value": 3.1432397686945754, "stage": "debug", "created_at": 1789663513.6758487}, {"event_id": "97c50be6cb7a471db0a7cbec96e3323a", "step": 6, "value": 3.2873495220743245, "stage": "debug", "created_at": 1789663972.752177}, {"event_id": "f0a731f6effb483bb8d8ec0e40a14b08", "step": 7, "value": 1.7333094033498366, "stage": "improve", "created_at": 1789664584.2552056}, {"event_id": "3391382044874f678286bfbe19a89a07", "step": 8, "value": 1.8924883243787998, "stage": "improve", "created_at": 1789665108.6684184}, {"event_id": "0a1fc209f8d74cc9984667c8f4d44ed6", "step": 9, "value": 1.6064886306157855, "stage": "evolution", "created_at": 1789665711.0753574}, {"event_id": "0942506a99db410da3820353291b91a7", "step": 10, "value": 1.3182464810469585, "stage": "draft", "created_at": 1789666159.055896}, {"event_id": "130bd7d675454d8da751c56f930a860c", "step": 11, "value": 3.7014550184445167, "stage": "evolution", "created_at": 1789666982.8230882}, {"event_id": "72bb7ce9fdb949cfa528e1032847c005", "step": 12, "value": 1.5745090756545579, "stage": "improve", "created_at": 1789667518.3423705}, {"event_id": "c7051a5518f444a7b55d678422745ae9", "step": 13, "value": 1.712793444566955, "stage": "improve", "created_at": 1789668074.6350427}, {"event_id": "bfa77bc6c1b74e60bb7ac919f0d92b24", "step": 14, "value": 1.8499764303117578, "stage": "improve", "created_at": 1789668615.7048965}, {"event_id": "6e3247f62e244ab7b7a833de0b30aff9", "step": 15, "value": 1.3436314707362953, "stage": "improve", "created_at": 1789669147.7941482}, {"event_id": "c17df6b06b274449976e9f076e650acd", "step": 16, "value": 1.3322528899156696, "stage": "improve", "created_at": 1789669690.929002}, {"event_id": "aed65b60adea4baeb946de5a10a446d5", "step": 17, "value": 1.6398456515487523, "stage": "evolution", "created_at": 1789670172.40901}, {"event_id": "ba3eeff580c34cf7aaec7440066a3aed", "step": 19, "value": 1.5109107392504901, "stage": "evolution", "created_at": 1789671072.4807496}, {"event_id": "49c87bcf70594b188aa2d115467e5df8", "step": 20, "value": 1.5934008439483633, "stage": "evolution", "created_at": 1789671578.7312713}, {"event_id": "679b37247cd24ed2b3fd1e9b32c39447", "step": 21, "value": 1.290184481403386, "stage": "debug", "created_at": 1789672056.1402586}, {"event_id": "4cc793b7d5274faaaeff595d042286b0", "step": 22, "value": 1.3877087123890546, "stage": "improve", "created_at": 1789672629.32011}, {"event_id": "088802c115cb4893b1fc76ea32e330f6", "step": 23, "value": 1.2663927504520793, "stage": "improve", "created_at": 1789673143.4085095}, {"event_id": "5900f52fc64640c889fbcd0219d44136", "step": 24, "value": 1.1649798686335682, "stage": "improve", "created_at": 1789673735.5786495}, {"event_id": "ffd3f042e203412ba16286cb76925a2c", "step": 25, "value": 1.105124504801004, "stage": "improve", "created_at": 1789674289.715606}, {"event_id": "5446eba8d9c64636992e1eb1840732dc", "step": 26, "value": 1.1186630189522455, "stage": "improve", "created_at": 1789674816.0605114}, {"event_id": "3da640a7c7de4daa951ca50af6514faa", "step": 27, "value": 1.1115605756325049, "stage": "improve", "created_at": 1789675380.9370906}, {"event_id": "62aa7a4d4d494a1a993dd484f3e80199", "step": 28, "value": 1.13046748019968, "stage": "improve", "created_at": 1789675881.8659286}, {"event_id": "4cc5602867204699afb9a8b08017e921", "step": 29, "value": 1.1188756956736214, "stage": "improve", "created_at": 1789676429.0218847}, {"event_id": "f8c367bdad9e40ee85afaf6ccc09a736", "step": 30, "value": 1.1197665605080935, "stage": "improve", "created_at": 1789676947.6903412}, {"event_id": "fd4adaa0258c4b6cb69f52d81e9c07b9", "step": 31, "value": 1.1582688720665482, "stage": "improve", "created_at": 1789677470.482063}, {"event_id": "644e22e5418140f6b407c2f28c4b3274", "step": 32, "value": 1.1357046299868923, "stage": "evolution", "created_at": 1789677978.0324752}, {"event_id": "345a03ccae0e49d3adff342cea9df83a", "step": 33, "value": 1.1119112990807056, "stage": "evolution", "created_at": 1789678477.2296505}, {"event_id": "2f1d253e868c428c8d83c6b9494c597a", "step": 35, "value": 1.3867278540195869, "stage": "evolution", "created_at": 1789679082.2163248}, {"event_id": "0b5aad6f28634508941f0376965e466c", "step": 36, "value": 1.0990259698704752, "stage": "evolution", "created_at": 1789679588.8581028}, {"event_id": "4e32ca95ce124b138b81b0ac9e27e946", "step": 38, "value": 1.1640390195526469, "stage": "fusion", "created_at": 1789680241.833791}, {"event_id": "565bf7f385a5441dbe6d74cb224b0354", "step": 39, "value": 1.1121709752587545, "stage": "improve", "created_at": 1789680814.33651}, {"event_id": "60143b7c12ca439ca13aa8a63aea087a", "step": 40, "value": 1.2527768029574375, "stage": "improve", "created_at": 1789681316.2056713}, {"event_id": "9f4bdd3291aa4b089eb32702d377798f", "step": 42, "value": 1.1919442255814816, "stage": "improve", "created_at": 1789682071.556664}], "maximize": false, "node_count": 43, "metric_name": "BPB", "curve_scope": "原始候选验证 BPB（可能含回滚或预算后记录），不作为预算内最终成绩。最终成绩以 all_runs_final.csv 为准。", "official_score": null}, {"id": "xixian.bo-study-joint-ts.seed47", "experiment_id": "nanogpt-development-r3-v1-20260917", "family": "nanoGPT", "method": "bo_study_joint_ts", "dataset": "nanoGPT", "seed": "47", "status": "completed", "best_valid_bpb": 1.1673645796172885, "elapsed_seconds": 21600.0, "budget_seconds": 21600.0, "comparison_eligible": true, "note": "time_budget", "artifacts": [{"bundle_id": "01-read-first-and-final-states", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/01-read-first-and-final-states/logs-c828e9f97191.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/01-read-first-and-final-states", "member": "MLEvolve_BO/research/nanogpt_bo_20260917/analysis/final_closeout_20260918/all_runs_final.csv", "sha256": "c828e9f97191ffc3f6f4fa6f39045e6be494d2ab2ea3337eff18dfd2830908ba"}, {"bundle_id": "02-study-run-logs", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/02-study-run-logs/logs-50a9df8a8a5a.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/02-study-run-logs", "member": "MLEvolve_BO/research/nanogpt_bo_20260917/development_r3_v1/bo_study_joint_ts/runs/20260917_120833_bo_study_joint_ts/logs/journal.json", "sha256": "50a9df8a8a5acb631814aa5ea6a0f2e8b7d47ec05bff989ffaa975aa9ca71d25"}], "ledger": {"campaign": "development_r3_v1", "stage": "development", "method": "bo_study_joint_ts", "version": "r3_scale_linear_joint_ts_v1", "seed": "47", "training_seed": "42", "state": "finished", "complete_budget": "True", "launch_allowed": "", "not_launched_reason": "", "complete_8h": "False", "active_seconds": "21600", "budget_seconds": "21600", "source_duration_seconds": "21600", "budget_amended": "False", "raw_active_seconds": "21600.0", "post_budget_active_seconds": "0.0", "comparison_eligible": "True", "protocol_invalid_results": "0", "raw_reported_valid": "33", "raw_reported_best_bpb": "1.1673645796172885", "validity_audit": "", "comparison_exclusion_reason": "", "policy_contamination_started_at": "", "active_gpu_hours": "6.0", "actual_elapsed_seconds": "21988.17316007614", "segment_gpu_hours_including_cleanup": "6.008699631227388", "between_segment_seconds": "356.854487657547", "completed": "38", "raw_completed": "38", "unverified_commit_time_count": "0", "post_budget_completed": "0", "valid": "33", "failure_fraction": "0.13157894736842102", "best_bpb_so_far": "1.1673645796172885", "final_bpb": "1.1673645796172885", "best_node_id": "0ecad7577ffc4332bb6b536dabb19479", "llm_attempts": "150", "llm_cli_reported_tokens_known": "3003973", "llm_attempts_unknown_tokens": "0", "llm_measured_wall_seconds": "5302.352534770966", "llm_unfinished_attempts": "0", "llm_failed_or_interrupted_attempts": "0", "allocated_gpu_hours": "7.2643175733751715", "allocated_gpu_hours_accounting_final": "True", "resource_records": "[\"10833543\", \"10835358\", \"10836530\"]", "resource_accounting_captured_at": "[\"2026-09-18T07:58:41.254237+00:00\"]", "gpu_models": "[\"NVIDIA A100-SXM4-80GB\"]", "completed_proposal_wall_seconds": "20735.553513004445", "raw_completed_proposal_wall_seconds": "20735.553513004445", "diagnostic_feedback_scope": "Only results committed within the registered budget; later DEBUG repairs and mature labels excluded", "diagnostic_excluded_late_transitions": "0", "closed_proposals": "33", "unclosed_proposals": "1", "unknown_closure_proposals": "0", "closed_proposal_failure_fraction": "0.0", "raw_reported_closed_proposal_failure_fraction": "0.0", "debug_repaired_proposals": "4", "raw_serial_actions": "42", "raw_actions_with_error_logs": "0", "raw_training_launches": "39", "interrupted_actions": "1", "interrupted_action_active_seconds_upper_bound": "524.3601603507996", "gpu_uuid": "GPU-72dc27f5-0fa1-0bc5-1ef2-0657d9e0357e", "job_id": "10836530", "node": "cn-g013.server.mila.quebec", "started_at": "2026-09-17T16:06:54.591673+00:00", "finished_at": "2026-09-17T22:13:22.764833+00:00", "stop_reason": "time_budget", "training_rows": "26", "incomplete_windows": "", "current_label_diagnostics": "{}", "threshold_active_seconds": "{\"1.2\": 21075.63883972168, \"1.15\": null, \"1.1\": null}", "log_dir": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r3_v1/bo_study_joint_ts/runs/20260917_120833_bo_study_joint_ts/logs", "committed_evidence": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r3_v1/bo_study_joint_ts/checkpoints/boundary-1789682633973684970/logs", "final_solution": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r3_v1/bo_study_joint_ts/runs/20260917_120833_bo_study_joint_ts/workspace/trials/0ecad7577ffc4332bb6b536dabb19479/candidate.py"}, "journal_ref": "02-study-run-logs:MLEvolve_BO/research/nanogpt_bo_20260917/development_r3_v1/bo_study_joint_ts/runs/20260917_120833_bo_study_joint_ts/logs/journal.json", "metrics": [{"event_id": "f823c034a585477cacf4d084ce9b60e7", "step": 1, "value": 1.5057398524086547, "stage": "draft", "created_at": 1789661338.3106487}, {"event_id": "27de170499624f33829906acaac8983f", "step": 4, "value": 1.6628155867553078, "stage": "improve", "created_at": 1789663223.1764727}, {"event_id": "2e1e717dee974811bff6facdca6f55a1", "step": 5, "value": 3.084229445013237, "stage": "debug", "created_at": 1789663828.0456831}, {"event_id": "fd67b558e06947d5a6086d3f6e86de09", "step": 6, "value": 3.286850078167525, "stage": "debug", "created_at": 1789664276.9744356}, {"event_id": "f3e6f19ad6464fe58dd62cef1bbc9c3c", "step": 7, "value": 1.6612276128337133, "stage": "improve", "created_at": 1789664911.7200108}, {"event_id": "6a7d3d2664c74dc1a352f9dc6c99f002", "step": 8, "value": 1.714952926791231, "stage": "improve", "created_at": 1789665433.845156}, {"event_id": "bb8a15ceedbf44189824f02acb53175a", "step": 9, "value": 1.3976792295485279, "stage": "evolution", "created_at": 1789665952.6603396}, {"event_id": "f20a3250e0714514865a862771454cd0", "step": 10, "value": 1.5403022200304775, "stage": "improve", "created_at": 1789666842.7008362}, {"event_id": "21a85ef6c3f143bf9091416a45a152c5", "step": 11, "value": 1.281390667593766, "stage": "improve", "created_at": 1789667449.218767}, {"event_id": "acaa5e83cbc64eb087911f010a5824c1", "step": 12, "value": 1.6051719240587963, "stage": "improve", "created_at": 1789668052.8901446}, {"event_id": "60faf98e7aec4a9487ac5032ca22c136", "step": 13, "value": 1.2490032949295606, "stage": "improve", "created_at": 1789668928.3616252}, {"event_id": "7000d288d9e349edb969fdf96fb0131e", "step": 14, "value": 1.4771654326038726, "stage": "improve", "created_at": 1789669495.3606415}, {"event_id": "01e54d8d3d9e46388bc81c877b1e98b1", "step": 16, "value": 1.2417025875280068, "stage": "improve", "created_at": 1789670313.7315974}, {"event_id": "917f2e0e489a4ab697af49c34b20c906", "step": 17, "value": 1.2490826036506422, "stage": "improve", "created_at": 1789670898.7882614}, {"event_id": "6788be948df046a1ad71a766a36cdd06", "step": 18, "value": 1.7182839694868473, "stage": "improve", "created_at": 1789671540.3776968}, {"event_id": "465afe53d2714e4dafdfea3bfd4b67ce", "step": 19, "value": 1.3920567876232819, "stage": "improve", "created_at": 1789672259.8281446}, {"event_id": "8a955541197145e6a9c84f3cc9269813", "step": 20, "value": 1.7064410685879394, "stage": "evolution", "created_at": 1789672873.0094163}, {"event_id": "ad218b3ed9d7449888cb4523f49eb087", "step": 21, "value": 1.3180114781726038, "stage": "draft", "created_at": 1789673343.3962216}, {"event_id": "f4c1b38e70674ace9bdf1bf7feacf5cf", "step": 22, "value": 1.4148240651619675, "stage": "evolution", "created_at": 1789674172.1118195}, {"event_id": "9f5316b3cd584509af82c61ba57cc3c7", "step": 23, "value": 1.2886630084435862, "stage": "evolution", "created_at": 1789674755.2534833}, {"event_id": "715d1d6d192a4a0cbffb74b09132e0fe", "step": 24, "value": 1.3995938360093874, "stage": "evolution", "created_at": 1789675322.0629768}, {"event_id": "548b68e4728244f28c67258561162c0e", "step": 25, "value": 1.338603961862902, "stage": "improve", "created_at": 1789675933.4802372}, {"event_id": "857247a2ae9f4306b3ec97120a934246", "step": 26, "value": 1.2993971487308988, "stage": "evolution", "created_at": 1789676502.271546}, {"event_id": "7cf3517756824d5ab5b6a50201a4fa5a", "step": 28, "value": 1.2655226380401103, "stage": "evolution", "created_at": 1789677630.2422464}, {"event_id": "ac647d2d45f141f287a0c7d731831da6", "step": 29, "value": 1.6549217542216297, "stage": "improve", "created_at": 1789678143.7317016}, {"event_id": "5922fd3f2b7944c38e42410fbb8b0740", "step": 30, "value": 1.2971311926975542, "stage": "debug", "created_at": 1789678617.4926322}, {"event_id": "dc480bbc4e994832b68432eae94d1417", "step": 31, "value": 1.4336684282529915, "stage": "fusion", "created_at": 1789679081.957379}, {"event_id": "b575ee5abca74588a2fdacf5de8de757", "step": 32, "value": 1.257032590553797, "stage": "evolution", "created_at": 1789679588.1351562}, {"event_id": "b0b09af431c342c1a94050ccb5ff3940", "step": 33, "value": 1.3357940330844889, "stage": "fusion", "created_at": 1789680110.977306}, {"event_id": "83762b18be684fbbb72b1f8db00a1ff3", "step": 34, "value": 1.3812685366728987, "stage": "fusion", "created_at": 1789680579.8523898}, {"event_id": "57ca21b2d6ee42b6984e90934e29240a", "step": 36, "value": 1.2347280792308988, "stage": "evolution", "created_at": 1789681165.774412}, {"event_id": "97d45d1146e345f7b2769bb134597829", "step": 37, "value": 1.4318177209469436, "stage": "improve", "created_at": 1789681681.2578967}, {"event_id": "0ecad7577ffc4332bb6b536dabb19479", "step": 38, "value": 1.1673645796172885, "stage": "debug", "created_at": 1789682147.3872285}], "maximize": false, "node_count": 39, "metric_name": "BPB", "curve_scope": "原始候选验证 BPB（可能含回滚或预算后记录），不作为预算内最终成绩。最终成绩以 all_runs_final.csv 为准。", "official_score": null}, {"id": "xixian.bo-study-ancestor-summary-ucb.seed47", "experiment_id": "nanogpt-development-r4-ancestor-v1-20260917", "family": "nanoGPT", "method": "bo_study_ancestor_summary_ucb", "dataset": "nanoGPT", "seed": "47", "status": "completed", "best_valid_bpb": 1.1036148284300717, "elapsed_seconds": 21600.0, "budget_seconds": 21600.0, "comparison_eligible": true, "note": "time_budget", "artifacts": [{"bundle_id": "01-read-first-and-final-states", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/01-read-first-and-final-states/logs-c828e9f97191.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/01-read-first-and-final-states", "member": "MLEvolve_BO/research/nanogpt_bo_20260917/analysis/final_closeout_20260918/all_runs_final.csv", "sha256": "c828e9f97191ffc3f6f4fa6f39045e6be494d2ab2ea3337eff18dfd2830908ba"}, {"bundle_id": "02-study-run-logs", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/02-study-run-logs/logs-50a9df8a8a5a.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/02-study-run-logs", "member": "MLEvolve_BO/research/nanogpt_bo_20260917/development_r4_ancestor_v1/bo_study_ancestor_summary_ucb/runs/20260917_163813_bo_study_ancestor_summary_ucb/logs/journal.json", "sha256": "50a9df8a8a5acb631814aa5ea6a0f2e8b7d47ec05bff989ffaa975aa9ca71d25"}], "ledger": {"campaign": "development_r4_ancestor_v1", "stage": "development", "method": "bo_study_ancestor_summary_ucb", "version": "r4_ancestor_summary2_v1", "seed": "47", "training_seed": "42", "state": "finished", "complete_budget": "True", "launch_allowed": "", "not_launched_reason": "", "complete_8h": "False", "active_seconds": "21600", "budget_seconds": "21600", "source_duration_seconds": "21600", "budget_amended": "False", "raw_active_seconds": "21600.0", "post_budget_active_seconds": "0.0", "comparison_eligible": "True", "protocol_invalid_results": "0", "raw_reported_valid": "34", "raw_reported_best_bpb": "1.1036148284300717", "validity_audit": "", "comparison_exclusion_reason": "", "policy_contamination_started_at": "", "active_gpu_hours": "6.0", "actual_elapsed_seconds": "21631.109066963196", "segment_gpu_hours_including_cleanup": "6.008641407622231", "between_segment_seconds": "0.0", "completed": "46", "raw_completed": "46", "unverified_commit_time_count": "0", "post_budget_completed": "0", "valid": "34", "failure_fraction": "0.26086956521739135", "best_bpb_so_far": "1.1036148284300717", "final_bpb": "1.1036148284300717", "best_node_id": "da73f7bb24254936b65a735f37ecbb77", "llm_attempts": "167", "llm_cli_reported_tokens_known": "3484863", "llm_attempts_unknown_tokens": "0", "llm_measured_wall_seconds": "4506.742870330811", "llm_unfinished_attempts": "0", "llm_failed_or_interrupted_attempts": "0", "allocated_gpu_hours": "6.011111111111111", "allocated_gpu_hours_accounting_final": "True", "resource_records": "[\"10836564\"]", "resource_accounting_captured_at": "[\"2026-09-18T07:59:04.351903+00:00\"]", "gpu_models": "[\"NVIDIA A100-SXM4-80GB\"]", "completed_proposal_wall_seconds": "20991.15739245899", "raw_completed_proposal_wall_seconds": "20991.15739245899", "diagnostic_feedback_scope": "Only results committed within the registered budget; later DEBUG repairs and mature labels excluded", "diagnostic_excluded_late_transitions": "0", "closed_proposals": "34", "unclosed_proposals": "2", "unknown_closure_proposals": "0", "closed_proposal_failure_fraction": "0.0", "raw_reported_closed_proposal_failure_fraction": "0.0", "debug_repaired_proposals": "5", "raw_serial_actions": "50", "raw_actions_with_error_logs": "0", "raw_training_launches": "40", "interrupted_actions": "1", "interrupted_action_active_seconds_upper_bound": "464.21420216560364", "gpu_uuid": "GPU-e76a5c57-19e6-eed9-4466-8e18e640d11b", "job_id": "10836564", "node": "cn-g006.server.mila.quebec", "started_at": "2026-09-17T20:37:41.630202+00:00", "finished_at": "2026-09-18T02:38:12.739269+00:00", "stop_reason": "time_budget", "training_rows": "28", "incomplete_windows": "", "current_label_diagnostics": "{}", "threshold_active_seconds": "{\"1.2\": 5112.703798055649, \"1.15\": 5664.427798032761, \"1.1\": null}", "log_dir": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r4_ancestor_v1/bo_study_ancestor_summary_ucb/runs/20260917_163813_bo_study_ancestor_summary_ucb/logs", "committed_evidence": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r4_ancestor_v1/bo_study_ancestor_summary_ucb/checkpoints/boundary-1789698597074987801/logs", "final_solution": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r4_ancestor_v1/bo_study_ancestor_summary_ucb/runs/20260917_163813_bo_study_ancestor_summary_ucb/workspace/trials/da73f7bb24254936b65a735f37ecbb77/candidate.py"}, "journal_ref": "02-study-run-logs:MLEvolve_BO/research/nanogpt_bo_20260917/development_r4_ancestor_v1/bo_study_ancestor_summary_ucb/runs/20260917_163813_bo_study_ancestor_summary_ucb/logs/journal.json", "metrics": [{"event_id": "c611f2cefbb94c55b69fad229d25c579", "step": 1, "value": 1.47607014800795, "stage": "draft", "created_at": 1789677519.1640663}, {"event_id": "2a1bfd4570414f9b949a92ad67554c01", "step": 4, "value": 1.465384093160496, "stage": "improve", "created_at": 1789679422.209244}, {"event_id": "dcaf0e6040c245d184d1c6e0fc0d2440", "step": 5, "value": 1.440756240884572, "stage": "debug", "created_at": 1789679938.023376}, {"event_id": "eb658d71da4642fd9d0c2ce3a50b13ad", "step": 6, "value": 1.9533785178352365, "stage": "debug", "created_at": 1789680417.415228}, {"event_id": "1d3bfac3971f4e118aeed0e56235374f", "step": 7, "value": 1.2442984496916332, "stage": "improve", "created_at": 1789681021.058475}, {"event_id": "f08a63d6b21249b4aea34d500cb75537", "step": 8, "value": 1.2415904429245364, "stage": "improve", "created_at": 1789681542.139483}, {"event_id": "e8fcff15a093438da840bdc1df7880c6", "step": 9, "value": 1.1588829775871239, "stage": "improve", "created_at": 1789682105.8953333}, {"event_id": "2971df20f64c4b01bfc1e392e65703c6", "step": 10, "value": 1.1340420007781742, "stage": "improve", "created_at": 1789682659.645859}, {"event_id": "added6b075884b9d95d45e13ba8ad1d4", "step": 11, "value": 1.575433533551164, "stage": "improve", "created_at": 1789683198.7791693}, {"event_id": "74daf43bfc2846348748911af0a226fd", "step": 13, "value": 1.1542000278628513, "stage": "improve", "created_at": 1789683997.2412202}, {"event_id": "48c074ae37e045ea92ee51af7de8d075", "step": 15, "value": 1.1641923726786703, "stage": "debug", "created_at": 1789684618.5288596}, {"event_id": "6c13d695b6ab416c85724dee34ce098d", "step": 16, "value": 1.152044611219904, "stage": "evolution", "created_at": 1789685137.9566793}, {"event_id": "fc3b13208bc34eea97743c8a716b74c1", "step": 18, "value": 1.317348609903705, "stage": "draft", "created_at": 1789685687.5030122}, {"event_id": "8413b399d77d4b5c92a7fefd2b38b456", "step": 19, "value": 1.2036595759048567, "stage": "evolution", "created_at": 1789686563.0008986}, {"event_id": "f77ded79604148a4ba5b3731a4bada4f", "step": 21, "value": 1.1728130443205333, "stage": "evolution", "created_at": 1789687128.3781052}, {"event_id": "44232cf04ac64ea79642d68a7cd84a2d", "step": 22, "value": 1.1347052516305094, "stage": "evolution", "created_at": 1789687608.6327827}, {"event_id": "869f6114cbf8451393902ef2f11f86a8", "step": 25, "value": 1.139329733846444, "stage": "evolution", "created_at": 1789688246.0432444}, {"event_id": "45b22969d29f4cf9a3604ebdf00ffeb2", "step": 28, "value": 1.1572223615340467, "stage": "evolution", "created_at": 1789689231.4094326}, {"event_id": "9303dd5fa9fc4d47aca02fdbbbf5480f", "step": 29, "value": 1.2925094271701283, "stage": "debug", "created_at": 1789689742.8311975}, {"event_id": "6718fc1e57334f82b974fbd2feb45760", "step": 31, "value": 1.148654845560969, "stage": "evolution", "created_at": 1789690293.6960924}, {"event_id": "aa52a28e51f54da7b608542479ac98ea", "step": 32, "value": 1.1513031705100174, "stage": "evolution", "created_at": 1789690772.825471}, {"event_id": "dc8f8aac08c54e38acb126eeb1bc34a8", "step": 33, "value": 1.1404540528511298, "stage": "evolution", "created_at": 1789691321.196002}, {"event_id": "7e3cff4859864a768b353a1e1e6cbf93", "step": 34, "value": 2.678599563388856, "stage": "evolution", "created_at": 1789691803.115069}, {"event_id": "d79ed6c8dd2c46b18d1100722a0a34d1", "step": 36, "value": 1.1384759749461695, "stage": "fusion", "created_at": 1789692491.1168768}, {"event_id": "ad8206306ae24faa8f45289eab550272", "step": 37, "value": 1.1161903819349217, "stage": "evolution", "created_at": 1789692981.11721}, {"event_id": "2ee6e7fec7a0450bb34834553a1cee89", "step": 38, "value": 1.1199384239366392, "stage": "debug", "created_at": 1789693510.2758636}, {"event_id": "e4ef667c7dff4a67822ac4b74258003a", "step": 39, "value": 1.1481147354576162, "stage": "improve", "created_at": 1789694026.889035}, {"event_id": "316b894c05f449f2bc470e74ad386f5d", "step": 40, "value": 1.1038080707382023, "stage": "improve", "created_at": 1789694596.255862}, {"event_id": "4e83346c0e504f1cb42d976f0bb5d3b2", "step": 41, "value": 1.1461899949286058, "stage": "improve", "created_at": 1789695185.0130835}, {"event_id": "a7f327d2c33b4cafab6545448d2f51b4", "step": 42, "value": 1.1988421282678994, "stage": "improve", "created_at": 1789695743.4698317}, {"event_id": "323817fc1dc145a18b64cd1bb946d8cd", "step": 43, "value": 1.1066123417012972, "stage": "improve", "created_at": 1789696331.9054542}, {"event_id": "da73f7bb24254936b65a735f37ecbb77", "step": 44, "value": 1.1036148284300717, "stage": "fusion", "created_at": 1789696901.1026385}, {"event_id": "a0027727bbd8438fb11bf5cb010d15ee", "step": 45, "value": 1.179124979206889, "stage": "improve", "created_at": 1789697444.928773}, {"event_id": "e5b16fc55708431e9a9fd05d5863ae9c", "step": 46, "value": 1.1506117664953877, "stage": "improve", "created_at": 1789698070.8005242}], "maximize": false, "node_count": 47, "metric_name": "BPB", "curve_scope": "原始候选验证 BPB（可能含回滚或预算后记录），不作为预算内最终成绩。最终成绩以 all_runs_final.csv 为准。", "official_score": null}, {"id": "xixian.bo-study-bounded-parent-mean.seed47", "experiment_id": "nanogpt-development-r5-bounded-v1-20260917", "family": "nanoGPT", "method": "bo_study_bounded_parent_mean", "dataset": "nanoGPT", "seed": "47", "status": "completed", "best_valid_bpb": 1.095294273925799, "elapsed_seconds": 21600.0, "budget_seconds": 21600.0, "comparison_eligible": true, "note": "time_budget", "artifacts": [{"bundle_id": "01-read-first-and-final-states", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/01-read-first-and-final-states/logs-c828e9f97191.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/01-read-first-and-final-states", "member": "MLEvolve_BO/research/nanogpt_bo_20260917/analysis/final_closeout_20260918/all_runs_final.csv", "sha256": "c828e9f97191ffc3f6f4fa6f39045e6be494d2ab2ea3337eff18dfd2830908ba"}, {"bundle_id": "02-study-run-logs", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/02-study-run-logs/logs-50a9df8a8a5a.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/02-study-run-logs", "member": "MLEvolve_BO/research/nanogpt_bo_20260917/development_r5_bounded_v1/bo_study_bounded_parent_mean/runs/20260917_152833_bo_study_bounded_parent_mean/logs/journal.json", "sha256": "50a9df8a8a5acb631814aa5ea6a0f2e8b7d47ec05bff989ffaa975aa9ca71d25"}], "ledger": {"campaign": "development_r5_bounded_v1", "stage": "development", "method": "bo_study_bounded_parent_mean", "version": "r5_bounded_parent_mean_v1", "seed": "47", "training_seed": "42", "state": "finished", "complete_budget": "True", "launch_allowed": "", "not_launched_reason": "", "complete_8h": "False", "active_seconds": "21600", "budget_seconds": "21600", "source_duration_seconds": "21600", "budget_amended": "False", "raw_active_seconds": "21600.0", "post_budget_active_seconds": "0.0", "comparison_eligible": "True", "protocol_invalid_results": "0", "raw_reported_valid": "34", "raw_reported_best_bpb": "1.095294273925799", "validity_audit": "", "comparison_exclusion_reason": "", "policy_contamination_started_at": "", "active_gpu_hours": "6.0", "actual_elapsed_seconds": "22294.4240090847", "segment_gpu_hours_including_cleanup": "6.000857850246959", "between_segment_seconds": "691.3357481956482", "completed": "41", "raw_completed": "41", "unverified_commit_time_count": "0", "post_budget_completed": "0", "valid": "34", "failure_fraction": "0.1707317073170732", "best_bpb_so_far": "1.095294273925799", "final_bpb": "1.095294273925799", "best_node_id": "e3fe01b76395496fa58e0eecd2469ebf", "llm_attempts": "174", "llm_cli_reported_tokens_known": "3564669", "llm_attempts_unknown_tokens": "0", "llm_measured_wall_seconds": "5116.441802024841", "llm_unfinished_attempts": "0", "llm_failed_or_interrupted_attempts": "0", "allocated_gpu_hours": "6.166502297057046", "allocated_gpu_hours_accounting_final": "True", "resource_records": "[\"10835358\", \"10836530\", \"10838575\"]", "resource_accounting_captured_at": "[\"2026-09-18T07:59:22.278807+00:00\"]", "gpu_models": "[\"NVIDIA A100-SXM4-80GB\"]", "completed_proposal_wall_seconds": "21132.292490289547", "raw_completed_proposal_wall_seconds": "21132.292490289547", "diagnostic_feedback_scope": "Only results committed within the registered budget; later DEBUG repairs and mature labels excluded", "diagnostic_excluded_late_transitions": "0", "closed_proposals": "34", "unclosed_proposals": "2", "unknown_closure_proposals": "0", "closed_proposal_failure_fraction": "0.0", "raw_reported_closed_proposal_failure_fraction": "0.0", "debug_repaired_proposals": "5", "raw_serial_actions": "45", "raw_actions_with_error_logs": "0", "raw_training_launches": "41", "interrupted_actions": "1", "interrupted_action_active_seconds_upper_bound": "210.49472308158875", "gpu_uuid": "GPU-5456775e-a92b-9f28-0e59-f4168badf9fc", "job_id": "10838575", "node": "cn-g016.server.mila.quebec", "started_at": "2026-09-17T19:28:01.358975+00:00", "finished_at": "2026-09-18T01:39:35.782984+00:00", "stop_reason": "time_budget", "training_rows": "30", "incomplete_windows": "", "current_label_diagnostics": "{}", "threshold_active_seconds": "{\"1.2\": 4455.06010556221, \"1.15\": 8709.846105575562, \"1.1\": 16971.852276802063}", "log_dir": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r5_bounded_v1/bo_study_bounded_parent_mean/runs/20260917_152833_bo_study_bounded_parent_mean/logs", "committed_evidence": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r5_bounded_v1/bo_study_bounded_parent_mean/checkpoints/boundary-1789695361969118210/logs", "final_solution": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r5_bounded_v1/bo_study_bounded_parent_mean/runs/20260917_152833_bo_study_bounded_parent_mean/workspace/trials/e3fe01b76395496fa58e0eecd2469ebf/candidate.py"}, "journal_ref": "02-study-run-logs:MLEvolve_BO/research/nanogpt_bo_20260917/development_r5_bounded_v1/bo_study_bounded_parent_mean/runs/20260917_152833_bo_study_bounded_parent_mean/logs/journal.json", "metrics": [{"event_id": "b1eb72fbbb4a43a686acebc37520f726", "step": 1, "value": 1.4882188382365968, "stage": "draft", "created_at": 1789673334.975689}, {"event_id": "6036e4c50eb54443b82a14470cbef40d", "step": 4, "value": 1.8007155937638588, "stage": "improve", "created_at": 1789675235.3068569}, {"event_id": "28e6cce3dab8410188395c8835e1bb1a", "step": 5, "value": 1.31552050054595, "stage": "debug", "created_at": 1789675828.6072187}, {"event_id": "f136e6ebe248498fa160e7dd2b0ea97c", "step": 6, "value": 3.2158487232443296, "stage": "debug", "created_at": 1789676316.303914}, {"event_id": "0dfccdfdfd4f4e479bac56e8ea4dc53f", "step": 8, "value": 1.1966647406329367, "stage": "improve", "created_at": 1789677434.9558997}, {"event_id": "3f34ce0bfdd8477c8c51bea83b252889", "step": 10, "value": 1.2394759241048585, "stage": "debug", "created_at": 1789678047.9756129}, {"event_id": "057163b1a3904252801b434cbd8f7cd3", "step": 11, "value": 1.2055132561531074, "stage": "improve", "created_at": 1789678545.3495896}, {"event_id": "824da73d72884d4690fe3c60ea7314de", "step": 12, "value": 1.1621412679288898, "stage": "debug", "created_at": 1789679020.166827}, {"event_id": "4df2c5b06264444a81d5a7a23664ad05", "step": 13, "value": 1.2771837939686888, "stage": "improve", "created_at": 1789679535.482974}, {"event_id": "5285b37875b043dc85c54a88bc73884a", "step": 14, "value": 1.185057336212901, "stage": "improve", "created_at": 1789680136.1501443}, {"event_id": "204d1e49891d48bf866dd56e5523a319", "step": 15, "value": 1.2031725561089577, "stage": "improve", "created_at": 1789680659.7970774}, {"event_id": "cbd236fb01004cfb9c063ef5dc5c06da", "step": 16, "value": 1.1617521924213874, "stage": "evolution", "created_at": 1789681240.8562634}, {"event_id": "086fe6c70be8448da46436ce75cdc4ff", "step": 17, "value": 1.1307694005645605, "stage": "improve", "created_at": 1789681729.1456535}, {"event_id": "407f6d0da2c24a0cb58746745e779437", "step": 18, "value": 1.186602081667243, "stage": "improve", "created_at": 1789682213.0126886}, {"event_id": "4d9746b09f374850a35897a07af63287", "step": 20, "value": 1.170554576020117, "stage": "improve", "created_at": 1789683250.5386643}, {"event_id": "a446db0691b34d4aae815b221f6058cf", "step": 21, "value": 1.1233019014276944, "stage": "improve", "created_at": 1789683771.413352}, {"event_id": "42d41f73bec84852b827400cd6729a0e", "step": 22, "value": 1.1942829313728602, "stage": "debug", "created_at": 1789684268.0440745}, {"event_id": "7e3bfd2fd5bc4aaebbc1293878913da3", "step": 23, "value": 1.1743727185160326, "stage": "improve", "created_at": 1789684786.727382}, {"event_id": "60d87703af7f4085b7d6154161c2847a", "step": 24, "value": 1.206682467343832, "stage": "improve", "created_at": 1789685296.666928}, {"event_id": "6dbc4b9cf53249299986354fb25a35e6", "step": 25, "value": 1.1164770512780253, "stage": "evolution", "created_at": 1789685847.1952276}, {"event_id": "4c653c566ba942dd9f5803315114f4c5", "step": 26, "value": 1.2065815987015953, "stage": "improve", "created_at": 1789686371.5749059}, {"event_id": "9faae0e9a3464501a67b13195a91f010", "step": 27, "value": 1.178395671610201, "stage": "improve", "created_at": 1789686923.7155955}, {"event_id": "c3a9ab91b34d480598251451c5d8109f", "step": 28, "value": 1.7379389313008387, "stage": "improve", "created_at": 1789688114.2724621}, {"event_id": "2910128d128242b189c7b95de6c77e78", "step": 29, "value": 1.1046634085605864, "stage": "evolution", "created_at": 1789688731.3636942}, {"event_id": "3a130fb8b07d463fbf7a051b5ff5f501", "step": 30, "value": 1.1103876411088913, "stage": "improve", "created_at": 1789689295.151142}, {"event_id": "fb481418b6a74c9282ea2b258a121451", "step": 31, "value": 1.1100154188410654, "stage": "improve", "created_at": 1789689871.443815}, {"event_id": "cdf3cce8e431435c8ff8a3227d79637e", "step": 32, "value": 1.0980224804061332, "stage": "improve", "created_at": 1789690452.121848}, {"event_id": "4c8c4044b82b46c4a2f87635aa16ef03", "step": 33, "value": 1.1205954202020674, "stage": "improve", "created_at": 1789691012.8789785}, {"event_id": "5c9148d6000e468ab6a62f75711d4033", "step": 35, "value": 1.1107784922880921, "stage": "improve", "created_at": 1789691709.126638}, {"event_id": "e3fe01b76395496fa58e0eecd2469ebf", "step": 37, "value": 1.095294273925799, "stage": "improve", "created_at": 1789692488.798692}, {"event_id": "23cb7a9b259f4ac395f5a24f3d72ebc7", "step": 38, "value": 1.1529147884607298, "stage": "improve", "created_at": 1789693058.7361772}, {"event_id": "6565d52777a6481e9e8cb06b5c65c5be", "step": 39, "value": 1.174000760888385, "stage": "improve", "created_at": 1789693678.8837824}, {"event_id": "cc39fe3522e44b8dbb7c5108a0f10904", "step": 40, "value": 1.2746516652269653, "stage": "improve", "created_at": 1789694275.575622}, {"event_id": "b46e02d8aa9c47aeb5ded41cf8e7d566", "step": 41, "value": 1.1268580284488552, "stage": "evolution", "created_at": 1789694852.2975001}], "maximize": false, "node_count": 42, "metric_name": "BPB", "curve_scope": "原始候选验证 BPB（可能含回滚或预算后记录），不作为预算内最终成绩。最终成绩以 all_runs_final.csv 为准。", "official_score": null}, {"id": "xixian.bo-study-lineage-shared-ucb.seed47", "experiment_id": "nanogpt-development-r6-shared-lineage-v1-20260917", "family": "nanoGPT", "method": "bo_study_lineage_shared_ucb", "dataset": "nanoGPT", "seed": "47", "status": "completed", "best_valid_bpb": 1.1412489315747811, "elapsed_seconds": 21600.0, "budget_seconds": 21600.0, "comparison_eligible": true, "note": "time_budget", "artifacts": [{"bundle_id": "01-read-first-and-final-states", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/01-read-first-and-final-states/logs-c828e9f97191.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/01-read-first-and-final-states", "member": "MLEvolve_BO/research/nanogpt_bo_20260917/analysis/final_closeout_20260918/all_runs_final.csv", "sha256": "c828e9f97191ffc3f6f4fa6f39045e6be494d2ab2ea3337eff18dfd2830908ba"}, {"bundle_id": "02-study-run-logs", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/02-study-run-logs/logs-50a9df8a8a5a.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/02-study-run-logs", "member": "MLEvolve_BO/research/nanogpt_bo_20260917/development_r6_shared_lineage_v1/bo_study_lineage_shared_ucb/runs/20260917_180905_bo_study_lineage_shared_ucb/logs/journal.json", "sha256": "50a9df8a8a5acb631814aa5ea6a0f2e8b7d47ec05bff989ffaa975aa9ca71d25"}], "ledger": {"campaign": "development_r6_shared_lineage_v1", "stage": "development", "method": "bo_study_lineage_shared_ucb", "version": "r6_fixed_lineage_and_stable_birth_v1", "seed": "47", "training_seed": "42", "state": "finished", "complete_budget": "True", "launch_allowed": "", "not_launched_reason": "", "complete_8h": "False", "active_seconds": "21600", "budget_seconds": "21600", "source_duration_seconds": "21600", "budget_amended": "False", "raw_active_seconds": "21600.0", "post_budget_active_seconds": "0.0", "comparison_eligible": "True", "protocol_invalid_results": "0", "raw_reported_valid": "33", "raw_reported_best_bpb": "1.1412489315747811", "validity_audit": "", "comparison_exclusion_reason": "", "policy_contamination_started_at": "", "active_gpu_hours": "6.0", "actual_elapsed_seconds": "21632.154808998108", "segment_gpu_hours_including_cleanup": "6.008931891388364", "between_segment_seconds": "0.0", "completed": "42", "raw_completed": "42", "unverified_commit_time_count": "0", "post_budget_completed": "0", "valid": "33", "failure_fraction": "0.2142857142857143", "best_bpb_so_far": "1.1412489315747811", "final_bpb": "1.1412489315747811", "best_node_id": "174da11d11d243789de0ecdf1053adeb", "llm_attempts": "166", "llm_cli_reported_tokens_known": "3587251", "llm_attempts_unknown_tokens": "0", "llm_measured_wall_seconds": "4501.637343406677", "llm_unfinished_attempts": "0", "llm_failed_or_interrupted_attempts": "0", "allocated_gpu_hours": "6.016111111111111", "allocated_gpu_hours_accounting_final": "True", "resource_records": "[\"10837587\"]", "resource_accounting_captured_at": "[\"2026-09-18T07:59:40.754520+00:00\"]", "gpu_models": "[\"NVIDIA A100-SXM4-80GB\"]", "completed_proposal_wall_seconds": "21071.73139641434", "raw_completed_proposal_wall_seconds": "21071.73139641434", "diagnostic_feedback_scope": "Only results committed within the registered budget; later DEBUG repairs and mature labels excluded", "diagnostic_excluded_late_transitions": "0", "closed_proposals": "33", "unclosed_proposals": "1", "unknown_closure_proposals": "0", "closed_proposal_failure_fraction": "0.0", "raw_reported_closed_proposal_failure_fraction": "0.0", "debug_repaired_proposals": "4", "raw_serial_actions": "46", "raw_actions_with_error_logs": "0", "raw_training_launches": "43", "interrupted_actions": "1", "interrupted_action_active_seconds_upper_bound": "386.89444494247437", "gpu_uuid": "GPU-494b165d-3293-0a38-5640-62f2aa809c2f", "job_id": "10837587", "node": "cn-g008.server.mila.quebec", "started_at": "2026-09-17T22:08:20.132445+00:00", "finished_at": "2026-09-18T04:08:52.287254+00:00", "stop_reason": "time_budget", "training_rows": "27", "incomplete_windows": "", "current_label_diagnostics": "{}", "threshold_active_seconds": "{\"1.2\": 14210.37055516243, \"1.15\": 16377.596555233002, \"1.1\": null}", "log_dir": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r6_shared_lineage_v1/bo_study_lineage_shared_ucb/runs/20260917_180905_bo_study_lineage_shared_ucb/logs", "committed_evidence": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r6_shared_lineage_v1/bo_study_lineage_shared_ucb/checkpoints/boundary-1789704112966875794/logs", "final_solution": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r6_shared_lineage_v1/bo_study_lineage_shared_ucb/runs/20260917_180905_bo_study_lineage_shared_ucb/workspace/trials/174da11d11d243789de0ecdf1053adeb/candidate.py"}, "journal_ref": "02-study-run-logs:MLEvolve_BO/research/nanogpt_bo_20260917/development_r6_shared_lineage_v1/bo_study_lineage_shared_ucb/runs/20260917_180905_bo_study_lineage_shared_ucb/logs/journal.json", "metrics": [{"event_id": "923ba6f83c844117a6b4c2a9436eb61a", "step": 1, "value": 1.4848667973811691, "stage": "draft", "created_at": 1789682980.3291628}, {"event_id": "18d4a7b9b25b456db26f76faf918fc2e", "step": 4, "value": 1.6515737157826593, "stage": "improve", "created_at": 1789684841.0864222}, {"event_id": "abd6e7c65e6f4b1fa77437c04804cf33", "step": 6, "value": 3.2893812270217477, "stage": "debug", "created_at": 1789685733.7420344}, {"event_id": "9c84977b9cbf461e9857d54af0c23e24", "step": 7, "value": 1.6495684394434516, "stage": "improve", "created_at": 1789686399.5010214}, {"event_id": "9d31ff292a514a45a2f29d11def7fb72", "step": 9, "value": 1.6483036304494512, "stage": "improve", "created_at": 1789687060.0150843}, {"event_id": "3f61e1f39e494bb3ad24f3cc508e235b", "step": 10, "value": 1.5377980474352217, "stage": "evolution", "created_at": 1789687574.7197087}, {"event_id": "ad97df765768426d9f48203ceee21b31", "step": 11, "value": 3.0806870589141644, "stage": "debug", "created_at": 1789688066.4838362}, {"event_id": "e7905db2d9b0435ca1ef275e31f662e8", "step": 12, "value": 1.3195060434961792, "stage": "draft", "created_at": 1789688514.947041}, {"event_id": "de0c57bbf2cb4f2fb9c955b2f7f1cec1", "step": 13, "value": 1.748003597698065, "stage": "evolution", "created_at": 1789689349.1561458}, {"event_id": "d398dc7bd1a2493a9c6ea78bdd61ab70", "step": 14, "value": 2.5908332409315524, "stage": "evolution", "created_at": 1789689853.5866709}, {"event_id": "1ff9b28d8eb3440299eba1069a236678", "step": 15, "value": 1.864058803724289, "stage": "improve", "created_at": 1789690382.5770302}, {"event_id": "65700a6eb6ff4204bc2bed581e53711e", "step": 17, "value": 1.3951032557332612, "stage": "improve", "created_at": 1789691396.6254587}, {"event_id": "6ddd901d117346d99bb39af62af48b6d", "step": 18, "value": 1.551573280095937, "stage": "improve", "created_at": 1789691889.1511617}, {"event_id": "468dbd0dac574be4943bb0615a693db8", "step": 20, "value": 1.5520761972053962, "stage": "improve", "created_at": 1789692776.3849268}, {"event_id": "a9d2f877eadc432aaf3f5b1871106736", "step": 21, "value": 1.5749583986018982, "stage": "improve", "created_at": 1789693308.6594152}, {"event_id": "b946eefa32684afcaf4088c02259c5cc", "step": 23, "value": 1.7835114024734353, "stage": "improve", "created_at": 1789694309.5456333}, {"event_id": "185e7ff263da455f82cc4ef0f3361552", "step": 24, "value": 3.579724215889212, "stage": "improve", "created_at": 1789694830.0265646}, {"event_id": "962e9dee698e49cd9a36cc0b5e0abd13", "step": 26, "value": 1.562639396843698, "stage": "improve", "created_at": 1789695717.0920188}, {"event_id": "053faca8d5eb40fb985679814cd6ea57", "step": 27, "value": 1.4561193742515406, "stage": "evolution", "created_at": 1789696175.7820053}, {"event_id": "f7ef9ebe482641dbaaf9658887592498", "step": 28, "value": 1.1799554334644313, "stage": "debug", "created_at": 1789696659.0657713}, {"event_id": "02cfb0285fd74886962398a0caf71e45", "step": 29, "value": 1.1759999187546604, "stage": "improve", "created_at": 1789697193.5655499}, {"event_id": "2069c2b27435488eb263828f10aa30da", "step": 30, "value": 1.196430256389434, "stage": "improve", "created_at": 1789697711.8076792}, {"event_id": "0f7f4bd6167c40a8add340cc5d5abb98", "step": 31, "value": 1.1753104441639455, "stage": "improve", "created_at": 1789698282.9208112}, {"event_id": "d04e675485dc497e9e3cf08489a2c529", "step": 32, "value": 1.1418386911307965, "stage": "improve", "created_at": 1789698808.4824986}, {"event_id": "03730697a1f54482b1ef6870c4706abe", "step": 34, "value": 1.141278755511158, "stage": "improve", "created_at": 1789699567.8184276}, {"event_id": "bc0a6b5fd9cc4383b3775b11fe06c46e", "step": 35, "value": 1.2198208073405818, "stage": "improve", "created_at": 1789700068.5114307}, {"event_id": "0365dc3780ae45759065b5182909d061", "step": 36, "value": 1.4697598205311273, "stage": "debug", "created_at": 1789700533.729646}, {"event_id": "df1fe00a6a6f4dfc9ebd223e29858c47", "step": 37, "value": 1.2567032723427036, "stage": "improve", "created_at": 1789701035.150615}, {"event_id": "9b9a0edb66574b31a8e6ef095a2d0990", "step": 38, "value": 1.1800245535386533, "stage": "evolution", "created_at": 1789701578.004028}, {"event_id": "91af79803cb649cca7a46813dd6f0889", "step": 39, "value": 1.1742388424012713, "stage": "evolution", "created_at": 1789702097.6362288}, {"event_id": "a872bb360da24c2db22df6111edc529a", "step": 40, "value": 1.2010151522685357, "stage": "evolution", "created_at": 1789702653.088338}, {"event_id": "174da11d11d243789de0ecdf1053adeb", "step": 41, "value": 1.1412489315747811, "stage": "evolution", "created_at": 1789703143.6482697}, {"event_id": "6548550f427742f18e6011ef8cfbbd5e", "step": 42, "value": 1.1499016921694356, "stage": "improve", "created_at": 1789703667.0583603}], "maximize": false, "node_count": 43, "metric_name": "BPB", "curve_scope": "原始候选验证 BPB（可能含回滚或预算后记录），不作为预算内最终成绩。最终成绩以 all_runs_final.csv 为准。", "official_score": null}, {"id": "xixian.bo-study-stable-birth-shared-ucb.seed47", "experiment_id": "nanogpt-development-r6-shared-lineage-v1-20260917", "family": "nanoGPT", "method": "bo_study_stable_birth_shared_ucb", "dataset": "nanoGPT", "seed": "47", "status": "completed", "best_valid_bpb": 1.1085957112783111, "elapsed_seconds": 21600.0, "budget_seconds": 21600.0, "comparison_eligible": true, "note": "time_budget", "artifacts": [{"bundle_id": "01-read-first-and-final-states", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/01-read-first-and-final-states/logs-c828e9f97191.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/01-read-first-and-final-states", "member": "MLEvolve_BO/research/nanogpt_bo_20260917/analysis/final_closeout_20260918/all_runs_final.csv", "sha256": "c828e9f97191ffc3f6f4fa6f39045e6be494d2ab2ea3337eff18dfd2830908ba"}, {"bundle_id": "02-study-run-logs", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/02-study-run-logs/logs-50a9df8a8a5a.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/02-study-run-logs", "member": "MLEvolve_BO/research/nanogpt_bo_20260917/development_r6_shared_lineage_v1/bo_study_stable_birth_shared_ucb/runs/20260917_180905_bo_study_stable_birth_shared_ucb/logs/journal.json", "sha256": "50a9df8a8a5acb631814aa5ea6a0f2e8b7d47ec05bff989ffaa975aa9ca71d25"}], "ledger": {"campaign": "development_r6_shared_lineage_v1", "stage": "development", "method": "bo_study_stable_birth_shared_ucb", "version": "r6_fixed_lineage_and_stable_birth_v1", "seed": "47", "training_seed": "42", "state": "finished", "complete_budget": "True", "launch_allowed": "", "not_launched_reason": "", "complete_8h": "False", "active_seconds": "21600", "budget_seconds": "21600", "source_duration_seconds": "21600", "budget_amended": "False", "raw_active_seconds": "21600.0", "post_budget_active_seconds": "0.0", "comparison_eligible": "True", "protocol_invalid_results": "0", "raw_reported_valid": "36", "raw_reported_best_bpb": "1.1085957112783111", "validity_audit": "", "comparison_exclusion_reason": "", "policy_contamination_started_at": "", "active_gpu_hours": "6.0", "actual_elapsed_seconds": "21632.252815961838", "segment_gpu_hours_including_cleanup": "6.008959115611182", "between_segment_seconds": "0.0", "completed": "44", "raw_completed": "44", "unverified_commit_time_count": "0", "post_budget_completed": "0", "valid": "36", "failure_fraction": "0.18181818181818177", "best_bpb_so_far": "1.1085957112783111", "final_bpb": "1.1085957112783111", "best_node_id": "a6c16d79f7be4cd58e1a86f95e3d40e8", "llm_attempts": "174", "llm_cli_reported_tokens_known": "3716457", "llm_attempts_unknown_tokens": "0", "llm_measured_wall_seconds": "4363.24159693718", "llm_unfinished_attempts": "0", "llm_failed_or_interrupted_attempts": "0", "allocated_gpu_hours": "6.016111111111111", "allocated_gpu_hours_accounting_final": "True", "resource_records": "[\"10837587\"]", "resource_accounting_captured_at": "[\"2026-09-18T07:59:40.754520+00:00\"]", "gpu_models": "[\"NVIDIA A100-SXM4-80GB\"]", "completed_proposal_wall_seconds": "21289.8110198183", "raw_completed_proposal_wall_seconds": "21289.8110198183", "diagnostic_feedback_scope": "Only results committed within the registered budget; later DEBUG repairs and mature labels excluded", "diagnostic_excluded_late_transitions": "0", "closed_proposals": "36", "unclosed_proposals": "3", "unknown_closure_proposals": "0", "closed_proposal_failure_fraction": "0.0", "raw_reported_closed_proposal_failure_fraction": "0.0", "debug_repaired_proposals": "4", "raw_serial_actions": "48", "raw_actions_with_error_logs": "0", "raw_training_launches": "43", "interrupted_actions": "1", "interrupted_action_active_seconds_upper_bound": "161.62580132484436", "gpu_uuid": "GPU-f2889935-21f0-e2a7-ee01-0b164aafcd5b", "job_id": "10837587", "node": "cn-g008.server.mila.quebec", "started_at": "2026-09-17T22:08:20.132801+00:00", "finished_at": "2026-09-18T04:08:52.385617+00:00", "stop_reason": "time_budget", "training_rows": "31", "incomplete_windows": "", "current_label_diagnostics": "{}", "threshold_active_seconds": "{\"1.2\": 7438.891198635101, \"1.15\": 9646.714198589325, \"1.1\": null}", "log_dir": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r6_shared_lineage_v1/bo_study_stable_birth_shared_ucb/runs/20260917_180905_bo_study_stable_birth_shared_ucb/logs", "committed_evidence": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r6_shared_lineage_v1/bo_study_stable_birth_shared_ucb/checkpoints/boundary-1789704338236361568/logs", "final_solution": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r6_shared_lineage_v1/bo_study_stable_birth_shared_ucb/runs/20260917_180905_bo_study_stable_birth_shared_ucb/workspace/trials/a6c16d79f7be4cd58e1a86f95e3d40e8/candidate.py"}, "journal_ref": "02-study-run-logs:MLEvolve_BO/research/nanogpt_bo_20260917/development_r6_shared_lineage_v1/bo_study_stable_birth_shared_ucb/runs/20260917_180905_bo_study_stable_birth_shared_ucb/logs/journal.json", "metrics": [{"event_id": "959e33445b18498693165d982cac4281", "step": 1, "value": 1.497240893417267, "stage": "draft", "created_at": 1789682980.3670237}, {"event_id": "09eda663b3044c2dac499aa54074d27f", "step": 4, "value": 1.5723058477964837, "stage": "improve", "created_at": 1789684837.15619}, {"event_id": "aab75ad7e23a499396e29b14432f1580", "step": 5, "value": 3.057582079475361, "stage": "debug", "created_at": 1789685329.8469105}, {"event_id": "84b276d570c7400c8a11516712c8cc3b", "step": 6, "value": 3.2861402764688794, "stage": "debug", "created_at": 1789685819.101189}, {"event_id": "b5d9ac679ccb4ea5be5d7d920d821f87", "step": 7, "value": 1.527214904470495, "stage": "improve", "created_at": 1789686416.2323105}, {"event_id": "dc7eb50d920a43a1a97b132bcdb6e382", "step": 9, "value": 1.5660124099007706, "stage": "improve", "created_at": 1789687180.361596}, {"event_id": "cca22f1504064360bc65659c855a972d", "step": 10, "value": 1.6525100847503025, "stage": "evolution", "created_at": 1789687648.9377618}, {"event_id": "afed6037a11146839d361b1cd11ea8c9", "step": 11, "value": 1.6881544527765693, "stage": "debug", "created_at": 1789688099.89668}, {"event_id": "d00fe5ec14f74d23bc12cac4b835426e", "step": 12, "value": 1.3170859042079626, "stage": "draft", "created_at": 1789688625.6551354}, {"event_id": "86f64f6e03924e1db0e1fdb102a349a4", "step": 13, "value": 1.4970601388508236, "stage": "improve", "created_at": 1789689447.459811}, {"event_id": "38254a171fde45b29f900cae1fda39f6", "step": 14, "value": 1.158416454958425, "stage": "improve", "created_at": 1789689923.5458167}, {"event_id": "a8f4ecaaad0d4dc3af52394f400dc4b4", "step": 15, "value": 1.1745129434658126, "stage": "improve", "created_at": 1789690412.7618454}, {"event_id": "44b1940792704177acec836feef1aee6", "step": 16, "value": 1.165806376850466, "stage": "improve", "created_at": 1789690938.494183}, {"event_id": "a694287e65494f12ab8c516f5734b2a4", "step": 18, "value": 1.5461068960045312, "stage": "improve", "created_at": 1789691622.0531595}, {"event_id": "cd20673d5dae409fa04c46be2b133b6e", "step": 19, "value": 1.1455405962856773, "stage": "evolution", "created_at": 1789692102.2420933}, {"event_id": "96deb95261ca4a91b5d7ecb3ad206d54", "step": 20, "value": 1.130017081918658, "stage": "debug", "created_at": 1789692572.805524}, {"event_id": "63045c781b314e708f23377ae0625af1", "step": 21, "value": 1.1748525536239556, "stage": "improve", "created_at": 1789693088.7710116}, {"event_id": "d69132b6612a4a64b1d7250ef91eb75a", "step": 22, "value": 1.1287234639525856, "stage": "improve", "created_at": 1789693582.2734916}, {"event_id": "2d65aa3211ca41d085678f062d4117ce", "step": 23, "value": 1.1571314021888637, "stage": "improve", "created_at": 1789694125.4197323}, {"event_id": "1dfb0adc131d4d7cb3d4f8bc077761d7", "step": 24, "value": 1.1307101082521265, "stage": "improve", "created_at": 1789694624.9596748}, {"event_id": "d348d99b093b4797a2bb44f6fb02f4de", "step": 25, "value": 1.1350389748093166, "stage": "improve", "created_at": 1789695146.6246147}, {"event_id": "a7c55ecd21ac4d12b63c133c552745a1", "step": 26, "value": 1.109111169643216, "stage": "evolution", "created_at": 1789695666.851312}, {"event_id": "554865f95486472185bfd6ca5745b324", "step": 27, "value": 1.114936744869811, "stage": "improve", "created_at": 1789696213.9658482}, {"event_id": "e0d319a91e6b48998287981a5bb89afa", "step": 28, "value": 1.150414344989031, "stage": "improve", "created_at": 1789696735.2076895}, {"event_id": "a6c16d79f7be4cd58e1a86f95e3d40e8", "step": 29, "value": 1.1085957112783111, "stage": "improve", "created_at": 1789697251.507985}, {"event_id": "1d0804f41d30433d8993539badebc161", "step": 31, "value": 1.1117692172567577, "stage": "improve", "created_at": 1789697884.4180028}, {"event_id": "21cd713510b44a13a73053d657ed4802", "step": 32, "value": 1.111143740195649, "stage": "improve", "created_at": 1789698417.9221854}, {"event_id": "f11148a595754d90b5241b008ead0ea3", "step": 33, "value": 1.1521636151024393, "stage": "improve", "created_at": 1789698984.239794}, {"event_id": "b126a79982fe48038f8462aa90762d66", "step": 34, "value": 1.143579919204585, "stage": "evolution", "created_at": 1789699536.59364}, {"event_id": "b7fea353042445d8a90a03debddeb615", "step": 37, "value": 1.1432901139153058, "stage": "evolution", "created_at": 1789700525.3667033}, {"event_id": "c8dbaeb2904c45ff9d564f92735a521e", "step": 38, "value": 1.1935893322291873, "stage": "fusion", "created_at": 1789701068.8124654}, {"event_id": "418a713c2f424315bb22a419bfbe4155", "step": 40, "value": 1.1867530072387946, "stage": "fusion", "created_at": 1789701771.8750818}, {"event_id": "db97544a2a8a4f4d847b4f1aee921123", "step": 41, "value": 1.1736314022056662, "stage": "fusion", "created_at": 1789702306.186863}, {"event_id": "2d6e420e05d4410b9c79f189ff590822", "step": 42, "value": 1.194945608616278, "stage": "fusion", "created_at": 1789702814.5302875}, {"event_id": "b5225a2833614ae8ab098ebef9224b20", "step": 43, "value": 1.1647489967018738, "stage": "evolution", "created_at": 1789703319.5428538}, {"event_id": "efb224deab5f4ff79ab0391170588a50", "step": 44, "value": 1.1133209335437202, "stage": "evolution", "created_at": 1789703851.1990628}], "maximize": false, "node_count": 45, "metric_name": "BPB", "curve_scope": "原始候选验证 BPB（可能含回滚或预算后记录），不作为预算内最终成绩。最终成绩以 all_runs_final.csv 为准。", "official_score": null}, {"id": "xixian.bo-study-stable-birth-matern-ucb.seed47", "experiment_id": "nanogpt-development-r7-birth-matern-v1-20260917", "family": "nanoGPT", "method": "bo_study_stable_birth_matern_ucb", "dataset": "nanoGPT", "seed": "47", "status": "completed", "best_valid_bpb": 1.079610711222615, "elapsed_seconds": 21600.0, "budget_seconds": 21600.0, "comparison_eligible": true, "note": "time_budget", "artifacts": [{"bundle_id": "01-read-first-and-final-states", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/01-read-first-and-final-states/logs-c828e9f97191.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/01-read-first-and-final-states", "member": "MLEvolve_BO/research/nanogpt_bo_20260917/analysis/final_closeout_20260918/all_runs_final.csv", "sha256": "c828e9f97191ffc3f6f4fa6f39045e6be494d2ab2ea3337eff18dfd2830908ba"}, {"bundle_id": "02-study-run-logs", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/02-study-run-logs/logs-50a9df8a8a5a.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/02-study-run-logs", "member": "MLEvolve_BO/research/nanogpt_bo_20260917/development_r7_birth_matern_v1/bo_study_stable_birth_matern_ucb/runs/20260917_212120_bo_study_stable_birth_matern_ucb/logs/journal.json", "sha256": "50a9df8a8a5acb631814aa5ea6a0f2e8b7d47ec05bff989ffaa975aa9ca71d25"}], "ledger": {"campaign": "development_r7_birth_matern_v1", "stage": "development", "method": "bo_study_stable_birth_matern_ucb", "version": "r7_frozen_birth_matern_v1", "seed": "47", "training_seed": "42", "state": "finished", "complete_budget": "True", "launch_allowed": "", "not_launched_reason": "", "complete_8h": "False", "active_seconds": "21600", "budget_seconds": "21600", "source_duration_seconds": "21600", "budget_amended": "False", "raw_active_seconds": "21600.0", "post_budget_active_seconds": "0.0", "comparison_eligible": "True", "protocol_invalid_results": "0", "raw_reported_valid": "37", "raw_reported_best_bpb": "1.079610711222615", "validity_audit": "", "comparison_exclusion_reason": "", "policy_contamination_started_at": "", "active_gpu_hours": "6.0", "actual_elapsed_seconds": "22455.21659207344", "segment_gpu_hours_including_cleanup": "6.000733750992351", "between_segment_seconds": "852.5750885009766", "completed": "40", "raw_completed": "40", "unverified_commit_time_count": "0", "post_budget_completed": "0", "valid": "37", "failure_fraction": "0.07499999999999996", "best_bpb_so_far": "1.079610711222615", "final_bpb": "1.079610711222615", "best_node_id": "faebf487538c4f9191c09ff42b6b44e8", "llm_attempts": "154", "llm_cli_reported_tokens_known": "3325094", "llm_attempts_unknown_tokens": "1", "llm_measured_wall_seconds": "4413.804983377457", "llm_unfinished_attempts": "0", "llm_failed_or_interrupted_attempts": "1", "allocated_gpu_hours": "6.540470994446013", "allocated_gpu_hours_accounting_final": "True", "resource_records": "[\"10838575\", \"10841315\", \"10842805\"]", "resource_accounting_captured_at": "[\"2026-09-18T07:59:59.490972+00:00\"]", "gpu_models": "[\"NVIDIA A100-SXM4-80GB\"]", "completed_proposal_wall_seconds": "21203.3676945474", "raw_completed_proposal_wall_seconds": "21203.3676945474", "diagnostic_feedback_scope": "Only results committed within the registered budget; later DEBUG repairs and mature labels excluded", "diagnostic_excluded_late_transitions": "0", "closed_proposals": "37", "unclosed_proposals": "0", "unknown_closure_proposals": "0", "closed_proposal_failure_fraction": "0.0", "raw_reported_closed_proposal_failure_fraction": "0.0", "debug_repaired_proposals": "3", "raw_serial_actions": "44", "raw_actions_with_error_logs": "0", "raw_training_launches": "40", "interrupted_actions": "1", "interrupted_action_active_seconds_upper_bound": "154.20212292671204", "gpu_uuid": "GPU-ce2ace98-f497-a6cd-cb02-883ad1aab016", "job_id": "10842805", "node": "cn-g016.server.mila.quebec", "started_at": "2026-09-18T01:20:49.670034+00:00", "finished_at": "2026-09-18T07:35:04.886626+00:00", "stop_reason": "time_budget", "training_rows": "31", "incomplete_windows": "", "current_label_diagnostics": "{}", "threshold_active_seconds": "{\"1.2\": 5293.223778486252, \"1.15\": 5293.223778486252, \"1.1\": 7436.96977853775}", "log_dir": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r7_birth_matern_v1/bo_study_stable_birth_matern_ucb/runs/20260917_212120_bo_study_stable_birth_matern_ucb/logs", "committed_evidence": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r7_birth_matern_v1/bo_study_stable_birth_matern_ucb/checkpoints/boundary-1789716747704154581/logs", "final_solution": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r7_birth_matern_v1/bo_study_stable_birth_matern_ucb/runs/20260917_212120_bo_study_stable_birth_matern_ucb/workspace/trials/faebf487538c4f9191c09ff42b6b44e8/candidate.py"}, "journal_ref": "02-study-run-logs:MLEvolve_BO/research/nanogpt_bo_20260917/development_r7_birth_matern_v1/bo_study_stable_birth_matern_ucb/runs/20260917_212120_bo_study_stable_birth_matern_ucb/logs/journal.json", "metrics": [{"event_id": "cae50b6ff45b47cdb57a68da64cdc833", "step": 1, "value": 1.4967059969117904, "stage": "draft", "created_at": 1789694500.4867375}, {"event_id": "14f66111851f44a0b1e6e5b25d28da0d", "step": 4, "value": 1.8111751475023599, "stage": "improve", "created_at": 1789696375.6984534}, {"event_id": "a0bb1877d3c0493680d031aace846062", "step": 5, "value": 1.5054377348948285, "stage": "debug", "created_at": 1789696969.214375}, {"event_id": "a0fd011cf307478b92c3738bfcec1e15", "step": 6, "value": 1.9533620576953818, "stage": "debug", "created_at": 1789697445.8914933}, {"event_id": "5f655f4d6cc0494189bc7b0a62e306d2", "step": 7, "value": 1.2426842866425474, "stage": "improve", "created_at": 1789698728.2251465}, {"event_id": "2f27ce2c141045d1b71f495666a02063", "step": 8, "value": 1.29179688249201, "stage": "improve", "created_at": 1789699288.4465287}, {"event_id": "17bbe5ba5da646feb97efd2f7630e361", "step": 9, "value": 1.1400201498533262, "stage": "improve", "created_at": 1789699862.771105}, {"event_id": "77acf8cfcd1942518f4b9a7073d05575", "step": 10, "value": 1.2271028166089837, "stage": "improve", "created_at": 1789700380.858037}, {"event_id": "c8a925504a4949dc91d50fab9702e623", "step": 11, "value": 1.1760723665992516, "stage": "improve", "created_at": 1789700867.800339}, {"event_id": "16353f27bfbb46c8a5c75a5a75ded263", "step": 12, "value": 1.1880657395339533, "stage": "improve", "created_at": 1789701427.2445998}, {"event_id": "faebf487538c4f9191c09ff42b6b44e8", "step": 13, "value": 1.079610711222615, "stage": "evolution", "created_at": 1789702009.01428}, {"event_id": "765526c8abb74db9b12c18d818048780", "step": 14, "value": 1.123901789327752, "stage": "improve", "created_at": 1789702513.052233}, {"event_id": "59d5ef6cbb9e4126946526736fe95341", "step": 15, "value": 1.266549794430004, "stage": "improve", "created_at": 1789703061.85748}, {"event_id": "531845d388f149438ec890f0cba2b1f1", "step": 16, "value": 1.135143037970002, "stage": "improve", "created_at": 1789703631.9732745}, {"event_id": "5604db05cef64f81a5149407fe8e57b0", "step": 17, "value": 1.0829772350043325, "stage": "evolution", "created_at": 1789704110.6656759}, {"event_id": "d65ef79c52e14bf7ac41208e6aa37763", "step": 18, "value": 1.3198205085110348, "stage": "draft", "created_at": 1789704534.9823573}, {"event_id": "0cdc3a974799498386c3bcaf33943820", "step": 19, "value": 1.0896168167952236, "stage": "evolution", "created_at": 1789705392.8285003}, {"event_id": "981d989ba4914b2f874eb8e303303a75", "step": 20, "value": 1.1211613396449698, "stage": "evolution", "created_at": 1789705902.8354099}, {"event_id": "723d78ba1d964f9fbf68370e3fcfa361", "step": 21, "value": 1.1767296023454041, "stage": "evolution", "created_at": 1789706413.1533704}, {"event_id": "d6b4916df44c469680cf76b1044a13d5", "step": 22, "value": 1.0837448628449287, "stage": "evolution", "created_at": 1789706901.05463}, {"event_id": "5698f8d2de49446e94c875e20445d8b3", "step": 24, "value": 1.0818767322844944, "stage": "evolution", "created_at": 1789707788.4378004}, {"event_id": "043c7ce9541849f8a9ac873272999a74", "step": 25, "value": 1.3978187767904875, "stage": "evolution", "created_at": 1789708266.646461}, {"event_id": "4e3a734029024f1caee3024acd11c63b", "step": 26, "value": 1.1789612145265724, "stage": "debug", "created_at": 1789709086.6168337}, {"event_id": "2bd5b4e6f10f4abebad14554cebd905e", "step": 27, "value": 1.1227666597451644, "stage": "evolution", "created_at": 1789709654.1228466}, {"event_id": "7cc947ffd68b45b9bc253c734839800a", "step": 28, "value": 1.1547527376608038, "stage": "fusion", "created_at": 1789710153.2611554}, {"event_id": "a5733f53a880424dadfaa2b370c372b7", "step": 29, "value": 1.0866506716384774, "stage": "evolution", "created_at": 1789710640.253007}, {"event_id": "8909407d45f143d89fd7dab6bde7aed2", "step": 30, "value": 1.1084650725462526, "stage": "fusion", "created_at": 1789711180.7554078}, {"event_id": "dc663996e3174c8d9ed0d17d7b2962a5", "step": 31, "value": 1.1251241036053357, "stage": "fusion", "created_at": 1789711625.1619434}, {"event_id": "efe00ef7d011449da9a143f49f1d7968", "step": 32, "value": 1.1212530570351702, "stage": "fusion", "created_at": 1789712084.2125099}, {"event_id": "0014dfbc6377415087427d389eb52d4d", "step": 33, "value": 1.1247895327925572, "stage": "evolution", "created_at": 1789712573.0010688}, {"event_id": "75b7943f9434485fa01bd3f727ee3e23", "step": 34, "value": 1.1264456743233462, "stage": "evolution", "created_at": 1789713083.987429}, {"event_id": "f3dbce79fea9457989254a6fa34e2047", "step": 35, "value": 1.0820523893326568, "stage": "evolution", "created_at": 1789713617.3389003}, {"event_id": "bbee6c76440c40e0b0c9fa7b3db81c8f", "step": 36, "value": 1.1185074173165395, "stage": "evolution", "created_at": 1789714149.8268023}, {"event_id": "d4813d7dfca445bca7edd0111c46408f", "step": 37, "value": 1.1235952795590574, "stage": "evolution", "created_at": 1789714725.2712247}, {"event_id": "da719182360544258e5387b701ceb127", "step": 38, "value": 1.1618446251920291, "stage": "evolution", "created_at": 1789715240.8495362}, {"event_id": "a7d54fa8a81a4e51adb28433ed678399", "step": 39, "value": 1.1548093068950265, "stage": "fusion", "created_at": 1789715798.4284256}, {"event_id": "8572bcfa06cd479690f036d3d7b86fd4", "step": 40, "value": 1.0926624121783377, "stage": "evolution", "created_at": 1789716300.6991715}], "maximize": false, "node_count": 41, "metric_name": "BPB", "curve_scope": "原始候选验证 BPB（可能含回滚或预算后记录），不作为预算内最终成绩。最终成绩以 all_runs_final.csv 为准。", "official_score": null}, {"id": "xixian.bo-study-stable-context-shared-ucb.seed47", "experiment_id": "nanogpt-development-r7-context-v1-20260917", "family": "nanoGPT", "method": "bo_study_stable_context_shared_ucb", "dataset": "nanoGPT", "seed": "47", "status": "completed", "best_valid_bpb": 1.1342718767149929, "elapsed_seconds": 21600.0, "budget_seconds": 21600.0, "comparison_eligible": true, "note": "time_budget", "artifacts": [{"bundle_id": "01-read-first-and-final-states", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/01-read-first-and-final-states/logs-c828e9f97191.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/01-read-first-and-final-states", "member": "MLEvolve_BO/research/nanogpt_bo_20260917/analysis/final_closeout_20260918/all_runs_final.csv", "sha256": "c828e9f97191ffc3f6f4fa6f39045e6be494d2ab2ea3337eff18dfd2830908ba"}, {"bundle_id": "02-study-run-logs", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/02-study-run-logs/logs-50a9df8a8a5a.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/02-study-run-logs", "member": "MLEvolve_BO/research/nanogpt_bo_20260917/development_r7_context_v1/bo_study_stable_context_shared_ucb/runs/20260917_214147_bo_study_stable_context_shared_ucb/logs/journal.json", "sha256": "50a9df8a8a5acb631814aa5ea6a0f2e8b7d47ec05bff989ffaa975aa9ca71d25"}], "ledger": {"campaign": "development_r7_context_v1", "stage": "development", "method": "bo_study_stable_context_shared_ucb", "version": "r7_frozen_birth_decision_context_v1", "seed": "47", "training_seed": "42", "state": "finished", "complete_budget": "True", "launch_allowed": "", "not_launched_reason": "", "complete_8h": "False", "active_seconds": "21600", "budget_seconds": "21600", "source_duration_seconds": "21600", "budget_amended": "False", "raw_active_seconds": "21600.0", "post_budget_active_seconds": "0.0", "comparison_eligible": "True", "protocol_invalid_results": "0", "raw_reported_valid": "35", "raw_reported_best_bpb": "1.1342718767149929", "validity_audit": "", "comparison_exclusion_reason": "", "policy_contamination_started_at": "", "active_gpu_hours": "6.0", "actual_elapsed_seconds": "22154.238560914993", "segment_gpu_hours_including_cleanup": "6.009571498632431", "between_segment_seconds": "519.7811658382416", "completed": "41", "raw_completed": "41", "unverified_commit_time_count": "0", "post_budget_completed": "0", "valid": "35", "failure_fraction": "0.14634146341463417", "best_bpb_so_far": "1.1342718767149929", "final_bpb": "1.1342718767149929", "best_node_id": "60046f6de40f4bceb407b3859e2bdfe2", "llm_attempts": "164", "llm_cli_reported_tokens_known": "3264844", "llm_attempts_unknown_tokens": "0", "llm_measured_wall_seconds": "4796.900541782379", "llm_unfinished_attempts": "0", "llm_failed_or_interrupted_attempts": "0", "allocated_gpu_hours": "6.20075774901443", "allocated_gpu_hours_accounting_final": "True", "resource_records": "[\"10838575\", \"10841315\", \"10842805\"]", "resource_accounting_captured_at": "[\"2026-09-18T08:00:20.665558+00:00\"]", "gpu_models": "[\"NVIDIA A100-SXM4-80GB\"]", "completed_proposal_wall_seconds": "21264.543684390374", "raw_completed_proposal_wall_seconds": "21264.543684390374", "diagnostic_feedback_scope": "Only results committed within the registered budget; later DEBUG repairs and mature labels excluded", "diagnostic_excluded_late_transitions": "0", "closed_proposals": "35", "unclosed_proposals": "2", "unknown_closure_proposals": "0", "closed_proposal_failure_fraction": "0.0", "raw_reported_closed_proposal_failure_fraction": "0.0", "debug_repaired_proposals": "4", "raw_serial_actions": "45", "raw_actions_with_error_logs": "0", "raw_training_launches": "41", "interrupted_actions": "1", "interrupted_action_active_seconds_upper_bound": "81.46601557731628", "gpu_uuid": "GPU-ceae127e-cd6d-229f-8288-b79051487ee7", "job_id": "10842805", "node": "cn-g016.server.mila.quebec", "started_at": "2026-09-18T01:41:14.411850+00:00", "finished_at": "2026-09-18T07:50:28.650411+00:00", "stop_reason": "time_budget", "training_rows": "29", "incomplete_windows": "", "current_label_diagnostics": "{}", "threshold_active_seconds": "{\"1.2\": 10911.789061307907, \"1.15\": 12822.379061222076, \"1.1\": null}", "log_dir": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r7_context_v1/bo_study_stable_context_shared_ucb/runs/20260917_214147_bo_study_stable_context_shared_ucb/logs", "committed_evidence": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r7_context_v1/bo_study_stable_context_shared_ucb/checkpoints/boundary-1789717712437190385/logs", "final_solution": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r7_context_v1/bo_study_stable_context_shared_ucb/runs/20260917_214147_bo_study_stable_context_shared_ucb/workspace/trials/60046f6de40f4bceb407b3859e2bdfe2/candidate.py"}, "journal_ref": "02-study-run-logs:MLEvolve_BO/research/nanogpt_bo_20260917/development_r7_context_v1/bo_study_stable_context_shared_ucb/runs/20260917_214147_bo_study_stable_context_shared_ucb/logs/journal.json", "metrics": [{"event_id": "8b68ed3bc8054d98976e188849b4cff6", "step": 1, "value": 1.48717375047785, "stage": "draft", "created_at": 1789695727.9784803}, {"event_id": "9438927884214d23a9718595e17486cf", "step": 4, "value": 1.5170918590889342, "stage": "improve", "created_at": 1789697630.8273993}, {"event_id": "1d9fd4697e4d459da9d4b01b7e4836f7", "step": 5, "value": 3.0868172473658837, "stage": "debug", "created_at": 1789698758.4704268}, {"event_id": "acdb78c5c97c498ea2fd7eca34156e5b", "step": 6, "value": 3.285664391395165, "stage": "debug", "created_at": 1789699269.5349321}, {"event_id": "8be2fc053a384336a8009b29cff946d6", "step": 7, "value": 1.6646201745199634, "stage": "improve", "created_at": 1789699972.1963618}, {"event_id": "a2acb15a426247dc9e6172d609cae238", "step": 8, "value": 1.4933331840653958, "stage": "improve", "created_at": 1789700536.9205413}, {"event_id": "095fe7caa1ed4f9793ca3135a748d938", "step": 9, "value": 1.5651352412604693, "stage": "evolution", "created_at": 1789701084.9353638}, {"event_id": "f546548247074919afa87cb7842b8251", "step": 10, "value": 1.3163105156743349, "stage": "draft", "created_at": 1789701556.2273753}, {"event_id": "5529f4e687484a1490eaf46d2f99947c", "step": 11, "value": 1.2861181980060812, "stage": "evolution", "created_at": 1789702387.2125912}, {"event_id": "3b518d165ad0401d9198e27d417fc31d", "step": 12, "value": 1.7338752538371995, "stage": "improve", "created_at": 1789702897.6379225}, {"event_id": "b07fa4ba8f1349ed84222174c7a4ffd2", "step": 13, "value": 1.3656802874645093, "stage": "improve", "created_at": 1789703501.8135285}, {"event_id": "3cfc7bd6404b40e6865bb82e8bf000bf", "step": 14, "value": 1.5404116117371245, "stage": "improve", "created_at": 1789704060.4742615}, {"event_id": "c0e7009504c443ebb04d470022974202", "step": 15, "value": 1.7475276098566355, "stage": "improve", "created_at": 1789704577.2595956}, {"event_id": "96396f061dfd4d9188ee782f466e8fb2", "step": 16, "value": 1.6265105463878988, "stage": "improve", "created_at": 1789705106.1404037}, {"event_id": "981d2b0aa33344328b5a656aa63eda63", "step": 17, "value": 1.3724874817679653, "stage": "evolution", "created_at": 1789705624.0523944}, {"event_id": "0bf13209720840ab9d292b30f055da82", "step": 19, "value": 1.1833672945149023, "stage": "evolution", "created_at": 1789706557.7381322}, {"event_id": "f5ea2ddae0f646d8b8ae25bd6187d030", "step": 20, "value": 1.8721786219974785, "stage": "improve", "created_at": 1789707202.440533}, {"event_id": "d2ffcae543eb4035befd60c7fe1351bc", "step": 21, "value": 1.2970383454615226, "stage": "debug", "created_at": 1789707647.2065618}, {"event_id": "b81d2bf0ae664a2e928dfb30110e0e0b", "step": 24, "value": 1.14960852097125, "stage": "improve", "created_at": 1789708484.5775366}, {"event_id": "4baf99a52e824631b0fe56d2020b55ee", "step": 25, "value": 1.1940789946995416, "stage": "debug", "created_at": 1789709086.1863651}, {"event_id": "339527eff7634efe92bd721ee0803b6a", "step": 26, "value": 1.2386453020510664, "stage": "improve", "created_at": 1789709623.5663998}, {"event_id": "81be9e99f985471b91301583440697c3", "step": 27, "value": 1.2009839228638484, "stage": "improve", "created_at": 1789710153.8266597}, {"event_id": "297ca2f97c5a473cb4252ff4f3b44ec3", "step": 28, "value": 1.146008201103676, "stage": "evolution", "created_at": 1789710632.4350934}, {"event_id": "73bc7388d6e94fd881c1a639f02f9c39", "step": 29, "value": 1.2307051816472705, "stage": "improve", "created_at": 1789711169.5778463}, {"event_id": "0f1aa7448ced4308b4203ee8236af180", "step": 30, "value": 1.1641543852317668, "stage": "improve", "created_at": 1789711657.6406937}, {"event_id": "226b7b94e1d24bd0a1e8ae3e1265cf95", "step": 31, "value": 1.5028541880174813, "stage": "improve", "created_at": 1789712192.8009968}, {"event_id": "4e31f2d150ff4f01839ef0ac265eaf16", "step": 32, "value": 1.1789140772253799, "stage": "evolution", "created_at": 1789712719.4458115}, {"event_id": "8b81ef091e754a9ba1e95670aeac57e5", "step": 34, "value": 1.209288953053444, "stage": "evolution", "created_at": 1789713367.3825998}, {"event_id": "e990b588b7ca4a61af34698e8a929800", "step": 35, "value": 1.1639410603549445, "stage": "evolution", "created_at": 1789713867.705483}, {"event_id": "60046f6de40f4bceb407b3859e2bdfe2", "step": 36, "value": 1.1342718767149929, "stage": "evolution", "created_at": 1789714463.99421}, {"event_id": "f9331afed01a40f3a0e7fc7276091c7d", "step": 37, "value": 1.3215347254820102, "stage": "improve", "created_at": 1789715035.8067682}, {"event_id": "6b7ff62a225a473da78a9e192aed1535", "step": 38, "value": 1.1474281036189158, "stage": "improve", "created_at": 1789715578.9882376}, {"event_id": "1ba33ad900a94f61a02e708905425fca", "step": 39, "value": 1.2170586188249743, "stage": "improve", "created_at": 1789716164.563215}, {"event_id": "ffd084e97954442bb26cb4f2a0664830", "step": 40, "value": 1.1764045057308756, "stage": "fusion", "created_at": 1789716709.3193958}, {"event_id": "e958aa3d713848f983448247f1de98c0", "step": 41, "value": 1.135186052448781, "stage": "evolution", "created_at": 1789717242.1459196}], "maximize": false, "node_count": 42, "metric_name": "BPB", "curve_scope": "原始候选验证 BPB（可能含回滚或预算后记录），不作为预算内最终成绩。最终成绩以 all_runs_final.csv 为准。", "official_score": null}, {"id": "xixian.bo-study-frozen-scale-ucb.seed47", "experiment_id": "nanogpt-development-r7-frozen-scale-v1-20260917", "family": "nanoGPT", "method": "bo_study_frozen_scale_ucb", "dataset": "nanoGPT", "seed": "47", "status": "completed", "best_valid_bpb": 1.0675152649205193, "elapsed_seconds": 21600.0, "budget_seconds": 21600.0, "comparison_eligible": true, "note": "time_budget", "artifacts": [{"bundle_id": "01-read-first-and-final-states", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/01-read-first-and-final-states/logs-c828e9f97191.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/01-read-first-and-final-states", "member": "MLEvolve_BO/research/nanogpt_bo_20260917/analysis/final_closeout_20260918/all_runs_final.csv", "sha256": "c828e9f97191ffc3f6f4fa6f39045e6be494d2ab2ea3337eff18dfd2830908ba"}, {"bundle_id": "02-study-run-logs", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/02-study-run-logs/logs-50a9df8a8a5a.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/02-study-run-logs", "member": "MLEvolve_BO/research/nanogpt_bo_20260917/development_r7_frozen_scale_v1/bo_study_frozen_scale_ucb/runs/20260917_214739_bo_study_frozen_scale_ucb/logs/journal.json", "sha256": "50a9df8a8a5acb631814aa5ea6a0f2e8b7d47ec05bff989ffaa975aa9ca71d25"}], "ledger": {"campaign": "development_r7_frozen_scale_v1", "stage": "development", "method": "bo_study_frozen_scale_ucb", "version": "r7_frozen_initial_draft_scale_v1", "seed": "47", "training_seed": "42", "state": "finished", "complete_budget": "True", "launch_allowed": "", "not_launched_reason": "", "complete_8h": "False", "active_seconds": "21600", "budget_seconds": "21600", "source_duration_seconds": "21600", "budget_amended": "False", "raw_active_seconds": "21600.0", "post_budget_active_seconds": "0.0", "comparison_eligible": "True", "protocol_invalid_results": "0", "raw_reported_valid": "35", "raw_reported_best_bpb": "1.0675152649205193", "validity_audit": "", "comparison_exclusion_reason": "", "policy_contamination_started_at": "", "active_gpu_hours": "6.0", "actual_elapsed_seconds": "21908.058860063553", "segment_gpu_hours_including_cleanup": "6.008773492243555", "between_segment_seconds": "276.47428798675537", "completed": "42", "raw_completed": "42", "unverified_commit_time_count": "0", "post_budget_completed": "0", "valid": "35", "failure_fraction": "0.16666666666666663", "best_bpb_so_far": "1.0675152649205193", "final_bpb": "1.0675152649205193", "best_node_id": "315f84bcb43f4b44b6bac83d29800f2f", "llm_attempts": "169", "llm_cli_reported_tokens_known": "3422586", "llm_attempts_unknown_tokens": "0", "llm_measured_wall_seconds": "4664.82061624527", "llm_unfinished_attempts": "0", "llm_failed_or_interrupted_attempts": "0", "allocated_gpu_hours": "6.105687161882718", "allocated_gpu_hours_accounting_final": "True", "resource_records": "[\"10838575\", \"10841315\", \"10842805\"]", "resource_accounting_captured_at": "[\"2026-09-18T08:00:39.958428+00:00\"]", "gpu_models": "[\"NVIDIA A100-SXM4-80GB\"]", "completed_proposal_wall_seconds": "20940.892487288453", "raw_completed_proposal_wall_seconds": "20940.892487288453", "diagnostic_feedback_scope": "Only results committed within the registered budget; later DEBUG repairs and mature labels excluded", "diagnostic_excluded_late_transitions": "0", "closed_proposals": "35", "unclosed_proposals": "1", "unknown_closure_proposals": "0", "closed_proposal_failure_fraction": "0.0", "raw_reported_closed_proposal_failure_fraction": "0.0", "debug_repaired_proposals": "5", "raw_serial_actions": "46", "raw_actions_with_error_logs": "0", "raw_training_launches": "40", "interrupted_actions": "1", "interrupted_action_active_seconds_upper_bound": "411.69257497787476", "gpu_uuid": "GPU-5456775e-a92b-9f28-0e59-f4168badf9fc", "job_id": "10842805", "node": "cn-g016.server.mila.quebec", "started_at": "2026-09-18T01:46:58.946287+00:00", "finished_at": "2026-09-18T07:52:07.005147+00:00", "stop_reason": "time_budget", "training_rows": "29", "incomplete_windows": "", "current_label_diagnostics": "{}", "threshold_active_seconds": "{\"1.2\": 13257.022425174713, \"1.15\": 16775.144425153732, \"1.1\": 16775.144425153732}", "log_dir": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r7_frozen_scale_v1/bo_study_frozen_scale_ucb/runs/20260917_214739_bo_study_frozen_scale_ucb/logs", "committed_evidence": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r7_frozen_scale_v1/bo_study_frozen_scale_ucb/checkpoints/boundary-1789717483467317210/logs", "final_solution": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r7_frozen_scale_v1/bo_study_frozen_scale_ucb/runs/20260917_214739_bo_study_frozen_scale_ucb/workspace/trials/315f84bcb43f4b44b6bac83d29800f2f/candidate.py"}, "journal_ref": "02-study-run-logs:MLEvolve_BO/research/nanogpt_bo_20260917/development_r7_frozen_scale_v1/bo_study_frozen_scale_ucb/runs/20260917_214739_bo_study_frozen_scale_ucb/logs/journal.json", "metrics": [{"event_id": "397638035d8c405ab5883628b07f3c31", "step": 1, "value": 1.4943801823451874, "stage": "draft", "created_at": 1789696079.3131666}, {"event_id": "b80a5cc723a8441e8e8919793854c9e7", "step": 4, "value": 1.7837055278916976, "stage": "improve", "created_at": 1789698007.3087542}, {"event_id": "b0402d297f304728a164bfdf02c13d5e", "step": 5, "value": 3.090505952859725, "stage": "debug", "created_at": 1789698724.1313107}, {"event_id": "ae2f6eaa6fe34e45a7ad70900b014987", "step": 6, "value": 3.412117616195, "stage": "debug", "created_at": 1789699180.5355115}, {"event_id": "f86387857c9f4ea598db01d09ba88a97", "step": 7, "value": 1.4910512483845118, "stage": "improve", "created_at": 1789699929.226198}, {"event_id": "7008c0918fea43a9b2076787d01e74e1", "step": 8, "value": 1.498499784748048, "stage": "improve", "created_at": 1789700424.4270408}, {"event_id": "a1aa9097f0754c47a94482286b124ee9", "step": 9, "value": 1.624776768241299, "stage": "improve", "created_at": 1789700914.3363802}, {"event_id": "40c2dd8957ef415da11fc74d6e30d723", "step": 10, "value": 1.6478069697905622, "stage": "improve", "created_at": 1789701431.669556}, {"event_id": "c0dfd0594cd842169cf632f9f5d3a275", "step": 11, "value": 2.591848815453206, "stage": "evolution", "created_at": 1789701972.3269002}, {"event_id": "b4d922e805574bbc8aed4e7c82ebbfe9", "step": 12, "value": 1.3195221578266663, "stage": "draft", "created_at": 1789702415.7274587}, {"event_id": "1b5fdb23e4f4445d88ffb671c933e94c", "step": 13, "value": 1.562495559315872, "stage": "improve", "created_at": 1789703242.1739368}, {"event_id": "e545a855ffa245bda58e9681edc397b7", "step": 14, "value": 1.4682923629213354, "stage": "evolution", "created_at": 1789703726.5533268}, {"event_id": "a532a08c6e3e4b01850113759505ae40", "step": 15, "value": 1.5371806176719254, "stage": "improve", "created_at": 1789704215.1727571}, {"event_id": "ae69cf4db7294665ad79868ec27637b1", "step": 16, "value": 1.663603823116982, "stage": "improve", "created_at": 1789704722.0197659}, {"event_id": "44f3af76e37f40ca8dda72cb69950847", "step": 18, "value": 1.3800152401922428, "stage": "improve", "created_at": 1789705328.739953}, {"event_id": "7acd57cf601845f59473cc84c220ac0e", "step": 19, "value": 1.3432915464510595, "stage": "improve", "created_at": 1789705851.5629988}, {"event_id": "f6f158462d2c4647a5ee36c0c9fbf024", "step": 20, "value": 1.869585177670651, "stage": "debug", "created_at": 1789706409.8454874}, {"event_id": "492dac707e2f44bcb9696bbe58b265d4", "step": 21, "value": 1.5317225102420273, "stage": "evolution", "created_at": 1789706881.6876316}, {"event_id": "3be11529d4ef47be9f08bfd4aab2d2d9", "step": 23, "value": 1.3393843545319712, "stage": "improve", "created_at": 1789707841.07668}, {"event_id": "6bcb0b2eee794f75865305592b510c7a", "step": 24, "value": 1.3650868806197203, "stage": "improve", "created_at": 1789708355.2143657}, {"event_id": "e10d2c081e8541b589474a014ffd2900", "step": 25, "value": 1.1509492316437162, "stage": "debug", "created_at": 1789709103.6185834}, {"event_id": "276d12fe85b247b78f90851099c3e736", "step": 26, "value": 1.210568333897094, "stage": "improve", "created_at": 1789709618.0586383}, {"event_id": "3b85e26168e7404bb0786a2a517163fa", "step": 27, "value": 1.264859471984452, "stage": "improve", "created_at": 1789710248.2040567}, {"event_id": "bcc34341a3d845e4bb91169027bed4fc", "step": 28, "value": 1.1593765706563417, "stage": "improve", "created_at": 1789710804.7033052}, {"event_id": "8eeae8b0d8a04f2481ce6b00311dafa1", "step": 29, "value": 1.2623640470250252, "stage": "evolution", "created_at": 1789711379.9714398}, {"event_id": "7e2566c830864187a9f797e8a04e66af", "step": 31, "value": 1.1790565626655352, "stage": "evolution", "created_at": 1789712037.3138678}, {"event_id": "1fc6790e1d4d4830bdc54dc2e4ff0ff0", "step": 32, "value": 1.0892209056372437, "stage": "evolution", "created_at": 1789712590.8906062}, {"event_id": "fab0c9f84d9e4c5ba578713113136891", "step": 33, "value": 1.1848511241399018, "stage": "debug", "created_at": 1789713090.4177327}, {"event_id": "5cf2c231adbc43189057131f18b85d5b", "step": 34, "value": 1.1357832044246625, "stage": "improve", "created_at": 1789713623.5157623}, {"event_id": "cb66b4f032114506b8bf2345aab7bfa3", "step": 36, "value": 1.181234508600753, "stage": "improve", "created_at": 1789714288.1100047}, {"event_id": "03e36ee75e0b4d79a3735a7f0e4109c4", "step": 37, "value": 1.2898099991776604, "stage": "evolution", "created_at": 1789714875.798378}, {"event_id": "1485b74c548641829509d3250acfe63d", "step": 39, "value": 1.103980569409671, "stage": "evolution", "created_at": 1789715500.254475}, {"event_id": "315f84bcb43f4b44b6bac83d29800f2f", "step": 40, "value": 1.0675152649205193, "stage": "fusion", "created_at": 1789716004.8253455}, {"event_id": "066069a8261247de8961e830bac0b635", "step": 41, "value": 1.1310222517416364, "stage": "improve", "created_at": 1789716504.9793825}, {"event_id": "bb9358566d4e47ffb34a6aa564e31862", "step": 42, "value": 1.080076912835323, "stage": "improve", "created_at": 1789717026.9549668}], "maximize": false, "node_count": 43, "metric_name": "BPB", "curve_scope": "原始候选验证 BPB（可能含回滚或预算后记录），不作为预算内最终成绩。最终成绩以 all_runs_final.csv 为准。", "official_score": null}, {"id": "xixian.bo-study-stable-parent-covariance-ucb.seed47", "experiment_id": "nanogpt-development-r7-parent-covariance-v1-20260917", "family": "nanoGPT", "method": "bo_study_stable_parent_covariance_ucb", "dataset": "nanoGPT", "seed": "47", "status": "not_launched", "best_valid_bpb": null, "elapsed_seconds": 0.0, "budget_seconds": 21600.0, "comparison_eligible": true, "note": "Stop after current seven active workflows; this prepared candidate is not in the active batch.", "artifacts": [{"bundle_id": "01-read-first-and-final-states", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/01-read-first-and-final-states/logs-c828e9f97191.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/01-read-first-and-final-states", "member": "MLEvolve_BO/research/nanogpt_bo_20260917/analysis/final_closeout_20260918/all_runs_final.csv", "sha256": "c828e9f97191ffc3f6f4fa6f39045e6be494d2ab2ea3337eff18dfd2830908ba"}], "ledger": {"campaign": "development_r7_parent_covariance_v1", "stage": "development", "method": "bo_study_stable_parent_covariance_ucb", "version": "r7_parent_mean_shared_covariance_heuristic_v1", "seed": "47", "training_seed": "42", "state": "not_launched", "complete_budget": "False", "launch_allowed": "False", "not_launched_reason": "Stop after current seven active workflows; this prepared candidate is not in the active batch.", "complete_8h": "False", "active_seconds": "0.0", "budget_seconds": "21600", "source_duration_seconds": "21600", "budget_amended": "False", "raw_active_seconds": "0.0", "post_budget_active_seconds": "0.0", "comparison_eligible": "True", "protocol_invalid_results": "0", "raw_reported_valid": "0", "raw_reported_best_bpb": "", "validity_audit": "", "comparison_exclusion_reason": "", "policy_contamination_started_at": "", "active_gpu_hours": "0.0", "actual_elapsed_seconds": "", "segment_gpu_hours_including_cleanup": "0.0", "between_segment_seconds": "", "completed": "0", "raw_completed": "0", "unverified_commit_time_count": "0", "post_budget_completed": "0", "valid": "0", "failure_fraction": "", "best_bpb_so_far": "", "final_bpb": "", "best_node_id": "", "llm_attempts": "0", "llm_cli_reported_tokens_known": "0", "llm_attempts_unknown_tokens": "0", "llm_measured_wall_seconds": "0", "llm_unfinished_attempts": "0", "llm_failed_or_interrupted_attempts": "0", "allocated_gpu_hours": "", "allocated_gpu_hours_accounting_final": "False", "resource_records": "[]", "resource_accounting_captured_at": "[]", "gpu_models": "[]", "completed_proposal_wall_seconds": "0", "raw_completed_proposal_wall_seconds": "0", "diagnostic_feedback_scope": "Only results committed within the registered budget; later DEBUG repairs and mature labels excluded", "diagnostic_excluded_late_transitions": "0", "closed_proposals": "0", "unclosed_proposals": "0", "unknown_closure_proposals": "0", "closed_proposal_failure_fraction": "", "raw_reported_closed_proposal_failure_fraction": "", "debug_repaired_proposals": "0", "raw_serial_actions": "0", "raw_actions_with_error_logs": "0", "raw_training_launches": "0", "interrupted_actions": "0", "interrupted_action_active_seconds_upper_bound": "0", "gpu_uuid": "", "job_id": "", "node": "", "started_at": "", "finished_at": "", "stop_reason": "", "training_rows": "", "incomplete_windows": "", "current_label_diagnostics": "{}", "threshold_active_seconds": "{\"1.2\": null, \"1.15\": null, \"1.1\": null}", "log_dir": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r7_parent_covariance_v1/bo_study_stable_parent_covariance_ucb/unstarted_logs", "committed_evidence": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r7_parent_covariance_v1/bo_study_stable_parent_covariance_ucb/checkpoints/not-yet-committed/logs", "final_solution": ""}, "curve_scope": "原始候选验证 BPB（可能含回滚或预算后记录），不作为预算内最终成绩。最终成绩以 all_runs_final.csv 为准。", "metrics": [], "maximize": null, "official_score": null, "metric_name": "validation"}, {"id": "xixian.bo-study-stable-birth-student-t-ucb.seed47", "experiment_id": "nanogpt-development-r7-student-t-v1-20260917", "family": "nanoGPT", "method": "bo_study_stable_birth_student_t_ucb", "dataset": "nanoGPT", "seed": "47", "status": "completed", "best_valid_bpb": 1.099027926051269, "elapsed_seconds": 21600.0, "budget_seconds": 21600.0, "comparison_eligible": true, "note": "time_budget", "artifacts": [{"bundle_id": "01-read-first-and-final-states", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/01-read-first-and-final-states/logs-c828e9f97191.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/01-read-first-and-final-states", "member": "MLEvolve_BO/research/nanogpt_bo_20260917/analysis/final_closeout_20260918/all_runs_final.csv", "sha256": "c828e9f97191ffc3f6f4fa6f39045e6be494d2ab2ea3337eff18dfd2830908ba"}, {"bundle_id": "02-study-run-logs", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/02-study-run-logs/logs-50a9df8a8a5a.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/02-study-run-logs", "member": "MLEvolve_BO/research/nanogpt_bo_20260917/development_r7_student_t_v1/bo_study_stable_birth_student_t_ucb/runs/20260917_214316_bo_study_stable_birth_student_t_ucb/logs/journal.json", "sha256": "50a9df8a8a5acb631814aa5ea6a0f2e8b7d47ec05bff989ffaa975aa9ca71d25"}], "ledger": {"campaign": "development_r7_student_t_v1", "stage": "development", "method": "bo_study_stable_birth_student_t_ucb", "version": "r7_frozen_birth_exact_student_t_v1", "seed": "47", "training_seed": "42", "state": "finished", "complete_budget": "True", "launch_allowed": "", "not_launched_reason": "", "complete_8h": "False", "active_seconds": "21600", "budget_seconds": "21600", "source_duration_seconds": "21600", "budget_amended": "False", "raw_active_seconds": "21600.0", "post_budget_active_seconds": "0.0", "comparison_eligible": "True", "protocol_invalid_results": "0", "raw_reported_valid": "34", "raw_reported_best_bpb": "1.099027926051269", "validity_audit": "", "comparison_exclusion_reason": "", "policy_contamination_started_at": "", "active_gpu_hours": "6.0", "actual_elapsed_seconds": "22301.392982959747", "segment_gpu_hours_including_cleanup": "6.000555177463426", "between_segment_seconds": "699.3943440914154", "completed": "40", "raw_completed": "40", "unverified_commit_time_count": "0", "post_budget_completed": "0", "valid": "34", "failure_fraction": "0.15000000000000002", "best_bpb_so_far": "1.099027926051269", "final_bpb": "1.099027926051269", "best_node_id": "f89161301eab4c1da394bb1b2d55b5d9", "llm_attempts": "163", "llm_cli_reported_tokens_known": "3320722", "llm_attempts_unknown_tokens": "1", "llm_measured_wall_seconds": "5311.291633605957", "llm_unfinished_attempts": "0", "llm_failed_or_interrupted_attempts": "1", "allocated_gpu_hours": "6.178071839080916", "allocated_gpu_hours_accounting_final": "True", "resource_records": "[\"10838575\", \"10841315\", \"10842805\"]", "resource_accounting_captured_at": "[\"2026-09-18T08:01:15.752863+00:00\"]", "gpu_models": "[\"NVIDIA A100-SXM4-80GB\"]", "completed_proposal_wall_seconds": "21315.692454056814", "raw_completed_proposal_wall_seconds": "21315.692454056814", "diagnostic_feedback_scope": "Only results committed within the registered budget; later DEBUG repairs and mature labels excluded", "diagnostic_excluded_late_transitions": "0", "closed_proposals": "34", "unclosed_proposals": "1", "unknown_closure_proposals": "0", "closed_proposal_failure_fraction": "0.0", "raw_reported_closed_proposal_failure_fraction": "0.0", "debug_repaired_proposals": "5", "raw_serial_actions": "44", "raw_actions_with_error_logs": "0", "raw_training_launches": "40", "interrupted_actions": "1", "interrupted_action_active_seconds_upper_bound": "37.513514041900635", "gpu_uuid": "GPU-9b3fd9e7-7bc7-2fb7-c545-6547f59252b8", "job_id": "10842805", "node": "cn-g016.server.mila.quebec", "started_at": "2026-09-18T01:42:41.427170+00:00", "finished_at": "2026-09-18T07:54:22.820153+00:00", "stop_reason": "time_budget", "training_rows": "28", "incomplete_windows": "", "current_label_diagnostics": "{}", "threshold_active_seconds": "{\"1.2\": 4882.31103682518, \"1.15\": 12560.768036842346, \"1.1\": 21562.48548579216}", "log_dir": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r7_student_t_v1/bo_study_stable_birth_student_t_ucb/runs/20260917_214316_bo_study_stable_birth_student_t_ucb/logs", "committed_evidence": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r7_student_t_v1/bo_study_stable_birth_student_t_ucb/checkpoints/boundary-1789718023048283109/logs", "final_solution": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/research/nanogpt_bo_20260917/development_r7_student_t_v1/bo_study_stable_birth_student_t_ucb/runs/20260917_214316_bo_study_stable_birth_student_t_ucb/workspace/trials/f89161301eab4c1da394bb1b2d55b5d9/candidate.py"}, "journal_ref": "02-study-run-logs:MLEvolve_BO/research/nanogpt_bo_20260917/development_r7_student_t_v1/bo_study_stable_birth_student_t_ucb/runs/20260917_214316_bo_study_stable_birth_student_t_ucb/logs/journal.json", "metrics": [{"event_id": "392ed2e068b64ddb913dda3232456c8d", "step": 1, "value": 1.5015179572586148, "stage": "draft", "created_at": 1789695816.7129107}, {"event_id": "f164dc2c21df4d959c72f41702c468b4", "step": 4, "value": 1.5802717928484913, "stage": "improve", "created_at": 1789697723.5939305}, {"event_id": "f28314fc4e6c4bd9832da5f1616a512f", "step": 5, "value": 1.4472172464650936, "stage": "debug", "created_at": 1789698757.138923}, {"event_id": "6a14f772f01040e4b3802ef8e3a8e2e0", "step": 6, "value": 1.9533606434412305, "stage": "debug", "created_at": 1789699263.8645504}, {"event_id": "ba14c93d78074a4f8c5485b5cf2798b0", "step": 7, "value": 1.2273723491693627, "stage": "improve", "created_at": 1789699930.6013782}, {"event_id": "fe8769f9b64149b99056d90c39a47819", "step": 8, "value": 1.1581191919545069, "stage": "improve", "created_at": 1789700549.5360203}, {"event_id": "4d4e35f323644a5596371d984e4a5f63", "step": 9, "value": 1.212487387191531, "stage": "improve", "created_at": 1789701139.3873942}, {"event_id": "80604d62395c4bdf8fe07f585967d8d0", "step": 11, "value": 1.213880870949346, "stage": "improve", "created_at": 1789701936.1692817}, {"event_id": "61f4b94b1f924ba0b39bd6cce83323dc", "step": 12, "value": 1.1893796099948681, "stage": "improve", "created_at": 1789702579.632301}, {"event_id": "d9a8c37ebc1e4b95a4b8aa78ddf66a08", "step": 13, "value": 1.1767901431790815, "stage": "debug", "created_at": 1789703075.300618}, {"event_id": "eb94cd434c2345f690a16ddf560d74f0", "step": 14, "value": 1.319162657556339, "stage": "draft", "created_at": 1789703584.3081968}, {"event_id": "616c86dc8827467e9a7860cc1cf19bea", "step": 15, "value": 1.1577145520635679, "stage": "evolution", "created_at": 1789704449.3072069}, {"event_id": "0790fadf9c914f919c5f00dc74307912", "step": 16, "value": 1.1908867889239578, "stage": "improve", "created_at": 1789705030.106871}, {"event_id": "39a2abc39a6543f2b8cc8aab9547bf7c", "step": 17, "value": 1.3824043564764743, "stage": "improve", "created_at": 1789705581.6872442}, {"event_id": "cbbe49d6a2af4ee7be37ff2747967375", "step": 18, "value": 1.2254557190364768, "stage": "improve", "created_at": 1789706175.5516646}, {"event_id": "c00dc9d4b9144d9cb1fee1ee660112fc", "step": 19, "value": 1.1709000712273732, "stage": "improve", "created_at": 1789706759.8657262}, {"event_id": "9f415c1f12c941dca64c029ae7d41504", "step": 20, "value": 1.1588220893133736, "stage": "evolution", "created_at": 1789707337.7391882}, {"event_id": "c3c603c3b6de4e3f97ecfd7dce06413b", "step": 22, "value": 1.1410438559369935, "stage": "evolution", "created_at": 1789708257.552633}, {"event_id": "a01c977d20f7406d86684a62129dc094", "step": 23, "value": 1.1747421169347136, "stage": "improve", "created_at": 1789709141.9271097}, {"event_id": "13b658495899416da2294c70d6baf5ff", "step": 24, "value": 1.1797454061400101, "stage": "debug", "created_at": 1789709665.6824486}, {"event_id": "c7b79f606fc746a4801388c373550de5", "step": 26, "value": 1.1809007615271205, "stage": "improve", "created_at": 1789710399.1410866}, {"event_id": "84eac87196d0473592236548d738c0b9", "step": 27, "value": 1.229076352966339, "stage": "improve", "created_at": 1789710916.7406468}, {"event_id": "5e74fad7f51d4c968750400b3bc0ec26", "step": 28, "value": 1.145275297435674, "stage": "debug", "created_at": 1789711349.5641744}, {"event_id": "df5888bfc9604ae4a04cfdea57580434", "step": 29, "value": 1.126109763403589, "stage": "improve", "created_at": 1789711887.2667067}, {"event_id": "ad5362645f8c48a4acf4beac2f583fd0", "step": 30, "value": 1.2210430925982665, "stage": "improve", "created_at": 1789712396.3010361}, {"event_id": "b786284dbd144d83876db7c618e9e201", "step": 31, "value": 1.1431771642093216, "stage": "improve", "created_at": 1789712949.1657004}, {"event_id": "9017b62bb84545379a3c9e1933e842fb", "step": 33, "value": 1.1415473908508125, "stage": "improve", "created_at": 1789713647.0003088}, {"event_id": "055d5b846f234cd3b039bc950ae87398", "step": 34, "value": 1.125497960971405, "stage": "evolution", "created_at": 1789714227.2677286}, {"event_id": "5a6265b3cc6b4d8e98bf23909a9172bd", "step": 35, "value": 1.1162556190668111, "stage": "improve", "created_at": 1789714780.1931798}, {"event_id": "034dbb1575534503a49cdf56c7bcc23e", "step": 36, "value": 1.2537523325479853, "stage": "improve", "created_at": 1789715369.5613122}, {"event_id": "c7063b8202684dd9b6bcbd9a884a2860", "step": 37, "value": 1.1818403722038278, "stage": "improve", "created_at": 1789715918.8177967}, {"event_id": "2de8d004757542bda5e8e26dfaf67254", "step": 38, "value": 1.2783451980079197, "stage": "improve", "created_at": 1789716442.920624}, {"event_id": "dad5b09849174b59aa593ace3fcd7339", "step": 39, "value": 1.1215510092616852, "stage": "improve", "created_at": 1789717070.0476856}, {"event_id": "f89161301eab4c1da394bb1b2d55b5d9", "step": 40, "value": 1.099027926051269, "stage": "improve", "created_at": 1789717595.8729615}], "maximize": false, "node_count": 41, "metric_name": "BPB", "curve_scope": "原始候选验证 BPB（可能含回滚或预算后记录），不作为预算内最终成绩。最终成绩以 all_runs_final.csv 为准。", "official_score": null}, {"id": "xixian.e01.seed42", "experiment_id": "nanogpt-study7-20260918", "family": "nanoGPT", "method": "seven_e01_gp6_original", "dataset": "nanoGPT", "seed": 42, "status": "completed", "best_valid_bpb": 1.1081542735566419, "budget_seconds": 21600, "artifacts": [{"bundle_id": "study7-complete-for-gpt-20260919", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/study7-complete-for-gpt-20260919/logs-ee645141ae41.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/study7-complete-for-gpt-20260919", "member": "study7_complete_for_gpt_20260919/raw/study7_20260918/analysis/summary.json", "sha256": "ee645141ae417cc245c3e1412a8331050e8000178b3fca386cb53d5263f29def"}, {"bundle_id": "study7-complete-for-gpt-20260919", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/study7-complete-for-gpt-20260919/logs-ee645141ae41.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/study7-complete-for-gpt-20260919", "member": "study7_complete_for_gpt_20260919/raw/study7_20260918/seven_e01_gp6_original/runs/20260918_214554_seven_e01_gp6_original/logs/journal.json", "sha256": "ee645141ae417cc245c3e1412a8331050e8000178b3fca386cb53d5263f29def"}], "coverage": {"method": "E01", "preset": "seven_e01_gp6_original", "state": "finished", "best_valid_bpb": 1.1081542735566419, "raw_outcomes": 44, "valid_outcomes": 32, "failed_outcomes": 12, "censored_outcomes": 0, "required_logs_preserved": 9, "trial_directories": 44, "candidate_files": 40, "train_logs": 44, "result_files": 32, "interrupted_archives": 2, "log_directory": "raw/study7_20260918/seven_e01_gp6_original/runs/20260918_214554_seven_e01_gp6_original/logs"}, "note": "预算内有效结果；恢复快照和 interrupted-state 保留在资料包中。", "journal_ref": "study7-complete-for-gpt-20260919:study7_complete_for_gpt_20260919/raw/study7_20260918/seven_e01_gp6_original/runs/20260918_214554_seven_e01_gp6_original/logs/journal.json", "metrics": [{"event_id": "10a8e582f8754f43a1ec088c9b270a3f", "step": 2, "value": 1.7759969383576657, "elapsed_seconds": 1441.4395303726196}, {"event_id": "ed25d1b4439b49d8948b381006add587", "step": 4, "value": 1.4430655620316197, "elapsed_seconds": 2214.260864019394}, {"event_id": "74b781c9ed4247cf891d77784701509b", "step": 9, "value": 1.2955150185561686, "elapsed_seconds": 4416.9049751758575}, {"event_id": "3c1eb6190f6c494e92dbcaca93ed8d52", "step": 10, "value": 1.246635423074924, "elapsed_seconds": 4572.096174955368}, {"event_id": "c43a0857ec234015a372d74d40d0a9f4", "step": 12, "value": 1.2089154573711594, "elapsed_seconds": 5507.045627832413}, {"event_id": "81ab06d4dea445efb3129e7b66765180", "step": 20, "value": 1.2021407110086235, "elapsed_seconds": 8732.73421382904}, {"event_id": "8e3bd73f32944bd2b8a903bd025775b2", "step": 27, "value": 1.1081542735566419, "elapsed_seconds": 12635.9039041996}], "maximize": false, "elapsed_seconds": 21600, "node_count": 45, "metric_name": "预算内 best-so-far BPB", "raw_metrics": [{"event_id": "10a8e582f8754f43a1ec088c9b270a3f", "step": 2, "value": 1.7759969383576657, "stage": "draft", "created_at": 1789782373.367821}, {"event_id": "ed25d1b4439b49d8948b381006add587", "step": 4, "value": 1.4430655620316197, "stage": "debug", "created_at": 1789784018.7508469}, {"event_id": "2b9bc9a2bf484ba698d6d49ee510daa5", "step": 5, "value": 1.4791837501927458, "stage": "improve", "created_at": 1789784654.6324127}, {"event_id": "8dcc7edce49e4f5db9b71ced5143437e", "step": 6, "value": 1.9918584830066544, "stage": "debug", "created_at": 1789784600.9080436}, {"event_id": "dbd66f425a0d4a34a96161f8d5ed47e7", "step": 7, "value": 1.7062083215448014, "stage": "improve", "created_at": 1789785470.766498}, {"event_id": "8a9115b62f2d4053b97e144ce8ef1da3", "step": 8, "value": 1.5806976351034836, "stage": "improve", "created_at": 1789785517.795241}, {"event_id": "74b781c9ed4247cf891d77784701509b", "step": 9, "value": 1.2955150185561686, "stage": "evolution", "created_at": 1789786108.6498473}, {"event_id": "3c1eb6190f6c494e92dbcaca93ed8d52", "step": 10, "value": 1.246635423074924, "stage": "evolution", "created_at": 1789786107.1733277}, {"event_id": "524be9a16c84414190a0b9766e3ff377", "step": 11, "value": 1.5085429990503485, "stage": "improve", "created_at": 1789787073.287798}, {"event_id": "c43a0857ec234015a372d74d40d0a9f4", "step": 12, "value": 1.2089154573711594, "stage": "improve", "created_at": 1789787095.7834494}, {"event_id": "3ec44723ce1e45698732b70c537a4e67", "step": 14, "value": 1.2719373122872257, "stage": "improve", "created_at": 1789788053.3636239}, {"event_id": "6aa0f91d78ef4272a56cab3e73bf809a", "step": 15, "value": 1.2090938566666407, "stage": "improve", "created_at": 1789788804.2673442}, {"event_id": "774c7447330a4a3d8ddbc31bf127a146", "step": 16, "value": 1.2297752471100356, "stage": "debug", "created_at": 1789788718.788332}, {"event_id": "35a2c18b9a0b408ca829d8e0caafab65", "step": 17, "value": 1.3271237978515906, "stage": "evolution", "created_at": 1789789705.1956568}, {"event_id": "125b19c4d4b34595944b6fc8c769ca6a", "step": 18, "value": 1.5304435286216642, "stage": "evolution", "created_at": 1789789766.5546641}, {"event_id": "81ab06d4dea445efb3129e7b66765180", "step": 20, "value": 1.2021407110086235, "stage": "evolution", "created_at": 1789790489.5605352}, {"event_id": "c0ca3602617748a49cb75a6b04fa70e4", "step": 21, "value": 1.2925948748644376, "stage": "improve", "created_at": 1789791198.8196356}, {"event_id": "50190d2e8886491fa14639c8ae638aba", "step": 23, "value": 1.2115289903901436, "stage": "improve", "created_at": 1789792088.3776078}, {"event_id": "0e24c820928d423fb0858f564b9fea16", "step": 24, "value": 1.2709437883626313, "stage": "improve", "created_at": 1789792067.4226935}, {"event_id": "2df4d13a5f1848e7843dc4164ef4f107", "step": 26, "value": 1.23273370159424, "stage": "evolution", "created_at": 1789793370.4449272}, {"event_id": "8e3bd73f32944bd2b8a903bd025775b2", "step": 27, "value": 1.1081542735566419, "stage": "fusion", "created_at": 1789794596.6354542}, {"event_id": "cb4566ec56f74e59868ad5362eda9e1f", "step": 28, "value": 1.1485388881687748, "stage": "debug", "created_at": 1789794654.1085367}, {"event_id": "196131429da84342a576f846a16a2d57", "step": 29, "value": 1.1686319428948597, "stage": "improve", "created_at": 1789795769.2182846}, {"event_id": "af5246715de04a7d92601979651506a3", "step": 31, "value": 1.1092719456733113, "stage": "improve", "created_at": 1789796627.2760603}, {"event_id": "593945b18c264802a541179e2d4c03e3", "step": 33, "value": 1.1474551586842132, "stage": "fusion", "created_at": 1789798426.5351274}, {"event_id": "11286df663304efb9f55df9ddbeb6fc4", "step": 34, "value": 1.20776548837013, "stage": "fusion", "created_at": 1789798441.2138066}, {"event_id": "42cc18e87d4e4a94b5a0c082b27a4127", "step": 36, "value": 1.2288085949461487, "stage": "debug", "created_at": 1789799082.7373579}, {"event_id": "d5dcde33da8942cfa683665cba4c4e49", "step": 40, "value": 1.1673309140054073, "stage": "evolution", "created_at": 1789801544.90265}, {"event_id": "f4ec2aaab15747cd9998aea24bc6360c", "step": 41, "value": 1.4156749834401285, "stage": "evolution", "created_at": 1789802646.2566016}, {"event_id": "82577a492f5d4abd856d9ea7ec21a6a5", "step": 42, "value": 1.3678723917490982, "stage": "fusion", "created_at": 1789802592.3577676}, {"event_id": "2ab3d6940a2445639716b55dac61c803", "step": 43, "value": 1.1786401381664204, "stage": "fusion", "created_at": 1789803535.481857}, {"event_id": "866c83848ac9437fa9887c136812ef86", "step": 44, "value": 1.2059368798501475, "stage": "fusion", "created_at": 1789803537.536326}], "curve_scope": "已审计的预算内 best-so-far；横轴为对应原始节点 step，时间模式为 active seconds，保留完整已记录范围。", "official_score": null}, {"id": "xixian.e02.seed42", "experiment_id": "nanogpt-study7-20260918", "family": "nanoGPT", "method": "seven_e02_state4_ucb", "dataset": "nanoGPT", "seed": 42, "status": "completed", "best_valid_bpb": 1.114956696116805, "budget_seconds": 21600, "artifacts": [{"bundle_id": "study7-complete-for-gpt-20260919", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/study7-complete-for-gpt-20260919/logs-ee645141ae41.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/study7-complete-for-gpt-20260919", "member": "study7_complete_for_gpt_20260919/raw/study7_20260918/analysis/summary.json", "sha256": "ee645141ae417cc245c3e1412a8331050e8000178b3fca386cb53d5263f29def"}, {"bundle_id": "study7-complete-for-gpt-20260919", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/study7-complete-for-gpt-20260919/logs-ee645141ae41.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/study7-complete-for-gpt-20260919", "member": "study7_complete_for_gpt_20260919/raw/study7_20260918/seven_e02_state4_ucb/runs/20260918_214554_seven_e02_state4_ucb/logs/journal.json", "sha256": "ee645141ae417cc245c3e1412a8331050e8000178b3fca386cb53d5263f29def"}], "coverage": {"method": "E02", "preset": "seven_e02_state4_ucb", "state": "finished", "best_valid_bpb": 1.114956696116805, "raw_outcomes": 54, "valid_outcomes": 40, "failed_outcomes": 12, "censored_outcomes": 2, "required_logs_preserved": 11, "trial_directories": 54, "candidate_files": 51, "train_logs": 54, "result_files": 41, "interrupted_archives": 3, "log_directory": "raw/study7_20260918/seven_e02_state4_ucb/runs/20260918_214554_seven_e02_state4_ucb/logs"}, "note": "预算内有效结果；恢复快照和 interrupted-state 保留在资料包中。", "journal_ref": "study7-complete-for-gpt-20260919:study7_complete_for_gpt_20260919/raw/study7_20260918/seven_e02_state4_ucb/runs/20260918_214554_seven_e02_state4_ucb/logs/journal.json", "metrics": [{"event_id": "401d5146308d4f8192bacb5db5a515de", "step": 2, "value": 1.8143899849385727, "elapsed_seconds": 1446.575611114502}, {"event_id": "c10566b424d842939e3b4f0e0b919b98", "step": 9, "value": 1.3183508325762485, "elapsed_seconds": 4201.674150466919}, {"event_id": "ec6420ae51754dcc93a359eb90713a24", "step": 18, "value": 1.313000898283485, "elapsed_seconds": 7854.665162801743}, {"event_id": "77e5764a473c4bc584338a3ba349e1b5", "step": 38, "value": 1.1213689923296433, "elapsed_seconds": 15538.778127908707}, {"event_id": "f26a113a81854d39a4317be6f3ca7e6c", "step": 44, "value": 1.114956696116805, "elapsed_seconds": 18069.499847650528}], "maximize": false, "elapsed_seconds": 21600, "node_count": 51, "metric_name": "预算内 best-so-far BPB", "raw_metrics": [{"event_id": "401d5146308d4f8192bacb5db5a515de", "step": 2, "value": 1.8143899849385727, "stage": "draft", "created_at": 1789782373.979846}, {"event_id": "1d04c9a47a29411ab8e534d2567e86ee", "step": 4, "value": 3.086427232172759, "stage": "debug", "created_at": 1789783888.0076864}, {"event_id": "5b02b0f2dd854ac09e7887b245ed5ffe", "step": 5, "value": 1.9435224133241005, "stage": "improve", "created_at": 1789784548.581493}, {"event_id": "bc18c5e670fc457faab9afc2729c8cbc", "step": 6, "value": 3.283366630950468, "stage": "debug", "created_at": 1789784394.2714462}, {"event_id": "f9b6e681ad67418183862cef30b848fc", "step": 7, "value": 1.8779853775534554, "stage": "improve", "created_at": 1789785288.8862953}, {"event_id": "16fc0ca0cf26428099d4f6ced67eb63e", "step": 8, "value": 1.8983602333349396, "stage": "improve", "created_at": 1789785289.5977147}, {"event_id": "c10566b424d842939e3b4f0e0b919b98", "step": 9, "value": 1.3183508325762485, "stage": "evolution", "created_at": 1789785981.7899249}, {"event_id": "a080a47923684da7aac7027360ade65a", "step": 10, "value": 1.7181653912516812, "stage": "evolution", "created_at": 1789786336.1783574}, {"event_id": "c4f63e78d0fe46598fbda590499d74ee", "step": 11, "value": 1.5251075354616672, "stage": "improve", "created_at": 1789786949.1162817}, {"event_id": "e711681c1175418e8885c46dc758ad5e", "step": 12, "value": 1.5117451686351355, "stage": "improve", "created_at": 1789787022.7846797}, {"event_id": "1bade327fefb400d973a63f0457d2d0c", "step": 13, "value": 1.8877953365650326, "stage": "evolution", "created_at": 1789787856.2581298}, {"event_id": "e52ff801b58146e39a1a594774af1e05", "step": 14, "value": 2.441311422853749, "stage": "evolution", "created_at": 1789787894.1396923}, {"event_id": "3d9b94acb4c34da3a3ef4e05032afdec", "step": 15, "value": 1.4538163695916428, "stage": "evolution", "created_at": 1789788586.2827337}, {"event_id": "c0d027c9687a48ea9950f7e119ff5044", "step": 16, "value": 1.3950940493700408, "stage": "evolution", "created_at": 1789788781.2186058}, {"event_id": "ec6420ae51754dcc93a359eb90713a24", "step": 18, "value": 1.313000898283485, "stage": "evolution", "created_at": 1789789675.5619843}, {"event_id": "aa72e11418734e0d97860594cb733e66", "step": 20, "value": 1.3831928493580796, "stage": "improve", "created_at": 1789790316.5112956}, {"event_id": "056e4ffc7ce54924a5bfa8893ebfe1ea", "step": 21, "value": 1.360536767152688, "stage": "debug", "created_at": 1789790907.780105}, {"event_id": "2f4969c14578496ab48a58c98f68a21a", "step": 22, "value": 1.4502593722397552, "stage": "improve", "created_at": 1789790996.7866993}, {"event_id": "6eb7d3f8627b4d4394e34fa963e119e1", "step": 24, "value": 1.5646366256188557, "stage": "evolution", "created_at": 1789791628.835485}, {"event_id": "b5cd49ecc1334a3ab556dc4feaff032f", "step": 25, "value": 1.4491293955528701, "stage": "evolution", "created_at": 1789792271.2876604}, {"event_id": "6c25c988807f458d9ff9454d95f78850", "step": 26, "value": 1.8508393910492138, "stage": "evolution", "created_at": 1789792316.7968428}, {"event_id": "4ed50c0c802c43dfa040dd3dce0370a7", "step": 27, "value": 1.7699922805367792, "stage": "evolution", "created_at": 1789793044.9086113}, {"event_id": "4f91f1da9a58464d94358293ba57bb45", "step": 28, "value": 1.3840481642840299, "stage": "evolution", "created_at": 1789793073.0758717}, {"event_id": "2d44d6ea51354882bc510fa5377bc499", "step": 29, "value": 1.515885044898406, "stage": "evolution", "created_at": 1789794652.2021046}, {"event_id": "6866e7931c2047139fc7335f11b5c796", "step": 30, "value": 2.0675220267120165, "stage": "fusion", "created_at": 1789794646.928027}, {"event_id": "14d8ad0c9dc64796868e7875c3171590", "step": 31, "value": 1.378502041630931, "stage": "fusion", "created_at": 1789795302.535229}, {"event_id": "c500ebdfe80e4dfd824d0cc270b9833e", "step": 32, "value": 1.554605425554664, "stage": "fusion", "created_at": 1789795310.0816336}, {"event_id": "3752b0f3976747d5b64816957495c39e", "step": 34, "value": 2.6152280214875807, "stage": "evolution", "created_at": 1789796191.349174}, {"event_id": "ef1418d1ee314631b424c819e62abe2d", "step": 36, "value": 1.4860260836333807, "stage": "evolution", "created_at": 1789797015.8037777}, {"event_id": "77e5764a473c4bc584338a3ba349e1b5", "step": 38, "value": 1.1213689923296433, "stage": "fusion", "created_at": 1789797593.2464979}, {"event_id": "afd3fa311ad04159aa92352155159812", "step": 39, "value": 1.2763529470772401, "stage": "improve", "created_at": 1789798351.7668378}, {"event_id": "5d8c8f647b504a52bfff74893dec71ce", "step": 40, "value": 1.3423545155501737, "stage": "improve", "created_at": 1789798390.81096}, {"event_id": "d3360dcf553d44b88be8e5f7a3ea6e8d", "step": 41, "value": 1.131223830348498, "stage": "improve", "created_at": 1789799265.0323849}, {"event_id": "f26a113a81854d39a4317be6f3ca7e6c", "step": 44, "value": 1.114956696116805, "stage": "fusion", "created_at": 1789800092.806401}, {"event_id": "e79bc28d8a374bb3babb0b4c114eccff", "step": 45, "value": 1.167896733209852, "stage": "debug", "created_at": 1789800694.3880777}, {"event_id": "9792e799241943eabf29131eba7684f7", "step": 46, "value": 1.2397760161495546, "stage": "improve", "created_at": 1789800911.7679243}, {"event_id": "6e5ea04ff9ab47afbc4c8a831bab96e0", "step": 47, "value": 1.149702355682554, "stage": "improve", "created_at": 1789801798.3378603}, {"event_id": "20ecf8741f2d4624b59db80d0ed03eee", "step": 48, "value": 1.1339529133495834, "stage": "improve", "created_at": 1789801853.4441335}, {"event_id": "840c696fb8c94bf08981dd2683f786d4", "step": 49, "value": 1.1508345967202596, "stage": "fusion", "created_at": 1789802931.390997}, {"event_id": "391ea26f238e45e2ad693237b5ff146f", "step": 50, "value": 1.1573030602816576, "stage": "fusion", "created_at": 1789802968.0524743}], "curve_scope": "已审计的预算内 best-so-far；横轴为对应原始节点 step，时间模式为 active seconds，保留完整已记录范围。", "official_score": null}, {"id": "xixian.e03.seed42", "experiment_id": "nanogpt-study7-20260918", "family": "nanoGPT", "method": "seven_e03_state4_ancestorB_ucb", "dataset": "nanoGPT", "seed": 42, "status": "completed", "best_valid_bpb": 1.163705352217177, "budget_seconds": 21600, "artifacts": [{"bundle_id": "study7-complete-for-gpt-20260919", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/study7-complete-for-gpt-20260919/logs-ee645141ae41.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/study7-complete-for-gpt-20260919", "member": "study7_complete_for_gpt_20260919/raw/study7_20260918/analysis/summary.json", "sha256": "ee645141ae417cc245c3e1412a8331050e8000178b3fca386cb53d5263f29def"}, {"bundle_id": "study7-complete-for-gpt-20260919", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/study7-complete-for-gpt-20260919/logs-ee645141ae41.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/study7-complete-for-gpt-20260919", "member": "study7_complete_for_gpt_20260919/raw/study7_20260918/seven_e03_state4_ancestorB_ucb/runs/20260918_214606_seven_e03_state4_ancestorB_ucb/logs/journal.json", "sha256": "ee645141ae417cc245c3e1412a8331050e8000178b3fca386cb53d5263f29def"}], "coverage": {"method": "E03", "preset": "seven_e03_state4_ancestorB_ucb", "state": "finished", "best_valid_bpb": 1.163705352217177, "raw_outcomes": 66, "valid_outcomes": 55, "failed_outcomes": 10, "censored_outcomes": 1, "required_logs_preserved": 11, "trial_directories": 66, "candidate_files": 60, "train_logs": 66, "result_files": 55, "interrupted_archives": 1, "log_directory": "raw/study7_20260918/seven_e03_state4_ancestorB_ucb/runs/20260918_214606_seven_e03_state4_ancestorB_ucb/logs"}, "note": "预算内有效结果；恢复快照和 interrupted-state 保留在资料包中。", "journal_ref": "study7-complete-for-gpt-20260919:study7_complete_for_gpt_20260919/raw/study7_20260918/seven_e03_state4_ancestorB_ucb/runs/20260918_214606_seven_e03_state4_ancestorB_ucb/logs/journal.json", "metrics": [{"event_id": "56f1aa945b6e4d819e26070ff34f2510", "step": 2, "value": 1.7993776253387117, "elapsed_seconds": 1424.9780077934265}, {"event_id": "48ad1deace714ca5a6bd1edd078339eb", "step": 7, "value": 1.6130783556880395, "elapsed_seconds": 3546.7066621780396}, {"event_id": "f935b43bcb8a4695902e21bc87ff10f3", "step": 28, "value": 1.5512437627391162, "elapsed_seconds": 9895.471776247025}, {"event_id": "d829a279cc2243b7aa48ebbe1113ff41", "step": 38, "value": 1.2166055523106871, "elapsed_seconds": 13004.908578157425}, {"event_id": "8ca946c2295d41edb419cdd46262c712", "step": 54, "value": 1.1984163461826054, "elapsed_seconds": 17871.82110929489}, {"event_id": "cb74a215bc6a42c6a6c2291cf734e851", "step": 56, "value": 1.163705352217177, "elapsed_seconds": 18496.68541955948}], "maximize": false, "elapsed_seconds": 21600, "node_count": 65, "metric_name": "预算内 best-so-far BPB", "raw_metrics": [{"event_id": "56f1aa945b6e4d819e26070ff34f2510", "step": 2, "value": 1.7993776253387117, "stage": "draft", "created_at": 1789782383.888733}, {"event_id": "0872dcd7cadd453eb95f311102dce01e", "step": 4, "value": 3.0797928610511307, "stage": "debug", "created_at": 1789784135.9377747}, {"event_id": "71da52c5bacf45f5bea5d998ab2b760e", "step": 5, "value": 1.9036338382385267, "stage": "improve", "created_at": 1789784694.3605483}, {"event_id": "79369ffab8d845ee88c188f49893ba5d", "step": 6, "value": 3.323117217215896, "stage": "debug", "created_at": 1789784622.4972694}, {"event_id": "48ad1deace714ca5a6bd1edd078339eb", "step": 7, "value": 1.6130783556880395, "stage": "improve", "created_at": 1789785384.7999418}, {"event_id": "209b2340a535479d87fa362d7c69e7ab", "step": 8, "value": 1.8291529294238726, "stage": "improve", "created_at": 1789785642.11406}, {"event_id": "84c1e5340d46419eb310c318add94467", "step": 9, "value": 1.9309656154597252, "stage": "improve", "created_at": 1789786233.1274137}, {"event_id": "4f31885f751e41d0835ec49b065bf189", "step": 10, "value": 1.92374836476112, "stage": "improve", "created_at": 1789786267.797041}, {"event_id": "f93314e95a384e0f828e2829f8f5f054", "step": 11, "value": 1.840913514581083, "stage": "evolution", "created_at": 1789786851.381678}, {"event_id": "1dad13977a8847d6b584e910e7b8b161", "step": 12, "value": 1.7448206588547566, "stage": "evolution", "created_at": 1789786848.63752}, {"event_id": "6995263de5e4429db003a7eda335e7ae", "step": 13, "value": 1.7040466038564852, "stage": "evolution", "created_at": 1789787461.8102338}, {"event_id": "621565d375e4466085d657cea10e562c", "step": 14, "value": 1.8896934662461873, "stage": "evolution", "created_at": 1789787453.0904706}, {"event_id": "19f18163443944ba96315de1edcd0b72", "step": 15, "value": 1.8135540226909237, "stage": "evolution", "created_at": 1789788062.7001746}, {"event_id": "a7a691c023114a4bb645a72141c6b799", "step": 16, "value": 1.767371775021189, "stage": "evolution", "created_at": 1789788087.7926924}, {"event_id": "edc657fe7cdc4992a938fbb18e7b979e", "step": 17, "value": 1.8503034361161432, "stage": "improve", "created_at": 1789788751.2133858}, {"event_id": "a9eb836e57b942cd903492b1f18690da", "step": 18, "value": 1.779114697709526, "stage": "improve", "created_at": 1789788750.487588}, {"event_id": "40f4206a7f6f4d7cbb1d7f313e7ca97e", "step": 19, "value": 1.7648010558043896, "stage": "evolution", "created_at": 1789789357.0494688}, {"event_id": "da1c0b0c8d55426baacbb44bf3939c81", "step": 20, "value": 1.9269681877627016, "stage": "evolution", "created_at": 1789789342.710204}, {"event_id": "2d94183c1ecd42659786f43f81257921", "step": 21, "value": 1.9121703644207602, "stage": "evolution", "created_at": 1789789914.0443637}, {"event_id": "fedb855799d0417db8b9ea825a580b36", "step": 22, "value": 1.8990442692238843, "stage": "evolution", "created_at": 1789789928.3819818}, {"event_id": "b2e9977a4ee3464591693ff367392abb", "step": 23, "value": 1.6613638912103736, "stage": "evolution", "created_at": 1789790510.6660926}, {"event_id": "394d395e65b64e6cb1668c92ba5f8d71", "step": 24, "value": 1.9103508359342551, "stage": "evolution", "created_at": 1789790541.2269511}, {"event_id": "77f0df00662c400bb373e257f19f1508", "step": 25, "value": 1.8932097667841963, "stage": "evolution", "created_at": 1789791146.600165}, {"event_id": "d612c6c6d1ce437bb6fa03343f3dd842", "step": 26, "value": 1.6569506737246829, "stage": "evolution", "created_at": 1789791173.1660426}, {"event_id": "f935b43bcb8a4695902e21bc87ff10f3", "step": 28, "value": 1.5512437627391162, "stage": "evolution", "created_at": 1789791756.435476}, {"event_id": "45ffc9b46de9424fad42a0f2cac06239", "step": 29, "value": 1.789576182070011, "stage": "debug", "created_at": 1789792274.5890412}, {"event_id": "98556d96a631400097d42f61f53cf79e", "step": 30, "value": 1.8933891353176744, "stage": "improve", "created_at": 1789792385.672043}, {"event_id": "8cd3ea949f19449382b428d5a0f0ebca", "step": 31, "value": 1.576900847925125, "stage": "improve", "created_at": 1789793027.6484559}, {"event_id": "032b77e2b38246eb8bf88afcb9c025b0", "step": 32, "value": 1.870558806191589, "stage": "improve", "created_at": 1789793048.8071227}, {"event_id": "1e0ccbf61a7d48069bc1e13581dee800", "step": 33, "value": 1.895080439780628, "stage": "improve", "created_at": 1789793696.7840762}, {"event_id": "10f0ad49ddc7432c9d7d7082869a0859", "step": 34, "value": 1.8458522235957775, "stage": "improve", "created_at": 1789793709.7308471}, {"event_id": "68df6b6ee000435c9dc6f55332df2b30", "step": 35, "value": 1.5881226326017552, "stage": "evolution", "created_at": 1789794257.602012}, {"event_id": "3e7d688b651a432b892269b7bb255ea1", "step": 36, "value": 1.621159820171383, "stage": "fusion", "created_at": 1789794255.9872274}, {"event_id": "d829a279cc2243b7aa48ebbe1113ff41", "step": 38, "value": 1.2166055523106871, "stage": "fusion", "created_at": 1789794848.883868}, {"event_id": "a86f10d694c641f9a76ea134881c1d0f", "step": 40, "value": 1.2640314619877904, "stage": "improve", "created_at": 1789795450.0915098}, {"event_id": "20b807f063bc43c38de5ebd3d1324e95", "step": 41, "value": 1.3887109655458036, "stage": "improve", "created_at": 1789796037.3555155}, {"event_id": "b6330aeaaf3d4312a3af8b080031d07f", "step": 42, "value": 1.5284627988570512, "stage": "improve", "created_at": 1789796038.539021}, {"event_id": "573d8a6a594f460888aa839b899f8160", "step": 43, "value": 1.4690250468101957, "stage": "evolution", "created_at": 1789796720.6042209}, {"event_id": "83ff286692f9438c887b958441254406", "step": 44, "value": 1.4855604424508286, "stage": "evolution", "created_at": 1789796716.8916638}, {"event_id": "8ca8b976a5a349c694b4c0bb146b751e", "step": 45, "value": 1.4147136931684632, "stage": "improve", "created_at": 1789797401.395058}, {"event_id": "860f3d9dfcf242c198018bf5ffaf7e71", "step": 46, "value": 1.466637925178092, "stage": "improve", "created_at": 1789797401.1323774}, {"event_id": "caaa1e1472fd48969c304f0068ecef81", "step": 47, "value": 1.3123251797904019, "stage": "evolution", "created_at": 1789798003.8302255}, {"event_id": "b68dd92c41534f9b8bf35a0aba96094d", "step": 48, "value": 1.2892739917957818, "stage": "fusion", "created_at": 1789798008.5523524}, {"event_id": "b35c832b7eec45c19698c8d7aff3a430", "step": 49, "value": 1.294186470149919, "stage": "fusion", "created_at": 1789798583.4263377}, {"event_id": "5a293249e6ac458d86fdf39c5608823e", "step": 50, "value": 1.4476626650379745, "stage": "evolution", "created_at": 1789798584.998447}, {"event_id": "089905ef844046c1bddeaf6deee75496", "step": 51, "value": 1.273168250799509, "stage": "evolution", "created_at": 1789799160.3262997}, {"event_id": "e93f26a1224d4b6da184e98fe34fb7a7", "step": 52, "value": 1.3214583151566024, "stage": "fusion", "created_at": 1789799176.7722762}, {"event_id": "8ca946c2295d41edb419cdd46262c712", "step": 54, "value": 1.1984163461826054, "stage": "fusion", "created_at": 1789799753.858765}, {"event_id": "cb74a215bc6a42c6a6c2291cf734e851", "step": 56, "value": 1.163705352217177, "stage": "improve", "created_at": 1789800318.2772577}, {"event_id": "54755112a5244204a02264dd2988ed58", "step": 59, "value": 1.4908165543457774, "stage": "improve", "created_at": 1789801484.1358383}, {"event_id": "bedd3136fcdc43138a9c4e730c5f5efa", "step": 60, "value": 1.5800011551358188, "stage": "improve", "created_at": 1789801518.3673685}, {"event_id": "7e129b2b897048c9a9cd1c22d25d7c45", "step": 61, "value": 1.3769538120581872, "stage": "debug", "created_at": 1789802089.161523}, {"event_id": "86d166abee81445099e7c8b373bce96d", "step": 62, "value": 1.3013327923553786, "stage": "improve", "created_at": 1789802187.8643198}, {"event_id": "ee9cb7904ff24e109f4f5dc6dc058678", "step": 63, "value": 1.2358888279262679, "stage": "fusion", "created_at": 1789802906.5753736}, {"event_id": "39ffe3f374f344baab2723bf224ebcba", "step": 64, "value": 1.1648967334125262, "stage": "evolution", "created_at": 1789803120.8047998}], "curve_scope": "已审计的预算内 best-so-far；横轴为对应原始节点 step，时间模式为 active seconds，保留完整已记录范围。", "official_score": null}, {"id": "xixian.e04.seed42", "experiment_id": "nanogpt-study7-20260918", "family": "nanoGPT", "method": "seven_e04_state4_ratingmean_ucb", "dataset": "nanoGPT", "seed": 42, "status": "completed", "best_valid_bpb": 1.0569796098253497, "budget_seconds": 21600, "artifacts": [{"bundle_id": "study7-complete-for-gpt-20260919", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/study7-complete-for-gpt-20260919/logs-ee645141ae41.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/study7-complete-for-gpt-20260919", "member": "study7_complete_for_gpt_20260919/raw/study7_20260918/analysis/summary.json", "sha256": "ee645141ae417cc245c3e1412a8331050e8000178b3fca386cb53d5263f29def"}, {"bundle_id": "study7-complete-for-gpt-20260919", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/study7-complete-for-gpt-20260919/logs-ee645141ae41.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/study7-complete-for-gpt-20260919", "member": "study7_complete_for_gpt_20260919/raw/study7_20260918/seven_e04_state4_ratingmean_ucb/runs/20260918_214613_seven_e04_state4_ratingmean_ucb/logs/journal.json", "sha256": "ee645141ae417cc245c3e1412a8331050e8000178b3fca386cb53d5263f29def"}], "coverage": {"method": "E04", "preset": "seven_e04_state4_ratingmean_ucb", "state": "finished", "best_valid_bpb": 1.0569796098253497, "raw_outcomes": 52, "valid_outcomes": 46, "failed_outcomes": 5, "censored_outcomes": 1, "required_logs_preserved": 12, "trial_directories": 52, "candidate_files": 51, "train_logs": 52, "result_files": 46, "interrupted_archives": 3, "log_directory": "raw/study7_20260918/seven_e04_state4_ratingmean_ucb/runs/20260918_214613_seven_e04_state4_ratingmean_ucb/logs"}, "note": "预算内有效结果；恢复快照和 interrupted-state 保留在资料包中。", "journal_ref": "study7-complete-for-gpt-20260919:study7_complete_for_gpt_20260919/raw/study7_20260918/seven_e04_state4_ratingmean_ucb/runs/20260918_214613_seven_e04_state4_ratingmean_ucb/logs/journal.json", "metrics": [{"event_id": "ee1cd1925b6348aaba1f3b64df34c608", "step": 2, "value": 1.784426449536341, "elapsed_seconds": 1483.2880408763885}, {"event_id": "30289f8bfcbc4a53b32f101c2b50bf0d", "step": 4, "value": 1.1414288601390588, "elapsed_seconds": 3638.6700410842896}, {"event_id": "d5c2ba8222bb485ba681d185d96ec7c0", "step": 6, "value": 1.0968850574528264, "elapsed_seconds": 4709.812677145004}, {"event_id": "1378c57d5574487fb4db7247cf1e73b5", "step": 24, "value": 1.0833982501053305, "elapsed_seconds": 11052.985512971878}, {"event_id": "58d955850b544277b0c2e4cd1242425e", "step": 26, "value": 1.0693285445442258, "elapsed_seconds": 12216.227562904358}, {"event_id": "df1c9786b34f4c279188c4a6eb6d55c4", "step": 46, "value": 1.0569796098253497, "elapsed_seconds": 19473.94898891449}], "maximize": false, "elapsed_seconds": 21600, "node_count": 51, "metric_name": "预算内 best-so-far BPB", "raw_metrics": [{"event_id": "ee1cd1925b6348aaba1f3b64df34c608", "step": 2, "value": 1.784426449536341, "stage": "draft", "created_at": 1789782400.9328043}, {"event_id": "30289f8bfcbc4a53b32f101c2b50bf0d", "step": 4, "value": 1.1414288601390588, "stage": "debug", "created_at": 1789785370.5162284}, {"event_id": "2e78d0e90a4e4205a6fa0ae5d31d3813", "step": 5, "value": 3.289290207573426, "stage": "debug", "created_at": 1789785996.5211687}, {"event_id": "d5c2ba8222bb485ba681d185d96ec7c0", "step": 6, "value": 1.0968850574528264, "stage": "improve", "created_at": 1789786099.8903604}, {"event_id": "a9272bd8377b46ddab685026327f5db4", "step": 7, "value": 1.1766053894575916, "stage": "improve", "created_at": 1789787191.539347}, {"event_id": "d39ac605931e4827b79557512d8f995f", "step": 8, "value": 1.176792579386275, "stage": "improve", "created_at": 1789787217.2222323}, {"event_id": "58f9d34427994aa7a95ee16d8ac1637f", "step": 9, "value": 1.1581111245557556, "stage": "improve", "created_at": 1789787878.2225754}, {"event_id": "e9a7f2db7cf74180bd35d04344b45584", "step": 10, "value": 1.2389928965418282, "stage": "improve", "created_at": 1789787962.5848546}, {"event_id": "45056faf56db4ea79cd018c56abde109", "step": 11, "value": 1.1687176160258599, "stage": "evolution", "created_at": 1789788598.5178564}, {"event_id": "eb3ca6cfec904d7798df8b1f5acbb240", "step": 12, "value": 1.1714565577388543, "stage": "evolution", "created_at": 1789788599.7384846}, {"event_id": "6eefae0fedad433780492deaf7cdcc00", "step": 13, "value": 1.1593212475472237, "stage": "evolution", "created_at": 1789789269.2072098}, {"event_id": "25900ea5b430436aa805c9d103f1ad19", "step": 14, "value": 1.1298496381674539, "stage": "evolution", "created_at": 1789789323.8199306}, {"event_id": "7c33b01507934e2380f65ef15f077f32", "step": 15, "value": 1.16473558751184, "stage": "evolution", "created_at": 1789790427.8215528}, {"event_id": "900afe06b2b54197a264d8e465c4f38f", "step": 16, "value": 1.1815726656340544, "stage": "evolution", "created_at": 1789790457.2324815}, {"event_id": "d4e830bc945a4ae89949f148f885c765", "step": 17, "value": 1.152975780700264, "stage": "evolution", "created_at": 1789791129.9951186}, {"event_id": "0dba54f754f741b0a1451a8f8bdadaeb", "step": 18, "value": 1.146395814700496, "stage": "evolution", "created_at": 1789791140.005444}, {"event_id": "d16fdde348604ee3a4e5f73c23aa5640", "step": 19, "value": 1.1796216577036973, "stage": "evolution", "created_at": 1789791909.1516616}, {"event_id": "e276befdb8ab4e3bb88aae1008596185", "step": 20, "value": 1.1979887325157161, "stage": "evolution", "created_at": 1789791868.0484762}, {"event_id": "a754eb3c9cca4d9788c8f11343db2ed7", "step": 21, "value": 1.169967221122139, "stage": "evolution", "created_at": 1789792560.5803082}, {"event_id": "e51fae637e1643c39cb2dd78d4fb1b7a", "step": 22, "value": 2.9880152910352655, "stage": "evolution", "created_at": 1789792560.3789628}, {"event_id": "1378c57d5574487fb4db7247cf1e73b5", "step": 24, "value": 1.0833982501053305, "stage": "evolution", "created_at": 1789793202.9698954}, {"event_id": "5decc0141f6a4866bec95639fcab00dd", "step": 25, "value": 1.164693076554929, "stage": "debug", "created_at": 1789793763.2931628}, {"event_id": "58d955850b544277b0c2e4cd1242425e", "step": 26, "value": 1.0693285445442258, "stage": "improve", "created_at": 1789793836.6905985}, {"event_id": "d0ee799d6d364365af439312933598b1", "step": 27, "value": 1.120936291927096, "stage": "improve", "created_at": 1789794999.194478}, {"event_id": "e37015d3d1064ec8a5ce4ed432053557", "step": 28, "value": 1.120992515584909, "stage": "improve", "created_at": 1789795015.3393357}, {"event_id": "9ab3a1620e454450854e2a28d3e21510", "step": 29, "value": 1.138834425275226, "stage": "improve", "created_at": 1789795723.4316008}, {"event_id": "79bb7c4cc375483d9a1b20cb15afa0aa", "step": 30, "value": 1.1748395795992852, "stage": "improve", "created_at": 1789795776.4740305}, {"event_id": "12d6d198825c46228c65e9d12da6039a", "step": 31, "value": 1.1088934372694224, "stage": "improve", "created_at": 1789796473.4039843}, {"event_id": "b29d8e4f06404d5e87fbd807b924316d", "step": 32, "value": 1.1006609745316611, "stage": "improve", "created_at": 1789796469.4232206}, {"event_id": "e46fa0edace94c76ba3842c0df013a8f", "step": 33, "value": 1.1248059656430576, "stage": "evolution", "created_at": 1789797143.1920638}, {"event_id": "e3f4994836d84b0285bdb041c26a6bd7", "step": 34, "value": 1.1527616114508814, "stage": "fusion", "created_at": 1789797144.4123278}, {"event_id": "be54d7f104c44f2abb5b14cdc090fb26", "step": 35, "value": 1.211131025608407, "stage": "fusion", "created_at": 1789797825.3723269}, {"event_id": "14865d4a7a88473e80f5d5b6fa018edb", "step": 36, "value": 1.138197616342987, "stage": "fusion", "created_at": 1789797857.8923087}, {"event_id": "4220a57e168444ac91392907840da54d", "step": 37, "value": 1.1869856547090687, "stage": "evolution", "created_at": 1789798549.705137}, {"event_id": "c00f5c5d453d448fb879450087ef548d", "step": 38, "value": 1.1334481576697917, "stage": "evolution", "created_at": 1789798533.6774933}, {"event_id": "2b951453de27480db70d3649256e6a6c", "step": 39, "value": 1.122083364262996, "stage": "evolution", "created_at": 1789799161.7092552}, {"event_id": "d873590d44304b38a62f8cbd10346e57", "step": 40, "value": 1.1401658188296286, "stage": "fusion", "created_at": 1789799151.0075858}, {"event_id": "a1bed573a18043ec84d1e1d18dd6d463", "step": 41, "value": 1.2047017676640683, "stage": "fusion", "created_at": 1789799879.2185657}, {"event_id": "dc8ad37477a540a791b245f100d93f33", "step": 42, "value": 1.1335820629375706, "stage": "evolution", "created_at": 1789799887.2106373}, {"event_id": "510508d6f34e4218a858f0831655fd97", "step": 44, "value": 1.1140448017064843, "stage": "fusion", "created_at": 1789800907.710099}, {"event_id": "97aef87965d14676a87d9419ce5e5340", "step": 45, "value": 1.1409278054947567, "stage": "evolution", "created_at": 1789801536.3172157}, {"event_id": "df1c9786b34f4c279188c4a6eb6d55c4", "step": 46, "value": 1.0569796098253497, "stage": "fusion", "created_at": 1789801570.6201472}, {"event_id": "c654ba5567ef43ddada3b3dbd4a9c74a", "step": 47, "value": 1.1001446717941958, "stage": "improve", "created_at": 1789802604.7834055}, {"event_id": "e2538b3362e24632bcd74b6ea47f0c77", "step": 48, "value": 1.0932843506754546, "stage": "improve", "created_at": 1789802603.5592117}, {"event_id": "e173d92ff1d34e13a971235f4afbe397", "step": 49, "value": 1.1275001983414843, "stage": "improve", "created_at": 1789803408.1333513}, {"event_id": "edeb7dca4791488db740b35aeae5cff1", "step": 50, "value": 1.102993983903269, "stage": "improve", "created_at": 1789803533.7551687}], "curve_scope": "已审计的预算内 best-so-far；横轴为对应原始节点 step，时间模式为 active seconds，保留完整已记录范围。", "official_score": null}, {"id": "xixian.e05.seed42", "experiment_id": "nanogpt-study7-20260918", "family": "nanoGPT", "method": "seven_e05_state4_ancestorB_ratingmean_ucb", "dataset": "nanoGPT", "seed": 42, "status": "completed", "best_valid_bpb": 1.1309563601977168, "budget_seconds": 21600, "artifacts": [{"bundle_id": "study7-complete-for-gpt-20260919", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/study7-complete-for-gpt-20260919/logs-ee645141ae41.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/study7-complete-for-gpt-20260919", "member": "study7_complete_for_gpt_20260919/raw/study7_20260918/analysis/summary.json", "sha256": "ee645141ae417cc245c3e1412a8331050e8000178b3fca386cb53d5263f29def"}, {"bundle_id": "study7-complete-for-gpt-20260919", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/study7-complete-for-gpt-20260919/logs-ee645141ae41.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/study7-complete-for-gpt-20260919", "member": "study7_complete_for_gpt_20260919/raw/study7_20260918/seven_e05_state4_ancestorB_ratingmean_ucb/runs/20260918_214613_seven_e05_state4_ancestorB_ratingmean_ucb/logs/journal.json", "sha256": "ee645141ae417cc245c3e1412a8331050e8000178b3fca386cb53d5263f29def"}], "coverage": {"method": "E05", "preset": "seven_e05_state4_ancestorB_ratingmean_ucb", "state": "finished", "best_valid_bpb": 1.1309563601977168, "raw_outcomes": 62, "valid_outcomes": 52, "failed_outcomes": 9, "censored_outcomes": 1, "required_logs_preserved": 12, "trial_directories": 62, "candidate_files": 61, "train_logs": 62, "result_files": 52, "interrupted_archives": 3, "log_directory": "raw/study7_20260918/seven_e05_state4_ancestorB_ratingmean_ucb/runs/20260918_214613_seven_e05_state4_ancestorB_ratingmean_ucb/logs"}, "note": "预算内有效结果；恢复快照和 interrupted-state 保留在资料包中。", "journal_ref": "study7-complete-for-gpt-20260919:study7_complete_for_gpt_20260919/raw/study7_20260918/seven_e05_state4_ancestorB_ratingmean_ucb/runs/20260918_214613_seven_e05_state4_ancestorB_ratingmean_ucb/logs/journal.json", "metrics": [{"event_id": "c36ba70ffa1a41ec91bfe3fc6f13b771", "step": 2, "value": 1.7755560177359824, "elapsed_seconds": 1479.4692199230194}, {"event_id": "d136e9c6d9cd46f6b9282bf35a0cff3f", "step": 6, "value": 1.484733447884388, "elapsed_seconds": 3224.7603108882904}, {"event_id": "608ee57911f84993ac13269c96c06a04", "step": 13, "value": 1.4640830703945087, "elapsed_seconds": 6272.652196645737}, {"event_id": "9be91b9a6b0c48ac9759bcfdb216f96d", "step": 15, "value": 1.4552558504215527, "elapsed_seconds": 7126.836864471436}, {"event_id": "b596a5b6849b48a9a64c43254e372057", "step": 19, "value": 1.3817483731120097, "elapsed_seconds": 8509.89048576355}, {"event_id": "b68146b50a73400e9db9c51f7b777ed8", "step": 25, "value": 1.3387269012031369, "elapsed_seconds": 9857.361734867096}, {"event_id": "41a98c8bce29412d9a4e385c61c0d29e", "step": 30, "value": 1.2469396589082447, "elapsed_seconds": 11017.357397794724}, {"event_id": "1c00b2f3a7284607b825a7de3466f542", "step": 34, "value": 1.2437450281740063, "elapsed_seconds": 12418.9500374794}, {"event_id": "5ca52ee0d27b41bd874fad0e24d2c594", "step": 41, "value": 1.2186195840066145, "elapsed_seconds": 14710.506766796112}, {"event_id": "cb0fedffdae043fc9e06090505f61402", "step": 45, "value": 1.2118563651998477, "elapsed_seconds": 16081.282177686691}, {"event_id": "0d471e70bd6a4111a45a99d8578fa5bd", "step": 48, "value": 1.156751316127494, "elapsed_seconds": 17202.521148443222}, {"event_id": "43166c1a8bce472893ac434afe465419", "step": 52, "value": 1.1309563601977168, "elapsed_seconds": 18938.95088648796}], "maximize": false, "elapsed_seconds": 21600, "node_count": 61, "metric_name": "预算内 best-so-far BPB", "raw_metrics": [{"event_id": "c36ba70ffa1a41ec91bfe3fc6f13b771", "step": 2, "value": 1.7755560177359824, "stage": "draft", "created_at": 1789782400.852157}, {"event_id": "e2c87ee696bc4d1cb71ddb01dc6be78e", "step": 4, "value": 3.083083449209088, "stage": "debug", "created_at": 1789783888.6284366}, {"event_id": "87816567de2f42afaec8c57de1f01270", "step": 5, "value": 3.294494507101419, "stage": "debug", "created_at": 1789784506.967113}, {"event_id": "d136e9c6d9cd46f6b9282bf35a0cff3f", "step": 6, "value": 1.484733447884388, "stage": "improve", "created_at": 1789785062.2961934}, {"event_id": "ac71f3e9bec74f509432c079242c7a01", "step": 7, "value": 1.8490679096643527, "stage": "improve", "created_at": 1789785722.1266625}, {"event_id": "d3f51b2360e749b485f98fd10ab53a1d", "step": 8, "value": 1.8770352194747175, "stage": "improve", "created_at": 1789785721.907684}, {"event_id": "9f83a8448a734f288d1ea4310538aff1", "step": 9, "value": 1.7360052365356187, "stage": "improve", "created_at": 1789786562.8469012}, {"event_id": "5541cc0e2b2c491bb93d9881299d9e27", "step": 10, "value": 1.8879189709185322, "stage": "improve", "created_at": 1789786586.9230957}, {"event_id": "c890338b94534699a2b781b5e85ac8b2", "step": 11, "value": 1.6056755912927043, "stage": "evolution", "created_at": 1789787347.1281123}, {"event_id": "6fc478535bc94d219707fee72ebba5ec", "step": 12, "value": 1.6564247805762538, "stage": "evolution", "created_at": 1789787254.032257}, {"event_id": "608ee57911f84993ac13269c96c06a04", "step": 13, "value": 1.4640830703945087, "stage": "evolution", "created_at": 1789788041.278307}, {"event_id": "475a9e8b04c447a4a412b998b7569e1a", "step": 14, "value": 3.1235461185631888, "stage": "evolution", "created_at": 1789788081.4564834}, {"event_id": "9be91b9a6b0c48ac9759bcfdb216f96d", "step": 15, "value": 1.4552558504215527, "stage": "improve", "created_at": 1789788893.4505322}, {"event_id": "d4c7191a54d741e3a6646c1a34890351", "step": 16, "value": 1.7280796573641481, "stage": "improve", "created_at": 1789788936.8862486}, {"event_id": "def7e8e00fe74166b8b6221027289c2f", "step": 17, "value": 1.5116932239480907, "stage": "improve", "created_at": 1789789592.7975726}, {"event_id": "22f735d9eee146e4bcaddd27a983569c", "step": 18, "value": 1.6776931863315632, "stage": "improve", "created_at": 1789789638.5020797}, {"event_id": "b596a5b6849b48a9a64c43254e372057", "step": 19, "value": 1.3817483731120097, "stage": "evolution", "created_at": 1789790358.5787523}, {"event_id": "05266a3b6a49419b92ef45a429a1d0ca", "step": 20, "value": 1.7874747801114779, "stage": "evolution", "created_at": 1789790356.959884}, {"event_id": "1b222705440d485ca26af5b3b93ec047", "step": 21, "value": 1.550963832934715, "stage": "improve", "created_at": 1789791030.2141016}, {"event_id": "f7d29862dbc14a01bb70716f7cf5d5db", "step": 22, "value": 1.6875006928954528, "stage": "improve", "created_at": 1789791016.893615}, {"event_id": "b68146b50a73400e9db9c51f7b777ed8", "step": 25, "value": 1.3387269012031369, "stage": "evolution", "created_at": 1789791788.4665277}, {"event_id": "3525d34a079e4ddc8ef5fc47494ffb34", "step": 26, "value": 1.8187827989061403, "stage": "debug", "created_at": 1789791751.984196}, {"event_id": "196c9e9897aa43ea8f9c88a99dd03055", "step": 27, "value": 1.7494907859104365, "stage": "debug", "created_at": 1789792310.8955662}, {"event_id": "e3fc6f413a21418fa68576792fcee81a", "step": 28, "value": 1.7534153832459916, "stage": "improve", "created_at": 1789792391.0361133}, {"event_id": "05c6bbc70f974cd7b52a2cf37c45e96a", "step": 29, "value": 1.7303361267526352, "stage": "evolution", "created_at": 1789792907.8036737}, {"event_id": "41a98c8bce29412d9a4e385c61c0d29e", "step": 30, "value": 1.2469396589082447, "stage": "evolution", "created_at": 1789792931.8515332}, {"event_id": "2b5b9a9db3a047e5aac9c3c208247c5f", "step": 31, "value": 1.818119280751251, "stage": "improve", "created_at": 1789793510.0769506}, {"event_id": "c82adfa11a6e4265b9165350f32a6277", "step": 32, "value": 1.5036385837020425, "stage": "improve", "created_at": 1789793607.270419}, {"event_id": "a785686b316c4f7693aecaf1ec885218", "step": 33, "value": 1.2641562198639782, "stage": "improve", "created_at": 1789794286.3782408}, {"event_id": "1c00b2f3a7284607b825a7de3466f542", "step": 34, "value": 1.2437450281740063, "stage": "improve", "created_at": 1789794315.842089}, {"event_id": "0c14b925d50349eabe9a76d6f2ed3947", "step": 35, "value": 1.3652489240739285, "stage": "improve", "created_at": 1789794902.327977}, {"event_id": "407f36be27fc4ae58af1fcb1dda92155", "step": 36, "value": 1.4966304963202746, "stage": "improve", "created_at": 1789794882.1193714}, {"event_id": "600a7cdb2f9c4ac6ab65fe2f0ede6e3d", "step": 37, "value": 1.612181729072465, "stage": "improve", "created_at": 1789795485.0003626}, {"event_id": "ee7cd19c29f44cf896d08034ddb024ef", "step": 38, "value": 1.4976809686014394, "stage": "improve", "created_at": 1789795477.9066439}, {"event_id": "48599267922d480c9588d3bbc6b7fe82", "step": 40, "value": 4.859499363287707, "stage": "improve", "created_at": 1789796014.619707}, {"event_id": "5ca52ee0d27b41bd874fad0e24d2c594", "step": 41, "value": 1.2186195840066145, "stage": "fusion", "created_at": 1789796597.6075995}, {"event_id": "4c7ab33580254ba68419bfbda5f25dfc", "step": 42, "value": 1.2837420375092443, "stage": "evolution", "created_at": 1789796673.3619943}, {"event_id": "5ae6d0c519bd470286e7957b451bf739", "step": 43, "value": 1.2307848182399612, "stage": "improve", "created_at": 1789797347.17153}, {"event_id": "30ced4521b4a47f6a55a6e7344648458", "step": 44, "value": 1.4653256196618123, "stage": "improve", "created_at": 1789797351.812049}, {"event_id": "cb0fedffdae043fc9e06090505f61402", "step": 45, "value": 1.2118563651998477, "stage": "fusion", "created_at": 1789797994.8213384}, {"event_id": "164228a4e7154f04979878f0b5f13c85", "step": 46, "value": 1.250687617178236, "stage": "fusion", "created_at": 1789798008.9026492}, {"event_id": "50fa5e3c93884887b9084fd15fa248b6", "step": 47, "value": 1.2149086100002355, "stage": "improve", "created_at": 1789798750.415307}, {"event_id": "0d471e70bd6a4111a45a99d8578fa5bd", "step": 48, "value": 1.156751316127494, "stage": "improve", "created_at": 1789799022.898719}, {"event_id": "900896192c58418f9c4da3f73eb21e86", "step": 49, "value": 1.2149323908754817, "stage": "improve", "created_at": 1789799810.8396626}, {"event_id": "713421961a1a48c1a28a72ef69dda190", "step": 50, "value": 1.2413632464029623, "stage": "improve", "created_at": 1789799933.0098388}, {"event_id": "43166c1a8bce472893ac434afe465419", "step": 52, "value": 1.1309563601977168, "stage": "improve", "created_at": 1789800957.1873755}, {"event_id": "3805393b9af244f7a82f197830ea614b", "step": 53, "value": 1.1831033996689024, "stage": "debug", "created_at": 1789801536.4449134}, {"event_id": "6b47b8c5d3d44c0db85d9844fbdaa092", "step": 54, "value": 1.2592301195959616, "stage": "improve", "created_at": 1789801639.2399712}, {"event_id": "a6d49c0fe6e24ebd866c531fd55742c2", "step": 58, "value": 1.1566949285338766, "stage": "debug", "created_at": 1789802582.8566904}, {"event_id": "11769862bd904c5fbe50191c25f92639", "step": 59, "value": 1.211922528772039, "stage": "debug", "created_at": 1789803038.6340818}, {"event_id": "4a86eb9dcf7c4a338a5cb3804dfb9c98", "step": 60, "value": 1.28942388449855, "stage": "evolution", "created_at": 1789803084.6429386}], "curve_scope": "已审计的预算内 best-so-far；横轴为对应原始节点 step，时间模式为 active seconds，保留完整已记录范围。", "official_score": null}, {"id": "xixian.e06.seed42", "experiment_id": "nanogpt-study7-20260918", "family": "nanoGPT", "method": "seven_e06_mcgs_original", "dataset": "nanoGPT", "seed": 42, "status": "completed", "best_valid_bpb": 1.1388738191222716, "budget_seconds": 21600, "artifacts": [{"bundle_id": "study7-complete-for-gpt-20260919", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/study7-complete-for-gpt-20260919/logs-ee645141ae41.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/study7-complete-for-gpt-20260919", "member": "study7_complete_for_gpt_20260919/raw/study7_20260918/analysis/summary.json", "sha256": "ee645141ae417cc245c3e1412a8331050e8000178b3fca386cb53d5263f29def"}, {"bundle_id": "study7-complete-for-gpt-20260919", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/study7-complete-for-gpt-20260919/logs-ee645141ae41.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/study7-complete-for-gpt-20260919", "member": "study7_complete_for_gpt_20260919/raw/study7_20260918/seven_e06_mcgs_original/runs/20260918_214613_seven_e06_mcgs_original/logs/journal.json", "sha256": "ee645141ae417cc245c3e1412a8331050e8000178b3fca386cb53d5263f29def"}], "coverage": {"method": "E06", "preset": "seven_e06_mcgs_original", "state": "finished", "best_valid_bpb": 1.1388738191222716, "raw_outcomes": 56, "valid_outcomes": 49, "failed_outcomes": 7, "censored_outcomes": 0, "required_logs_preserved": 9, "trial_directories": 56, "candidate_files": 56, "train_logs": 56, "result_files": 49, "interrupted_archives": 3, "log_directory": "raw/study7_20260918/seven_e06_mcgs_original/runs/20260918_214613_seven_e06_mcgs_original/logs"}, "note": "预算内有效结果；恢复快照和 interrupted-state 保留在资料包中。", "journal_ref": "study7-complete-for-gpt-20260919:study7_complete_for_gpt_20260919/raw/study7_20260918/seven_e06_mcgs_original/runs/20260918_214613_seven_e06_mcgs_original/logs/journal.json", "metrics": [{"event_id": "626c3d6656d14be7be0fffde0fa38f62", "step": 2, "value": 1.7512762196100433, "elapsed_seconds": 1483.7028169631958}, {"event_id": "608c12be3db943d48cb463c24b58aff3", "step": 15, "value": 1.7177570663660682, "elapsed_seconds": 7615.30818104744}, {"event_id": "7dc64d4aa4a444d7a8f2197f3651e482", "step": 22, "value": 1.617272384014328, "elapsed_seconds": 10081.669394731522}, {"event_id": "ebcd4b7d35954d878682a1d5d4337bc9", "step": 23, "value": 1.3524976405718128, "elapsed_seconds": 10769.080193042755}, {"event_id": "d56a2aef3a674d468dbb98074ffaf17f", "step": 25, "value": 1.307609870349695, "elapsed_seconds": 11390.813163280487}, {"event_id": "14c3f9765c25454dae5e6976643ce36d", "step": 31, "value": 1.2307610074129847, "elapsed_seconds": 13141.811091899872}, {"event_id": "ecf652941a624deba4315f19c703a9f7", "step": 41, "value": 1.1388738191222716, "elapsed_seconds": 16582.61132669449}], "maximize": false, "elapsed_seconds": 21600, "node_count": 57, "metric_name": "预算内 best-so-far BPB", "raw_metrics": [{"event_id": "626c3d6656d14be7be0fffde0fa38f62", "step": 2, "value": 1.7512762196100433, "stage": "draft", "created_at": 1789782400.8922064}, {"event_id": "ca321689e13a4f34942ff7deda8519a9", "step": 4, "value": 3.082355002358573, "stage": "debug", "created_at": 1789784053.120231}, {"event_id": "2d4efd9d30dd493e9f82ec280d0f9ce2", "step": 5, "value": 1.782181380841405, "stage": "improve", "created_at": 1789784747.2002482}, {"event_id": "34b57636514b47e5bf2c6411a7655aec", "step": 6, "value": 3.27911259093774, "stage": "debug", "created_at": 1789784593.1609735}, {"event_id": "85d17157a28a42a5a4000f8a5ded501f", "step": 7, "value": 3.127000398918275, "stage": "improve", "created_at": 1789785484.107861}, {"event_id": "b734ff6943b24d8d8e191181b58273b5", "step": 8, "value": 1.7975778428965672, "stage": "improve", "created_at": 1789785738.0839934}, {"event_id": "6551ef813c5d4582ab27d4c81ed6c50d", "step": 9, "value": 3.2096035270699486, "stage": "improve", "created_at": 1789786463.982695}, {"event_id": "d6f97e765c2a4a269c0c6bbc5713057b", "step": 10, "value": 3.0970102030148747, "stage": "improve", "created_at": 1789786402.9412894}, {"event_id": "e1ae9debbfc64e6295ccc79ee93c384f", "step": 11, "value": 3.0258681420505487, "stage": "improve", "created_at": 1789787557.5500844}, {"event_id": "f4d54d3e119a447d9416ed3f7ca3065b", "step": 12, "value": 1.8580432448047148, "stage": "improve", "created_at": 1789787653.7010975}, {"event_id": "6568bc254a0641baaac161d3a3b974e1", "step": 13, "value": 3.0172229837375517, "stage": "improve", "created_at": 1789788487.2258658}, {"event_id": "c80b71b950b04fbaa460616dc1470efc", "step": 14, "value": 3.068389195223636, "stage": "improve", "created_at": 1789788623.8732264}, {"event_id": "608c12be3db943d48cb463c24b58aff3", "step": 15, "value": 1.7177570663660682, "stage": "evolution", "created_at": 1789789352.4488893}, {"event_id": "1e78d4af8fe3490a8c3f03eda2ec8e9b", "step": 16, "value": 3.201945199201949, "stage": "improve", "created_at": 1789789386.985298}, {"event_id": "8b21289823954820857f45f6f9bbcb0c", "step": 17, "value": 3.1047102503153887, "stage": "improve", "created_at": 1789790397.8962138}, {"event_id": "013d81be96224c899ea3e588c4f63ab6", "step": 18, "value": 1.7540716843650361, "stage": "improve", "created_at": 1789790694.0067592}, {"event_id": "d764e7b682e24d77b3db7cebae0aaceb", "step": 19, "value": 3.090649548643807, "stage": "improve", "created_at": 1789791309.7652426}, {"event_id": "c4158016ac7946f4af5cf0d8148b7beb", "step": 20, "value": 3.3137144555736797, "stage": "improve", "created_at": 1789791347.18779}, {"event_id": "a6635f993eeb4d3082f3f3d9202fb08f", "step": 21, "value": 3.1333583610946936, "stage": "improve", "created_at": 1789792009.9291327}, {"event_id": "7dc64d4aa4a444d7a8f2197f3651e482", "step": 22, "value": 1.617272384014328, "stage": "improve", "created_at": 1789792168.0276475}, {"event_id": "ebcd4b7d35954d878682a1d5d4337bc9", "step": 23, "value": 1.3524976405718128, "stage": "evolution", "created_at": 1789792759.731369}, {"event_id": "56cf2042ce064212a200b6407457930d", "step": 24, "value": 1.877632659586246, "stage": "improve", "created_at": 1789792789.860207}, {"event_id": "d56a2aef3a674d468dbb98074ffaf17f", "step": 25, "value": 1.307609870349695, "stage": "improve", "created_at": 1789793457.5666528}, {"event_id": "7825b73c4a04496cbd2d7bfc134d84f6", "step": 26, "value": 1.8367182132396922, "stage": "improve", "created_at": 1789793473.3210592}, {"event_id": "4f5ea4b13b1643738ceedeec6081430f", "step": 29, "value": 1.6298209990659507, "stage": "improve", "created_at": 1789794453.0458047}, {"event_id": "72632648412441d6a7302f86abee27ce", "step": 30, "value": 1.4727220022419454, "stage": "draft", "created_at": 1789794356.865733}, {"event_id": "14c3f9765c25454dae5e6976643ce36d", "step": 31, "value": 1.2307610074129847, "stage": "debug", "created_at": 1789795175.6779137}, {"event_id": "022093d37fca40f79926bf0ad6dae6a0", "step": 32, "value": 1.4631878062498718, "stage": "improve", "created_at": 1789795300.815576}, {"event_id": "b9d207cd8b9c426aa2618999056606b6", "step": 33, "value": 1.3818625525694859, "stage": "improve", "created_at": 1789795952.267738}, {"event_id": "88229d381db34420b77781b90cf897cd", "step": 34, "value": 1.2551929848233518, "stage": "improve", "created_at": 1789795942.0982122}, {"event_id": "b14a44285e5449978d2c383a2159d534", "step": 35, "value": 1.4690235442982789, "stage": "improve", "created_at": 1789796683.856057}, {"event_id": "3e84203201a9478285ceb6ae4f8cc858", "step": 36, "value": 1.2466222010499255, "stage": "improve", "created_at": 1789796728.538274}, {"event_id": "cb3ecc14e35c4ef7a95cf2a4f06bfb41", "step": 38, "value": 1.4229219084495774, "stage": "improve", "created_at": 1789797364.9809513}, {"event_id": "1f570473809a4f1d93e8949a73292ca4", "step": 39, "value": 1.2636612317097162, "stage": "improve", "created_at": 1789798046.294241}, {"event_id": "f62cbc3f6c814a5db9008659a3072cae", "step": 40, "value": 1.2414751346196202, "stage": "improve", "created_at": 1789798081.2662914}, {"event_id": "ecf652941a624deba4315f19c703a9f7", "step": 41, "value": 1.1388738191222716, "stage": "fusion", "created_at": 1789798700.0357444}, {"event_id": "25e3f8084c5342b4a000047e9f497591", "step": 42, "value": 1.427152263965072, "stage": "improve", "created_at": 1789799092.59113}, {"event_id": "d441eadc482c4a8191f3659e6ec9603a", "step": 43, "value": 1.2858278689608758, "stage": "improve", "created_at": 1789799875.2672555}, {"event_id": "737d496d53b045cf91fadde6b3f7dbac", "step": 44, "value": 1.313587207000799, "stage": "improve", "created_at": 1789799849.0796745}, {"event_id": "c307b02dfe5240e18772f9da2a28eba9", "step": 47, "value": 1.2314919285426702, "stage": "debug", "created_at": 1789801329.487697}, {"event_id": "a50a63749376474185cc0e0fd9912a26", "step": 48, "value": 1.2525029906275775, "stage": "improve", "created_at": 1789801402.7385564}, {"event_id": "e865a1d75bf64b2fb29dd38b5d91a20d", "step": 49, "value": 1.2445893632614977, "stage": "debug", "created_at": 1789801955.9174626}, {"event_id": "47fb0f29141144a8bb28b30366c12051", "step": 50, "value": 1.2583398383543172, "stage": "evolution", "created_at": 1789802029.0427034}, {"event_id": "e52cc735dcc34e6a986acbef8f499816", "step": 51, "value": 1.7236835372580168, "stage": "improve", "created_at": 1789802675.452667}, {"event_id": "f3f4c7c30d424de68dc1d747f5c9d0d7", "step": 52, "value": 1.4986345764539284, "stage": "improve", "created_at": 1789802695.2928228}, {"event_id": "0ce10a8ad8d64a45925b61e5d384e3df", "step": 53, "value": 1.236815615202229, "stage": "improve", "created_at": 1789803281.001048}, {"event_id": "1cc3889f087748b59ada4f4dddae22b4", "step": 54, "value": 1.666574777057328, "stage": "fusion", "created_at": 1789803308.9067671}, {"event_id": "2be0d94b39e64442b154434fbaef9aef", "step": 55, "value": 1.271883427327084, "stage": "improve", "created_at": 1789803921.2091627}, {"event_id": "1a637fb2ba3f49fa88ce2ae9487ce50c", "step": 56, "value": 1.3298409243215679, "stage": "improve", "created_at": 1789803941.474704}], "curve_scope": "已审计的预算内 best-so-far；横轴为对应原始节点 step，时间模式为 active seconds，保留完整已记录范围。", "official_score": null}, {"id": "xixian.e07.seed42", "experiment_id": "nanogpt-study7-20260918", "family": "nanoGPT", "method": "seven_e07_parent_greedy_managed", "dataset": "nanoGPT", "seed": 42, "status": "completed", "best_valid_bpb": 1.1892053940908551, "budget_seconds": 21600, "artifacts": [{"bundle_id": "study7-complete-for-gpt-20260919", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/study7-complete-for-gpt-20260919/logs-ee645141ae41.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/study7-complete-for-gpt-20260919", "member": "study7_complete_for_gpt_20260919/raw/study7_20260918/analysis/summary.json", "sha256": "ee645141ae417cc245c3e1412a8331050e8000178b3fca386cb53d5263f29def"}, {"bundle_id": "study7-complete-for-gpt-20260919", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/study7-complete-for-gpt-20260919/logs-ee645141ae41.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/study7-complete-for-gpt-20260919", "member": "study7_complete_for_gpt_20260919/raw/study7_20260918/seven_e07_parent_greedy_managed/runs/20260918_214613_seven_e07_parent_greedy_managed/logs/journal.json", "sha256": "ee645141ae417cc245c3e1412a8331050e8000178b3fca386cb53d5263f29def"}], "coverage": {"method": "E07", "preset": "seven_e07_parent_greedy_managed", "state": "finished", "best_valid_bpb": 1.1892053940908551, "raw_outcomes": 62, "valid_outcomes": 48, "failed_outcomes": 12, "censored_outcomes": 2, "required_logs_preserved": 9, "trial_directories": 62, "candidate_files": 62, "train_logs": 62, "result_files": 48, "interrupted_archives": 3, "log_directory": "raw/study7_20260918/seven_e07_parent_greedy_managed/runs/20260918_214613_seven_e07_parent_greedy_managed/logs"}, "note": "预算内有效结果；恢复快照和 interrupted-state 保留在资料包中。", "journal_ref": "study7-complete-for-gpt-20260919:study7_complete_for_gpt_20260919/raw/study7_20260918/seven_e07_parent_greedy_managed/runs/20260918_214613_seven_e07_parent_greedy_managed/logs/journal.json", "metrics": [{"event_id": "c75b70cb6c5640538c27c6d7c6844662", "step": 2, "value": 1.7850440535521495, "elapsed_seconds": 1467.3055131435394}, {"event_id": "596131dba72b4d9bb90ae813eaac71b7", "step": 5, "value": 1.7410812106035332, "elapsed_seconds": 2596.557191133499}, {"event_id": "c096ee36cfcd4a298d33e638d10832da", "step": 9, "value": 1.6863699805940684, "elapsed_seconds": 3925.0826621055603}, {"event_id": "2a90ec2f29584182bf650e4ad6f73aa6", "step": 17, "value": 1.6510266439653234, "elapsed_seconds": 6310.270253658295}, {"event_id": "b26a50ebf7b14752a18cc5da124d59f4", "step": 23, "value": 1.5742697469516167, "elapsed_seconds": 8314.118368387222}, {"event_id": "241a370fdb13426495b447b23c0eb686", "step": 26, "value": 1.5340282515582546, "elapsed_seconds": 9069.375188827515}, {"event_id": "ccd430c168b542a19bee6b91211bb66d", "step": 35, "value": 1.2504130186487319, "elapsed_seconds": 12519.630789279938}, {"event_id": "54e425b35d0144ae926cb4c7b0d01c61", "step": 42, "value": 1.1892053940908551, "elapsed_seconds": 14649.554210662842}], "maximize": false, "elapsed_seconds": 21600, "node_count": 61, "metric_name": "预算内 best-so-far BPB", "raw_metrics": [{"event_id": "c75b70cb6c5640538c27c6d7c6844662", "step": 2, "value": 1.7850440535521495, "stage": "draft", "created_at": 1789782400.9331365}, {"event_id": "596131dba72b4d9bb90ae813eaac71b7", "step": 5, "value": 1.7410812106035332, "stage": "improve", "created_at": 1789784458.0701451}, {"event_id": "570e941ae840410bb16990049a94b338", "step": 6, "value": 3.3000255246309473, "stage": "debug", "created_at": 1789784380.2178283}, {"event_id": "64a6afb424214a2994d10eda43e8f573", "step": 7, "value": 3.076219031758575, "stage": "debug", "created_at": 1789785162.7116175}, {"event_id": "b2add9343cd046e7a32b8498c86f465a", "step": 8, "value": 1.8397681106231272, "stage": "improve", "created_at": 1789785136.115327}, {"event_id": "c096ee36cfcd4a298d33e638d10832da", "step": 9, "value": 1.6863699805940684, "stage": "improve", "created_at": 1789785780.9641938}, {"event_id": "9f4b66af3e0443eaab54d7abe10a0d1f", "step": 10, "value": 1.778634670378053, "stage": "improve", "created_at": 1789785778.108836}, {"event_id": "6a204f143fba4e0ea3b47cec83c2a4c6", "step": 11, "value": 1.7409806621120147, "stage": "improve", "created_at": 1789786407.8748634}, {"event_id": "186ffa84b4734ad794bf60ad46146b02", "step": 12, "value": 1.7241649342488425, "stage": "improve", "created_at": 1789786398.6309552}, {"event_id": "6cce4ec042634c1786686795fa624c1a", "step": 13, "value": 3.074706468307067, "stage": "evolution", "created_at": 1789786966.562764}, {"event_id": "d49150db877d48f88cfefae41de4bb6f", "step": 14, "value": 1.7699550309673946, "stage": "evolution", "created_at": 1789786935.02875}, {"event_id": "1f3e3ec014dd4a7a9df96b39f2a3a14b", "step": 15, "value": 1.7180532131022728, "stage": "evolution", "created_at": 1789787565.3410242}, {"event_id": "5dd0d34d86c54fcea45203c734b5426d", "step": 16, "value": 1.882640574270552, "stage": "evolution", "created_at": 1789787574.4356751}, {"event_id": "2a90ec2f29584182bf650e4ad6f73aa6", "step": 17, "value": 1.6510266439653234, "stage": "evolution", "created_at": 1789788187.8442912}, {"event_id": "84b5dddcf0a24e199a650f9415533220", "step": 18, "value": 1.8194327261638312, "stage": "evolution", "created_at": 1789788270.1788955}, {"event_id": "b713c48670df4ce79bea268053fd763e", "step": 19, "value": 1.7231564267381443, "stage": "improve", "created_at": 1789788829.645368}, {"event_id": "6790d29e06ae42528b09a62ac8813bb5", "step": 20, "value": 1.740177562237396, "stage": "improve", "created_at": 1789788904.9020956}, {"event_id": "7bec3052de524e59a8c872bec9de81fb", "step": 21, "value": 1.718478145090898, "stage": "evolution", "created_at": 1789789448.379237}, {"event_id": "e1a16358491a4abdaf61fbbfb11a1f2b", "step": 22, "value": 1.7015732462670867, "stage": "improve", "created_at": 1789789477.7979722}, {"event_id": "b26a50ebf7b14752a18cc5da124d59f4", "step": 23, "value": 1.5742697469516167, "stage": "evolution", "created_at": 1789790405.844136}, {"event_id": "ced10e7bd0124e0d974783213528fa3b", "step": 24, "value": 1.6287791005674597, "stage": "evolution", "created_at": 1789790436.5530999}, {"event_id": "241a370fdb13426495b447b23c0eb686", "step": 26, "value": 1.5340282515582546, "stage": "improve", "created_at": 1789791094.8263724}, {"event_id": "576865ffce194896bebf6ae14214d957", "step": 27, "value": 1.7335445385442805, "stage": "debug", "created_at": 1789791690.0147617}, {"event_id": "3e7fb8ea60c742b189cb376f192e77f6", "step": 28, "value": 2.1158833603463885, "stage": "improve", "created_at": 1789791809.3195155}, {"event_id": "cae984b1ffe141d29aad79baafe06751", "step": 30, "value": 1.7477583598515074, "stage": "improve", "created_at": 1789792510.0629516}, {"event_id": "f364afd80f044815abda957c9f6387fa", "step": 32, "value": 1.590548615472578, "stage": "evolution", "created_at": 1789793251.932292}, {"event_id": "6b07fa09672f4dcba33369436916a8e7", "step": 33, "value": 1.695504326010178, "stage": "improve", "created_at": 1789793940.4139814}, {"event_id": "958c269ab5ae476e83c404e509cf6715", "step": 34, "value": 1.6854205610584436, "stage": "improve", "created_at": 1789793967.420532}, {"event_id": "ccd430c168b542a19bee6b91211bb66d", "step": 35, "value": 1.2504130186487319, "stage": "fusion", "created_at": 1789794593.0641677}, {"event_id": "4930fec45e3f4cca860900ac54ec6279", "step": 36, "value": 1.6360543817453759, "stage": "evolution", "created_at": 1789794610.253663}, {"event_id": "26e4d82111ba4c0fb346a5c6f5076952", "step": 37, "value": 1.3341326458741924, "stage": "improve", "created_at": 1789795265.575249}, {"event_id": "d6f6909b73e944d2af3e5e3f927db759", "step": 38, "value": 1.5034888704434195, "stage": "improve", "created_at": 1789795268.126359}, {"event_id": "5408a52ba6e54b55b367bc235b7e1d06", "step": 39, "value": 1.3192758737994446, "stage": "fusion", "created_at": 1789795894.1116598}, {"event_id": "5a49138dcb244aadbf4eea0510a13f6b", "step": 40, "value": 1.385770579809056, "stage": "fusion", "created_at": 1789795901.1969392}, {"event_id": "54e425b35d0144ae926cb4c7b0d01c61", "step": 42, "value": 1.1892053940908551, "stage": "improve", "created_at": 1789796736.801306}, {"event_id": "420e0f6791aa4bf4b09c3f4b83a6ae57", "step": 43, "value": 1.207812848046281, "stage": "debug", "created_at": 1789797288.8418531}, {"event_id": "55c4247b9a63470fbda2d889a4eec59a", "step": 44, "value": 1.2621741763499092, "stage": "improve", "created_at": 1789797414.9754174}, {"event_id": "8ac1d4744cd54b79b9b09b6ad25784e3", "step": 46, "value": 1.1898149610589988, "stage": "improve", "created_at": 1789798060.2317822}, {"event_id": "b59bacb123d845bc85950bfb53ff3157", "step": 47, "value": 1.3007937215105119, "stage": "debug", "created_at": 1789798635.4117615}, {"event_id": "08b6acf0a4384fafae6b0605e89c5794", "step": 48, "value": 1.35721896205697, "stage": "improve", "created_at": 1789798752.9997673}, {"event_id": "2a11791247fe47f18e671a0d679e5a42", "step": 51, "value": 1.2896814310420062, "stage": "improve", "created_at": 1789800124.260349}, {"event_id": "bbd4716c270141a29c865f4814647667", "step": 52, "value": 1.8683443782499984, "stage": "improve", "created_at": 1789800076.102817}, {"event_id": "95fb3ba368e64d07910c801d09d5679f", "step": 53, "value": 1.2482193085187558, "stage": "evolution", "created_at": 1789800910.9468737}, {"event_id": "1bef76045fdf415183bbf4e3d0fb4557", "step": 55, "value": 1.5391590974625486, "stage": "evolution", "created_at": 1789801602.6767478}, {"event_id": "1b361ab299724d8e81660e8387509dfc", "step": 56, "value": 1.5446826251958072, "stage": "fusion", "created_at": 1789801640.364653}, {"event_id": "12cb4b902c694dad9b4a87d723ead6f3", "step": 58, "value": 1.5259832875847974, "stage": "fusion", "created_at": 1789802337.7826803}, {"event_id": "0ec0086571304e7da2fe16430c2f9387", "step": 59, "value": 1.5483786027035584, "stage": "fusion", "created_at": 1789803018.4913917}, {"event_id": "da3f322110644d70837e021eef89ec44", "step": 60, "value": 1.2838365961871525, "stage": "evolution", "created_at": 1789803056.4867868}], "curve_scope": "已审计的预算内 best-so-far；横轴为对应原始节点 step，时间模式为 active seconds，保留完整已记录范围。", "official_score": null}, {"id": "xixian.20260916-003927-gp7-long-horizon-logei", "experiment_id": "nanogpt-autoresearch-full-workflow-8h-20260916-043851", "family": "nanoGPT", "method": "gp7_long_horizon_logei", "dataset": "nanoGPT", "status": "archived", "artifacts": [{"bundle_id": "03-historical-run-logs", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/03-historical-run-logs/logs-18799fb1fca5.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/03-historical-run-logs", "member": "MLEvolve_BO/runs/autoresearch_full_workflow_8h_20260916_043851/gp7_long_horizon_logei/runs/20260916_003927_gp7_long_horizon_logei/logs/journal.json", "sha256": "18799fb1fca5aa0c206be70e600c8d13ba65086d8360620e18525cd877b72d9b"}], "curve_scope": "原始 journal 候选 BPB，未按预算或恢复边界重新审计。", "journal_ref": "03-historical-run-logs:MLEvolve_BO/runs/autoresearch_full_workflow_8h_20260916_043851/gp7_long_horizon_logei/runs/20260916_003927_gp7_long_horizon_logei/logs/journal.json", "metrics": [{"event_id": "ea21f3e9391949b3942720de58ea1656", "step": 1, "value": 1.8704910465915225, "stage": "draft", "created_at": 1789533796.8462727}, {"event_id": "5b3e195ea4eb48389ea72c81b0c3188e", "step": 2, "value": 2.159904279167827, "stage": "draft", "created_at": 1789534523.5315218}, {"event_id": "82c6193c01f344d8aeb8286c204324cb", "step": 3, "value": 1.4088880065214309, "stage": "draft", "created_at": 1789571730.3371985}, {"event_id": "d3f2794f935845b69fc3942913654428", "step": 4, "value": 1.8768211255705767, "stage": "improve", "created_at": 1789571939.0588777}, {"event_id": "117ea2b7cb964f1fb5423a646caf1765", "step": 5, "value": 1.8737933918020635, "stage": "improve", "created_at": 1789571924.3318925}, {"event_id": "972086fada464c20b17dfe5976c4a5f6", "step": 7, "value": 1.4297777141785586, "stage": "improve", "created_at": 1789572488.2197683}, {"event_id": "bb916a8ba6b8496c81d3d84d18c52c8c", "step": 8, "value": 1.8596550090529906, "stage": "improve", "created_at": 1789572569.001697}, {"event_id": "13bb02956520467885b14a5f2c94e21c", "step": 9, "value": 1.6097780081913586, "stage": "debug", "created_at": 1789572874.2589178}, {"event_id": "cb491d43cd8c4e5abf59fdeeee45fda5", "step": 12, "value": 1.2379862070346075, "stage": "improve", "created_at": 1789574453.285879}, {"event_id": "972428c421924a67ae71e7cfaf62d281", "step": 13, "value": 1.2721991630940226, "stage": "improve", "created_at": 1789574473.1428378}, {"event_id": "2964cac03ff14b48a556e747952928e8", "step": 14, "value": 1.639350622127662, "stage": "improve", "created_at": 1789574461.5595582}, {"event_id": "39160a37ac8743a6a071d7e4f703069a", "step": 15, "value": 1.280639158975773, "stage": "improve", "created_at": 1789575062.884728}, {"event_id": "b56a9e7a88034e96b57f05458a1ad0db", "step": 16, "value": 1.2257090719383168, "stage": "improve", "created_at": 1789575129.6189046}, {"event_id": "88ec713a834a431599a1957d809d9d7f", "step": 17, "value": 1.3240708592360073, "stage": "improve", "created_at": 1789575106.5857964}, {"event_id": "6f5310b395814c2a988a4953e9db2c29", "step": 18, "value": 1.2682668765502323, "stage": "improve", "created_at": 1789575668.3190465}, {"event_id": "9c34c12acba44908a39439ec5604e8af", "step": 19, "value": 1.2964711982639103, "stage": "improve", "created_at": 1789575704.772728}, {"event_id": "bc433517dbc94ddcad789b2d1279d460", "step": 20, "value": 1.32145746878726, "stage": "evolution", "created_at": 1789575635.955147}, {"event_id": "0748053b33d24d449dfa587775e981cb", "step": 22, "value": 1.2356218291491643, "stage": "evolution", "created_at": 1789576198.5852895}, {"event_id": "0a9d8d99cbe04ade878040403ceed95e", "step": 23, "value": 1.2121476168914693, "stage": "improve", "created_at": 1789576259.8006015}, {"event_id": "8016eb717a7043c6ba36914015045038", "step": 24, "value": 1.884115125648178, "stage": "debug", "created_at": 1789576391.0195441}, {"event_id": "e0239c76719b4f0dbc7f8d3c6a07f90d", "step": 25, "value": 1.22501015003935, "stage": "evolution", "created_at": 1789576757.6732278}, {"event_id": "25b3ef6ca3c841f4a4e2d4b5720ddcf0", "step": 26, "value": 1.3991460421977244, "stage": "improve", "created_at": 1789576855.8052313}, {"event_id": "aba242f7a0d347608b765d34046b50e9", "step": 27, "value": 1.125631652583507, "stage": "improve", "created_at": 1789577200.222144}, {"event_id": "4e4b223ca101452897d0cb2657cdc68b", "step": 28, "value": 1.3126738988688023, "stage": "improve", "created_at": 1789577386.464965}, {"event_id": "158e2d2ca9ed4cd58d06ee1a5df247bd", "step": 29, "value": 1.422392077780107, "stage": "improve", "created_at": 1789577445.9750268}, {"event_id": "3e8948117d83485ea4e576f06e5679a8", "step": 30, "value": 1.0972387192323412, "stage": "improve", "created_at": 1789577772.7479956}, {"event_id": "428bcc694c804edeb30707d875c552da", "step": 31, "value": 1.188892854839147, "stage": "improve", "created_at": 1789578049.8600526}, {"event_id": "bee1905e01e74080995eeabfae68e8bf", "step": 32, "value": 1.2638795377589869, "stage": "improve", "created_at": 1789578056.4742873}, {"event_id": "fac820ae6598451eb0f9993f6f743f45", "step": 33, "value": 1.4841338093158465, "stage": "improve", "created_at": 1789578351.3080924}, {"event_id": "b73c233e2ce842d1a3d238d127bca491", "step": 34, "value": 1.29993908788659, "stage": "improve", "created_at": 1789578734.5915701}, {"event_id": "d089ab456aec46b88ab5c6e92b91e4f0", "step": 35, "value": 1.3699129869025877, "stage": "improve", "created_at": 1789578868.5087419}, {"event_id": "7d2d4adc5b734f0a9ab73c573d56eb12", "step": 37, "value": 1.256718166339854, "stage": "evolution", "created_at": 1789579126.6412194}, {"event_id": "814337c448dc4ea583a2c3767b68f520", "step": 38, "value": 1.3649612407649108, "stage": "draft", "created_at": 1789579421.766776}, {"event_id": "2dff30e3985c4dd1bef5eaa6b9b10a36", "step": 39, "value": 1.8650274876804493, "stage": "debug", "created_at": 1789579571.2688966}, {"event_id": "3eaab159f7fd43f3a12e5861d4b3e1ea", "step": 40, "value": 1.1938425070180703, "stage": "evolution", "created_at": 1789579651.486043}, {"event_id": "8986d16eb385499d828db9d0fbc9afab", "step": 44, "value": 1.1383533901013039, "stage": "evolution", "created_at": 1789580058.0449226}, {"event_id": "1df0fe4ea3624527a4c067e9e753dd68", "step": 45, "value": 1.2148662639775205, "stage": "evolution", "created_at": 1789580179.15785}, {"event_id": "db1703a27e854a529ee0724b5d6e4bc1", "step": 49, "value": 1.854997887171781, "stage": "evolution", "created_at": 1789580848.5517206}, {"event_id": "4eafb15745624534a278d0c9d641d48b", "step": 50, "value": 1.2912621019330097, "stage": "debug", "created_at": 1789580815.632616}, {"event_id": "d64ba31af2f84de88c7015d8b33f4e5f", "step": 51, "value": 1.1356248412394112, "stage": "debug", "created_at": 1789581216.8021655}, {"event_id": "4215c86c7bfd432196a56bc79a734bff", "step": 52, "value": 1.2515773415839322, "stage": "evolution", "created_at": 1789581372.3410149}, {"event_id": "c02ec03f4b2d49d0865bb6ed755f3d78", "step": 53, "value": 1.225954674929748, "stage": "evolution", "created_at": 1789581439.8888335}, {"event_id": "eecae2ee81f04b008f873780e1680dc2", "step": 54, "value": 1.1884838695511577, "stage": "evolution", "created_at": 1789581756.6447775}, {"event_id": "62047bd816fb408b858b5e190d15bc31", "step": 55, "value": 1.2715180912283208, "stage": "evolution", "created_at": 1789581961.3957567}, {"event_id": "4e3eb6e5c11b4b6189a1ea10ce1bcd7b", "step": 56, "value": 1.3151515850822821, "stage": "evolution", "created_at": 1789581975.0367596}, {"event_id": "f594e8cd4a89477f8eb99645fc8c2f37", "step": 58, "value": 1.1586449778091819, "stage": "evolution", "created_at": 1789582395.3854544}, {"event_id": "9b9c1160fa724862bd95b027f26a125b", "step": 59, "value": 1.2424305866999907, "stage": "evolution", "created_at": 1789582496.0414226}, {"event_id": "d8e2d8df7c4e409185e3a749bc7904fc", "step": 60, "value": 1.1835508465729674, "stage": "evolution", "created_at": 1789582761.750563}, {"event_id": "740c6d2d69f4406d97fbb43a68430d79", "step": 61, "value": 1.2001518918806569, "stage": "evolution", "created_at": 1789582955.8332014}, {"event_id": "eb58d71265234a5a91af8893dc3da554", "step": 62, "value": 1.185535593729903, "stage": "evolution", "created_at": 1789583159.1239457}, {"event_id": "31284b9f117d4c0f8e98b21ca136111f", "step": 63, "value": 1.1696043994378658, "stage": "evolution", "created_at": 1789583341.8624988}, {"event_id": "dcebc754243147fe893826511da653ed", "step": 64, "value": 1.1865283735203946, "stage": "evolution", "created_at": 1789583524.9102318}, {"event_id": "def5ca6caf4a4475b4e6b50cd601dc8a", "step": 65, "value": 1.203287916063969, "stage": "evolution", "created_at": 1789583718.5998368}, {"event_id": "780eee9a05ef40cabbfaf61ccab525a0", "step": 66, "value": 1.2754384974515172, "stage": "evolution", "created_at": 1789583907.3801548}, {"event_id": "f7362db50b26457899cb7817e49c6fe2", "step": 67, "value": 1.154917963253412, "stage": "evolution", "created_at": 1789584167.7687905}, {"event_id": "34ceb6f3ac5647d18601fc8270369f49", "step": 69, "value": 1.173820733683075, "stage": "evolution", "created_at": 1789584303.3079612}, {"event_id": "92f841101b4449e6aac33a9c54845372", "step": 72, "value": 1.2281486013777771, "stage": "evolution", "created_at": 1789589588.186069}, {"event_id": "03d149f7655f4be1800895f3d1940f92", "step": 73, "value": 1.2240681199284182, "stage": "evolution", "created_at": 1789589577.2582736}, {"event_id": "02b699528a8141bf994df85424973b45", "step": 74, "value": 1.2274208082736984, "stage": "evolution", "created_at": 1789589604.1743293}, {"event_id": "7e78a46470e24dae86f3657e3ec80f48", "step": 75, "value": 1.2402207924907753, "stage": "evolution", "created_at": 1789590142.5782554}, {"event_id": "1ed4ca794f194cf0b5670b51a82f5b67", "step": 76, "value": 1.5114392602971876, "stage": "fusion", "created_at": 1789590152.0306258}, {"event_id": "0f243a6c5efa49ae9eeb14adcaf3f397", "step": 77, "value": 1.4171707619419052, "stage": "fusion", "created_at": 1789590183.6583931}, {"event_id": "86117e5782554473bed798340eba6328", "step": 80, "value": 1.4159145919587914, "stage": "fusion", "created_at": 1789590667.1655152}, {"event_id": "994923e9327741ba950e605a23d2d5bf", "step": 81, "value": 1.1901085939797484, "stage": "debug", "created_at": 1789590861.6045346}, {"event_id": "b285323d765c4ec8bddc23a953325193", "step": 82, "value": 1.226991085339393, "stage": "evolution", "created_at": 1789591173.2904882}, {"event_id": "7a5b02fb1347407b87fe19203d2d97e3", "step": 83, "value": 1.2806804889026733, "stage": "fusion", "created_at": 1789591222.777464}, {"event_id": "d0680d2fe384452b98c2095c68b732ee", "step": 84, "value": 1.3851325931747764, "stage": "evolution", "created_at": 1789591368.2085643}], "maximize": false, "elapsed_seconds": 17274.923844337463, "node_count": 85, "metric_name": "BPB", "versions": [{"bundle_id": "03-historical-run-logs", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/03-historical-run-logs/logs-18799fb1fca5.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/03-historical-run-logs", "member": "MLEvolve_BO/runs/autoresearch_full_workflow_8h_20260916_043851/gp7_long_horizon_logei/runs/20260916_003927_gp7_long_horizon_logei/logs/journal.json", "sha256": "18799fb1fca5aa0c206be70e600c8d13ba65086d8360620e18525cd877b72d9b"}], "official_score": null, "note": ""}, {"id": "xixian.20260916-003927-mlevolve-original", "experiment_id": "nanogpt-autoresearch-full-workflow-8h-20260916-043851", "family": "nanoGPT", "method": "mlevolve_original", "dataset": "nanoGPT", "status": "archived", "artifacts": [{"bundle_id": "03-historical-run-logs", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/03-historical-run-logs/logs-18799fb1fca5.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/03-historical-run-logs", "member": "MLEvolve_BO/runs/autoresearch_full_workflow_8h_20260916_043851/mlevolve_original/runs/20260916_003927_mlevolve_original/logs/journal.json", "sha256": "18799fb1fca5aa0c206be70e600c8d13ba65086d8360620e18525cd877b72d9b"}], "curve_scope": "原始 journal 候选 BPB，未按预算或恢复边界重新审计。", "journal_ref": "03-historical-run-logs:MLEvolve_BO/runs/autoresearch_full_workflow_8h_20260916_043851/mlevolve_original/runs/20260916_003927_mlevolve_original/logs/journal.json", "metrics": [{"event_id": "a5e58eec13fa45399968b84c40f75833", "step": 2, "value": 1.6116203955722879, "stage": "draft", "created_at": 1789534451.7537103}, {"event_id": "51a31aa7276045c997c15eaef655e24e", "step": 3, "value": 2.6280146525576393, "stage": "draft", "created_at": 1789533816.0594666}, {"event_id": "6f781864400f4555bb783d267130ff31", "step": 4, "value": 1.7156924927890305, "stage": "debug", "created_at": 1789534607.9044979}, {"event_id": "9f9f5fb2825f4110a3adc99078be98f4", "step": 5, "value": 1.2824994755956547, "stage": "improve", "created_at": 1789535197.1050227}, {"event_id": "c304f76de46d4d54be0e36240045ff17", "step": 6, "value": 2.627731543476892, "stage": "improve", "created_at": 1789535231.8884246}, {"event_id": "733ee76da9a94f6484385944019b97d8", "step": 7, "value": 1.6288074410279083, "stage": "improve", "created_at": 1789535263.7827897}, {"event_id": "031adf3b674f4d97beb94eff7bd59726", "step": 8, "value": 1.3168626980223146, "stage": "improve", "created_at": 1789535946.7509794}, {"event_id": "c7300696e6694b3db1ce47139754da54", "step": 9, "value": 2.627519000273675, "stage": "improve", "created_at": 1789535947.0048826}, {"event_id": "26bcd49fb8794f1bbbaa67ee6e62ac27", "step": 10, "value": 1.474207816368764, "stage": "improve", "created_at": 1789535969.3359015}, {"event_id": "b0d37e7a9e334a648000512be8abebfd", "step": 11, "value": 1.4704320325418498, "stage": "improve", "created_at": 1789536636.517713}, {"event_id": "98ee6fa66d354c97b8586cff91a0996e", "step": 12, "value": 2.6274369631496297, "stage": "improve", "created_at": 1789536607.558722}, {"event_id": "180b3526af244b41845987004a6727c5", "step": 13, "value": 1.5247344362071744, "stage": "improve", "created_at": 1789536678.9230306}, {"event_id": "0866d16eabf146aeb238c2dac8064a0e", "step": 18, "value": 1.2932835735056563, "stage": "improve", "created_at": 1789537328.0951798}, {"event_id": "2d9002f376084af0a13752ff19a5a98e", "step": 19, "value": 1.6202962747761491, "stage": "improve", "created_at": 1789537268.5032325}, {"event_id": "402be3d1adad4103aabdf05746f04aad", "step": 21, "value": 1.311774802633215, "stage": "improve", "created_at": 1789537943.9146514}, {"event_id": "655ed8dec9884786871381f7734c6e1f", "step": 22, "value": 1.249266591273427, "stage": "evolution", "created_at": 1789537919.5405803}, {"event_id": "229ffdfd93424a4f997d6213bdde13b9", "step": 23, "value": 4.20277580530344, "stage": "debug", "created_at": 1789538187.1788428}, {"event_id": "f3b830d2effd4a979a8f8b32ffb31501", "step": 24, "value": 1.2902916572144567, "stage": "improve", "created_at": 1789538584.218993}, {"event_id": "a9755b7ae22b4f0293e834c82673ffe3", "step": 25, "value": 1.2762780250200374, "stage": "improve", "created_at": 1789538721.75082}, {"event_id": "7471cc9be90742208043a46cad771e70", "step": 26, "value": 1.3476147025444454, "stage": "improve", "created_at": 1789538936.695863}, {"event_id": "b84ef8e486d24743a50c6e15c7ed8b9e", "step": 31, "value": 1.413366074029535, "stage": "improve", "created_at": 1789539381.5556679}, {"event_id": "149212cedba24f26aaced75ef1451219", "step": 32, "value": 1.2185100135214164, "stage": "improve", "created_at": 1789539506.6189883}, {"event_id": "540a28e134b34b23b0e6d5350e3a0ec1", "step": 33, "value": 1.4122608699529702, "stage": "improve", "created_at": 1789540070.99874}, {"event_id": "3353ee577c8c4170a9c44b10a7712dbc", "step": 34, "value": 1.4630435785508373, "stage": "draft", "created_at": 1789540159.5436704}, {"event_id": "53b69014a7c848e581fc6bc3a3952e49", "step": 35, "value": 1.254216578379256, "stage": "improve", "created_at": 1789540131.2656326}, {"event_id": "002a451d8e77421b8c35099a77da089d", "step": 42, "value": 1.1070718744613866, "stage": "improve", "created_at": 1789540856.9660988}, {"event_id": "f461c45061fd4746accdf9f809977234", "step": 43, "value": 1.53184575761917, "stage": "improve", "created_at": 1789541208.8274982}, {"event_id": "ee19f98abd47486080621061fd404e6f", "step": 44, "value": 1.4836901729374856, "stage": "debug", "created_at": 1789541162.2360258}, {"event_id": "3bbe09643c7f40d3a41cc5f10844104e", "step": 45, "value": 1.1488958560868536, "stage": "improve", "created_at": 1789541522.1231594}, {"event_id": "bff534a0bdd94dbe9a222c4436c9c258", "step": 46, "value": 1.2413025061573197, "stage": "improve", "created_at": 1789541906.6018841}, {"event_id": "9852c0bbbf074a95ab9283554308efc7", "step": 47, "value": 1.3200806332661665, "stage": "evolution", "created_at": 1789541831.6040616}, {"event_id": "eb8832c8d4534f068a907b3b45fd0b73", "step": 48, "value": 1.1471318778101427, "stage": "improve", "created_at": 1789542165.2963111}, {"event_id": "6f46f89eb31042d0830739c13c302ef9", "step": 49, "value": 1.3005470751339114, "stage": "evolution", "created_at": 1789542566.739143}, {"event_id": "f95ae3275dd048099d88f02b844b7bf0", "step": 50, "value": 1.215019966274161, "stage": "improve", "created_at": 1789542561.0642018}, {"event_id": "007010518b904da6bdf7417befb5e498", "step": 51, "value": 1.1490568188160686, "stage": "improve", "created_at": 1789542808.1867392}, {"event_id": "5a9b79c85a0e47fba968859b188ade27", "step": 53, "value": 1.2448987173796326, "stage": "evolution", "created_at": 1789543161.863093}, {"event_id": "7d82b31da2624ec0ad7d33f60bee81f6", "step": 54, "value": 1.226960789097507, "stage": "improve", "created_at": 1789543222.5768526}, {"event_id": "9c6278593d884cceaaebf4db47710aa7", "step": 55, "value": 1.1258415765411784, "stage": "debug", "created_at": 1789543588.2109456}, {"event_id": "f916d4eb1bcc4a3ab0b592855b437459", "step": 56, "value": 1.2166253082058391, "stage": "improve", "created_at": 1789543942.38479}, {"event_id": "25f58d31a23243728b310964482d5890", "step": 57, "value": 1.2780974870802604, "stage": "improve", "created_at": 1789544029.3410027}, {"event_id": "003c5e5c84dd4b53bab86dda1abf998c", "step": 58, "value": 1.3422700049456704, "stage": "improve", "created_at": 1789544216.8961563}, {"event_id": "007deb0b29d64e5cac089e21099b496a", "step": 60, "value": 1.1689314556730892, "stage": "improve", "created_at": 1789544670.8041048}, {"event_id": "414c2370195a40dc93f3be63e0f6da52", "step": 61, "value": 1.4973328303203717, "stage": "evolution", "created_at": 1789544815.6070578}, {"event_id": "e3c3500e4ea14daca93f1a51aab108da", "step": 62, "value": 1.2637563494865922, "stage": "debug", "created_at": 1789544914.601589}, {"event_id": "c90cf93822ff4a478b49688e2eb3b208", "step": 63, "value": 1.183267587334212, "stage": "improve", "created_at": 1789545368.6950197}, {"event_id": "2545924d21144d4b9a3e84d67484176b", "step": 64, "value": 1.2642440626983305, "stage": "evolution", "created_at": 1789545453.2165713}, {"event_id": "7cb4b332aa434934b4fe4ceeb572b573", "step": 65, "value": 1.6455594925771435, "stage": "evolution", "created_at": 1789545498.3724625}, {"event_id": "e620564f802342278b5d246f11dea858", "step": 66, "value": 1.5033338078057423, "stage": "improve", "created_at": 1789546082.2162294}, {"event_id": "75f39299e56242b0b003d6ae2fde4780", "step": 67, "value": 1.3294652618645446, "stage": "improve", "created_at": 1789546132.147141}, {"event_id": "53855855743a43cd9b934b6ad2d82621", "step": 68, "value": 1.5688625048815177, "stage": "improve", "created_at": 1789546163.29171}, {"event_id": "140abc7932e64b3ea942d51bab3e345f", "step": 71, "value": 1.2227796878049522, "stage": "improve", "created_at": 1789546855.9920778}, {"event_id": "3afe52991fbb4d2192ebdbf12fd29772", "step": 72, "value": 1.7175732088003526, "stage": "debug", "created_at": 1789546923.8718605}, {"event_id": "c9bb3339374d4dc580f0bf46efbffbc1", "step": 74, "value": 1.2912479979959488, "stage": "debug", "created_at": 1789546974.828949}, {"event_id": "3913d65aeeea40d5a6173e4c7de58294", "step": 76, "value": 1.3890981232107271, "stage": "evolution", "created_at": 1789547556.9080667}, {"event_id": "44225d3bfa364257a1bdd6852d965807", "step": 77, "value": 1.3715636133214142, "stage": "evolution", "created_at": 1789547684.2480218}, {"event_id": "8da456b648ee4358b968feee4b7d4473", "step": 78, "value": 1.5048305547468026, "stage": "evolution", "created_at": 1789547683.1728785}, {"event_id": "73a7a551e61f4bdaa44be983c481817c", "step": 80, "value": 1.2884018305523328, "stage": "evolution", "created_at": 1789548175.0541465}, {"event_id": "b8df8e535e634c3e95422680eb0fa4da", "step": 81, "value": 1.4271429553000523, "stage": "fusion", "created_at": 1789548289.083758}, {"event_id": "99cee7dcb7ff4ef6b2c21e0dc0074eec", "step": 82, "value": 1.46826074773836, "stage": "debug", "created_at": 1789548419.7471309}, {"event_id": "3e0563f7bc9d41ad9948e32cfd7646db", "step": 83, "value": 1.5276213317475873, "stage": "evolution", "created_at": 1789548769.866379}, {"event_id": "dc5c3ef1f8e241d98f7f175b010f03e3", "step": 85, "value": 1.1815025988189134, "stage": "evolution", "created_at": 1789549012.0179367}, {"event_id": "fb3aa6aa3b194cf38f909c97d33606fe", "step": 86, "value": 1.5694340565809284, "stage": "evolution", "created_at": 1789549369.0769799}, {"event_id": "d5c2cf5472ca4ba18beab73de5fdb3d6", "step": 87, "value": 3.2185512162306518, "stage": "debug", "created_at": 1789549387.8123116}, {"event_id": "641d34fa3dd94e7fa4b34b2b7a1dd1b3", "step": 91, "value": 1.2261584361524855, "stage": "fusion", "created_at": 1789571590.0534835}, {"event_id": "3ef246f69358460698c18bd5ab88998e", "step": 92, "value": 1.419163099399806, "stage": "debug", "created_at": 1789571695.5806358}, {"event_id": "1b1612f4f5144ba88d2963f9cebf820d", "step": 93, "value": 1.3650573715758691, "stage": "evolution", "created_at": 1789571794.6250205}, {"event_id": "28e85769e7094aee88f7aca0b63464d4", "step": 94, "value": 1.2969286849880144, "stage": "fusion", "created_at": 1789572318.8130717}, {"event_id": "044112f3668547678ffecd4957c5bb81", "step": 95, "value": 1.647613785655348, "stage": "fusion", "created_at": 1789572289.4132931}, {"event_id": "df6eb008616d4cf4ad5afbe266c63c16", "step": 96, "value": 1.2124545976344852, "stage": "fusion", "created_at": 1789572407.4022286}], "maximize": false, "elapsed_seconds": 18728.76839351654, "node_count": 100, "metric_name": "BPB", "versions": [{"bundle_id": "03-historical-run-logs", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/03-historical-run-logs/logs-18799fb1fca5.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/03-historical-run-logs", "member": "MLEvolve_BO/runs/autoresearch_full_workflow_8h_20260916_043851/mlevolve_original/runs/20260916_003927_mlevolve_original/logs/journal.json", "sha256": "18799fb1fca5aa0c206be70e600c8d13ba65086d8360620e18525cd877b72d9b"}], "official_score": null, "note": ""}, {"id": "xixian.20260916-003928-gp7-ancestry-logei", "experiment_id": "nanogpt-autoresearch-full-workflow-8h-20260916-043851", "family": "nanoGPT", "method": "gp7_ancestry_logei", "dataset": "nanoGPT", "status": "archived", "artifacts": [{"bundle_id": "03-historical-run-logs", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/03-historical-run-logs/logs-18799fb1fca5.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/03-historical-run-logs", "member": "MLEvolve_BO/runs/autoresearch_full_workflow_8h_20260916_043851/gp7_ancestry_logei/runs/20260916_003928_gp7_ancestry_logei/logs/journal.json", "sha256": "18799fb1fca5aa0c206be70e600c8d13ba65086d8360620e18525cd877b72d9b"}], "curve_scope": "原始 journal 候选 BPB，未按预算或恢复边界重新审计。", "journal_ref": "03-historical-run-logs:MLEvolve_BO/runs/autoresearch_full_workflow_8h_20260916_043851/gp7_ancestry_logei/runs/20260916_003928_gp7_ancestry_logei/logs/journal.json", "metrics": [{"event_id": "1e73625095ab4b8eb8e9bcb04491895d", "step": 3, "value": 1.6188297277655217, "stage": "draft", "created_at": 1789534026.2661736}, {"event_id": "2e70279855f24b23a87c2585126a43fd", "step": 4, "value": 1.9301800068632005, "stage": "draft", "created_at": 1789533776.5685263}, {"event_id": "351f40bf29814d17888c6fb6cd2f8f4a", "step": 5, "value": 1.5312990100792356, "stage": "debug", "created_at": 1789534609.4111526}, {"event_id": "7eb567593abb4ed4ae07a945afebd8fc", "step": 6, "value": 1.466652352227765, "stage": "improve", "created_at": 1789534959.0176358}, {"event_id": "5162cfe9500f4a98806f6a9178ceb790", "step": 7, "value": 1.5289643466066751, "stage": "improve", "created_at": 1789535177.691329}, {"event_id": "4bd9276439a24821a9012d8fb0b86150", "step": 8, "value": 1.6102816168529936, "stage": "improve", "created_at": 1789535129.8628793}, {"event_id": "d19a3e6fe5444cc89a14718990576ae1", "step": 9, "value": 1.4718930344555043, "stage": "improve", "created_at": 1789535577.565093}, {"event_id": "31ebc148f51542ef9d8625e273bd3d9c", "step": 10, "value": 1.684469572052144, "stage": "improve", "created_at": 1789535753.3849378}, {"event_id": "d1ab06d9a9734ddab24a5fdbe24bdd19", "step": 11, "value": 1.3011612466814129, "stage": "improve", "created_at": 1789535789.372561}, {"event_id": "9e51bc6b9ec94790a3c44c155430f634", "step": 12, "value": 1.5853079422969172, "stage": "improve", "created_at": 1789536214.9763293}, {"event_id": "100660308e2e4eb9b3da42812f9703c1", "step": 13, "value": 1.6213955271110811, "stage": "improve", "created_at": 1789536339.2369933}, {"event_id": "c4dfee13a7d940cab73fe491db95bbcf", "step": 14, "value": 1.1274332458407137, "stage": "improve", "created_at": 1789536785.7552414}, {"event_id": "84384234a38c482fbfc53cb1ae5b3ccc", "step": 15, "value": 3.093698188587039, "stage": "draft", "created_at": 1789537024.4844406}, {"event_id": "6366c0c01abd4edaaaf9c9c9c1c229a7", "step": 16, "value": 1.1210908764020366, "stage": "improve", "created_at": 1789537383.5042934}, {"event_id": "c62c6bbc753144d69e352d8e13c574fa", "step": 17, "value": 1.1355350478152546, "stage": "improve", "created_at": 1789537732.029306}, {"event_id": "615acd9604ee4ea1bf34587e7f30c8ab", "step": 18, "value": 1.6077551929175258, "stage": "improve", "created_at": 1789537983.8200219}, {"event_id": "b9aa7546f35945ce8351f1a37fad12ff", "step": 19, "value": 1.193604620923585, "stage": "improve", "created_at": 1789538305.053236}, {"event_id": "1e3fb57e6ca14e4dbd029cd37872c7c3", "step": 20, "value": 1.1450435872548839, "stage": "improve", "created_at": 1789538663.7543867}, {"event_id": "aca225013c8f4116bfa453fccba2acee", "step": 21, "value": 2.5183538935097016, "stage": "improve", "created_at": 1789536444.2883308}, {"event_id": "57dc6158e6ab4b86a82eff9cd8897515", "step": 22, "value": 1.2058896759229947, "stage": "evolution", "created_at": 1789539082.9757757}, {"event_id": "b458eaced0e44f62812b8fa6006f2f8f", "step": 23, "value": 1.202225169829913, "stage": "draft", "created_at": 1789539335.1945896}, {"event_id": "9167679e99064743b4cf231f01b4dd25", "step": 24, "value": 1.3492951508363074, "stage": "evolution", "created_at": 1789539627.9575984}, {"event_id": "1ddc511e883d4b56a6e61818ad2ae50a", "step": 25, "value": 1.2958990034675677, "stage": "evolution", "created_at": 1789539689.1915886}, {"event_id": "c0af25ba06074f1b8e6ea06fe1ad4abc", "step": 26, "value": 1.1219124367927462, "stage": "evolution", "created_at": 1789540015.4003406}, {"event_id": "3bb2cade9f72423994de1224945902a8", "step": 27, "value": 1.2041798953690506, "stage": "improve", "created_at": 1789540341.3365004}, {"event_id": "326577e7eae1497c81cd6fd88b4e4d65", "step": 28, "value": 1.1875262690664434, "stage": "evolution", "created_at": 1789571669.1013026}, {"event_id": "06e1d37600e44754bfd6c4dce81cd6be", "step": 29, "value": 1.291074878591507, "stage": "evolution", "created_at": 1789571606.3196142}, {"event_id": "4e3ce67b39854f0a92cfdf0c70a5d520", "step": 30, "value": 1.5146003395689176, "stage": "evolution", "created_at": 1789571727.8732748}, {"event_id": "85a71abe4ddf489782242adfda115075", "step": 32, "value": 1.4826003343648673, "stage": "evolution", "created_at": 1789572370.8632782}, {"event_id": "35f25f549a2046e6b2a54d24af1c7286", "step": 33, "value": 1.5597674401614718, "stage": "improve", "created_at": 1789572491.1631424}, {"event_id": "099747e4d60d457b863caa47be534130", "step": 34, "value": 1.3220383018623358, "stage": "debug", "created_at": 1789572460.4080505}, {"event_id": "544d21e850c94a3fa1a41210706fe33e", "step": 38, "value": 1.282309316318976, "stage": "evolution", "created_at": 1789574332.168752}, {"event_id": "89c2a74e8d5c437b8e7f34fc30977e2f", "step": 39, "value": 1.384762737359892, "stage": "evolution", "created_at": 1789574340.7060223}, {"event_id": "cc5e04ad4cd045c4a9528c5f6f312578", "step": 40, "value": 1.4202433146811162, "stage": "evolution", "created_at": 1789574384.3471372}, {"event_id": "57de33d2d5174cbd810ab4d1797148fb", "step": 41, "value": 1.337878948146288, "stage": "evolution", "created_at": 1789574980.9347794}, {"event_id": "6511d67a20464a3baa1c30d4ac369199", "step": 42, "value": 1.218514667887206, "stage": "evolution", "created_at": 1789574939.9786017}, {"event_id": "b0aee55514204f28aa8aeebb3e8fa3d7", "step": 43, "value": 1.2254591637517134, "stage": "improve", "created_at": 1789575018.5467365}, {"event_id": "f2e5f771955043e99d4ba53a9ee7f462", "step": 44, "value": 1.485882110191258, "stage": "evolution", "created_at": 1789575657.2660758}, {"event_id": "9812c40f23b84fa3972100f6b6f65292", "step": 45, "value": 1.5333939085187018, "stage": "evolution", "created_at": 1789575636.1175053}, {"event_id": "8da02ff2788648878d1fcae3fd6f2d29", "step": 46, "value": 1.5739996707340507, "stage": "evolution", "created_at": 1789575627.9500773}, {"event_id": "c1ee4f644ae840f48d5e3837cfcf5e1f", "step": 47, "value": 1.2069444940005662, "stage": "evolution", "created_at": 1789576306.4523716}, {"event_id": "901459aac44649adb7d0df928828b61f", "step": 48, "value": 1.3071330369376357, "stage": "evolution", "created_at": 1789576338.291043}, {"event_id": "2b8fe696c79a4e088f3a7d258895917d", "step": 49, "value": 1.9941895672141492, "stage": "evolution", "created_at": 1789576338.8450649}, {"event_id": "e0961b48740848f29b9490bda91bd82b", "step": 50, "value": 1.248901066079406, "stage": "evolution", "created_at": 1789576898.5587792}, {"event_id": "786b83bd358948c59f37c07cb72755af", "step": 51, "value": 1.293120478213235, "stage": "evolution", "created_at": 1789577005.332829}, {"event_id": "edbccc8aba694e9eb13bd254a8a922a3", "step": 52, "value": 1.1728939044081321, "stage": "evolution", "created_at": 1789577049.2048712}, {"event_id": "9f3a4a875c8c4b7c8e2aab75ad13779c", "step": 54, "value": 1.1429348596355637, "stage": "evolution", "created_at": 1789577560.2936327}, {"event_id": "9b34b425285b4423add1581fb789acc3", "step": 55, "value": 1.1638744445116238, "stage": "evolution", "created_at": 1789577572.4327896}, {"event_id": "f64401c04ed842b09be497695597daae", "step": 56, "value": 1.1025707340038247, "stage": "evolution", "created_at": 1789577881.2669628}, {"event_id": "583316dbaf1e43d4ac577152560bea9e", "step": 57, "value": 1.2738827550529508, "stage": "evolution", "created_at": 1789578257.0516276}, {"event_id": "d44256c667e841c8beea1a11a8439a94", "step": 58, "value": 1.195170305566109, "stage": "evolution", "created_at": 1789578342.552698}, {"event_id": "faca3fec37204d149321e69c409dfa45", "step": 59, "value": 1.1514580815253792, "stage": "improve", "created_at": 1789578655.6802173}, {"event_id": "fe09a2508d414c7cbfec33ba39e2dad0", "step": 61, "value": 1.1272811148784108, "stage": "improve", "created_at": 1789578920.546029}, {"event_id": "be4684ef1cb94d9181cac578a37974f2", "step": 63, "value": 1.247128819128315, "stage": "debug", "created_at": 1789579344.6961148}, {"event_id": "235181e17ed645c593c6f8aaa02c00bb", "step": 64, "value": 1.1660293885828241, "stage": "evolution", "created_at": 1789579396.399081}, {"event_id": "ebea3a49b8f24f04ae51b5481113cc85", "step": 65, "value": 1.2257951213296105, "stage": "debug", "created_at": 1789579877.4134753}, {"event_id": "53390aa932d44df68d2b1330e906f262", "step": 66, "value": 1.3442325170028875, "stage": "fusion", "created_at": 1789579958.347508}, {"event_id": "4ef1ca0aec894b53867391d41bd96c0b", "step": 67, "value": 1.1742539922527588, "stage": "evolution", "created_at": 1789579978.584922}, {"event_id": "b0d082a450484fdb8a90a95a25e24068", "step": 69, "value": 1.1729090192493747, "stage": "fusion", "created_at": 1789580558.6102211}, {"event_id": "cbb3fd2cfc3d4d848887b6116edfa37b", "step": 70, "value": 1.2365251939722532, "stage": "fusion", "created_at": 1789580584.0705953}, {"event_id": "9f1735f720104d3784bbbb9a42f13467", "step": 71, "value": 1.1045607617173938, "stage": "evolution", "created_at": 1789580885.6621463}, {"event_id": "7b0b5c1e995742038e106367d937161f", "step": 74, "value": 1.1588018663043458, "stage": "fusion", "created_at": 1789581181.8681712}, {"event_id": "250d9a6b66f54a18a8689127e1de91fd", "step": 75, "value": 1.290854898307065, "stage": "evolution", "created_at": 1789581201.8514261}, {"event_id": "408e04661a184f83951e8e5e725e25f5", "step": 78, "value": 1.1249408019437368, "stage": "fusion", "created_at": 1789581797.4841106}, {"event_id": "10174a13ae9b41e29613306f15f101af", "step": 79, "value": 1.2200766767202529, "stage": "evolution", "created_at": 1789581990.6530626}, {"event_id": "6b065f48a16a4fd39a38f8a40afaf289", "step": 80, "value": 1.1757499633774418, "stage": "debug", "created_at": 1789582007.699357}, {"event_id": "6703af11acbc448eb576f87eb7b14f0e", "step": 81, "value": 1.1388061753355627, "stage": "fusion", "created_at": 1789582412.2101338}, {"event_id": "6a535c01c8764c04943656db7fb042ef", "step": 82, "value": 1.3921366541121434, "stage": "fusion", "created_at": 1789582600.7940145}, {"event_id": "f615f93cd0834473bf5ecf625c23038d", "step": 83, "value": 1.211901827134359, "stage": "evolution", "created_at": 1789582678.2201505}, {"event_id": "fde7ed2fa24540bf980fa2b4519a1f06", "step": 84, "value": 1.1611382687410952, "stage": "evolution", "created_at": 1789583117.248314}, {"event_id": "1ec145c31a8943acbae5155867ad3d84", "step": 85, "value": 1.2136744963382895, "stage": "fusion", "created_at": 1789583239.9646459}, {"event_id": "5e7b3c3515434111a746c6c4fbcd2d78", "step": 86, "value": 1.1653227075882513, "stage": "evolution", "created_at": 1789583292.7955866}, {"event_id": "0765f2ee782d4a38ac83f1603fef9942", "step": 88, "value": 1.140748128258777, "stage": "evolution", "created_at": 1789583715.5406644}, {"event_id": "30de161169834e44bd2ba4b3c98ac8fb", "step": 89, "value": 1.1982175821065721, "stage": "fusion", "created_at": 1789583778.8719003}, {"event_id": "cf7ea36f878c4765beb50b7e57a94cb6", "step": 90, "value": 3.0515474506218214, "stage": "debug", "created_at": 1789584128.244958}, {"event_id": "59cc65dd077e4eacbfe86c529ce8eb73", "step": 91, "value": 1.169275367831553, "stage": "evolution", "created_at": 1789584336.8947728}, {"event_id": "dce8e7a8f16c4b99aa892225762ccc1f", "step": 94, "value": 1.2190743858576032, "stage": "evolution", "created_at": 1789589570.377013}, {"event_id": "4a38d6ae9f344f9587e0a1819fd0e1ed", "step": 95, "value": 1.2274795362955315, "stage": "fusion", "created_at": 1789589582.8018532}, {"event_id": "e5902c233d0c4e1585ceebbad549ec6c", "step": 96, "value": 1.270226292929711, "stage": "fusion", "created_at": 1789589575.8536513}, {"event_id": "e817459d25254fedb3fdb716cf2dae09", "step": 99, "value": 3.102923254999117, "stage": "evolution", "created_at": 1789590151.4098427}, {"event_id": "5a15795ffe3c44d18d343ad79d744104", "step": 100, "value": 1.2166069222362776, "stage": "evolution", "created_at": 1789590373.109894}, {"event_id": "77187987b5124657a3406ca0b53aaec1", "step": 101, "value": 3.122605690403919, "stage": "debug", "created_at": 1789590448.3045604}, {"event_id": "27e11e39df0d4e4fa8b816e9d6e2a714", "step": 102, "value": 1.1740572535792966, "stage": "evolution", "created_at": 1789590882.2843843}, {"event_id": "29d4a31e61fe48b196d7ca2a7eddc549", "step": 103, "value": 1.2468338771172676, "stage": "evolution", "created_at": 1789590995.0243917}, {"event_id": "580ab1d49417461d98498f4af6a62471", "step": 104, "value": 1.1572604573396548, "stage": "evolution", "created_at": 1789591069.4050572}], "maximize": false, "elapsed_seconds": 23074.487886428833, "node_count": 105, "metric_name": "BPB", "versions": [{"bundle_id": "03-historical-run-logs", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/03-historical-run-logs/logs-18799fb1fca5.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/03-historical-run-logs", "member": "MLEvolve_BO/runs/autoresearch_full_workflow_8h_20260916_043851/gp7_ancestry_logei/runs/20260916_003928_gp7_ancestry_logei/logs/journal.json", "sha256": "18799fb1fca5aa0c206be70e600c8d13ba65086d8360620e18525cd877b72d9b"}], "official_score": null, "note": ""}, {"id": "xixian.20260916-004421-gp7-long-horizon-pibo", "experiment_id": "nanogpt-autoresearch-full-workflow-8h-20260916-043851", "family": "nanoGPT", "method": "gp7_long_horizon_pibo", "dataset": "nanoGPT", "status": "archived", "artifacts": [{"bundle_id": "03-historical-run-logs", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/03-historical-run-logs/logs-18799fb1fca5.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/03-historical-run-logs", "member": "MLEvolve_BO/runs/autoresearch_full_workflow_8h_20260916_043851/gp7_long_horizon_pibo/runs/20260916_004421_gp7_long_horizon_pibo/logs/journal.json", "sha256": "18799fb1fca5aa0c206be70e600c8d13ba65086d8360620e18525cd877b72d9b"}], "curve_scope": "原始 journal 候选 BPB，未按预算或恢复边界重新审计。", "journal_ref": "03-historical-run-logs:MLEvolve_BO/runs/autoresearch_full_workflow_8h_20260916_043851/gp7_long_horizon_pibo/runs/20260916_004421_gp7_long_horizon_pibo/logs/journal.json", "metrics": [{"event_id": "30de0918b56244c5b0039b369c3ef44f", "step": 1, "value": 1.2888751678652979, "stage": "draft", "created_at": 1789534314.987481}, {"event_id": "e4d817645d2d481f993db701e87df56f", "step": 2, "value": 1.8772836039835143, "stage": "draft", "created_at": 1789534057.3817823}, {"event_id": "b3d548fb4a564c6b9d62d1a705c4fcc5", "step": 3, "value": 1.9970548960443477, "stage": "draft", "created_at": 1789534630.8348346}, {"event_id": "b7aacd2aa44c4481915bdea8f7f7aeab", "step": 4, "value": 1.2207097074746567, "stage": "improve", "created_at": 1789535256.5928428}, {"event_id": "2a9ebc38117947e69021cf199c2afbf2", "step": 5, "value": 1.3129758780721934, "stage": "improve", "created_at": 1789535404.857993}, {"event_id": "c6b0baa8b7114eec8905cc1ce1694438", "step": 6, "value": 1.9050284640225434, "stage": "improve", "created_at": 1789535302.482799}, {"event_id": "66dca9f7fc834d73a9a88c24bb06f862", "step": 11, "value": 1.3106068287817538, "stage": "improve", "created_at": 1789571671.1958716}, {"event_id": "c5071f7393ed448696e61302213eff12", "step": 12, "value": 1.1958296963725454, "stage": "improve", "created_at": 1789571671.026308}, {"event_id": "053b9c0a31b24411badb361a1a5d686a", "step": 13, "value": 1.225875435031087, "stage": "improve", "created_at": 1789571722.3872106}, {"event_id": "9b4d70b68b474d528f2b4a6a054b377b", "step": 14, "value": 1.2245893930557088, "stage": "improve", "created_at": 1789572407.0134554}, {"event_id": "01ad8eaf3c874a6ebb04670fb51ca190", "step": 15, "value": 1.8953199106544498, "stage": "improve", "created_at": 1789572284.182604}, {"event_id": "1b1de53d79a440328c89b94b3315b65f", "step": 16, "value": 1.2305860224816532, "stage": "improve", "created_at": 1789572385.2522569}, {"event_id": "e0309b475b574f2fa34588050dda4750", "step": 24, "value": 1.3186029149922434, "stage": "evolution", "created_at": 1789574389.2727}, {"event_id": "16264e08e8664e5593aecd0b1002d61d", "step": 25, "value": 1.7630100341768355, "stage": "evolution", "created_at": 1789574454.720105}, {"event_id": "469bbd57d4fc48bda091ac3d8bdd5315", "step": 26, "value": 1.192575940855885, "stage": "debug", "created_at": 1789574571.7793872}, {"event_id": "2bb4f64e832945b18157bd391b9ad612", "step": 27, "value": 1.1704600438328505, "stage": "evolution", "created_at": 1789575013.478899}, {"event_id": "c2709a5ab8a94c32a4fd6cd25966a468", "step": 28, "value": 1.2800123222392217, "stage": "draft", "created_at": 1789575071.04837}, {"event_id": "c8773e59b83c4d61a1abfa923d2441bd", "step": 29, "value": 1.1950961513381555, "stage": "improve", "created_at": 1789575087.4325275}, {"event_id": "9d8c476ddba941d69846f553fe3c6625", "step": 30, "value": 1.3761105864493504, "stage": "improve", "created_at": 1789575611.355925}, {"event_id": "17621135486a43b7b449de7d871eaa7d", "step": 31, "value": 1.5976220565983057, "stage": "improve", "created_at": 1789575611.1907225}, {"event_id": "9d7898ab1ca5438da02d0eaea1613283", "step": 32, "value": 1.4547023839763302, "stage": "improve", "created_at": 1789575638.7778597}, {"event_id": "2b48fdcd9d9d4f0ebebf064b7f57d667", "step": 33, "value": 1.1520289270295458, "stage": "evolution", "created_at": 1789576221.1670265}, {"event_id": "70f81930c4ef484e9c10ee14592c791e", "step": 34, "value": 1.1718047114617032, "stage": "evolution", "created_at": 1789576280.607836}, {"event_id": "c3aa011082b94296a0210631399adafd", "step": 35, "value": 1.4774867739369997, "stage": "improve", "created_at": 1789576266.2977679}, {"event_id": "afbf66686f654e359dc3813d3d18c803", "step": 37, "value": 1.1635532472130403, "stage": "improve", "created_at": 1789576788.202822}, {"event_id": "2041d9128f5e4e8e99bd352d343ae608", "step": 38, "value": 1.199810971833503, "stage": "improve", "created_at": 1789576837.907125}, {"event_id": "f50e7276f0e44a438844414ef135eaab", "step": 40, "value": 1.1321784353939321, "stage": "debug", "created_at": 1789577029.1078708}, {"event_id": "859ab7c9b4e742c59c89fb073672afb5", "step": 42, "value": 1.1211032157162597, "stage": "evolution", "created_at": 1789577375.8601305}, {"event_id": "ce65664246804b7bb18eb789c93818f6", "step": 43, "value": 1.1756059342916598, "stage": "debug", "created_at": 1789577648.4373825}, {"event_id": "2d9792c8cc44497eb090c07cb24926dc", "step": 44, "value": 1.2245892072218614, "stage": "improve", "created_at": 1789577651.942374}, {"event_id": "6af7e38ba81f41f8aa733e6e368d5d2c", "step": 45, "value": 1.1903702175527504, "stage": "improve", "created_at": 1789577986.1715913}, {"event_id": "99bea74183214c2790500783e816bd73", "step": 46, "value": 1.1919359200331936, "stage": "improve", "created_at": 1789578209.2878795}, {"event_id": "0405e9b594c94ff999a92ea1ea4eac24", "step": 47, "value": 1.176814945075538, "stage": "improve", "created_at": 1789578273.5537934}, {"event_id": "c4e5439c35b1407eb455e6c832786377", "step": 48, "value": 1.235434034994239, "stage": "evolution", "created_at": 1789578691.4632983}, {"event_id": "459e9a5089c14d5c8c4956c0820900ca", "step": 49, "value": 1.2192668958792046, "stage": "evolution", "created_at": 1789578796.9121878}, {"event_id": "b43b8a62c2e34018abb566eed34aeb79", "step": 50, "value": 1.2230752818318913, "stage": "evolution", "created_at": 1789578873.747063}, {"event_id": "46f9dde5233c4116a17e3106cde5693e", "step": 51, "value": 1.2257955376586636, "stage": "evolution", "created_at": 1789579353.2349029}, {"event_id": "12a30493fd404d05af483589acb037b8", "step": 52, "value": 1.251746929612797, "stage": "evolution", "created_at": 1789579372.3010006}, {"event_id": "03f96a6c15c5454cad21c666879d4a79", "step": 58, "value": 1.1807936827596566, "stage": "evolution", "created_at": 1789579962.936276}, {"event_id": "6f9af006f9f74abc99051aaed94e23db", "step": 59, "value": 1.180716860964032, "stage": "debug", "created_at": 1789580021.3710902}, {"event_id": "0b0716bb73e5419aa4252a63f560939a", "step": 60, "value": 1.1723886019428615, "stage": "evolution", "created_at": 1789580353.9865935}, {"event_id": "ea2e2fec51bb4e4a85d43513f95cdf3f", "step": 61, "value": 1.1632099143876022, "stage": "evolution", "created_at": 1789580530.0489268}, {"event_id": "0972c631c07f4933b887173221b32376", "step": 62, "value": 1.1291215101364698, "stage": "evolution", "created_at": 1789580617.6740696}, {"event_id": "5cafd1b95d4f4908b4fd42ed950959d7", "step": 64, "value": 1.244460002403378, "stage": "evolution", "created_at": 1789580951.0145285}, {"event_id": "78ce1ee132484a4081c1bc7323c49120", "step": 65, "value": 1.1755941214622982, "stage": "evolution", "created_at": 1789581065.2455137}, {"event_id": "dfe4677336bb4abcbfa6873af8e3005b", "step": 66, "value": 1.1143879980851505, "stage": "debug", "created_at": 1789581278.5554025}, {"event_id": "25c28e6ff648402f870ef2599b3450dd", "step": 67, "value": 1.149412101716353, "stage": "evolution", "created_at": 1789581566.2888951}, {"event_id": "828f77db9ba84392b7b5a9fd8c1723d9", "step": 68, "value": 1.162546123339169, "stage": "evolution", "created_at": 1789581607.260191}, {"event_id": "2bf1df7ed037473f938229bbdf1736d8", "step": 70, "value": 1.0908599300868906, "stage": "improve", "created_at": 1789581827.996189}, {"event_id": "1c0e134f70ed46f7aaeef862bf843e80", "step": 71, "value": 1.1724217079232995, "stage": "improve", "created_at": 1789582140.964127}, {"event_id": "b21133c1f33f4f0b828569d331f8b10e", "step": 72, "value": 1.1602997817622491, "stage": "debug", "created_at": 1789582265.0561912}, {"event_id": "41329aab043b443dbf8db5fcb00c6c52", "step": 73, "value": 1.1752409354493814, "stage": "improve", "created_at": 1789582450.027905}, {"event_id": "b0e765d7dfae4abd9233d3e7a8cfa0ac", "step": 75, "value": 1.367178825752007, "stage": "improve", "created_at": 1789582777.5376272}, {"event_id": "f373d858c6634cc296a95075ced737e3", "step": 76, "value": 1.2276497763402883, "stage": "improve", "created_at": 1789582814.8267045}, {"event_id": "9056f83a558e4a0790faf07156890568", "step": 77, "value": 3.040148440225067, "stage": "debug", "created_at": 1789583293.0169108}, {"event_id": "c6bc0c6b50524112a4867bcc6331a06b", "step": 78, "value": 1.1624572457723696, "stage": "evolution", "created_at": 1789583423.2556512}, {"event_id": "ef590addd88f4cfebf164201c84d9ef3", "step": 79, "value": 1.1403675742182593, "stage": "evolution", "created_at": 1789583477.793027}, {"event_id": "976f6ef0580c4d4696218baa742147ae", "step": 81, "value": 1.157863530107048, "stage": "evolution", "created_at": 1789583841.5072117}, {"event_id": "3c449272eef84ee7af33c93e7ecf94a9", "step": 82, "value": 1.9067006283979226, "stage": "evolution", "created_at": 1789583936.8228402}, {"event_id": "2218cb0a2a134d408bf11e2e47a97e81", "step": 83, "value": 1.11201865446904, "stage": "evolution", "created_at": 1789584180.0097954}, {"event_id": "0322a019881d490a92678c8e1708be8b", "step": 84, "value": 1.1666295685455332, "stage": "fusion", "created_at": 1789584466.1532078}, {"event_id": "11f5d49024c046b0b9a6afc2d6fb1bea", "step": 87, "value": 1.1950393114734086, "stage": "evolution", "created_at": 1789589565.6224473}, {"event_id": "df461963fa1e4eda88f56ee3ff961788", "step": 88, "value": 1.9612486303955206, "stage": "evolution", "created_at": 1789589598.9301226}, {"event_id": "dbe1449c0f704059ab5d3ee15934d81f", "step": 89, "value": 1.2494619499042703, "stage": "evolution", "created_at": 1789589587.3068612}, {"event_id": "aeec2ebbb5ad4e5d8fa69e2e1351d1fd", "step": 90, "value": 1.2401457962864002, "stage": "fusion", "created_at": 1789590214.20445}, {"event_id": "3f864093e0954042a27f892d3a874f8e", "step": 91, "value": 1.2978039453702905, "stage": "fusion", "created_at": 1789590138.484665}, {"event_id": "15dcd50e8e814be3941b154a7735a8ee", "step": 92, "value": 1.230572517312963, "stage": "evolution", "created_at": 1789590198.9742486}, {"event_id": "bc9ab8562ec24556bbeda1fe1cc6658f", "step": 93, "value": 1.2159082564578856, "stage": "fusion", "created_at": 1789590788.7480266}, {"event_id": "0e6ff09a63eb4ea7a837d168d93d13ab", "step": 94, "value": 1.232425905099206, "stage": "fusion", "created_at": 1789590799.9696877}, {"event_id": "a549973e29ed430aa7432609f61cb628", "step": 95, "value": 1.2769144139624566, "stage": "evolution", "created_at": 1789590803.502696}, {"event_id": "d24b9e1de8194b849eebcc28651fb54d", "step": 96, "value": 1.1677288078348227, "stage": "evolution", "created_at": 1789591369.1987135}, {"event_id": "67038ae4456e4fb289a21e3e928f3805", "step": 97, "value": 1.2631899466893202, "stage": "fusion", "created_at": 1789591373.569047}, {"event_id": "bd160377e467450884f8c8dd1b019d74", "step": 98, "value": 1.1761582551164733, "stage": "evolution", "created_at": 1789591425.8042326}], "maximize": false, "elapsed_seconds": 18269.95136499405, "node_count": 99, "metric_name": "BPB", "versions": [{"bundle_id": "03-historical-run-logs", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/03-historical-run-logs/logs-18799fb1fca5.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/03-historical-run-logs", "member": "MLEvolve_BO/runs/autoresearch_full_workflow_8h_20260916_043851/gp7_long_horizon_pibo/runs/20260916_004421_gp7_long_horizon_pibo/logs/journal.json", "sha256": "18799fb1fca5aa0c206be70e600c8d13ba65086d8360620e18525cd877b72d9b"}], "official_score": null, "note": ""}, {"id": "xixian.20260916-103932-gp7-long-horizon-pibo", "experiment_id": "nanogpt-autoresearch-paired-drafts5-8h-20260916-061810", "family": "nanoGPT", "method": "gp7_long_horizon_pibo", "dataset": "nanoGPT", "status": "archived", "artifacts": [{"bundle_id": "03-historical-run-logs", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/03-historical-run-logs/logs-18799fb1fca5.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/03-historical-run-logs", "member": "MLEvolve_BO/runs/autoresearch_paired_drafts5_8h_20260916_061810/gp7_long_horizon_pibo/runs/20260916_103932_gp7_long_horizon_pibo/logs/journal.json", "sha256": "18799fb1fca5aa0c206be70e600c8d13ba65086d8360620e18525cd877b72d9b"}], "curve_scope": "原始 journal 候选 BPB，未按预算或恢复边界重新审计。", "journal_ref": "03-historical-run-logs:MLEvolve_BO/runs/autoresearch_paired_drafts5_8h_20260916_061810/gp7_long_horizon_pibo/runs/20260916_103932_gp7_long_horizon_pibo/logs/journal.json", "metrics": [], "maximize": null, "elapsed_seconds": 1172.3640687465668, "node_count": 4, "metric_name": "BPB", "versions": [{"bundle_id": "03-historical-run-logs", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/03-historical-run-logs/logs-18799fb1fca5.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/03-historical-run-logs", "member": "MLEvolve_BO/runs/autoresearch_paired_drafts5_8h_20260916_061810/gp7_long_horizon_pibo/runs/20260916_103932_gp7_long_horizon_pibo/logs/journal.json", "sha256": "18799fb1fca5aa0c206be70e600c8d13ba65086d8360620e18525cd877b72d9b"}], "official_score": null, "note": ""}, {"id": "xixian.20260916-103937-gp7-ancestry-logei", "experiment_id": "nanogpt-autoresearch-paired-drafts5-8h-20260916-061810", "family": "nanoGPT", "method": "gp7_ancestry_logei", "dataset": "nanoGPT", "status": "archived", "artifacts": [{"bundle_id": "03-historical-run-logs", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/03-historical-run-logs/logs-18799fb1fca5.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/03-historical-run-logs", "member": "MLEvolve_BO/runs/autoresearch_paired_drafts5_8h_20260916_061810/gp7_ancestry_logei/runs/20260916_103937_gp7_ancestry_logei/logs/journal.json", "sha256": "18799fb1fca5aa0c206be70e600c8d13ba65086d8360620e18525cd877b72d9b"}], "curve_scope": "原始 journal 候选 BPB，未按预算或恢复边界重新审计。", "journal_ref": "03-historical-run-logs:MLEvolve_BO/runs/autoresearch_paired_drafts5_8h_20260916_061810/gp7_ancestry_logei/runs/20260916_103937_gp7_ancestry_logei/logs/journal.json", "metrics": [], "maximize": null, "elapsed_seconds": 1167.963225364685, "node_count": 3, "metric_name": "BPB", "versions": [{"bundle_id": "03-historical-run-logs", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/03-historical-run-logs/logs-18799fb1fca5.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/03-historical-run-logs", "member": "MLEvolve_BO/runs/autoresearch_paired_drafts5_8h_20260916_061810/gp7_ancestry_logei/runs/20260916_103937_gp7_ancestry_logei/logs/journal.json", "sha256": "18799fb1fca5aa0c206be70e600c8d13ba65086d8360620e18525cd877b72d9b"}], "official_score": null, "note": ""}, {"id": "xixian.20260916-103937-gp7-long-horizon-logei", "experiment_id": "nanogpt-autoresearch-paired-drafts5-8h-20260916-061810", "family": "nanoGPT", "method": "gp7_long_horizon_logei", "dataset": "nanoGPT", "status": "archived", "artifacts": [{"bundle_id": "03-historical-run-logs", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/03-historical-run-logs/logs-18799fb1fca5.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/03-historical-run-logs", "member": "MLEvolve_BO/runs/autoresearch_paired_drafts5_8h_20260916_061810/gp7_long_horizon_logei/runs/20260916_103937_gp7_long_horizon_logei/logs/journal.json", "sha256": "18799fb1fca5aa0c206be70e600c8d13ba65086d8360620e18525cd877b72d9b"}], "curve_scope": "原始 journal 候选 BPB，未按预算或恢复边界重新审计。", "journal_ref": "03-historical-run-logs:MLEvolve_BO/runs/autoresearch_paired_drafts5_8h_20260916_061810/gp7_long_horizon_logei/runs/20260916_103937_gp7_long_horizon_logei/logs/journal.json", "metrics": [], "maximize": null, "elapsed_seconds": 1167.8997991085052, "node_count": 4, "metric_name": "BPB", "versions": [{"bundle_id": "03-historical-run-logs", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/03-historical-run-logs/logs-18799fb1fca5.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/03-historical-run-logs", "member": "MLEvolve_BO/runs/autoresearch_paired_drafts5_8h_20260916_061810/gp7_long_horizon_logei/runs/20260916_103937_gp7_long_horizon_logei/logs/journal.json", "sha256": "18799fb1fca5aa0c206be70e600c8d13ba65086d8360620e18525cd877b72d9b"}], "official_score": null, "note": ""}, {"id": "xixian.20260916-103937-mlevolve-original", "experiment_id": "nanogpt-autoresearch-paired-drafts5-8h-20260916-061810", "family": "nanoGPT", "method": "mlevolve_original", "dataset": "nanoGPT", "status": "archived", "artifacts": [{"bundle_id": "03-historical-run-logs", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/03-historical-run-logs/logs-18799fb1fca5.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/03-historical-run-logs", "member": "MLEvolve_BO/runs/autoresearch_paired_drafts5_8h_20260916_061810/mlevolve_original/runs/20260916_103937_mlevolve_original/logs/journal.json", "sha256": "18799fb1fca5aa0c206be70e600c8d13ba65086d8360620e18525cd877b72d9b"}], "curve_scope": "原始 journal 候选 BPB，未按预算或恢复边界重新审计。", "journal_ref": "03-historical-run-logs:MLEvolve_BO/runs/autoresearch_paired_drafts5_8h_20260916_061810/mlevolve_original/runs/20260916_103937_mlevolve_original/logs/journal.json", "metrics": [], "maximize": null, "elapsed_seconds": 1167.2326266765594, "node_count": 3, "metric_name": "BPB", "versions": [{"bundle_id": "03-historical-run-logs", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/03-historical-run-logs/logs-18799fb1fca5.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/03-historical-run-logs", "member": "MLEvolve_BO/runs/autoresearch_paired_drafts5_8h_20260916_061810/mlevolve_original/runs/20260916_103937_mlevolve_original/logs/journal.json", "sha256": "18799fb1fca5aa0c206be70e600c8d13ba65086d8360620e18525cd877b72d9b"}], "official_score": null, "note": ""}, {"id": "xixian.20260916-111122-gp7-long-horizon-pibo", "experiment_id": "nanogpt-autoresearch-paired-drafts5-serial-8h-20260916-145852", "family": "nanoGPT", "method": "gp7_long_horizon_pibo", "dataset": "nanoGPT", "status": "archived", "artifacts": [{"bundle_id": "03-historical-run-logs", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/03-historical-run-logs/logs-18799fb1fca5.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/03-historical-run-logs", "member": "MLEvolve_BO/runs/autoresearch_paired_drafts5_serial_8h_20260916_145852/gp7_long_horizon_pibo/runs/20260916_111122_gp7_long_horizon_pibo/logs/journal.json", "sha256": "18799fb1fca5aa0c206be70e600c8d13ba65086d8360620e18525cd877b72d9b"}], "curve_scope": "原始 journal 候选 BPB，未按预算或恢复边界重新审计。", "journal_ref": "03-historical-run-logs:MLEvolve_BO/runs/autoresearch_paired_drafts5_serial_8h_20260916_145852/gp7_long_horizon_pibo/runs/20260916_111122_gp7_long_horizon_pibo/logs/journal.json", "metrics": [{"event_id": "02b4243139dc4cfcbb295a72d373be42", "step": 1, "value": 1.4783989664003176, "stage": "draft", "created_at": 1789571502.2929409}], "maximize": false, "elapsed_seconds": 2079.4559264183044, "node_count": 4, "metric_name": "BPB", "versions": [{"bundle_id": "03-historical-run-logs", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/03-historical-run-logs/logs-18799fb1fca5.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/03-historical-run-logs", "member": "MLEvolve_BO/runs/autoresearch_paired_drafts5_serial_8h_20260916_145852/gp7_long_horizon_pibo/runs/20260916_111122_gp7_long_horizon_pibo/logs/journal.json", "sha256": "18799fb1fca5aa0c206be70e600c8d13ba65086d8360620e18525cd877b72d9b"}], "official_score": null, "note": ""}, {"id": "xixian.20260916-111126-mlevolve-original", "experiment_id": "nanogpt-autoresearch-paired-drafts5-serial-8h-20260916-145852", "family": "nanoGPT", "method": "mlevolve_original", "dataset": "nanoGPT", "status": "archived", "artifacts": [{"bundle_id": "03-historical-run-logs", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/03-historical-run-logs/logs-18799fb1fca5.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/03-historical-run-logs", "member": "MLEvolve_BO/runs/autoresearch_paired_drafts5_serial_8h_20260916_145852/mlevolve_original/runs/20260916_111126_mlevolve_original/logs/journal.json", "sha256": "18799fb1fca5aa0c206be70e600c8d13ba65086d8360620e18525cd877b72d9b"}], "curve_scope": "原始 journal 候选 BPB，未按预算或恢复边界重新审计。", "journal_ref": "03-historical-run-logs:MLEvolve_BO/runs/autoresearch_paired_drafts5_serial_8h_20260916_145852/mlevolve_original/runs/20260916_111126_mlevolve_original/logs/journal.json", "metrics": [{"event_id": "e79ca958d9a24ffbbbb83788a28cd4f9", "step": 1, "value": 1.4904710789732227, "stage": "draft", "created_at": 1789571504.5664907}], "maximize": false, "elapsed_seconds": 2074.939085960388, "node_count": 5, "metric_name": "BPB", "versions": [{"bundle_id": "03-historical-run-logs", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/03-historical-run-logs/logs-18799fb1fca5.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/03-historical-run-logs", "member": "MLEvolve_BO/runs/autoresearch_paired_drafts5_serial_8h_20260916_145852/mlevolve_original/runs/20260916_111126_mlevolve_original/logs/journal.json", "sha256": "18799fb1fca5aa0c206be70e600c8d13ba65086d8360620e18525cd877b72d9b"}], "official_score": null, "note": ""}, {"id": "xixian.20260916-111127-gp7-ancestry-logei", "experiment_id": "nanogpt-autoresearch-paired-drafts5-serial-8h-20260916-145852", "family": "nanoGPT", "method": "gp7_ancestry_logei", "dataset": "nanoGPT", "status": "archived", "artifacts": [{"bundle_id": "03-historical-run-logs", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/03-historical-run-logs/logs-18799fb1fca5.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/03-historical-run-logs", "member": "MLEvolve_BO/runs/autoresearch_paired_drafts5_serial_8h_20260916_145852/gp7_ancestry_logei/runs/20260916_111127_gp7_ancestry_logei/logs/journal.json", "sha256": "18799fb1fca5aa0c206be70e600c8d13ba65086d8360620e18525cd877b72d9b"}], "curve_scope": "原始 journal 候选 BPB，未按预算或恢复边界重新审计。", "journal_ref": "03-historical-run-logs:MLEvolve_BO/runs/autoresearch_paired_drafts5_serial_8h_20260916_145852/gp7_ancestry_logei/runs/20260916_111127_gp7_ancestry_logei/logs/journal.json", "metrics": [{"event_id": "d63a8ffb1fb0437eb7e1d59dbf9c0f8b", "step": 1, "value": 1.4873718431026464, "stage": "draft", "created_at": 1789571505.8147469}], "maximize": false, "elapsed_seconds": 1640.103234052658, "node_count": 3, "metric_name": "BPB", "versions": [{"bundle_id": "03-historical-run-logs", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/03-historical-run-logs/logs-18799fb1fca5.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/03-historical-run-logs", "member": "MLEvolve_BO/runs/autoresearch_paired_drafts5_serial_8h_20260916_145852/gp7_ancestry_logei/runs/20260916_111127_gp7_ancestry_logei/logs/journal.json", "sha256": "18799fb1fca5aa0c206be70e600c8d13ba65086d8360620e18525cd877b72d9b"}], "official_score": null, "note": ""}, {"id": "xixian.20260916-111127-gp7-long-horizon-logei", "experiment_id": "nanogpt-autoresearch-paired-drafts5-serial-8h-20260916-145852", "family": "nanoGPT", "method": "gp7_long_horizon_logei", "dataset": "nanoGPT", "status": "archived", "artifacts": [{"bundle_id": "03-historical-run-logs", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/03-historical-run-logs/logs-18799fb1fca5.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/03-historical-run-logs", "member": "MLEvolve_BO/runs/autoresearch_paired_drafts5_serial_8h_20260916_145852/gp7_long_horizon_logei/runs/20260916_111127_gp7_long_horizon_logei/logs/journal.json", "sha256": "18799fb1fca5aa0c206be70e600c8d13ba65086d8360620e18525cd877b72d9b"}], "curve_scope": "原始 journal 候选 BPB，未按预算或恢复边界重新审计。", "journal_ref": "03-historical-run-logs:MLEvolve_BO/runs/autoresearch_paired_drafts5_serial_8h_20260916_145852/gp7_long_horizon_logei/runs/20260916_111127_gp7_long_horizon_logei/logs/journal.json", "metrics": [{"event_id": "8b4d9d4f7a734a4ab1ed7083a027f82f", "step": 1, "value": 1.4852924520717696, "stage": "draft", "created_at": 1789571506.326212}], "maximize": false, "elapsed_seconds": 1640.0959587097168, "node_count": 2, "metric_name": "BPB", "versions": [{"bundle_id": "03-historical-run-logs", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/03-historical-run-logs/logs-18799fb1fca5.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/03-historical-run-logs", "member": "MLEvolve_BO/runs/autoresearch_paired_drafts5_serial_8h_20260916_145852/gp7_long_horizon_logei/runs/20260916_111127_gp7_long_horizon_logei/logs/journal.json", "sha256": "18799fb1fca5aa0c206be70e600c8d13ba65086d8360620e18525cd877b72d9b"}], "official_score": null, "note": ""}, {"id": "xixian.20260916-122453-gp7-ancestry-logei", "experiment_id": "nanogpt-autoresearch-paired-serial-segmented8h-20260916-160835", "family": "nanoGPT", "method": "gp7_ancestry_logei", "dataset": "nanoGPT", "status": "archived", "artifacts": [{"bundle_id": "03-historical-run-logs", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/03-historical-run-logs/logs-18799fb1fca5.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/03-historical-run-logs", "member": "MLEvolve_BO/runs/autoresearch_paired_serial_segmented8h_20260916_160835/gp7_ancestry_logei/runs/20260916_122453_gp7_ancestry_logei/logs/journal.json", "sha256": "18799fb1fca5aa0c206be70e600c8d13ba65086d8360620e18525cd877b72d9b"}], "curve_scope": "原始 journal 候选 BPB，未按预算或恢复边界重新审计。", "journal_ref": "03-historical-run-logs:MLEvolve_BO/runs/autoresearch_paired_serial_segmented8h_20260916_160835/gp7_ancestry_logei/runs/20260916_122453_gp7_ancestry_logei/logs/journal.json", "metrics": [{"event_id": "6bcf5d965058429fb2c41628cfc8a79b", "step": 1, "value": 1.5018076671682725, "stage": "draft", "created_at": 1789575921.791244}, {"event_id": "dfc222b79b4c4bc480c9061e98f3ed7c", "step": 4, "value": 1.4771525982208253, "stage": "improve", "created_at": 1789577900.2118337}, {"event_id": "063971672df148f7b3c239d322cd8672", "step": 5, "value": 1.456833796770038, "stage": "debug", "created_at": 1789578531.8790302}, {"event_id": "65e4603ddbae4e46a5410bddd18f2f4f", "step": 6, "value": 1.9533657418913433, "stage": "debug", "created_at": 1789579052.8163588}, {"event_id": "6c43806e32e345d98422c867d03866c6", "step": 7, "value": 1.170827445602622, "stage": "improve", "created_at": 1789579764.7207794}, {"event_id": "2e4daa840d3c4eeb98b6b2d6080cda9d", "step": 8, "value": 1.3392620053739446, "stage": "improve", "created_at": 1789580542.2970805}, {"event_id": "e3a8f499e9da4aa1a1dbc543657f4640", "step": 9, "value": 1.1791843456664959, "stage": "improve", "created_at": 1789581211.0258193}, {"event_id": "51272ae10f0e40e68904bdb46c76c172", "step": 10, "value": 1.2471461702323108, "stage": "improve", "created_at": 1789581859.3435426}, {"event_id": "b8ee55f136fb4787857f738188b27fe7", "step": 11, "value": 1.1328874339868462, "stage": "evolution", "created_at": 1789582529.717408}, {"event_id": "45596050fe614fe4af089ae83a245575", "step": 12, "value": 1.155133491113287, "stage": "improve", "created_at": 1789583163.4100764}, {"event_id": "f8d5f2aa07594a30b1436ee53d263dcf", "step": 13, "value": 1.1865916717769345, "stage": "improve", "created_at": 1789583966.027828}, {"event_id": "a54dd8edb9d1402187002c50b0fe2e47", "step": 14, "value": 1.1891466084285809, "stage": "improve", "created_at": 1789585516.7284057}, {"event_id": "640c26cbbdb44394bd8f2d3c009b0b52", "step": 15, "value": 1.1540558321123293, "stage": "evolution", "created_at": 1789588568.3208768}, {"event_id": "8578241c097c4bc4af319e0ddb6c9191", "step": 16, "value": 1.319562421272285, "stage": "draft", "created_at": 1789589083.8178024}, {"event_id": "8d1bc83902614f3a8c1a39d6a54dadc7", "step": 17, "value": 1.1234325585967069, "stage": "evolution", "created_at": 1789589957.24731}, {"event_id": "e34307092b9c48048ed1a25f70c3100f", "step": 18, "value": 1.1529986147014724, "stage": "improve", "created_at": 1789590545.4503486}, {"event_id": "26a1eba59e4c495997d1bcaf12cfa396", "step": 19, "value": 1.1634036203485199, "stage": "improve", "created_at": 1789591089.6537874}, {"event_id": "ae2aae8935cd4017ae77d30b5b4a28d2", "step": 20, "value": 1.1517160250291025, "stage": "improve", "created_at": 1789594441.5894728}, {"event_id": "5b08dc90d9144521bf99decfaa2bee7d", "step": 21, "value": 1.1681862244053183, "stage": "evolution", "created_at": 1789595066.0317192}, {"event_id": "af2534366e38410d8e68ee7443495176", "step": 23, "value": 1.1279804595626923, "stage": "evolution", "created_at": 1789596069.2728176}, {"event_id": "a17428fdb7bf487d8334d275a6526701", "step": 24, "value": 1.1220012693653907, "stage": "fusion", "created_at": 1789596653.7823637}, {"event_id": "9277d2ec2f40404eaae4188fca7c7835", "step": 25, "value": 1.2967931746402819, "stage": "debug", "created_at": 1789597226.4476633}, {"event_id": "743b62ef10024682b9624defe795f6c0", "step": 26, "value": 1.2006562603844133, "stage": "improve", "created_at": 1789597858.0125859}, {"event_id": "71f666c9ef1b406ea61dd12530ca4b59", "step": 27, "value": 1.2042753020137267, "stage": "improve", "created_at": 1789598418.3733184}, {"event_id": "564c097257bc4101a3e32efb6883772b", "step": 28, "value": 1.1297116868868102, "stage": "improve", "created_at": 1789599155.8364139}, {"event_id": "7941336247464aff940f3e2640d7ae54", "step": 29, "value": 1.2208873607723723, "stage": "fusion", "created_at": 1789599730.7393157}, {"event_id": "0f5f8afa6d274a178b5c4ddf77b26eb8", "step": 30, "value": 1.1467721840183573, "stage": "fusion", "created_at": 1789600509.1115296}, {"event_id": "0c2298eda8b344f19b1ce9f3fe8a59ad", "step": 31, "value": 2.52705205573605, "stage": "evolution", "created_at": 1789601099.6215644}, {"event_id": "cd77f32fe0bc465bad52f2a0c8a35fab", "step": 32, "value": 1.1202569575279968, "stage": "evolution", "created_at": 1789601707.9352548}, {"event_id": "29e41ce78aee482e9e6ca240f64b5d0a", "step": 33, "value": 1.1226400158417915, "stage": "improve", "created_at": 1789602239.4539707}, {"event_id": "01617eb288784d559213c8b1a5ff1a0d", "step": 34, "value": 1.3440795366095095, "stage": "improve", "created_at": 1789602781.9061563}, {"event_id": "2bc290578d81407d89aab5f5d1c11aa1", "step": 35, "value": 1.1360079041699882, "stage": "improve", "created_at": 1789603322.0139868}, {"event_id": "0b06e41dfe934ce99069c791dcf35622", "step": 36, "value": 1.1440083956809888, "stage": "improve", "created_at": 1789605728.0049586}, {"event_id": "f26eaa0c5af04641834caac8ea694f19", "step": 37, "value": 1.1623738298037742, "stage": "improve", "created_at": 1789606226.4811509}, {"event_id": "0339bb7d0d384228ac4a8ce62f8bca0d", "step": 38, "value": 1.1737067384620208, "stage": "improve", "created_at": 1789606737.5038059}, {"event_id": "5732073cf949449682333b8c8ee994ab", "step": 39, "value": 1.4472877983651489, "stage": "improve", "created_at": 1789607229.6078613}, {"event_id": "03062121414f4d3583c75c5878a3e292", "step": 41, "value": 1.1547902896761062, "stage": "fusion", "created_at": 1789607865.1287243}, {"event_id": "ef4c2bc8300a4abebe03f45578995ff8", "step": 42, "value": 1.1632361912403841, "stage": "improve", "created_at": 1789608426.6926951}, {"event_id": "a39c99b0ae364190a6e9f4b3c8698eb2", "step": 43, "value": 1.1151501145411105, "stage": "debug", "created_at": 1789608884.688953}, {"event_id": "206c98da2de94ad9bb54bc6f1944596e", "step": 44, "value": 1.2245425465525392, "stage": "improve", "created_at": 1789609586.3252647}, {"event_id": "c0f2ada209d847d4bb717e33593249ab", "step": 45, "value": 1.3450623276975822, "stage": "improve", "created_at": 1789610114.9194257}, {"event_id": "3e22d298722b4aa8be026dea0c2dcdc3", "step": 47, "value": 1.127048878478997, "stage": "fusion", "created_at": 1789610764.2812915}], "maximize": false, "elapsed_seconds": 28639.041058540344, "node_count": 48, "metric_name": "BPB", "versions": [{"bundle_id": "03-historical-run-logs", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/03-historical-run-logs/logs-18799fb1fca5.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/03-historical-run-logs", "member": "MLEvolve_BO/runs/autoresearch_paired_serial_segmented8h_20260916_160835/gp7_ancestry_logei/runs/20260916_122453_gp7_ancestry_logei/logs/journal.json", "sha256": "18799fb1fca5aa0c206be70e600c8d13ba65086d8360620e18525cd877b72d9b"}], "official_score": null, "note": ""}, {"id": "xixian.20260916-122453-gp7-long-horizon-logei", "experiment_id": "nanogpt-autoresearch-paired-serial-segmented8h-20260916-160835", "family": "nanoGPT", "method": "gp7_long_horizon_logei", "dataset": "nanoGPT", "status": "archived", "artifacts": [{"bundle_id": "03-historical-run-logs", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/03-historical-run-logs/logs-18799fb1fca5.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/03-historical-run-logs", "member": "MLEvolve_BO/runs/autoresearch_paired_serial_segmented8h_20260916_160835/gp7_long_horizon_logei/runs/20260916_122453_gp7_long_horizon_logei/logs/journal.json", "sha256": "18799fb1fca5aa0c206be70e600c8d13ba65086d8360620e18525cd877b72d9b"}], "curve_scope": "原始 journal 候选 BPB，未按预算或恢复边界重新审计。", "journal_ref": "03-historical-run-logs:MLEvolve_BO/runs/autoresearch_paired_serial_segmented8h_20260916_160835/gp7_long_horizon_logei/runs/20260916_122453_gp7_long_horizon_logei/logs/journal.json", "metrics": [{"event_id": "ba7adb2199454bec8ed834eedc907eae", "step": 1, "value": 1.4833697334842415, "stage": "draft", "created_at": 1789575921.9459574}, {"event_id": "90c42a3de64b48ca84c50605d6f45abd", "step": 4, "value": 1.5055124483548683, "stage": "improve", "created_at": 1789578154.940609}, {"event_id": "5de4730b9fc4452e85971013ac10c72c", "step": 5, "value": 3.0971402068368077, "stage": "debug", "created_at": 1789578727.2254114}, {"event_id": "036e447940454837b798f9a45ca0c897", "step": 6, "value": 3.2881257529837304, "stage": "debug", "created_at": 1789579252.865998}, {"event_id": "4896e8daa8d846dd865e60ae681bfbe7", "step": 7, "value": 1.6715968869981932, "stage": "improve", "created_at": 1789580036.4245014}, {"event_id": "af11724ec5a745fbabbb7edebb36ba0d", "step": 8, "value": 1.4840017338991185, "stage": "improve", "created_at": 1789580704.4920769}, {"event_id": "fcd2afd5be454150a9ccfbf4b5f61514", "step": 9, "value": 1.4665671260764217, "stage": "evolution", "created_at": 1789581275.5418766}, {"event_id": "ceb314fecc464e349aae0e0f531d7e8c", "step": 10, "value": 1.4734444154494846, "stage": "improve", "created_at": 1789581885.4996178}, {"event_id": "c2d0469ee0d1430380554d2ef59d28bd", "step": 11, "value": 1.5016320911894605, "stage": "improve", "created_at": 1789582539.7252264}, {"event_id": "544141ce0bb1433ab2d7d70b1dd26f29", "step": 12, "value": 1.6716810936924718, "stage": "improve", "created_at": 1789583197.3300593}, {"event_id": "26b5a685ea674bc393858a5acd48dd2c", "step": 13, "value": 1.4099890069724694, "stage": "evolution", "created_at": 1789583885.3458483}, {"event_id": "8c9116c0e83342509df6b7488686f40f", "step": 14, "value": 1.4657235761901832, "stage": "improve", "created_at": 1789585542.983414}, {"event_id": "852ada0652974a70ab6fbdd973b41e4d", "step": 15, "value": 1.51998194641886, "stage": "improve", "created_at": 1789588536.369117}, {"event_id": "8b1b75fc94a042bc97bc4428bc4bd2ac", "step": 16, "value": 1.5214449935365073, "stage": "improve", "created_at": 1789589123.092943}, {"event_id": "c2b446c958e54bb68c2472ffe2d90b2d", "step": 17, "value": 1.4311526928254843, "stage": "evolution", "created_at": 1789589632.7989342}, {"event_id": "308619f0b7964239b7fcc54a75ddf29b", "step": 18, "value": 1.3193698643595857, "stage": "draft", "created_at": 1789590098.0235326}, {"event_id": "8afafc7e0f5f48eca76e105e0453bb80", "step": 19, "value": 1.2620957615215824, "stage": "evolution", "created_at": 1789590961.661027}, {"event_id": "867bef37836442c8acd6a3857af65274", "step": 20, "value": 1.7793403174388915, "stage": "improve", "created_at": 1789594407.4963386}, {"event_id": "bab260a5f25e495db3057d63e9fe9b5f", "step": 21, "value": 1.410672102776435, "stage": "improve", "created_at": 1789595125.7895796}, {"event_id": "b63a6be6202f4ebb95bf3abbb3956a1f", "step": 22, "value": 1.4248859963671714, "stage": "improve", "created_at": 1789595697.775401}, {"event_id": "c16d02bcf3a8406794c4f690d5f94804", "step": 23, "value": 1.5650833076222852, "stage": "improve", "created_at": 1789596203.8941972}, {"event_id": "4c9cc31a690c49bfa4a7b6b59030aa5f", "step": 25, "value": 1.4083993317925865, "stage": "improve", "created_at": 1789597154.987339}, {"event_id": "c4060d9f298541cb91f0ecab27e40f14", "step": 26, "value": 1.857792996233335, "stage": "improve", "created_at": 1789597717.8911648}, {"event_id": "9277d773a275450fae1da0e763c2a794", "step": 28, "value": 1.9125346538729433, "stage": "evolution", "created_at": 1789598619.1260972}, {"event_id": "645308fb9b864f80a493a28034068e98", "step": 29, "value": 1.2238894754281038, "stage": "fusion", "created_at": 1789599165.4366236}, {"event_id": "2c9305686446458cbf594df9e617dedb", "step": 30, "value": 1.1795092143816355, "stage": "debug", "created_at": 1789599675.6339316}, {"event_id": "795cdab4de514f3db69186cbe299fed9", "step": 31, "value": 1.1397967894162664, "stage": "improve", "created_at": 1789600224.621523}, {"event_id": "be6a05f14b3847e99b0fac20330af313", "step": 32, "value": 1.1219860481622252, "stage": "improve", "created_at": 1789600788.4924064}, {"event_id": "a5efa7eac892442bbd9ec5a698ea45ff", "step": 33, "value": 1.123594599721336, "stage": "improve", "created_at": 1789601366.5625465}, {"event_id": "086cbbff96bd477684c29ae991b15923", "step": 34, "value": 1.0867725096868641, "stage": "improve", "created_at": 1789601890.1182463}, {"event_id": "6837c44f1fee4afa8e32d402dbe0482d", "step": 35, "value": 1.0929630920091036, "stage": "improve", "created_at": 1789602356.5806072}, {"event_id": "9790d4f985b043cd9578a0d410cfdcfb", "step": 36, "value": 1.0879203096501353, "stage": "improve", "created_at": 1789602826.5152678}, {"event_id": "8081c9526b344618983f7c43e9f57c1f", "step": 37, "value": 1.1031976230560654, "stage": "improve", "created_at": 1789603318.938283}, {"event_id": "fd7345bfb728447990d686acdafae14c", "step": 38, "value": 1.0861945782688727, "stage": "fusion", "created_at": 1789605695.643681}, {"event_id": "61334a6c37fb4d69b772fbaaba388e69", "step": 39, "value": 1.0915471362001026, "stage": "improve", "created_at": 1789606208.7123635}, {"event_id": "7f568f7850f14cd68559640bb10d1083", "step": 40, "value": 1.0969811322207692, "stage": "improve", "created_at": 1789606701.9567616}, {"event_id": "a110dfb24d434bb297f964be1a7a4acd", "step": 41, "value": 1.1031856338442914, "stage": "improve", "created_at": 1789607199.4258394}, {"event_id": "8c29c37c71b04118a8e3e5d7ffbb94c2", "step": 42, "value": 1.1336376434984514, "stage": "fusion", "created_at": 1789607646.2355664}, {"event_id": "cacd8fd903314ecd95bc97df50d4899f", "step": 43, "value": 1.0911308598622145, "stage": "evolution", "created_at": 1789608112.7416813}, {"event_id": "e4285560b5fb46be988d5a0de98cd1f3", "step": 44, "value": 1.1692255618311795, "stage": "evolution", "created_at": 1789608609.680936}, {"event_id": "0169718f859b4f6ba8a5d0e675d1aa7a", "step": 45, "value": 1.0979853157665442, "stage": "evolution", "created_at": 1789609064.3471987}, {"event_id": "72b0866fc352441d96999753cd0b255f", "step": 46, "value": 1.0942820296372124, "stage": "fusion", "created_at": 1789609518.7389517}, {"event_id": "3daf3c82ca0c4a75b20892e9df3263b2", "step": 47, "value": 1.093989950878475, "stage": "evolution", "created_at": 1789609950.6405203}, {"event_id": "e14930ae7317483b967c04bb0502888f", "step": 48, "value": 1.0896017209899695, "stage": "fusion", "created_at": 1789610431.8410852}, {"event_id": "3feef521d8c048df987e033fb8d54605", "step": 49, "value": 1.075012128733896, "stage": "fusion", "created_at": 1789610881.5924125}], "maximize": false, "elapsed_seconds": 28717.34429717064, "node_count": 50, "metric_name": "BPB", "versions": [{"bundle_id": "03-historical-run-logs", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/03-historical-run-logs/logs-18799fb1fca5.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/03-historical-run-logs", "member": "MLEvolve_BO/runs/autoresearch_paired_serial_segmented8h_20260916_160835/gp7_long_horizon_logei/runs/20260916_122453_gp7_long_horizon_logei/logs/journal.json", "sha256": "18799fb1fca5aa0c206be70e600c8d13ba65086d8360620e18525cd877b72d9b"}], "official_score": null, "note": ""}, {"id": "xixian.20260916-122453-gp7-long-horizon-pibo", "experiment_id": "nanogpt-autoresearch-paired-serial-segmented8h-20260916-160835", "family": "nanoGPT", "method": "gp7_long_horizon_pibo", "dataset": "nanoGPT", "status": "archived", "artifacts": [{"bundle_id": "03-historical-run-logs", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/03-historical-run-logs/logs-18799fb1fca5.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/03-historical-run-logs", "member": "MLEvolve_BO/runs/autoresearch_paired_serial_segmented8h_20260916_160835/gp7_long_horizon_pibo/runs/20260916_122453_gp7_long_horizon_pibo/logs/journal.json", "sha256": "18799fb1fca5aa0c206be70e600c8d13ba65086d8360620e18525cd877b72d9b"}], "curve_scope": "原始 journal 候选 BPB，未按预算或恢复边界重新审计。", "journal_ref": "03-historical-run-logs:MLEvolve_BO/runs/autoresearch_paired_serial_segmented8h_20260916_160835/gp7_long_horizon_pibo/runs/20260916_122453_gp7_long_horizon_pibo/logs/journal.json", "metrics": [{"event_id": "049fff26fb5c4275b7860968e728791c", "step": 1, "value": 1.4899884639453596, "stage": "draft", "created_at": 1789575921.7541084}, {"event_id": "0bb946fca0e849e98f600af4c00afe34", "step": 4, "value": 1.6663613593967008, "stage": "improve", "created_at": 1789577850.6488993}, {"event_id": "310dd8bbd0f745059498c563456ece63", "step": 5, "value": 1.444091253049742, "stage": "debug", "created_at": 1789578507.7279952}, {"event_id": "e857e77586e74262b37ed68905daffe9", "step": 6, "value": 1.9480521579504575, "stage": "debug", "created_at": 1789579094.2256386}, {"event_id": "6193a7cb85924eb7ac5e095c8d781c6a", "step": 7, "value": 1.2496000560020806, "stage": "improve", "created_at": 1789579831.796681}, {"event_id": "cddaa1cd90fc49158a5c2c8916fbf236", "step": 8, "value": 1.2344227688626088, "stage": "improve", "created_at": 1789580475.2020588}, {"event_id": "ef0fe34144bd41da92e2c01d75887117", "step": 9, "value": 1.2770723099007133, "stage": "improve", "created_at": 1789581152.615144}, {"event_id": "a3a46229ac3b49359a3723cfdd8b222e", "step": 10, "value": 1.2338830878011544, "stage": "improve", "created_at": 1789581763.1972065}, {"event_id": "f8c9255d17504e478535223ea79cf33d", "step": 11, "value": 1.1445641407207434, "stage": "improve", "created_at": 1789582505.0250778}, {"event_id": "3c521588f13a4ff7bbbdfafb88973dc6", "step": 12, "value": 1.1391144491946203, "stage": "improve", "created_at": 1789583186.6922312}, {"event_id": "f0ce4c25e5734deaaa614bb913bf94e4", "step": 13, "value": 1.183204240888666, "stage": "improve", "created_at": 1789583849.9779131}, {"event_id": "139db42cd9d64ca58d69cd8b77bb48d9", "step": 14, "value": 1.1388004544219323, "stage": "improve", "created_at": 1789585513.7480667}, {"event_id": "c5c9d201c47d4c2d95892893dbfab0fe", "step": 15, "value": 1.1455457845909813, "stage": "improve", "created_at": 1789588543.7014217}, {"event_id": "4a58ebd215364818b472bd8c5a36c5d5", "step": 16, "value": 1.2278273877055812, "stage": "improve", "created_at": 1789589151.9698343}, {"event_id": "52352e1ef917434ea22e8d26b2f1bd3c", "step": 17, "value": 1.1048690633982812, "stage": "improve", "created_at": 1789589788.81828}, {"event_id": "0f5b0e1c530d44918d574fffca8a4e4b", "step": 18, "value": 1.1722472946041034, "stage": "improve", "created_at": 1789590412.703737}, {"event_id": "25fee4ce07124c2aa8b24ad13bbc9a90", "step": 19, "value": 1.1273364879070795, "stage": "improve", "created_at": 1789591105.602172}, {"event_id": "eb4438f856a745758a0ee8afaa147a22", "step": 20, "value": 1.108020037621759, "stage": "improve", "created_at": 1789594479.2543685}, {"event_id": "f76d34b4ce95488a8fd591fa4e8d6fe4", "step": 21, "value": 1.1855942526630778, "stage": "evolution", "created_at": 1789595184.163213}, {"event_id": "018f6ac73de14c00969bdf04a489ea98", "step": 22, "value": 1.3579218410787215, "stage": "draft", "created_at": 1789595670.4694786}, {"event_id": "dcc8e3af57a14b559de664a9abdf471a", "step": 23, "value": 1.1401606801776378, "stage": "evolution", "created_at": 1789596560.2635226}, {"event_id": "e11cb95c1afc48f7a7fd01797201ab99", "step": 24, "value": 1.0682353204942376, "stage": "fusion", "created_at": 1789597145.0194905}, {"event_id": "a4a6da6b1ce6463dba7e96192479c062", "step": 25, "value": 1.0741612940543426, "stage": "improve", "created_at": 1789597834.5177944}, {"event_id": "c0a845edf7aa4a37a00ddb31eda5c8dd", "step": 26, "value": 1.0889597545028697, "stage": "improve", "created_at": 1789598436.6376228}, {"event_id": "e67eae7c0dab42c08ff70397c412fa08", "step": 27, "value": 1.127926970431308, "stage": "improve", "created_at": 1789599027.8412006}, {"event_id": "0bf5a0baa3944d0d97962ba10759f942", "step": 28, "value": 1.1193296912240271, "stage": "fusion", "created_at": 1789599567.9366071}, {"event_id": "9b5b81ec26474731811f6519c7800e69", "step": 30, "value": 1.1482861474803048, "stage": "fusion", "created_at": 1789600494.3740091}, {"event_id": "da05625e780f4cc1b84e22bdd520e006", "step": 32, "value": 1.2895430967120098, "stage": "debug", "created_at": 1789601238.922407}, {"event_id": "82b717a9aceb4edebf8d494b99b53f34", "step": 34, "value": 1.8438751661795525, "stage": "debug", "created_at": 1789601968.8433592}, {"event_id": "ba5e79ca3afa4599a6b4bf620b8a2ae5", "step": 35, "value": 1.0654847378082548, "stage": "evolution", "created_at": 1789602501.28327}, {"event_id": "4c560cbe46364b0ca9dc20e53ff4b535", "step": 36, "value": 1.0850925776962754, "stage": "debug", "created_at": 1789603010.9692404}, {"event_id": "7ff46579f8d0436f8473f1008a3eb859", "step": 37, "value": 1.0744545758076929, "stage": "improve", "created_at": 1789603537.1016693}, {"event_id": "20d9b0ff16fc4b14aa21e4902961b802", "step": 40, "value": 1.0689061069357106, "stage": "improve", "created_at": 1789605992.7909675}, {"event_id": "bcd66dec37f946e3a5517a6da1b814eb", "step": 42, "value": 1.146847211305973, "stage": "fusion_draft", "created_at": 1789606552.0836375}, {"event_id": "a1c3ed4e680648f4b86a16a704012d53", "step": 43, "value": 1.065042765281799, "stage": "fusion", "created_at": 1789607041.08657}, {"event_id": "a0e0f76881584d28b2c78301eb4310b8", "step": 45, "value": 1.080587662521967, "stage": "improve", "created_at": 1789607677.3596551}, {"event_id": "86eb2a901c224cc79428e50b1535abef", "step": 46, "value": 1.074694642521272, "stage": "improve", "created_at": 1789608177.7601225}, {"event_id": "d1365e54b57c476cbd1f0c34c6fbb04f", "step": 47, "value": 1.1398055708642711, "stage": "improve", "created_at": 1789608695.8145847}, {"event_id": "49d8bdeab8c342a8b2dd8cd2358d0b71", "step": 48, "value": 1.0650834048545925, "stage": "fusion", "created_at": 1789609236.705518}, {"event_id": "b0c718e8f2c34494ab100284857f409b", "step": 49, "value": 1.085079631094078, "stage": "evolution", "created_at": 1789609692.6209452}, {"event_id": "cf5a03d387014560b0fa506eab02d206", "step": 50, "value": 1.0691249771424636, "stage": "evolution", "created_at": 1789610171.4933698}], "maximize": false, "elapsed_seconds": 28355.28127026558, "node_count": 51, "metric_name": "BPB", "versions": [{"bundle_id": "03-historical-run-logs", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/03-historical-run-logs/logs-18799fb1fca5.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/03-historical-run-logs", "member": "MLEvolve_BO/runs/autoresearch_paired_serial_segmented8h_20260916_160835/gp7_long_horizon_pibo/runs/20260916_122453_gp7_long_horizon_pibo/logs/journal.json", "sha256": "18799fb1fca5aa0c206be70e600c8d13ba65086d8360620e18525cd877b72d9b"}], "official_score": null, "note": ""}, {"id": "xixian.20260916-122453-mlevolve-original", "experiment_id": "nanogpt-autoresearch-paired-serial-segmented8h-20260916-160835", "family": "nanoGPT", "method": "mlevolve_original", "dataset": "nanoGPT", "status": "archived", "artifacts": [{"bundle_id": "03-historical-run-logs", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/03-historical-run-logs/logs-18799fb1fca5.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/03-historical-run-logs", "member": "MLEvolve_BO/runs/autoresearch_paired_serial_segmented8h_20260916_160835/mlevolve_original/runs/20260916_122453_mlevolve_original/logs/journal.json", "sha256": "18799fb1fca5aa0c206be70e600c8d13ba65086d8360620e18525cd877b72d9b"}], "curve_scope": "原始 journal 候选 BPB，未按预算或恢复边界重新审计。", "journal_ref": "03-historical-run-logs:MLEvolve_BO/runs/autoresearch_paired_serial_segmented8h_20260916_160835/mlevolve_original/runs/20260916_122453_mlevolve_original/logs/journal.json", "metrics": [{"event_id": "2baedbea5c3246d69bbd8b1833c61c7e", "step": 1, "value": 1.4980395014641534, "stage": "draft", "created_at": 1789575921.9030309}, {"event_id": "4b0d0380c9cf4095ac503eab06f5ba0d", "step": 5, "value": 1.4328725166605563, "stage": "debug", "created_at": 1789578086.9934986}, {"event_id": "79eaa74cdba5490787f7c660d85dd50b", "step": 6, "value": 1.953418409546601, "stage": "debug", "created_at": 1789578580.9435625}, {"event_id": "b8f1484579b04acbbfecaecf3dcb5c03", "step": 7, "value": 1.6193084406153855, "stage": "debug", "created_at": 1789579207.5087342}, {"event_id": "ea4ccec0c68149feb1a619e2e1de9271", "step": 8, "value": 1.1753719384610413, "stage": "improve", "created_at": 1789579745.9957535}, {"event_id": "38179b2b2e904162bc32121d0625d54d", "step": 9, "value": 1.7182149103810367, "stage": "improve", "created_at": 1789580418.5142577}, {"event_id": "ac59bdf865584773899c3cebc0cf478a", "step": 10, "value": 1.8683703872677506, "stage": "improve", "created_at": 1789581038.4409184}, {"event_id": "1f41a239bab34b8eab08f39493ea8f2c", "step": 12, "value": 1.804728686615252, "stage": "improve", "created_at": 1789581828.1187515}, {"event_id": "7ebea5b9a5814ba0bad6fe898b7b9528", "step": 13, "value": 1.8604818924652315, "stage": "improve", "created_at": 1789582497.1158407}, {"event_id": "5f94e73b36c3475f81a06e466d594986", "step": 14, "value": 1.2476183211905132, "stage": "debug", "created_at": 1789583041.091931}, {"event_id": "8d448ed797fb4c69a43215eede835d0a", "step": 15, "value": 1.6576260298683876, "stage": "improve", "created_at": 1789583624.1217365}, {"event_id": "30ef8c6dcb2a4efcab94f9c6e66af06e", "step": 16, "value": 1.590782085617048, "stage": "evolution", "created_at": 1789584285.9715827}, {"event_id": "e53882931caf4ea393e037d8424c62c8", "step": 17, "value": 1.5406066741786335, "stage": "improve", "created_at": 1789585533.3925328}, {"event_id": "294f1aa2a00d4ed19fb515cfeccbe419", "step": 18, "value": 1.708519479864434, "stage": "improve", "created_at": 1789588553.9491227}, {"event_id": "9ad66bb1f87543c89212e9fc209972cd", "step": 19, "value": 1.3206516733234621, "stage": "draft", "created_at": 1789589223.5609672}, {"event_id": "4171082ed67e4aacb8ca08b9fe895700", "step": 20, "value": 1.10164083500931, "stage": "improve", "created_at": 1789590067.433235}, {"event_id": "7534694e38db40339cfa251b4788937d", "step": 21, "value": 1.66525880478365, "stage": "improve", "created_at": 1789590618.1711152}, {"event_id": "659e5fbcbc5d4e67bc4c41c35ade031e", "step": 22, "value": 1.1538943628660732, "stage": "improve", "created_at": 1789591319.5241668}, {"event_id": "734f511c2941478babe70eecc2e07857", "step": 23, "value": 1.1284416449927073, "stage": "improve", "created_at": 1789594453.904691}, {"event_id": "99a2ce8566834040b3c76ad1783bb1be", "step": 24, "value": 1.5950256853883809, "stage": "improve", "created_at": 1789595129.9187644}, {"event_id": "6821df7a707c454cbb321b169ec1afc5", "step": 25, "value": 1.0571271632314119, "stage": "improve", "created_at": 1789595936.395714}, {"event_id": "a590c99e5edc4d3bbd3f3eaf696ee8e0", "step": 26, "value": 1.1410306805035757, "stage": "improve", "created_at": 1789596610.1444447}, {"event_id": "2938babf8488417ba978e53efe913007", "step": 27, "value": 1.6441227589199483, "stage": "improve", "created_at": 1789597314.9423635}, {"event_id": "0a048a6a6b024e36aa33ec58051473b9", "step": 28, "value": 1.0827998858830794, "stage": "improve", "created_at": 1789598041.264958}, {"event_id": "248bb96e70164db3b68063bbb8ddc1af", "step": 29, "value": 1.11271590160036, "stage": "improve", "created_at": 1789598693.1943204}, {"event_id": "d2e79a88249846c19f3bb5468e70963b", "step": 30, "value": 1.071553071011247, "stage": "improve", "created_at": 1789599267.2456758}, {"event_id": "55352e8714804dada91bcc2c10e670cb", "step": 31, "value": 1.0756932193693487, "stage": "improve", "created_at": 1789599888.430309}, {"event_id": "a3be4c3448fd446798897887d5d65193", "step": 32, "value": 1.2730747477536999, "stage": "evolution", "created_at": 1789600415.684664}, {"event_id": "0067880e176442ce9eb0141704719420", "step": 33, "value": 1.0694463017026217, "stage": "fusion", "created_at": 1789600971.9832587}, {"event_id": "ff385c0827454a439dcde7ceb6c0bd02", "step": 35, "value": 1.1012084161530287, "stage": "fusion", "created_at": 1789602119.2862277}, {"event_id": "2453841a70f049e08ccf28269aaba993", "step": 36, "value": 1.0650554605556983, "stage": "fusion", "created_at": 1789602652.6601117}, {"event_id": "1ce052578e204d52ae9b1e0f8b7b0fa3", "step": 37, "value": 1.0920700500166265, "stage": "debug", "created_at": 1789603133.3901045}, {"event_id": "2be1bd6f80214ee7884f2037a16a70ae", "step": 38, "value": 1.0646741734299385, "stage": "fusion", "created_at": 1789605692.9748905}, {"event_id": "7381a3c7a2ce48919724df09e83edbc3", "step": 39, "value": 1.082041348059871, "stage": "evolution", "created_at": 1789606266.186789}, {"event_id": "d1d79eb689644f06875e9247c51b3ea5", "step": 41, "value": 1.0658520354791232, "stage": "evolution", "created_at": 1789606921.9603024}, {"event_id": "891a7a76f5024e6a94714c5551a613cb", "step": 43, "value": 1.092712351963107, "stage": "debug", "created_at": 1789607788.0902328}, {"event_id": "eb5784585d4e470a812f2d639b881f80", "step": 44, "value": 1.087348144273048, "stage": "improve", "created_at": 1789608301.2466455}, {"event_id": "2f9a7503ba3d45ff86e18bf9cf3bbb14", "step": 45, "value": 1.063450437842907, "stage": "evolution", "created_at": 1789608858.622525}, {"event_id": "745cc33aa923496894deb57631ab0444", "step": 46, "value": 1.115459828346248, "stage": "improve", "created_at": 1789609391.1052415}, {"event_id": "e7f1ede6276f445baf42f78956e42e25", "step": 47, "value": 1.0967002901532186, "stage": "fusion", "created_at": 1789609941.6172748}, {"event_id": "b4fac7ef892f47849724786a93ceda8a", "step": 49, "value": 1.1717659660363418, "stage": "improve", "created_at": 1789610644.473284}], "maximize": false, "elapsed_seconds": 28339.349556922913, "node_count": 50, "metric_name": "BPB", "versions": [{"bundle_id": "03-historical-run-logs", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/03-historical-run-logs/logs-18799fb1fca5.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/03-historical-run-logs", "member": "MLEvolve_BO/runs/autoresearch_paired_serial_segmented8h_20260916_160835/mlevolve_original/runs/20260916_122453_mlevolve_original/logs/journal.json", "sha256": "18799fb1fca5aa0c206be70e600c8d13ba65086d8360620e18525cd877b72d9b"}], "official_score": null, "note": ""}, {"id": "xixian.20260916-170640-gp7-long-horizon-pibo", "experiment_id": "nanogpt-autoresearch-paired-seed43-three-segmented8h-20260916-210252", "family": "nanoGPT", "method": "gp7_long_horizon_pibo", "dataset": "nanoGPT", "status": "archived", "artifacts": [{"bundle_id": "03-historical-run-logs", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/03-historical-run-logs/logs-18799fb1fca5.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/03-historical-run-logs", "member": "MLEvolve_BO/runs/autoresearch_paired_seed43_three_segmented8h_20260916_210252/gp7_long_horizon_pibo/runs/20260916_170640_gp7_long_horizon_pibo/logs/journal.json", "sha256": "18799fb1fca5aa0c206be70e600c8d13ba65086d8360620e18525cd877b72d9b"}], "curve_scope": "原始 journal 候选 BPB，未按预算或恢复边界重新审计。", "journal_ref": "03-historical-run-logs:MLEvolve_BO/runs/autoresearch_paired_seed43_three_segmented8h_20260916_210252/gp7_long_horizon_pibo/runs/20260916_170640_gp7_long_horizon_pibo/logs/journal.json", "metrics": [{"event_id": "6d2e4c85fe184792a112593483ca123d", "step": 1, "value": 1.4913732531817476, "stage": "draft", "created_at": 1789592820.2913642}], "maximize": false, "elapsed_seconds": 1843.6209859848022, "node_count": 4, "metric_name": "BPB", "versions": [{"bundle_id": "03-historical-run-logs", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/03-historical-run-logs/logs-18799fb1fca5.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/03-historical-run-logs", "member": "MLEvolve_BO/runs/autoresearch_paired_seed43_three_segmented8h_20260916_210252/gp7_long_horizon_pibo/runs/20260916_170640_gp7_long_horizon_pibo/logs/journal.json", "sha256": "18799fb1fca5aa0c206be70e600c8d13ba65086d8360620e18525cd877b72d9b"}], "official_score": null, "note": ""}, {"id": "xixian.20260916-170642-gp7-ancestry-logei", "experiment_id": "nanogpt-autoresearch-paired-seed43-three-segmented8h-20260916-210252", "family": "nanoGPT", "method": "gp7_ancestry_logei", "dataset": "nanoGPT", "status": "archived", "artifacts": [{"bundle_id": "03-historical-run-logs", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/03-historical-run-logs/logs-18799fb1fca5.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/03-historical-run-logs", "member": "MLEvolve_BO/runs/autoresearch_paired_seed43_three_segmented8h_20260916_210252/gp7_ancestry_logei/runs/20260916_170642_gp7_ancestry_logei/logs/journal.json", "sha256": "18799fb1fca5aa0c206be70e600c8d13ba65086d8360620e18525cd877b72d9b"}], "curve_scope": "原始 journal 候选 BPB，未按预算或恢复边界重新审计。", "journal_ref": "03-historical-run-logs:MLEvolve_BO/runs/autoresearch_paired_seed43_three_segmented8h_20260916_210252/gp7_ancestry_logei/runs/20260916_170642_gp7_ancestry_logei/logs/journal.json", "metrics": [{"event_id": "e5c610399b8247be8fa4dd4a0d3804cd", "step": 1, "value": 1.4876576841805647, "stage": "draft", "created_at": 1789592823.2928038}], "maximize": false, "elapsed_seconds": 1854.120801448822, "node_count": 4, "metric_name": "BPB", "versions": [{"bundle_id": "03-historical-run-logs", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/03-historical-run-logs/logs-18799fb1fca5.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/03-historical-run-logs", "member": "MLEvolve_BO/runs/autoresearch_paired_seed43_three_segmented8h_20260916_210252/gp7_ancestry_logei/runs/20260916_170642_gp7_ancestry_logei/logs/journal.json", "sha256": "18799fb1fca5aa0c206be70e600c8d13ba65086d8360620e18525cd877b72d9b"}], "official_score": null, "note": ""}, {"id": "xixian.20260916-170642-gp7-long-horizon-logei", "experiment_id": "nanogpt-autoresearch-paired-seed43-three-segmented8h-20260916-210252", "family": "nanoGPT", "method": "gp7_long_horizon_logei", "dataset": "nanoGPT", "status": "archived", "artifacts": [{"bundle_id": "03-historical-run-logs", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/03-historical-run-logs/logs-18799fb1fca5.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/03-historical-run-logs", "member": "MLEvolve_BO/runs/autoresearch_paired_seed43_three_segmented8h_20260916_210252/gp7_long_horizon_logei/runs/20260916_170642_gp7_long_horizon_logei/logs/journal.json", "sha256": "18799fb1fca5aa0c206be70e600c8d13ba65086d8360620e18525cd877b72d9b"}], "curve_scope": "原始 journal 候选 BPB，未按预算或恢复边界重新审计。", "journal_ref": "03-historical-run-logs:MLEvolve_BO/runs/autoresearch_paired_seed43_three_segmented8h_20260916_210252/gp7_long_horizon_logei/runs/20260916_170642_gp7_long_horizon_logei/logs/journal.json", "metrics": [{"event_id": "5246af791f844af4ade923b2717c8346", "step": 1, "value": 1.4907705176042796, "stage": "draft", "created_at": 1789592823.6480649}], "maximize": false, "elapsed_seconds": 1862.358922958374, "node_count": 4, "metric_name": "BPB", "versions": [{"bundle_id": "03-historical-run-logs", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/03-historical-run-logs/logs-18799fb1fca5.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/03-historical-run-logs", "member": "MLEvolve_BO/runs/autoresearch_paired_seed43_three_segmented8h_20260916_210252/gp7_long_horizon_logei/runs/20260916_170642_gp7_long_horizon_logei/logs/journal.json", "sha256": "18799fb1fca5aa0c206be70e600c8d13ba65086d8360620e18525cd877b72d9b"}], "official_score": null, "note": ""}, {"id": "xixian.20260918-211001-study7-bounded-smoke", "experiment_id": "nanogpt-study7-smoke-20260918", "family": "nanoGPT", "method": "study7-bounded-smoke", "dataset": "nanoGPT", "status": "archived", "artifacts": [{"bundle_id": "study7-complete-for-gpt-20260919", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/study7-complete-for-gpt-20260919/logs-ee645141ae41.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/study7-complete-for-gpt-20260919", "member": "study7_complete_for_gpt_20260919/raw/study7_20260918/smoke/runs/20260918_211001_study7-bounded-smoke/logs/journal.json", "sha256": "ee645141ae417cc245c3e1412a8331050e8000178b3fca386cb53d5263f29def"}], "curve_scope": "原始 journal 候选 BPB，未按预算或恢复边界重新审计。", "journal_ref": "study7-complete-for-gpt-20260919:study7_complete_for_gpt_20260919/raw/study7_20260918/smoke/runs/20260918_211001_study7-bounded-smoke/logs/journal.json", "metrics": [], "maximize": null, "elapsed_seconds": 857.541139125824, "node_count": 1, "metric_name": "BPB", "versions": [{"bundle_id": "study7-complete-for-gpt-20260919", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/study7-complete-for-gpt-20260919/logs-ee645141ae41.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/study7-complete-for-gpt-20260919", "member": "study7_complete_for_gpt_20260919/raw/study7_20260918/smoke/runs/20260918_211001_study7-bounded-smoke/logs/journal.json", "sha256": "ee645141ae417cc245c3e1412a8331050e8000178b3fca386cb53d5263f29def"}], "official_score": null, "note": ""}, {"id": "xixian.20260918-213105-study7-review-recovery-smoke", "experiment_id": "nanogpt-study7-smoke-20260918", "family": "nanoGPT", "method": "study7-review-recovery-smoke", "dataset": "nanoGPT", "status": "archived", "artifacts": [{"bundle_id": "study7-complete-for-gpt-20260919", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/study7-complete-for-gpt-20260919/logs-ee645141ae41.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/study7-complete-for-gpt-20260919", "member": "study7_complete_for_gpt_20260919/raw/study7_20260918/smoke/runs/20260918_213105_study7-review-recovery-smoke/logs/journal.json", "sha256": "ee645141ae417cc245c3e1412a8331050e8000178b3fca386cb53d5263f29def"}], "curve_scope": "原始 journal 候选 BPB，未按预算或恢复边界重新审计。", "journal_ref": "study7-complete-for-gpt-20260919:study7_complete_for_gpt_20260919/raw/study7_20260918/smoke/runs/20260918_213105_study7-review-recovery-smoke/logs/journal.json", "metrics": [{"event_id": "84fb762902b540cf920007a2deab3e44", "step": 1, "value": 1.2729465990753903, "stage": "draft", "created_at": 1789781485.9397573}, {"event_id": "8c0caaa13741439b893114aa34f39bdf", "step": 2, "value": 1.6997098343688233, "stage": "draft", "created_at": 1789781485.9260387}, {"event_id": "70586f43bfbf4e1091ff636be7a28c80", "step": 4, "value": 1.4455682112153065, "stage": "debug", "created_at": 1789781758.4395092}], "maximize": false, "elapsed_seconds": 757.9253835678101, "node_count": 5, "metric_name": "BPB", "versions": [{"bundle_id": "study7-complete-for-gpt-20260919", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/study7-complete-for-gpt-20260919/logs-ee645141ae41.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/study7-complete-for-gpt-20260919", "member": "study7_complete_for_gpt_20260919/raw/study7_20260918/smoke/runs/20260918_213105_study7-review-recovery-smoke/logs/journal.json", "sha256": "ee645141ae417cc245c3e1412a8331050e8000178b3fca386cb53d5263f29def"}], "official_score": null, "note": ""}, {"id": "harry123.aq04-20260921.aerial-cactus-identification", "experiment_id": "mlebench-aq04-12h-20260921", "family": "MLEBench", "method": "AQ04", "dataset": "aerial-cactus-identification", "seed": 42, "status": "completed", "source_status": "completed", "wrapper_status": "completed", "source_updated_at": "2026-09-21T16:32:51.140384+00:00", "uploaded_at": "2026-09-22T04:54:17.397534+00:00", "elapsed_seconds": 42898.248155117035, "budget_seconds": 43200.0, "metrics": [{"event_id": "9ab473bb5c8f42e78fe898469a1e9f45", "step": 3, "value": 0.9999336577029377, "stage": "debug"}, {"event_id": "634f061cbc02493483577e796d95c933", "step": 4, "value": 0.9999988215051736, "stage": "draft"}, {"event_id": "48e41c9399174c14aac2052fb822b1a7", "step": 5, "value": 0.9998314752398237, "stage": "debug"}, {"event_id": "f24ae93f816f4067b27ba6aad9abf079", "step": 6, "value": 0.9999336577029377, "stage": "improve"}, {"event_id": "8cc8b88e34be457392c4e2a60c5d5617", "step": 7, "value": 0.9999004865544067, "stage": "improve"}, {"event_id": "3e8eedf051d64ccea4c6552b71f92034", "step": 8, "value": 0.9998991597084654, "stage": "improve"}, {"event_id": "601a337466ca435bb4595ed12fe69e63", "step": 9, "value": 0.999936361279374, "stage": "improve"}, {"event_id": "0f446e529f2c4012a04446b16fd55943", "step": 10, "value": 0.9999893935465622, "stage": "improve"}, {"event_id": "df6a7e8994ad4b57850b4f00c86f3dca", "step": 12, "value": 0.9999157376199119, "stage": "improve"}, {"event_id": "f94853e7b5ae4c0c919e3bf9eb22e326", "step": 15, "value": 0.9999846795672567, "stage": "debug"}, {"event_id": "580a3b840f7941e899e9e8fb5fdc32ce", "step": 16, "value": 0.9999098451457799, "stage": "debug"}, {"event_id": "8819d0ff3f31470db43a5d45fd7f6023", "step": 17, "value": 0.9999960194621763, "stage": "improve"}, {"event_id": "78f50cfd52084bb3b9097ec17bf5a166", "step": 18, "value": 0.9999398967638531, "stage": "debug"}, {"event_id": "e23a016baac34cc6b0fb7370d5b0916c", "step": 19, "value": 0.9999960194621763, "stage": "improve"}, {"event_id": "78ca67ef321a428bad30c2702411a38c", "step": 20, "value": 0.9999980097310881, "stage": "improve"}, {"event_id": "e6bb4a1608bb4be9ad2dd94b711a4bb6", "step": 22, "value": 0.9999336577029377, "stage": "improve"}, {"event_id": "c4ec08d998c94d7ebec99aadfeaf03fc", "step": 24, "value": 1.0, "stage": "debug"}, {"event_id": "27fea2b71bd7467297389d39317fe974", "step": 26, "value": 0.9999964645155208, "stage": "debug"}, {"event_id": "64b6fb0ece0a4e5cbea50e1ef827f90d", "step": 27, "value": 0.999936361279374, "stage": "improve"}, {"event_id": "0995f9267d7a450180d77d11d5d90144", "step": 28, "value": 0.9999905720413887, "stage": "debug"}, {"event_id": "966f7f138be248d685214f5c52c61c21", "step": 29, "value": 0.9999973463081175, "stage": "improve"}, {"event_id": "b29a21d2f3ec4f29a88002f615bfbfd1", "step": 30, "value": 0.9999846143708778, "stage": "improve"}, {"event_id": "45330d9b24e6497c85b3e79fdd598245", "step": 31, "value": 0.9999336577029379, "stage": "improve"}, {"event_id": "0ebe0c9cbf174a28bc79432f302949c9", "step": 32, "value": 0.9999980097310881, "stage": "evolution"}, {"event_id": "fa2e1aef76fa44fcaabdea08ac9853f8", "step": 34, "value": 0.9996687845427269, "stage": "debug"}, {"event_id": "db88bbb1b9a54263a6624e8d811c256d", "step": 35, "value": 0.9999562140839389, "stage": "improve"}, {"event_id": "1a04208ec81a4bb8bc593dca10749e6e", "step": 36, "value": 0.9998768751766032, "stage": "evolution"}, {"event_id": "78960e0cc04d4007b7ab9e07f811f2c4", "step": 37, "value": 0.9999608580447333, "stage": "improve"}, {"event_id": "e09f1bde14be4a27910ea47198294af6", "step": 38, "value": 0.9999354732020009, "stage": "evolution"}, {"event_id": "737b8c2089064f0cb28dd7dc8b568832", "step": 40, "value": 0.9999773207802005, "stage": "evolution"}, {"event_id": "314c3562921f4fed9ecf4dbe66687f06", "step": 41, "value": 0.9998238150234521, "stage": "evolution"}, {"event_id": "7d16fd2d6ea54fa397542894c5ef27a1", "step": 42, "value": 0.9998961204764791, "stage": "improve"}, {"event_id": "4026647cd427492ea8fec601a8d8784e", "step": 43, "value": 0.9999697460172177, "stage": "debug"}, {"event_id": "582440ccae3d4a7c94f36ba71e8c255c", "step": 45, "value": 0.9999984349101411, "stage": "improve"}, {"event_id": "375b23083c3549f787b5ad3ac09be134", "step": 46, "value": 0.9999846795672567, "stage": "debug"}, {"event_id": "4d5ce3f30e6948289368eb2666790142", "step": 47, "value": 0.9999960194621763, "stage": "improve"}, {"event_id": "b0fd10bf922e448d99eebeeb69bcd678", "step": 49, "value": 0.9995377812161417, "stage": "improve"}, {"event_id": "85172ade66e1473084a8e43ceb74ef8a", "step": 50, "value": 0.9999952860206943, "stage": "evolution"}, {"event_id": "d219f0df57644929857e3dc04a26d976", "step": 51, "value": 0.9999988215051736, "stage": "improve"}, {"event_id": "9f7961509abe431c8bbf29e538321985", "step": 52, "value": 0.9999980097310881, "stage": "improve"}, {"event_id": "6933868636f844eca6114ecb2d56af74", "step": 53, "value": 0.9999960194621763, "stage": "improve"}, {"event_id": "90ccbc3e47b7431cb2846e3172a07284", "step": 54, "value": 0.9999927023473232, "stage": "improve"}, {"event_id": "e192178ccd8846c7b34498b445ae8801", "step": 55, "value": 0.9999954108382102, "stage": "evolution"}, {"event_id": "eaba88b605ec43a99436998e5367c84b", "step": 56, "value": 0.9999976430103472, "stage": "evolution"}, {"event_id": "115bdd1bcd654d07891d17f0774665ac", "step": 57, "value": 0.9998025864621956, "stage": "debug"}, {"event_id": "1e38ee3b30bc40d386cf2453a06a19c3", "step": 58, "value": 0.9999776085982983, "stage": "improve"}, {"event_id": "724bfca5509d4cf891e242bc7069dd1b", "step": 59, "value": 0.9999907120784113, "stage": "evolution"}, {"event_id": "8f3674f2f4174d96b0cfe1c2fa8e0b86", "step": 61, "value": 0.9999980097310881, "stage": "evolution"}, {"event_id": "514a6f65dfbd4b0cafecba4a754127fa", "step": 62, "value": 0.9999980097310881, "stage": "evolution"}, {"event_id": "8530e7dee5f740ca8931e26b85ff1dbb", "step": 65, "value": 0.9999979839520461, "stage": "evolution"}, {"event_id": "ab17cf1f978f4c5c8be5806ca34f5cd8", "step": 66, "value": 0.9999557795797475, "stage": "debug"}, {"event_id": "c76f3a42eaaf4fdbbb28f01034c9564c", "step": 67, "value": 0.9999266529922025, "stage": "evolution"}, {"event_id": "6a0b22f631ba432d8721605f08834e5a", "step": 68, "value": 0.9995432192402278, "stage": "evolution"}, {"event_id": "d0f3976aa20948e2a769e420c906137e", "step": 69, "value": 0.9999917505362151, "stage": "debug"}, {"event_id": "a7fcf700153948a68ef38866c28500f5", "step": 70, "value": 0.9997239075380988, "stage": "evolution"}, {"event_id": "cf2ffce185574ae3996ea9598768e1f5", "step": 71, "value": 0.9999096757462747, "stage": "evolution"}, {"event_id": "69c84c00b787468eabb6b2ec69c82ad3", "step": 73, "value": 0.9998036210131194, "stage": "evolution"}, {"event_id": "0a0404e172f64f40bf67b24c49a3787d", "step": 74, "value": 0.9999270111059837, "stage": "evolution"}, {"event_id": "bb42dce452c440778beca82ec6b7877f", "step": 75, "value": 0.9999335499983607, "stage": "evolution"}, {"event_id": "b6d5a2594ef2468bb695bcbbe11c6a09", "step": 77, "value": 0.9999164087057015, "stage": "evolution"}, {"event_id": "bcec487ad5dc4849a577237f28c9f8e9", "step": 78, "value": 0.999997320778377, "stage": "evolution"}, {"event_id": "ea64dd07e1e84f2382058ec869206765", "step": 79, "value": 0.999992068442918, "stage": "evolution"}, {"event_id": "d7f28b4e208e4c39985f7b8a63cfc3dc", "step": 80, "value": 0.9999829118250171, "stage": "debug"}, {"event_id": "3e519e28a8064e568cd1316a93b2fa8e", "step": 81, "value": 0.9999953560392056, "stage": "evolution"}, {"event_id": "7bcee20730254fe7b97703b40903c658", "step": 82, "value": 0.9999368923936527, "stage": "evolution"}, {"event_id": "8ec02d2bd1ef49ba810fad27b461d846", "step": 83, "value": 0.9999953560392056, "stage": "evolution"}, {"event_id": "9b75ab98546c4a7eaff37033178da330", "step": 85, "value": 0.9999993365770294, "stage": "evolution"}, {"event_id": "43c96d8ed82849f5bf2c110403acf458", "step": 86, "value": 0.9999975595208979, "stage": "evolution"}, {"event_id": "7eb7a55c438e4f87926f80c15c06baf2", "step": 87, "value": 0.9999988215051736, "stage": "debug"}, {"event_id": "6c103abd4a2545af947c3c577455f3f9", "step": 88, "value": 0.9996081837328487, "stage": "evolution"}, {"event_id": "2aa3c8c8b3844a4aa2e46eff73b24977", "step": 89, "value": 0.9999774436189989, "stage": "improve"}, {"event_id": "afb0e675ceb14b23a20a44862392bca9", "step": 90, "value": 1.0, "stage": "evolution"}, {"event_id": "491e9d9dd7ee4056947615ea74cdfdcd", "step": 91, "value": 0.9999481462276381, "stage": "fusion"}, {"event_id": "26233b50f6d34bc3912566974dbe8bd7", "step": 92, "value": 0.9999896544907627, "stage": "evolution"}, {"event_id": "6559be4d2667443db1f3cfd05defe226", "step": 93, "value": 0.9999139698776723, "stage": "improve"}, {"event_id": "d80b983543564e7ea81a259ef92780c3", "step": 95, "value": 0.9996618079557285, "stage": "evolution"}, {"event_id": "4f1e939e782c4b2ebd61b110a0801b95", "step": 96, "value": 0.9996687845427269, "stage": "debug"}, {"event_id": "96195e1809904b839355484f9998eda7", "step": 97, "value": 0.9999906359877929, "stage": "improve"}, {"event_id": "10273638acff41819bf9901250402473", "step": 99, "value": 0.9999952860206944, "stage": "fusion_draft"}, {"event_id": "403d95cb64684f828b1d6c38e874e36a", "step": 100, "value": 1.0, "stage": "improve"}, {"event_id": "8e4219f8202344dd99726b52abedbca4", "step": 101, "value": 1.0, "stage": "improve"}, {"event_id": "b31cc3fa85b04552b991d583e5d301a3", "step": 102, "value": 0.9999979308981526, "stage": "evolution"}, {"event_id": "03a6aa542cc24504af8f6c1329850e35", "step": 103, "value": 0.9999573711965531, "stage": "evolution"}, {"event_id": "8ab470708eab4d869488477662db910b", "step": 104, "value": 0.9999978247903655, "stage": "evolution"}, {"event_id": "3888834d29a2431dad1f9b2196675d0e", "step": 105, "value": 0.9999929290310415, "stage": "improve"}, {"event_id": "90ef55ea97904c0596dbe1b06a86d4a6", "step": 106, "value": 0.9999980097310881, "stage": "evolution"}, {"event_id": "1c562247bf0d48b1a2ed9327022301bd", "step": 107, "value": 1.0, "stage": "improve"}, {"event_id": "2874cf09e731402d9deae87fd74ce0b0", "step": 108, "value": 0.9998357186187016, "stage": "evolution"}, {"event_id": "b9bc00d42eb44c729c542445e35a7541", "step": 110, "value": 0.9999646451552078, "stage": "debug"}, {"event_id": "9e2eca8b250343f983e8136759eb2c2f", "step": 112, "value": 0.9999905720413889, "stage": "evolution"}, {"event_id": "44a078eb5d7a4481a87bdabcd22f83bc", "step": 113, "value": 0.9999980097310881, "stage": "evolution"}, {"event_id": "84385f8440bc44da9711a486c793dd6b", "step": 114, "value": 0.9999336577029379, "stage": "evolution"}, {"event_id": "cdf46532e6a145f4b0c4a2afe739378a", "step": 115, "value": 0.9998409046367935, "stage": "improve"}, {"event_id": "0168e292a67447d1ae3ea45c8a6b7051", "step": 116, "value": 0.9996687845427269, "stage": "fusion"}, {"event_id": "520ec69ed5fe4f038fa8e51399420691", "step": 117, "value": 0.9999831288618591, "stage": "debug"}, {"event_id": "41bf5f3d2a3b48ce8d4410399841aae7", "step": 119, "value": 0.9999959679040922, "stage": "improve"}, {"event_id": "cd0997fc88ac4d6fa4b0d49c36198590", "step": 120, "value": 0.9999940291932644, "stage": "fusion"}, {"event_id": "4e4661d619614d79a2cb2a577042f8d0", "step": 121, "value": 0.9999963923352403, "stage": "fusion"}, {"event_id": "217213d7a84148e58f782236aaae3089", "step": 122, "value": 0.9999882150517359, "stage": "fusion"}, {"event_id": "e74d7e6286d642e1918ce509530226c7", "step": 123, "value": 0.9999976430103472, "stage": "improve"}, {"event_id": "e0fa019e93e94489b70d01893f166cf6", "step": 124, "value": 0.9996164070863449, "stage": "fusion"}, {"event_id": "566009aa44674757a551a65d857f1df6", "step": 125, "value": 0.9999974268861641, "stage": "improve"}, {"event_id": "9af8c630dc8142d982d6ae8b713b2c83", "step": 126, "value": 0.9999721362352338, "stage": "evolution"}, {"event_id": "ecd5b4a5dc284e77b6bbb05d796be10e", "step": 127, "value": 0.9988770016040315, "stage": "evolution"}, {"event_id": "c5b32bc0d71e4d149a20b1f3097db598", "step": 128, "value": 0.9999973473053237, "stage": "improve"}, {"event_id": "b6a490833c81488dad47d98eb17aff7b", "step": 129, "value": 0.9999988215051736, "stage": "evolution"}, {"event_id": "8c46bd0a723a4f908664f137c7a7629b", "step": 130, "value": 0.9999980097310881, "stage": "fusion"}, {"event_id": "86189d8b51404b7d87e148002495f7e6", "step": 132, "value": 1.0, "stage": "fusion"}, {"event_id": "d9537da763b34d28ba57a5313b023e61", "step": 135, "value": 0.9999976430103471, "stage": "improve"}, {"event_id": "91cf488b987e446abae21353e4449686", "step": 137, "value": 0.9999995225149583, "stage": "improve"}], "maximize": true, "metric_name": "native public validation metric", "official_score": 0.99996, "valid_submission": true, "medal": "none", "thresholds": {"gold": 1.0, "silver": 1.0, "bronze": 1.0}, "formal_result": true, "full_agent_budget_used": false, "note": "", "artifacts": [{"bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/experiments/mlebench-aq04-12h-20260921/runs/harry123.aq04-20260921.aerial-cactus-identification/artifacts/logs", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/experiments/mlebench-aq04-12h-20260921/runs/harry123.aq04-20260921.aerial-cactus-identification/live.json", "member": "live.json; persisted native/wrapper logs", "files": 140, "bytes": 234752239}], "logs_scope": "已存在 persisted wrapper/native logs；原上传者排除了 node-local workspaces、datasets、submissions、checkpoints。", "curve_scope": "上传者 live.json 验证指标；官方 grade 为另一条证据。", "source_grade": {"competition_id": "aerial-cactus-identification", "score": 0.99996, "gold_threshold": 1.0, "silver_threshold": 1.0, "bronze_threshold": 1.0, "median_threshold": 0.9991, "any_medal": false, "gold_medal": false, "silver_medal": false, "bronze_medal": false, "above_median": true, "submission_exists": true, "valid_submission": true, "is_lower_better": false, "created_at": "2026-09-21T12:32:49.077464", "submission_path": "/scratch/harry123/EvolveFold/MLEvolve_BO/runs/aq04-mlebench-lite-20260921/tasks/aerial-cactus-identification/22372429/submission.csv"}, "source_wrapper": {"task": "aerial-cactus-identification", "job_id": "22372429", "owner": "harry123", "host": "g3.nibi.sharcnet", "commit": "3a0479c4e597b3515697d776c2768736cea8c4d6", "source_sha256": "efedc394766bff346ee7a3f98737fe3cf912cd3da7c397456e86e844d3c7046b", "started_at": "2026-09-21T04:32:13.189463+00:00", "agent_budget_seconds": 43200, "state": "completed", "workspace_is_node_local": true, "formal_result": true, "gpu": "NVIDIA H100 80GB HBM3", "gpu_uuid": "ac5433d0-fe65-af88-b7b6-649e8ea7728a", "cpu_ids": [26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46], "grading_port": 32429, "grading_server_id": 27424, "search_started_at": "2026-09-21T04:32:42.709092+00:00", "search_exit_code": 124, "search_finished_at": "2026-09-21T16:32:43.832166+00:00", "fusion_exit_code": 0, "final_submission": "/scratch/harry123/EvolveFold/MLEvolve_BO/runs/aq04-mlebench-lite-20260921/tasks/aerial-cactus-identification/22372429/native/20260921_003258_AQ04_aerial-cactus-identification/final_submission.json", "log_dir": "/scratch/harry123/EvolveFold/MLEvolve_BO/runs/aq04-mlebench-lite-20260921/tasks/aerial-cactus-identification/22372429/native/20260921_003258_AQ04_aerial-cactus-identification", "journal_active_seconds": 42898.248155117035, "full_agent_budget_used": false, "outer_search_timeout_reached": true, "official_grade": "/scratch/harry123/EvolveFold/MLEvolve_BO/runs/aq04-mlebench-lite-20260921/tasks/aerial-cactus-identification/22372429/official-grade.json", "finished_at": "2026-09-21T16:32:51.134935+00:00", "elapsed_seconds": 43237.93613192509}}, {"id": "harry123.aq04-20260921.aptos2019-blindness-detection", "experiment_id": "mlebench-aq04-12h-20260921", "family": "MLEBench", "method": "AQ04", "dataset": "aptos2019-blindness-detection", "seed": 42, "status": "completed", "source_status": "complete", "wrapper_status": "complete", "source_updated_at": "2026-09-25T09:24:12.207254+00:00", "uploaded_at": "2026-09-25T17:05:52.307955+00:00", "elapsed_seconds": 43201.240099430084, "budget_seconds": 43200, "metrics": [{"event_id": "04189da8e6bd4dad9fd150d89e035c61", "node_id": "04189da8e6bd4dad9fd150d89e035c61", "transition_id": "cc9c95711b0d4fc5b6541e715264640f", "step": 2, "value": 0.8921032555098048, "stage": "debug", "elapsed_seconds": 1108.9411053657532}, {"event_id": "c50f1ac99fa946769cce4bce2dce3a57", "node_id": "c50f1ac99fa946769cce4bce2dce3a57", "transition_id": "ea468b641e0d4f5cb1dac77c9c943551", "step": 6, "value": 0.8840413042957426, "stage": "debug", "elapsed_seconds": 1998.0108649730682}, {"event_id": "7b9b8f7cea5844fcb012159677b2a832", "node_id": "7b9b8f7cea5844fcb012159677b2a832", "transition_id": "8de313c5ca6049288e014c8275028be2", "step": 7, "value": 0.9362273025852765, "stage": "debug", "elapsed_seconds": 2231.4491317272186}, {"event_id": "624015005e2a46f7926f683ad6530ed9", "node_id": "624015005e2a46f7926f683ad6530ed9", "transition_id": "aa58928611734bc18005c2d46eb3f97f", "step": 9, "value": 0.9091619825237056, "stage": "debug", "elapsed_seconds": 2417.07825922966}, {"event_id": "3e009af14ead479babe320c547e8e828", "node_id": "3e009af14ead479babe320c547e8e828", "transition_id": "c5ec549f727d40129ba79b6b8a124edb", "step": 10, "value": 0.8993444217581104, "stage": "debug", "elapsed_seconds": 2675.9837884902954}, {"event_id": "4714022e1a7a46589b09ecac8ec0fbe8", "node_id": "4714022e1a7a46589b09ecac8ec0fbe8", "transition_id": "4e683cf099184fc9bb93f5a1a8c04bae", "step": 11, "value": 0.864494216196941, "stage": "improve", "elapsed_seconds": 3005.511281490326}, {"event_id": "2ec32ffcf65b45669ed4ff8e4d0025d4", "node_id": "2ec32ffcf65b45669ed4ff8e4d0025d4", "transition_id": "6ab5b761d7674be28429bbc95a182b61", "step": 13, "value": 0.88850132449546, "stage": "improve", "elapsed_seconds": 3403.7311582565308}, {"event_id": "79401db0e6d34a088af4f877b9444f8f", "node_id": "79401db0e6d34a088af4f877b9444f8f", "transition_id": "28573aa9bbe445caa7ec77bee07a1c9d", "step": 15, "value": 0.9314061406097834, "stage": "debug", "elapsed_seconds": 4029.259763240814}, {"event_id": "fa1763ade6f9445a86459aac8da2d6ac", "node_id": "fa1763ade6f9445a86459aac8da2d6ac", "transition_id": "96c9bb6ac7da44e0b8c030d746d4c05d", "step": 17, "value": 0.9144355081801995, "stage": "improve", "elapsed_seconds": 5516.163751363754}, {"event_id": "5a34abc198e54342850f7d15b860a3f6", "node_id": "5a34abc198e54342850f7d15b860a3f6", "transition_id": "3c2aacf091f54cb0890c10dd4bd6b6d3", "step": 19, "value": 0.9118748686624154, "stage": "improve", "elapsed_seconds": 7224.863038778305}, {"event_id": "5ed7996e5bf049d498edede297eca014", "node_id": "5ed7996e5bf049d498edede297eca014", "transition_id": "53b5b3e5c34c4655b63d0544204afa1f", "step": 21, "value": 0.9133222935408747, "stage": "improve", "elapsed_seconds": 9210.127738237381}, {"event_id": "ec805946d8824adab9f6f7da8b5dd1de", "node_id": "ec805946d8824adab9f6f7da8b5dd1de", "transition_id": "a9f603d2c0df4860ab1d4ba84a3710a3", "step": 22, "value": 0.9191947572759752, "stage": "evolution", "elapsed_seconds": 9717.984614372253}, {"event_id": "96ef893b65d84fdeb0677e956c3963d0", "node_id": "96ef893b65d84fdeb0677e956c3963d0", "transition_id": "fd89854efd57478bb218f2e6753fb3fc", "step": 26, "value": 0.9016685361916645, "stage": "debug", "elapsed_seconds": 12304.456147193909}, {"event_id": "fdeff53509174aa59481145aeb04bf29", "node_id": "fdeff53509174aa59481145aeb04bf29", "transition_id": "2aa591817dca4c0a8019a858ae364dcd", "step": 28, "value": 0.9340543838255013, "stage": "evolution", "elapsed_seconds": 13724.733462572098}, {"event_id": "d384b35f69f14dcfa29fa48b8003330e", "node_id": "d384b35f69f14dcfa29fa48b8003330e", "transition_id": "3fe475eb73cb4303934eeef8b010f540", "step": 29, "value": 0.9028965952804731, "stage": "evolution", "elapsed_seconds": 14390.841425895691}, {"event_id": "f104a57321fe41c190e3c12e047d3cb9", "node_id": "f104a57321fe41c190e3c12e047d3cb9", "transition_id": "cb29eea0f5e641e6a3abce1349136479", "step": 31, "value": 0.9095959316021395, "stage": "evolution", "elapsed_seconds": 15376.220125198364}, {"event_id": "711df1d5923f4a8b820470ed2632498c", "node_id": "711df1d5923f4a8b820470ed2632498c", "transition_id": "c31941dc401c4974be1ac87f557a986d", "step": 33, "value": 0.9199171150064108, "stage": "debug", "elapsed_seconds": 17398.037672281265}, {"event_id": "4ddaf19c899f4b938c0856ac1f41b5bf", "node_id": "4ddaf19c899f4b938c0856ac1f41b5bf", "transition_id": "ae03939edf45470faa0a8f153680e39c", "step": 34, "value": 0.9091094095728556, "stage": "debug", "elapsed_seconds": 18491.261895418167}, {"event_id": "c60ce25ec1c04f3ba15c41fdd1d63729", "node_id": "c60ce25ec1c04f3ba15c41fdd1d63729", "transition_id": "ce9fbe0eb4974d1ab6f75fe86322b10b", "step": 35, "value": 0.930161907565499, "stage": "evolution", "elapsed_seconds": 18814.907107830048}, {"event_id": "2f19180ceb75443cbad4d4ebbb5699dc", "node_id": "2f19180ceb75443cbad4d4ebbb5699dc", "transition_id": "1044d10a00d44716b10c767391857912", "step": 38, "value": 0.9480488766259362, "stage": "evolution", "elapsed_seconds": 19861.042822360992}, {"event_id": "88f452e768db492faa41749b2e2aafd1", "node_id": "88f452e768db492faa41749b2e2aafd1", "transition_id": "da0ebc9ff87447b3bfb783c182d4f4ca", "step": 39, "value": 0.9185856551569919, "stage": "debug", "elapsed_seconds": 20471.58768415451}, {"event_id": "8b2d9bc6c88a4b8cb3fa3354fd216488", "node_id": "8b2d9bc6c88a4b8cb3fa3354fd216488", "transition_id": "6f3c1f48caa04e9092ea955b394a8ae3", "step": 40, "value": 0.938357882563362, "stage": "evolution", "elapsed_seconds": 20619.90301012993}, {"event_id": "38163c16d4204694b040f1587e4cc0d1", "node_id": "38163c16d4204694b040f1587e4cc0d1", "transition_id": "7e5c5c3957db4ed19a34c2fcc5303571", "step": 41, "value": 0.8936801201825438, "stage": "improve", "elapsed_seconds": 22857.217444896698}, {"event_id": "12878550faff4a5181467e50bf7b5c84", "node_id": "12878550faff4a5181467e50bf7b5c84", "transition_id": "116da30bee5d473695ff451328c7e01f", "step": 46, "value": 0.8967, "stage": "debug", "elapsed_seconds": 24893.99787926674}, {"event_id": "ce1894d761814553827290d2172f02fd", "node_id": "ce1894d761814553827290d2172f02fd", "transition_id": "9ef025b59d1f431897179b6860fcaa31", "step": 53, "value": 0.8398, "stage": "debug", "elapsed_seconds": 33718.10488009453}, {"event_id": "2b48d31aa08d44829d545dd909c18cc9", "node_id": "2b48d31aa08d44829d545dd909c18cc9", "transition_id": "11a310b4118747a795d0fbb2ba95cda5", "step": 54, "value": 0.8944046132396866, "stage": "evolution", "elapsed_seconds": 33835.77604866028}, {"event_id": "9292954da9614277b7ae7d158c7d3cfb", "node_id": "9292954da9614277b7ae7d158c7d3cfb", "transition_id": "2c33e19130884875803900232b8e5f70", "step": 55, "value": 0.9358675270845213, "stage": "evolution", "elapsed_seconds": 36452.65841817856}, {"event_id": "69abc0f6b373472fa9100c7ec04fc696", "node_id": "69abc0f6b373472fa9100c7ec04fc696", "transition_id": "03aba27848834a8aa9002f6672f391c6", "step": 56, "value": 0.9432039410201283, "stage": "evolution", "elapsed_seconds": 39454.84323763847}, {"event_id": "56372e5be9d946c68697567c387e9147", "node_id": "56372e5be9d946c68697567c387e9147", "transition_id": "30bac6cd171148ffbf9db3b8def9bb01", "step": 57, "value": 0.918888642785523, "stage": "debug", "elapsed_seconds": 39621.08516073227}, {"event_id": "d8190b8597744e55af0056d3c84381f3", "node_id": "d8190b8597744e55af0056d3c84381f3", "transition_id": "5ce92471d14d424e8a8ead169878b852", "step": 59, "value": 0.9395655481362523, "stage": "evolution", "elapsed_seconds": 42301.62023115158}], "maximize": true, "metric_name": "native public validation metric", "official_score": 0.91235, "valid_submission": true, "medal": "none", "thresholds": {"gold": 0.930508, "silver": 0.919654, "bronze": 0.914492}, "formal_result": false, "full_agent_budget_used": true, "note": "从 2026-09-21 首轮断点续跑；续跑使用独占 A100 80GB，仅补原 12h 剩余时间。 已保存评分来自本次续跑最终提交。 原首轮格式校验任务 ID 有误；续跑已修正。原全局记忆缺失，按保存记录重建；详情见 provenance。", "artifacts": [{"bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/experiments/mlebench-aq04-12h-20260921/continuations/liux-mila-20260924/runs/harry123.aq04-20260921.aptos2019-blindness-detection", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/experiments/mlebench-aq04-12h-20260921/continuations/liux-mila-20260924/runs/harry123.aq04-20260921.aptos2019-blindness-detection/live.json", "member": "live.json; immutable metric events and continuation archive index", "files": 1, "bytes": 0}, {"bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/experiments/mlebench-aq04-12h-20260921/continuations/liux-mila-20260924/runs/harry123.aq04-20260921.aptos2019-blindness-detection/final", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/experiments/mlebench-aq04-12h-20260921/continuations/liux-mila-20260924/runs/harry123.aq04-20260921.aptos2019-blindness-detection/final/submission-4576471c375d6df892bab4755cba0bcd2b8ec86ffa0613b3ac82c0d1b1baeef3.csv", "member": "Sealed final submission.csv; SHA256 4576471c375d6df892bab4755cba0bcd2b8ec86ffa0613b3ac82c0d1b1baeef3", "files": 1, "bytes": 5523}, {"bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/experiments/mlebench-aq04-12h-20260921/continuations/liux-mila-20260924/runs/harry123.aq04-20260921.aptos2019-blindness-detection/artifacts", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/experiments/mlebench-aq04-12h-20260921/continuations/liux-mila-20260924/runs/harry123.aq04-20260921.aptos2019-blindness-detection/artifacts/logs-029fb3033e9e20280d7c6df8a3102888e79216a334a7fcea6f2eb7e639aa4a41.tar.gz", "member": "experiments/mlebench-aq04-12h-20260921/continuations/liux-mila-20260924/runs/harry123.aq04-20260921.aptos2019-blindness-detection/artifacts/logs-029fb3033e9e20280d7c6df8a3102888e79216a334a7fcea6f2eb7e639aa4a41.tar.gz", "files": 195, "bytes": 18928715}, {"bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/experiments/mlebench-aq04-12h-20260921/runs/harry123.aq04-20260921.aptos2019-blindness-detection/artifacts/logs", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/experiments/mlebench-aq04-12h-20260921/runs/harry123.aq04-20260921.aptos2019-blindness-detection/live.json", "member": "live.json; persisted native/wrapper logs", "files": 53, "bytes": 52622173}], "logs_scope": "完整可用日志、候选代码及提交 CSV 已上传；日志快照时间 2026-09-25T09:28:20.785321+00:00；排除数据集、模型缓存及凭据。", "curve_scope": "保留原始指标点；续跑使用已提交的有效原生观察。仅有原生 active 时间的点参与时间曲线。", "source_grade": {"competition_id": "aptos2019-blindness-detection", "score": 0.91235, "gold_threshold": 0.930508, "silver_threshold": 0.919654, "bronze_threshold": 0.914492, "median_threshold": 0.888912, "any_medal": false, "gold_medal": false, "silver_medal": false, "bronze_medal": false, "above_median": true, "submission_exists": true, "valid_submission": true, "is_lower_better": false, "created_at": "2026-09-25T05:24:12.081051", "submission_path": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/runs/aq04-mlebench-lite-20260921-resume-mila-20260924/tasks/aptos2019-blindness-detection/20260921_003258_AQ04_aptos2019-blindness-detection/workspace/ensembles_csv/top6ens-total_run_time3.77h.csv"}, "source_wrapper": {"task": "aptos2019-blindness-detection", "job_id": "22372430", "owner": "harry123", "host": "g3.nibi.sharcnet", "commit": "3a0479c4e597b3515697d776c2768736cea8c4d6", "source_sha256": "efedc394766bff346ee7a3f98737fe3cf912cd3da7c397456e86e844d3c7046b", "started_at": "2026-09-21T04:32:13.189462+00:00", "agent_budget_seconds": 43200, "state": "failed", "workspace_is_node_local": true, "formal_result": false, "gpu": "NVIDIA H100 80GB HBM3", "gpu_uuid": "b4738f7d-0af3-b266-ea4b-3ba5824a42d2", "cpu_ids": [47, 48, 49, 50, 51, 52, 53, 54, 55, 74, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85], "grading_port": 32430, "grading_server_id": 27425, "search_started_at": "2026-09-21T04:32:42.936541+00:00", "search_exit_code": 1, "search_finished_at": "2026-09-21T11:31:34.968695+00:00", "fusion_exit_code": 0, "final_submission": "/scratch/harry123/EvolveFold/MLEvolve_BO/runs/aq04-mlebench-lite-20260921/tasks/aptos2019-blindness-detection/22372430/native/20260921_003258_AQ04_aptos2019-blindness-detection/final_submission.json", "log_dir": "/scratch/harry123/EvolveFold/MLEvolve_BO/runs/aq04-mlebench-lite-20260921/tasks/aptos2019-blindness-detection/22372430/native/20260921_003258_AQ04_aptos2019-blindness-detection", "journal_active_seconds": 24894.89327764511, "full_agent_budget_used": false, "outer_search_timeout_reached": false, "official_grade": "/scratch/harry123/EvolveFold/MLEvolve_BO/runs/aq04-mlebench-lite-20260921/tasks/aptos2019-blindness-detection/22372430/official-grade.json", "finished_at": "2026-09-21T11:31:39.374310+00:00", "elapsed_seconds": 25166.175741957035}, "score_phase": "continuation-final", "final_submission_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/experiments/mlebench-aq04-12h-20260921/continuations/liux-mila-20260924/runs/harry123.aq04-20260921.aptos2019-blindness-detection/final/submission-4576471c375d6df892bab4755cba0bcd2b8ec86ffa0613b3ac82c0d1b1baeef3.csv", "hardware": "A100 80GB (continuation); H100 80GB (first segment)", "model": "muse-spark-1.3-contributor", "provider": "codex://opencode-go", "scheduler": {"job_id": "10927555", "partition": "short-unkillable", "observed_at": "2026-09-25T17:05:52.307981+00:00", "allocation": null}, "completed_candidates": 67, "pending_decisions": 3, "remaining_seconds": 0, "continuation_source_status": {"state": "complete", "active_elapsed_seconds": 43201.240099430084, "updated_at": "2026-09-25T09:24:12.207254+00:00", "source_updated_at": "2026-09-21T11:31:39.374310+00:00", "imported_first_run": true, "run_root": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/runs/aq04-mlebench-lite-20260921-resume-mila-20260924/tasks/aptos2019-blindness-detection/20260921_003258_AQ04_aptos2019-blindness-detection", "previous_job_id": "22372430", "job_id": "10927555", "attempt": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/runs/aq04-mlebench-lite-20260921-resume-mila-20260924/tasks/aptos2019-blindness-detection/attempt-04-10927555", "gpu": "NVIDIA A100-SXM4-80GB", "host": "cn-g008.server.mila.quebec", "started_at": "2026-09-24T17:57:18.970124+00:00", "search_pid": 235129, "attempt_started_epoch": 1790324729.276471, "search_stopped_epoch": 1790328245.7008352, "search_exit_code": 75, "budget_complete": true, "completed_transitions": 67, "release_receipt": {"job_id": "10927029", "state": "COMPLETED", "end": "2026-09-25T04:24:35", "exit_code": "0:0", "end_epoch": 1790324675.0, "verified_at": "2026-09-25T08:25:00.641637+00:00"}, "stop_history": [{"stop_reason": "user_request", "stop_requested_at": "2026-09-24T19:15:09.692440+00:00", "stopped_at": "2026-09-24T19:15:13.108715+00:00", "job_id": "10919452", "active_elapsed_seconds": 29588.684705495834}], "resume_requested_at": "2026-09-25T05:30:03.052522+00:00", "resume_reason": "explicit_user_request", "error": null, "search_finished_at": "2026-09-25T09:24:07.859517+00:00", "finished_at": "2026-09-25T09:24:12.205796+00:00", "submission": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/runs/aq04-mlebench-lite-20260921-resume-mila-20260924/tasks/aptos2019-blindness-detection/20260921_003258_AQ04_aptos2019-blindness-detection/workspace/ensembles_csv/top6ens-total_run_time3.77h.csv", "official_grade": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/runs/aq04-mlebench-lite-20260921-resume-mila-20260924/tasks/aptos2019-blindness-detection/20260921_003258_AQ04_aptos2019-blindness-detection/logs/official-grade.json", "final_submission_sha256": "4576471c375d6df892bab4755cba0bcd2b8ec86ffa0613b3ac82c0d1b1baeef3"}, "config_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/experiments/mlebench-aq04-12h-20260921/continuations/liux-mila-20260924/runs/harry123.aq04-20260921.aptos2019-blindness-detection/config.yaml"}, {"id": "harry123.aq04-20260921.dog-breed-identification", "experiment_id": "mlebench-aq04-12h-20260921", "family": "MLEBench", "method": "AQ04", "dataset": "dog-breed-identification", "seed": 42, "status": "completed", "source_status": "completed", "wrapper_status": "completed", "source_updated_at": "2026-09-21T16:37:20.676653+00:00", "uploaded_at": "2026-09-22T04:51:57.062781+00:00", "elapsed_seconds": 42698.520332574844, "budget_seconds": 43200.0, "metrics": [{"event_id": "f09aa9b5e765449aacad9d8cc7776e9d", "step": 1, "value": 0.39302002960037735, "stage": "draft"}, {"event_id": "ff4c662b918f487bbb2ce8154b559a61", "step": 2, "value": 0.6091736604365829, "stage": "draft"}, {"event_id": "c8ccb95585284e75bd9fdaec5e49e3a1", "step": 3, "value": 0.42938560770603207, "stage": "draft"}, {"event_id": "49593944617b4e5196b37a25e1c8dc47", "step": 5, "value": 0.5743540547089004, "stage": "improve"}, {"event_id": "5137d7c60c2c4e0b84c1810437c235d4", "step": 7, "value": 0.45321437277783544, "stage": "improve"}, {"event_id": "3f552c79acc844aeaac3ea540d1414cd", "step": 14, "value": 0.695253584688513, "stage": "debug"}, {"event_id": "0df306d8fa29457e9cb04bc4c52f2127", "step": 15, "value": 0.4076259811460137, "stage": "improve"}, {"event_id": "2fdd2921aab04c689c4ece923514b66f", "step": 16, "value": 0.4045689560244984, "stage": "debug"}, {"event_id": "f3bb7220b8b14b68958c7f67632b53e1", "step": 17, "value": 0.3880598130746306, "stage": "debug"}, {"event_id": "c51a21faa8ce4101a38b0a422ea9bec2", "step": 19, "value": 0.24367925708396912, "stage": "improve"}, {"event_id": "b695a577d40b403c8db75167a38987d1", "step": 22, "value": 0.20402499947306277, "stage": "debug"}, {"event_id": "01a08ff562fd40bb86fbf3e76e4c4b97", "step": 23, "value": 0.34772971403107233, "stage": "debug"}, {"event_id": "e0c118b65dff4ba285b651d9d494475c", "step": 24, "value": 0.22826560226194673, "stage": "improve"}, {"event_id": "5dc78dff4b0a4bc9bd2525a59a7d6cf5", "step": 25, "value": 0.24367924970643326, "stage": "improve"}, {"event_id": "96984a7734e64cc8bf506e9c8750c89a", "step": 26, "value": 0.17201386184687523, "stage": "evolution"}, {"event_id": "f0e66a210a164f8d9dd78792746f6d1f", "step": 29, "value": 0.39818203690332754, "stage": "debug"}, {"event_id": "75ab5df8f92440839a942c132f7ff9b0", "step": 30, "value": 0.23024212184194415, "stage": "improve"}, {"event_id": "9f178a53c5fd4a318b2645a4b35f8d43", "step": 31, "value": 0.08392302934425873, "stage": "debug"}, {"event_id": "4febaac98ce543abbfad8f5c85bd15d6", "step": 36, "value": 0.4262842941647405, "stage": "fusion_draft"}, {"event_id": "68668b59dda34eaaa36ebac158e83219", "step": 37, "value": 0.20298099599562294, "stage": "debug"}, {"event_id": "41bc2254f403440ba717f969b94c3213", "step": 38, "value": 0.14371902021355412, "stage": "improve"}, {"event_id": "ba1c1489e60941b49f9f4360423f9240", "step": 39, "value": 0.1820579402714232, "stage": "improve"}, {"event_id": "12a8ffbf86a844aea652bf63b3dae776", "step": 40, "value": 0.15221165543404747, "stage": "improve"}, {"event_id": "934df39718ce4ee2a23f39942dcc5650", "step": 41, "value": 0.41184971601877934, "stage": "improve"}, {"event_id": "459b153fcb574322b844500e4b97da72", "step": 42, "value": 0.05216709118769656, "stage": "improve"}], "maximize": false, "metric_name": "native public validation metric", "official_score": 0.24181, "valid_submission": true, "medal": "none", "thresholds": {"gold": 0.0005, "silver": 0.00539, "bronze": 0.04598}, "formal_result": true, "full_agent_budget_used": false, "note": "", "artifacts": [{"bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/experiments/mlebench-aq04-12h-20260921/runs/harry123.aq04-20260921.dog-breed-identification/artifacts/logs", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/experiments/mlebench-aq04-12h-20260921/runs/harry123.aq04-20260921.dog-breed-identification/live.json", "member": "live.json; persisted native/wrapper logs", "files": 53, "bytes": 51158516}], "logs_scope": "已存在 persisted wrapper/native logs；原上传者排除了 node-local workspaces、datasets、submissions、checkpoints。", "curve_scope": "上传者 live.json 验证指标；官方 grade 为另一条证据。", "source_grade": {"competition_id": "dog-breed-identification", "score": 0.24181, "gold_threshold": 0.0005, "silver_threshold": 0.00539, "bronze_threshold": 0.04598, "median_threshold": 0.47205, "any_medal": false, "gold_medal": false, "silver_medal": false, "bronze_medal": false, "above_median": true, "submission_exists": true, "valid_submission": true, "is_lower_better": true, "created_at": "2026-09-21T12:37:05.515665", "submission_path": "/scratch/harry123/EvolveFold/MLEvolve_BO/runs/aq04-mlebench-lite-20260921/tasks/dog-breed-identification/22372436/submission.csv"}, "source_wrapper": {"task": "dog-breed-identification", "job_id": "22372436", "owner": "harry123", "host": "g2.nibi.sharcnet", "commit": "3a0479c4e597b3515697d776c2768736cea8c4d6", "source_sha256": "efedc394766bff346ee7a3f98737fe3cf912cd3da7c397456e86e844d3c7046b", "started_at": "2026-09-21T04:36:23.649228+00:00", "agent_budget_seconds": 43200, "state": "completed", "workspace_is_node_local": true, "formal_result": true, "gpu": "NVIDIA H100 80GB HBM3", "gpu_uuid": "7ab3fca3-53de-1a4d-3760-a2289065f9ed", "cpu_ids": [6, 7, 8, 9, 14, 15, 22, 23, 24, 25, 26, 27, 28, 29, 34, 35, 40, 41, 42, 43, 44], "grading_port": 32436, "grading_server_id": 27431, "search_started_at": "2026-09-21T04:36:57.233525+00:00", "search_exit_code": 124, "search_finished_at": "2026-09-21T16:36:58.360719+00:00", "fusion_exit_code": 0, "final_submission": "/scratch/harry123/EvolveFold/MLEvolve_BO/runs/aq04-mlebench-lite-20260921/tasks/dog-breed-identification/22372436/native/20260921_003718_AQ04_dog-breed-identification/final_submission.json", "log_dir": "/scratch/harry123/EvolveFold/MLEvolve_BO/runs/aq04-mlebench-lite-20260921/tasks/dog-breed-identification/22372436/native/20260921_003718_AQ04_dog-breed-identification", "journal_active_seconds": 42698.520332574844, "full_agent_budget_used": false, "outer_search_timeout_reached": true, "official_grade": "/scratch/harry123/EvolveFold/MLEvolve_BO/runs/aq04-mlebench-lite-20260921/tasks/dog-breed-identification/22372436/official-grade.json", "finished_at": "2026-09-21T16:37:20.669108+00:00", "elapsed_seconds": 43257.010728575755}}, {"id": "harry123.aq04-20260921.jigsaw-toxic-comment-classification-challenge", "experiment_id": "mlebench-aq04-12h-20260921", "family": "MLEBench", "method": "AQ04", "dataset": "jigsaw-toxic-comment-classification-challenge", "seed": 42, "status": "completed", "source_status": "completed", "wrapper_status": "completed", "source_updated_at": "2026-09-21T16:33:42.228313+00:00", "uploaded_at": "2026-09-22T04:54:37.996961+00:00", "elapsed_seconds": 38165.43772101402, "budget_seconds": 43200.0, "metrics": [{"event_id": "596c2adeaebd4e9e8d001a96b6901f27", "step": 7, "value": 0.9884370980072356, "stage": "draft"}, {"event_id": "021035fe59d74456bc71801a17b39255", "step": 9, "value": 0.9919857775757289, "stage": "debug"}, {"event_id": "ca51c6b14b234c0fb30a51f86b2c392b", "step": 10, "value": 0.9758222491507493, "stage": "debug"}, {"event_id": "584c95ae34104621bf56210f8b9721f0", "step": 11, "value": 0.9917199964089981, "stage": "improve"}], "maximize": true, "metric_name": "native public validation metric", "official_score": 0.98602, "valid_submission": true, "medal": "none", "thresholds": {"gold": 0.9874, "silver": 0.98668, "bronze": 0.98639}, "formal_result": true, "full_agent_budget_used": false, "note": "", "artifacts": [{"bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/experiments/mlebench-aq04-12h-20260921/runs/harry123.aq04-20260921.jigsaw-toxic-comment-classification-challenge/artifacts/logs", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/experiments/mlebench-aq04-12h-20260921/runs/harry123.aq04-20260921.jigsaw-toxic-comment-classification-challenge/live.json", "member": "live.json; persisted native/wrapper logs", "files": 32, "bytes": 10816823}], "logs_scope": "已存在 persisted wrapper/native logs；原上传者排除了 node-local workspaces、datasets、submissions、checkpoints。", "curve_scope": "上传者 live.json 验证指标；官方 grade 为另一条证据。", "source_grade": {"competition_id": "jigsaw-toxic-comment-classification-challenge", "score": 0.98602, "gold_threshold": 0.9874, "silver_threshold": 0.98668, "bronze_threshold": 0.98639, "median_threshold": 0.98079, "any_medal": false, "gold_medal": false, "silver_medal": false, "bronze_medal": false, "above_median": true, "submission_exists": true, "valid_submission": true, "is_lower_better": false, "created_at": "2026-09-21T12:33:10.477896", "submission_path": "/scratch/harry123/EvolveFold/MLEvolve_BO/runs/aq04-mlebench-lite-20260921/tasks/jigsaw-toxic-comment-classification-challenge/22372431/submission.csv"}, "source_wrapper": {"task": "jigsaw-toxic-comment-classification-challenge", "job_id": "22372431", "owner": "harry123", "host": "g4.nibi.sharcnet", "commit": "3a0479c4e597b3515697d776c2768736cea8c4d6", "source_sha256": "efedc394766bff346ee7a3f98737fe3cf912cd3da7c397456e86e844d3c7046b", "started_at": "2026-09-21T04:32:13.496419+00:00", "agent_budget_seconds": 43200, "state": "completed", "workspace_is_node_local": true, "formal_result": true, "gpu": "NVIDIA H100 80GB HBM3", "gpu_uuid": "79e55043-5720-5661-0718-644222d72db7", "cpu_ids": [28, 29, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50], "grading_port": 32431, "grading_server_id": 27426, "search_started_at": "2026-09-21T04:32:57.028774+00:00", "search_exit_code": 124, "search_finished_at": "2026-09-21T16:32:57.789499+00:00", "fusion_exit_code": 0, "final_submission": "/scratch/harry123/EvolveFold/MLEvolve_BO/runs/aq04-mlebench-lite-20260921/tasks/jigsaw-toxic-comment-classification-challenge/22372431/native/20260921_003318_AQ04_jigsaw-toxic-comment-classification-challenge/final_submission.json", "log_dir": "/scratch/harry123/EvolveFold/MLEvolve_BO/runs/aq04-mlebench-lite-20260921/tasks/jigsaw-toxic-comment-classification-challenge/22372431/native/20260921_003318_AQ04_jigsaw-toxic-comment-classification-challenge", "journal_active_seconds": 38165.43772101402, "full_agent_budget_used": false, "outer_search_timeout_reached": true, "official_grade": "/scratch/harry123/EvolveFold/MLEvolve_BO/runs/aq04-mlebench-lite-20260921/tasks/jigsaw-toxic-comment-classification-challenge/22372431/official-grade.json", "finished_at": "2026-09-21T16:33:42.197110+00:00", "elapsed_seconds": 43288.67113268189}}, {"id": "harry123.aq04-20260921.leaf-classification", "experiment_id": "mlebench-aq04-12h-20260921", "family": "MLEBench", "method": "AQ04", "dataset": "leaf-classification", "seed": 42, "status": "completed", "source_status": "completed", "wrapper_status": "completed", "source_updated_at": "2026-09-21T16:36:37.534855+00:00", "uploaded_at": "2026-09-22T04:52:06.586629+00:00", "elapsed_seconds": 41521.93798804283, "budget_seconds": 43200.0, "metrics": [{"event_id": "375752b5d53c477e929c9a009ed30ba9", "step": 1, "value": 0.05947043654398035, "stage": "draft"}, {"event_id": "fecedb11cb1a47c3899e5c068f7a4d9b", "step": 4, "value": 0.025364848671071544, "stage": "debug"}, {"event_id": "877d7270e63a46fe85f611952df925c4", "step": 5, "value": 0.0008804275202140084, "stage": "improve"}, {"event_id": "ef8ba4d66fa64e48879d4bea6ce1e239", "step": 6, "value": 0.026011637237860305, "stage": "improve"}, {"event_id": "ad77de32bf92452485945be96794275a", "step": 7, "value": 2.5573446127634827e-07, "stage": "debug"}, {"event_id": "27f66e7d7a794c82b85b857302ab1439", "step": 9, "value": 9.792415634587936e-14, "stage": "improve"}, {"event_id": "bd06edd3b9fe4eb1b7221e9b45dedeb6", "step": 10, "value": 0.06755139497739214, "stage": "debug"}, {"event_id": "550a26e56e44432b9129e179f081007b", "step": 11, "value": 0.06304749587129109, "stage": "improve"}, {"event_id": "10b66dad581f4cd6a5dcf19b6836ce0c", "step": 13, "value": 0.07954567487075874, "stage": "debug"}, {"event_id": "166262446f9f4a12a11a1428bf7a492a", "step": 14, "value": 0.008997740726973584, "stage": "improve"}, {"event_id": "9a78d64925fa437a882744c7f817c4d9", "step": 15, "value": 0.031081149975881732, "stage": "improve"}, {"event_id": "7777a5b730de468689afe3eb263ad9d7", "step": 16, "value": 0.08843950123294962, "stage": "improve"}, {"event_id": "23c4a8f4ec6544c79e90f62696ed5469", "step": 17, "value": 0.11803214871274784, "stage": "improve"}, {"event_id": "b272b708f5334a04bdea1154840b818b", "step": 18, "value": 9.792415634587936e-14, "stage": "evolution"}, {"event_id": "f208d729daa0496e955c9f90b6a69c8c", "step": 19, "value": 0.09041621250252614, "stage": "improve"}, {"event_id": "72a59861dee5410e8ee1b757d6e65cf1", "step": 20, "value": 0.00889042813663608, "stage": "improve"}, {"event_id": "a8fb2d1428374d03b7a5e38c7935fe5e", "step": 21, "value": 0.18598325906051957, "stage": "improve"}, {"event_id": "fb1d007deff7473182978e1755b786bb", "step": 23, "value": 0.02326564004662058, "stage": "improve"}, {"event_id": "58508865364d463f9eb088a652b21208", "step": 24, "value": 0.017154580587457776, "stage": "debug"}, {"event_id": "206038172a4f4a41b5e12fa64916bbfb", "step": 25, "value": 0.08956516678970931, "stage": "evolution"}, {"event_id": "4282ba5f27c042faa2a2ef79ec025d64", "step": 26, "value": 0.004842993240144523, "stage": "improve"}, {"event_id": "7e6ecf14e339492c8643cd4abbaacc51", "step": 27, "value": 0.06433192590705489, "stage": "evolution"}, {"event_id": "0a4c5a0aa8b1444aa6a1cfef3b945e9a", "step": 28, "value": 0.021869164675306123, "stage": "evolution"}, {"event_id": "eac7a181581143949f28fbedd47a6c4f", "step": 29, "value": 0.00960587864266669, "stage": "improve"}, {"event_id": "45fb05423b1344b18e77b338f5fa996a", "step": 30, "value": 0.020834360836707207, "stage": "evolution"}, {"event_id": "aaa356c76dcd4bc79af73e62b450ca1b", "step": 31, "value": 0.0006255642306601248, "stage": "evolution"}, {"event_id": "c24db1c5a1304c3198e589b1b3d3a00f", "step": 32, "value": 0.000596597376267584, "stage": "evolution"}, {"event_id": "3b552f9cdc7d4498b97481d198b6dc84", "step": 33, "value": 0.004837873933968839, "stage": "evolution"}, {"event_id": "d7547460239646b883ebfaec1bff2a76", "step": 36, "value": 0.017948882226799363, "stage": "evolution"}, {"event_id": "b35a67ea94904501b1a6053a53134ff4", "step": 37, "value": 0.0008335916997683906, "stage": "debug"}, {"event_id": "49d5caa482814c7d8b45b131877bb13c", "step": 38, "value": 0.008739999257947502, "stage": "evolution"}, {"event_id": "72c13fbac08f44cc97af76f43ef1410c", "step": 39, "value": 0.009808923312539202, "stage": "evolution"}, {"event_id": "eb2dcd09f13b4deab09de3b9fe90a613", "step": 41, "value": 0.0006452588373647713, "stage": "evolution"}, {"event_id": "0149f681192649cc903b589ec927af56", "step": 42, "value": 0.0009288002155738521, "stage": "evolution"}, {"event_id": "680f2e59edd44cb88d1bc8956d736785", "step": 43, "value": 0.00981109056969187, "stage": "evolution"}, {"event_id": "88eb7d0d2e014e178d720afc06174751", "step": 44, "value": 0.0008436508768127047, "stage": "evolution"}, {"event_id": "3b2214bea66d478dbbe385eda16fa578", "step": 46, "value": 0.0009093348498477122, "stage": "evolution"}, {"event_id": "e8ee4eb4d3ec445a8f77a02c98b95b5e", "step": 47, "value": 9.997704753625699e-05, "stage": "debug"}, {"event_id": "de9cc980065a421281169043dad01b35", "step": 48, "value": 0.017628189029535314, "stage": "evolution"}, {"event_id": "65b700746c404bf38009fda130d5868e", "step": 50, "value": 0.000999168826366961, "stage": "evolution"}, {"event_id": "a9ba574b3c3b46c3b5b4386b644349e5", "step": 51, "value": 0.00853957503536938, "stage": "fusion"}, {"event_id": "25a19bdaf5a946ccbba45037d2c3e677", "step": 52, "value": 0.000983734552975721, "stage": "debug"}, {"event_id": "24c69fbd8cfe46f385f9b3a07724321a", "step": 53, "value": 0.02545871149843765, "stage": "evolution"}, {"event_id": "c10a3ebb2822426693eaa4b5b6efffe6", "step": 57, "value": 0.30928315765966186, "stage": "fusion_draft"}, {"event_id": "efb76384c1124d378ce73a850144bad9", "step": 58, "value": 0.007606900888234362, "stage": "evolution"}, {"event_id": "947c793a9e514fe1a87ccfc8a1e8829b", "step": 61, "value": 0.0005755250027590488, "stage": "debug"}, {"event_id": "3653cca92f49483aa7f5d9afe65717af", "step": 62, "value": 0.051722565482328314, "stage": "evolution"}, {"event_id": "2b8463449e474d879d53ccc7b3b20fe2", "step": 63, "value": 0.00040079089025592366, "stage": "evolution"}, {"event_id": "2ba6fd7a5aa545e8aac125fc21e3a57d", "step": 66, "value": 0.0010853197144928865, "stage": "debug"}, {"event_id": "8b1966650c814faba7922793473761c8", "step": 67, "value": 0.04162430342583732, "stage": "evolution"}, {"event_id": "2e478167832747fcbc1772a65f8c0a01", "step": 68, "value": 0.04698100842441579, "stage": "evolution"}, {"event_id": "073a023bcbc541b89e725c6b923a1e5d", "step": 69, "value": 0.0003617123580218819, "stage": "fusion"}, {"event_id": "48c53dce4ea24abcaa316328490a918f", "step": 70, "value": 0.0010150903530196803, "stage": "fusion"}, {"event_id": "5fb3ca1151fb4162828414502ac97a54", "step": 71, "value": 0.007212437415911314, "stage": "fusion"}, {"event_id": "857598c322094be6a83b742d463616dd", "step": 72, "value": 0.002268580176905614, "stage": "fusion"}, {"event_id": "41d9be5a5e944e3687423f1206f03105", "step": 73, "value": 0.00632646307862152, "stage": "fusion"}, {"event_id": "80a4425548fc46008471d5305a6b88ba", "step": 74, "value": 0.000124484511580967, "stage": "fusion"}, {"event_id": "f1abcead39374a849477e401bd00042b", "step": 75, "value": 0.908646, "stage": "fusion"}, {"event_id": "ccd4e194560d47559efbae4f2d63133a", "step": 76, "value": 0.0121400383036606, "stage": "evolution"}, {"event_id": "d0b0ddb603894131bd489220a6ff6122", "step": 78, "value": 0.09982314556123863, "stage": "fusion"}], "maximize": false, "metric_name": "native public validation metric", "official_score": 6e-05, "valid_submission": true, "medal": "silver", "thresholds": {"gold": 0.0, "silver": 0.00791, "bronze": 0.01526}, "formal_result": true, "full_agent_budget_used": false, "note": "", "artifacts": [{"bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/experiments/mlebench-aq04-12h-20260921/runs/harry123.aq04-20260921.leaf-classification/artifacts/logs", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/experiments/mlebench-aq04-12h-20260921/runs/harry123.aq04-20260921.leaf-classification/live.json", "member": "live.json; persisted native/wrapper logs", "files": 90, "bytes": 153357869}], "logs_scope": "已存在 persisted wrapper/native logs；原上传者排除了 node-local workspaces、datasets、submissions、checkpoints。", "curve_scope": "上传者 live.json 验证指标；官方 grade 为另一条证据。", "source_grade": {"competition_id": "leaf-classification", "score": 6e-05, "gold_threshold": 0.0, "silver_threshold": 0.00791, "bronze_threshold": 0.01526, "median_threshold": 0.108345, "any_medal": true, "gold_medal": false, "silver_medal": true, "bronze_medal": false, "above_median": true, "submission_exists": true, "valid_submission": true, "is_lower_better": true, "created_at": "2026-09-21T12:36:34.676147", "submission_path": "/scratch/harry123/EvolveFold/MLEvolve_BO/runs/aq04-mlebench-lite-20260921/tasks/leaf-classification/22372437/submission.csv"}, "source_wrapper": {"task": "leaf-classification", "job_id": "22372437", "owner": "harry123", "host": "g10.nibi.sharcnet", "commit": "3a0479c4e597b3515697d776c2768736cea8c4d6", "source_sha256": "efedc394766bff346ee7a3f98737fe3cf912cd3da7c397456e86e844d3c7046b", "started_at": "2026-09-21T04:36:21.855370+00:00", "agent_budget_seconds": 43200, "state": "completed", "workspace_is_node_local": true, "formal_result": true, "gpu": "NVIDIA H100 80GB HBM3", "gpu_uuid": "f50a9e54-9ac0-7736-0147-07982bdca777", "cpu_ids": [2, 3, 4, 5, 10, 11, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 32], "grading_port": 32437, "grading_server_id": 27432, "search_started_at": "2026-09-21T04:36:30.750364+00:00", "search_exit_code": 124, "search_finished_at": "2026-09-21T16:36:31.113332+00:00", "fusion_exit_code": 0, "final_submission": "/scratch/harry123/EvolveFold/MLEvolve_BO/runs/aq04-mlebench-lite-20260921/tasks/leaf-classification/22372437/native/20260921_003637_AQ04_leaf-classification/final_submission.json", "log_dir": "/scratch/harry123/EvolveFold/MLEvolve_BO/runs/aq04-mlebench-lite-20260921/tasks/leaf-classification/22372437/native/20260921_003637_AQ04_leaf-classification", "journal_active_seconds": 41521.93798804283, "full_agent_budget_used": false, "outer_search_timeout_reached": true, "official_grade": "/scratch/harry123/EvolveFold/MLEvolve_BO/runs/aq04-mlebench-lite-20260921/tasks/leaf-classification/22372437/official-grade.json", "finished_at": "2026-09-21T16:36:37.531375+00:00", "elapsed_seconds": 43215.66716506705}}, {"id": "harry123.aq04-20260921.mlsp-2013-birds", "experiment_id": "mlebench-aq04-12h-20260921", "family": "MLEBench", "method": "AQ04", "dataset": "mlsp-2013-birds", "seed": 42, "status": "completed", "source_status": "complete", "wrapper_status": "complete", "source_updated_at": "2026-09-25T17:01:35.765323+00:00", "uploaded_at": "2026-09-25T17:05:53.228266+00:00", "elapsed_seconds": 43209.06550979614, "budget_seconds": 43200, "metrics": [{"event_id": "4d831f68d3ba41e8925163716055fa22", "node_id": "4d831f68d3ba41e8925163716055fa22", "transition_id": "b800712dbf2b4b2784b1b28e44c49369", "step": 5, "value": 0.7335000741986545, "stage": "debug", "elapsed_seconds": 872.3769977092743}, {"event_id": "f4a6597b628844088f47162eace2ffe2", "node_id": "f4a6597b628844088f47162eace2ffe2", "transition_id": "87639e201d9249bd9d7e08088b0b97a1", "step": 9, "value": 0.7484078205381877, "stage": "improve", "elapsed_seconds": 1121.7994697093964}, {"event_id": "48dac4c9befb428ea61f329b7f471351", "node_id": "48dac4c9befb428ea61f329b7f471351", "transition_id": "4639ae9ad295467eac82148c42eb25ed", "step": 11, "value": 0.7391546299960429, "stage": "improve", "elapsed_seconds": 1248.192581653595}, {"event_id": "225faf5f06664b6cb83d5a05a0d99f9d", "node_id": "225faf5f06664b6cb83d5a05a0d99f9d", "transition_id": "89b8a4d22c1d48898bb94dd6d3202e22", "step": 12, "value": 0.725873070834982, "stage": "improve", "elapsed_seconds": 1355.8568518161774}, {"event_id": "c2d4809a18874436ac5baa7dbb21b3f5", "node_id": "c2d4809a18874436ac5baa7dbb21b3f5", "transition_id": "31dec5a500a048ec833562b353674380", "step": 13, "value": 0.7230998961218835, "stage": "improve", "elapsed_seconds": 1410.606900691986}, {"event_id": "651f7056c5e649d0be07203569de132b", "node_id": "651f7056c5e649d0be07203569de132b", "transition_id": "f3f6a57e1d2843799ace40390a2ac666", "step": 15, "value": 0.9139776434465554, "stage": "improve", "elapsed_seconds": 1714.7607128620148}, {"event_id": "f39ec74a1b00405385475bc97e0b1943", "node_id": "f39ec74a1b00405385475bc97e0b1943", "transition_id": "5178e602022d4e758242d4d6a67c3072", "step": 17, "value": 0.6976499589153657, "stage": "debug", "elapsed_seconds": 1757.7988350391388}, {"event_id": "5664503fea7241ee9d338f524425858e", "node_id": "5664503fea7241ee9d338f524425858e", "transition_id": "dc5c65f4f0924b10b867a2b3c20c3a60", "step": 18, "value": 0.7169506826276217, "stage": "improve", "elapsed_seconds": 1885.2088644504547}, {"event_id": "96ee92047fa549c2a998cad6dc56d56c", "node_id": "96ee92047fa549c2a998cad6dc56d56c", "transition_id": "a671fdf291c745ed9c60ebf2dd73964c", "step": 19, "value": 0.7391783406895669, "stage": "debug", "elapsed_seconds": 1929.923805475235}, {"event_id": "4a0ac3b27e2b438dbe17fd258d01c35a", "node_id": "4a0ac3b27e2b438dbe17fd258d01c35a", "transition_id": "80183b49787f477594c1844ee9be60e8", "step": 20, "value": 0.9278065630397238, "stage": "improve", "elapsed_seconds": 2050.3599112033844}, {"event_id": "905a8b292a2744c69ba0c8aabb86f1a0", "node_id": "905a8b292a2744c69ba0c8aabb86f1a0", "transition_id": "54e1762eb49249fb9696cdba5338a332", "step": 21, "value": 0.9064207125951513, "stage": "improve", "elapsed_seconds": 2244.6573956012726}, {"event_id": "a63935b0e94d4f0891f657729bdb70ff", "node_id": "a63935b0e94d4f0891f657729bdb70ff", "transition_id": "53f2dbf01aaa4e9ca0dbea9101a9034d", "step": 22, "value": 0.9230561952280432, "stage": "improve", "elapsed_seconds": 2296.701479434967}, {"event_id": "565d6d229e594ddf886a20206b2d8eb5", "node_id": "565d6d229e594ddf886a20206b2d8eb5", "transition_id": "10072f6e6c344ef1a000afea385f868e", "step": 23, "value": 0.921182754429732, "stage": "improve", "elapsed_seconds": 2424.179603099823}, {"event_id": "0bd408b847734c0cb4cba5fbbd120e37", "node_id": "0bd408b847734c0cb4cba5fbbd120e37", "transition_id": "8ad0dbcbcd454d6ca679fcc77f9e9a5b", "step": 24, "value": 0.9139424614597327, "stage": "improve", "elapsed_seconds": 2523.0832512378693}, {"event_id": "bfded5b1317e4b0b8ab17c172ca4a8fa", "node_id": "bfded5b1317e4b0b8ab17c172ca4a8fa", "transition_id": "0c313f39c25c46dba700fda79beb096d", "step": 25, "value": 0.7602703304313415, "stage": "evolution", "elapsed_seconds": 2609.6564886569977}, {"event_id": "96ac27af9c8f43409721bbbee1ddd5e4", "node_id": "96ac27af9c8f43409721bbbee1ddd5e4", "transition_id": "2a60dd3167764f50b281bac9628f247b", "step": 26, "value": 0.912848621505789, "stage": "improve", "elapsed_seconds": 2634.9205939769745}, {"event_id": "dcf23e9d6ea74d779f7f9064df6832ce", "node_id": "dcf23e9d6ea74d779f7f9064df6832ce", "transition_id": "4ea6be4a3a7248efb4393c6bd165e395", "step": 28, "value": 0.8809089746050022, "stage": "evolution", "elapsed_seconds": 2917.1603507995605}, {"event_id": "00c2b5b6406c4186bc999da08d9e5408", "node_id": "00c2b5b6406c4186bc999da08d9e5408", "transition_id": "9d0c7b62600842b1b8df3ca0648668e9", "step": 29, "value": 0.9514656495874112, "stage": "evolution", "elapsed_seconds": 2978.325721502304}, {"event_id": "522d73ef4f3a49efa28180fb2ef8148d", "node_id": "522d73ef4f3a49efa28180fb2ef8148d", "transition_id": "0013decca93246ff9cb4f70290f649f8", "step": 30, "value": 0.9999520245634235, "stage": "debug", "elapsed_seconds": 3075.16326212883}, {"event_id": "14344195e51b49adb6bd96482c7c11ba", "node_id": "14344195e51b49adb6bd96482c7c11ba", "transition_id": "2af346b7a16c4e93a39dd5b1d6b79d8a", "step": 31, "value": 0.7676629565662381, "stage": "evolution", "elapsed_seconds": 3290.2208862304688}, {"event_id": "814b50a7580241ea86fa3725da570c96", "node_id": "814b50a7580241ea86fa3725da570c96", "transition_id": "0029c1d866014239a6623c2db993a597", "step": 32, "value": 0.919367683745922, "stage": "improve", "elapsed_seconds": 3316.2578115463257}, {"event_id": "d9fac154576c41a9a85b1086fc1d51dd", "node_id": "d9fac154576c41a9a85b1086fc1d51dd", "transition_id": "72c6a451708a4802b7a6af24d759199c", "step": 33, "value": 0.9189678884411181, "stage": "improve", "elapsed_seconds": 3380.183200120926}, {"event_id": "01b71614f96448e8b10664e4d27832a0", "node_id": "01b71614f96448e8b10664e4d27832a0", "transition_id": "f1991ac9fe134394bba1d25540b56522", "step": 35, "value": 0.7949921640120258, "stage": "evolution", "elapsed_seconds": 3703.3845150470734}, {"event_id": "349eece39ef247f2a2b36a8bcb2b3ec6", "node_id": "349eece39ef247f2a2b36a8bcb2b3ec6", "transition_id": "f2b5c7ff1f794656972873c5aab66e16", "step": 36, "value": 0.9999392311136699, "stage": "improve", "elapsed_seconds": 3708.80100607872}, {"event_id": "722f9a2896054a8089bbe63af64d2f3f", "node_id": "722f9a2896054a8089bbe63af64d2f3f", "transition_id": "10f3520f6b3b4423bfd784bf0c04fcfb", "step": 38, "value": 0.8448612814224402, "stage": "debug", "elapsed_seconds": 3876.592866420746}, {"event_id": "88c22ea79f214e138093a7962166eac8", "node_id": "88c22ea79f214e138093a7962166eac8", "transition_id": "216234dbdbb440739016b72358e752fc", "step": 40, "value": 0.876392886841937, "stage": "evolution", "elapsed_seconds": 3986.2630228996277}, {"event_id": "ea134186492c4ebb80d7d7346ba4ba90", "node_id": "ea134186492c4ebb80d7d7346ba4ba90", "transition_id": "34829521a8554a77a0096945f6adc6c3", "step": 42, "value": 0.852746593744003, "stage": "debug", "elapsed_seconds": 4326.672904729843}, {"event_id": "50620d20464048b983e73cfcdf9dd577", "node_id": "50620d20464048b983e73cfcdf9dd577", "transition_id": "f866f412cc06405b9fc65ce87261c87b", "step": 43, "value": 0.8766477621091354, "stage": "debug", "elapsed_seconds": 4384.408601284027}, {"event_id": "12f3c18198ce4ab3b276932d386c921f", "node_id": "12f3c18198ce4ab3b276932d386c921f", "transition_id": "dab90629c11c49819dae780db0a269e7", "step": 44, "value": 0.9544129405744259, "stage": "evolution", "elapsed_seconds": 4395.356762886047}, {"event_id": "7ca4099b211049f2aba3f2115a70203d", "node_id": "7ca4099b211049f2aba3f2115a70203d", "transition_id": "0d32e052536c4f54a9eb778de16c45c4", "step": 46, "value": 0.8136458133435681, "stage": "evolution", "elapsed_seconds": 4685.95728468895}, {"event_id": "37bcde27dd404882a89bbb3dc2640277", "node_id": "37bcde27dd404882a89bbb3dc2640277", "transition_id": "d472d93e51a84a1db2d0a79dfaae277f", "step": 47, "value": 0.8082653681315168, "stage": "evolution", "elapsed_seconds": 4692.088225364685}, {"event_id": "edb55009cd014bd2ae9c30b01c6f8f2d", "node_id": "edb55009cd014bd2ae9c30b01c6f8f2d", "transition_id": "bb432168ceb9492db0d9da35292204ee", "step": 48, "value": 0.9456294377278832, "stage": "debug", "elapsed_seconds": 4845.885330438614}, {"event_id": "326c9252fc21408fb990cfa72ddc4876", "node_id": "326c9252fc21408fb990cfa72ddc4876", "transition_id": "590cbaaa93914f0f8bd45e3314a08c01", "step": 51, "value": 0.931499072474893, "stage": "evolution", "elapsed_seconds": 5062.35027050972}, {"event_id": "1b28f1cb864540a2a6b90f8f148c2104", "node_id": "1b28f1cb864540a2a6b90f8f148c2104", "transition_id": "8646338243b14ba5b39492a0b5080792", "step": 53, "value": 0.8289943548902963, "stage": "evolution", "elapsed_seconds": 5175.53652381897}, {"event_id": "94709b854b8f464ca6b443746d154e57", "node_id": "94709b854b8f464ca6b443746d154e57", "transition_id": "539468f6c4fa4da3a8d3e62587f39c74", "step": 55, "value": 0.958205398835796, "stage": "evolution", "elapsed_seconds": 5474.985733747482}, {"event_id": "3f527fa99aaf476cbfb0e0a023734edb", "node_id": "3f527fa99aaf476cbfb0e0a023734edb", "transition_id": "ea06d7474ead461e85d11f67a964e7bb", "step": 56, "value": 0.9502414763641015, "stage": "evolution", "elapsed_seconds": 5487.707447767258}, {"event_id": "7fdd4ba373d94959b44ea7d5cf3a7661", "node_id": "7fdd4ba373d94959b44ea7d5cf3a7661", "transition_id": "02bb20d076934f8e98c38b159aaaef4f", "step": 57, "value": 0.8100564510970383, "stage": "evolution", "elapsed_seconds": 5621.849851608276}, {"event_id": "856806deb5814fb38ecc0156d3b2ad27", "node_id": "856806deb5814fb38ecc0156d3b2ad27", "transition_id": "04da522b3ec0434da531531848b05ab3", "step": 59, "value": 0.8618531311968273, "stage": "evolution", "elapsed_seconds": 5856.247161149979}, {"event_id": "da234b556b3248eeba2855d3a7d4684d", "node_id": "da234b556b3248eeba2855d3a7d4684d", "transition_id": "551840686c794b12b2ea6eb9ca877e3b", "step": 61, "value": 0.9553172775538924, "stage": "debug", "elapsed_seconds": 6110.651661157608}, {"event_id": "1bd65c234e444102b282d3e8ef3a9855", "node_id": "1bd65c234e444102b282d3e8ef3a9855", "transition_id": "fdf6498aed254b4dbc906b667ccd42e9", "step": 64, "value": 0.8558399754751685, "stage": "evolution", "elapsed_seconds": 6368.935914993286}, {"event_id": "f56e755bdd68413ebf7285d0071688ea", "node_id": "f56e755bdd68413ebf7285d0071688ea", "transition_id": "090a92c072784a3f8c9d29858625f13f", "step": 65, "value": 0.7486971183323115, "stage": "debug", "elapsed_seconds": 6389.076444387436}, {"event_id": "cfc4e16b14cb4d66874ad0343963d167", "node_id": "cfc4e16b14cb4d66874ad0343963d167", "transition_id": "24922b24871346f2b303d162db90f3e0", "step": 66, "value": 0.9438295592656559, "stage": "debug", "elapsed_seconds": 6586.625959157944}, {"event_id": "84d0e6a146184bd1999bc81937330e05", "node_id": "84d0e6a146184bd1999bc81937330e05", "transition_id": "8dedd9a6a77d476eb998e43fd9c9bcd3", "step": 67, "value": 0.9099660973581527, "stage": "evolution", "elapsed_seconds": 6697.5103969573975}, {"event_id": "b454c3208b06463690a6095c2bfddfdf", "node_id": "b454c3208b06463690a6095c2bfddfdf", "transition_id": "f96911d7f50b4bc3b71158729b0156b1", "step": 69, "value": 0.9621361862726284, "stage": "evolution", "elapsed_seconds": 6913.2597460746765}, {"event_id": "91d80e880e9c41909d2f3d3550eb93d1", "node_id": "91d80e880e9c41909d2f3d3550eb93d1", "transition_id": "9afce0c7b50c4018a137589229b3e992", "step": 70, "value": 0.8488861702808163, "stage": "debug", "elapsed_seconds": 7098.549338817596}, {"event_id": "eceac933d6414cd08987c2c069a59d6a", "node_id": "eceac933d6414cd08987c2c069a59d6a", "transition_id": "01ac36e5483f4f83b85416a682848a01", "step": 72, "value": 0.8827632252286829, "stage": "evolution", "elapsed_seconds": 7213.854830026627}, {"event_id": "fd2203b9259d4bcc87ab24c3211b3b73", "node_id": "fd2203b9259d4bcc87ab24c3211b3b73", "transition_id": "91439d0276944c768eecad7db9850f54", "step": 73, "value": 0.8393630461203865, "stage": "evolution", "elapsed_seconds": 7602.465134143829}, {"event_id": "51d00182fed04a56b12d80ccf19657df", "node_id": "51d00182fed04a56b12d80ccf19657df", "transition_id": "aaab2e108792417a8dacd71b41298df8", "step": 74, "value": 0.8976396085204374, "stage": "debug", "elapsed_seconds": 7688.620648384094}, {"event_id": "a1abeab907064026bcc404b56d76b187", "node_id": "a1abeab907064026bcc404b56d76b187", "transition_id": "53ad82bd2b9744329db4c2e5b6343baf", "step": 75, "value": 0.9367020085716112, "stage": "evolution", "elapsed_seconds": 7955.264472961426}, {"event_id": "2052d19fd80645cd9638a877d76a38c5", "node_id": "2052d19fd80645cd9638a877d76a38c5", "transition_id": "924c5ff87d7d4bb68772c3ba0d8f0811", "step": 76, "value": 0.9534590289771637, "stage": "evolution", "elapsed_seconds": 7962.485525846481}, {"event_id": "4cdea7c696314e988f053b3da8b9cbfb", "node_id": "4cdea7c696314e988f053b3da8b9cbfb", "transition_id": "f6dcb84761f84572bd25ec0958f92459", "step": 77, "value": 0.951782287468816, "stage": "evolution", "elapsed_seconds": 8116.300581932068}, {"event_id": "7f48d8c2ff42422f96591d8800bdf2a0", "node_id": "7f48d8c2ff42422f96591d8800bdf2a0", "transition_id": "c6b5208c34454c6f804b2ee9ea0a918c", "step": 78, "value": 0.9507748033007101, "stage": "evolution", "elapsed_seconds": 8294.518915891647}, {"event_id": "e8e669b7c46142ada336b39a2f88a006", "node_id": "e8e669b7c46142ada336b39a2f88a006", "transition_id": "1151fc77f05f44ffbf9d5fcfc58b47a7", "step": 79, "value": 0.9414779632827992, "stage": "evolution", "elapsed_seconds": 8364.260311365128}, {"event_id": "62de3f275f4840fda53ef24a460a0b61", "node_id": "62de3f275f4840fda53ef24a460a0b61", "transition_id": "21d1d9d0606f479ca3cea9cb3acd301b", "step": 80, "value": 0.8427537101004285, "stage": "evolution", "elapsed_seconds": 8414.858521223068}, {"event_id": "9b4a7c5e38ec43fd94ea1306ad88117d", "node_id": "9b4a7c5e38ec43fd94ea1306ad88117d", "transition_id": "61fbcc523485462bb5ae32ad7e2421ec", "step": 81, "value": 0.9482440990213011, "stage": "evolution", "elapsed_seconds": 8840.793563365936}, {"event_id": "404f635ccc9b4e61bc3a75071858d2b1", "node_id": "404f635ccc9b4e61bc3a75071858d2b1", "transition_id": "4bfbc7678938408492051fef71c6ca46", "step": 83, "value": 0.9505637113797736, "stage": "evolution", "elapsed_seconds": 8888.338559865952}, {"event_id": "99ecf7045893457ba5297de76bea2ac5", "node_id": "99ecf7045893457ba5297de76bea2ac5", "transition_id": "e806866142224e2884375d7f80c8faa2", "step": 84, "value": 0.8186568476939807, "stage": "evolution", "elapsed_seconds": 9211.405992984772}, {"event_id": "e9283ca847654a4e97bcb236308bc990", "node_id": "e9283ca847654a4e97bcb236308bc990", "transition_id": "d9eda4f8926148199f56095e6821e567", "step": 85, "value": 0.9351372097486086, "stage": "debug", "elapsed_seconds": 9230.524745702744}, {"event_id": "0462c368dd5747af8427558711595252", "node_id": "0462c368dd5747af8427558711595252", "transition_id": "f8f05a683df7494cb5e92eab177e8b60", "step": 86, "value": 0.9426005884986888, "stage": "evolution", "elapsed_seconds": 9348.426311016083}, {"event_id": "89866309852246859a9fee103a122507", "node_id": "89866309852246859a9fee103a122507", "transition_id": "54c60fdcc3d64386a93d76882142f2f5", "step": 87, "value": 0.9668529712787054, "stage": "evolution", "elapsed_seconds": 9631.608138561249}, {"event_id": "503b9cb0ecbf43578df7b5e39f7511fe", "node_id": "503b9cb0ecbf43578df7b5e39f7511fe", "transition_id": "adaa92e2f0e142089df8a61c73df53ee", "step": 88, "value": 0.9329367363909677, "stage": "evolution", "elapsed_seconds": 9751.349499702454}, {"event_id": "70eb8e5395d14c95b8357e1a88c93fe9", "node_id": "70eb8e5395d14c95b8357e1a88c93fe9", "transition_id": "0d691191bdd24023ad8981367ec5617e", "step": 89, "value": 0.9453319900211092, "stage": "evolution", "elapsed_seconds": 9756.29744720459}, {"event_id": "9e30db99f1364a129e7fc2f8c00d214f", "node_id": "9e30db99f1364a129e7fc2f8c00d214f", "transition_id": "6e608edae95e436fa7e98b951511a2e0", "step": 90, "value": 0.903287116996098, "stage": "evolution", "elapsed_seconds": 9959.707247495651}, {"event_id": "eec92d6277de4b95aa69b8b015c84e08", "node_id": "eec92d6277de4b95aa69b8b015c84e08", "transition_id": "8317ed5b398f4c20bc48b76030228a3c", "step": 92, "value": 0.942746913580247, "stage": "evolution", "elapsed_seconds": 10157.786959648132}, {"event_id": "74f0c48eae7148a485a2b70926a32bda", "node_id": "74f0c48eae7148a485a2b70926a32bda", "transition_id": "fbf1e290e4a845c597327ae79701ba7d", "step": 93, "value": 0.9342888441118148, "stage": "evolution", "elapsed_seconds": 10434.000180006027}, {"event_id": "40539b1f448242b6a3ba26804de1eb2d", "node_id": "40539b1f448242b6a3ba26804de1eb2d", "transition_id": "72207a1133e74eea9428b2566942b178", "step": 94, "value": 0.8840001919017464, "stage": "debug", "elapsed_seconds": 10530.51076388359}, {"event_id": "a0b324f62eaa49c99744ae49b0933a37", "node_id": "a0b324f62eaa49c99744ae49b0933a37", "transition_id": "f555b26e84bb4e3fb7417be33abbb12a", "step": 95, "value": 0.843513321179556, "stage": "evolution", "elapsed_seconds": 10561.509762763977}, {"event_id": "a4de4c47947d4d5db55979fae250c90c", "node_id": "a4de4c47947d4d5db55979fae250c90c", "transition_id": "d41f97c072bd473bb2c7466edda6e52b", "step": 96, "value": 0.9524027697818718, "stage": "evolution", "elapsed_seconds": 10826.333902359009}, {"event_id": "e876538f503f4ed68a30c6c07ceb37db", "node_id": "e876538f503f4ed68a30c6c07ceb37db", "transition_id": "abb6fd3bca994489893f02ff7a6f92b7", "step": 97, "value": 0.8546999936032752, "stage": "evolution", "elapsed_seconds": 10928.41849064827}, {"event_id": "1ac3ac962add44889db8e91efe289a49", "node_id": "1ac3ac962add44889db8e91efe289a49", "transition_id": "5b7a3d687fe543ed89d455b75cfeff64", "step": 98, "value": 0.9286381372737158, "stage": "evolution", "elapsed_seconds": 10971.634915590286}, {"event_id": "54ffd11ec55d4fffa48ee10781b3ab9c", "node_id": "54ffd11ec55d4fffa48ee10781b3ab9c", "transition_id": "93a30da7908346adbe8be0c03dce4a66", "step": 99, "value": 0.9557202712211348, "stage": "evolution", "elapsed_seconds": 11267.502714633942}, {"event_id": "5a0e524c0b4d497f8ad26a22128f2a2f", "node_id": "5a0e524c0b4d497f8ad26a22128f2a2f", "transition_id": "7faac34114234da3853ae70db5ba5a4a", "step": 100, "value": 0.8868691230090193, "stage": "evolution", "elapsed_seconds": 11289.745375871658}, {"event_id": "8781fd3787f94a64800ff52e80324a4d", "node_id": "8781fd3787f94a64800ff52e80324a4d", "transition_id": "028e175661144283bac9d6687c51042c", "step": 101, "value": 0.9264368643254653, "stage": "evolution", "elapsed_seconds": 11364.289065599442}, {"event_id": "c2b29983f36942f580352353e339449b", "node_id": "c2b29983f36942f580352353e339449b", "transition_id": "8e7e8edf8e904e65ab0d5b522ae62671", "step": 104, "value": 0.8431982824793705, "stage": "evolution", "elapsed_seconds": 12174.527275562286}, {"event_id": "54ed7bc21d834b91a15e37fcf545f18c", "node_id": "54ed7bc21d834b91a15e37fcf545f18c", "transition_id": "ed9f14ad1c91483f9f7e03f92070e325", "step": 105, "value": 0.7858748320859719, "stage": "debug", "elapsed_seconds": 12174.588645935059}, {"event_id": "2cd1a3a62e6d4582b267015d9382d3ff", "node_id": "2cd1a3a62e6d4582b267015d9382d3ff", "transition_id": "7f66318414554853bc3aecc52d43b511", "step": 106, "value": 0.9387937376063455, "stage": "evolution", "elapsed_seconds": 12212.02425289154}, {"event_id": "331506b6af32441c9891a1c8d672997b", "node_id": "331506b6af32441c9891a1c8d672997b", "transition_id": "4906e4bf4fab461b9dc5beb89aaaca5a", "step": 109, "value": 0.8327192477451544, "stage": "debug", "elapsed_seconds": 12807.475653886795}, {"event_id": "a59d439b07c84e6598f1d35d97e97bab", "node_id": "a59d439b07c84e6598f1d35d97e97bab", "transition_id": "78e73c6e52544b95b877cb1b15c386b5", "step": 111, "value": 0.9539683681954839, "stage": "evolution", "elapsed_seconds": 12902.622295618057}, {"event_id": "f569f60881f44a5b8577cddc062a5982", "node_id": "f569f60881f44a5b8577cddc062a5982", "transition_id": "3f4306c9fdc04dcf8c2b7f3b00dbd5ab", "step": 112, "value": 0.8399107656879677, "stage": "debug", "elapsed_seconds": 13332.80351448059}, {"event_id": "8f4077619909455cb538ece5ade3f126", "node_id": "8f4077619909455cb538ece5ade3f126", "transition_id": "6ffcb30d7b5544cb8e3d2f6d5afb52cf", "step": 113, "value": 0.9410973581526259, "stage": "evolution", "elapsed_seconds": 13368.001961946487}, {"event_id": "814499004cd0484e8a4f6d48e43478ce", "node_id": "814499004cd0484e8a4f6d48e43478ce", "transition_id": "4a2c88089a154df19276b607a7bc4201", "step": 115, "value": 0.8707861574873665, "stage": "evolution", "elapsed_seconds": 13598.546841144562}, {"event_id": "91e4e5300fb045efb4172a905a20d09d", "node_id": "91e4e5300fb045efb4172a905a20d09d", "transition_id": "788d40ad18344cfab9b1cf566f8609a1", "step": 120, "value": 0.9462187360071644, "stage": "evolution", "elapsed_seconds": 16479.77961206436}, {"event_id": "f3e990761d2245a0bb91665db426df93", "node_id": "f3e990761d2245a0bb91665db426df93", "transition_id": "0b0ba870a8fd477a96da04b3485c07c2", "step": 121, "value": 0.9509443165099469, "stage": "evolution", "elapsed_seconds": 16580.402824163437}, {"event_id": "fdf5cb2965fb4981ae14576b03041381", "node_id": "fdf5cb2965fb4981ae14576b03041381", "transition_id": "32604f9523c44a339c6b1e368d649862", "step": 123, "value": 0.7434137721486598, "stage": "evolution", "elapsed_seconds": 17174.810086250305}, {"event_id": "1987ea4e11ea435692b0a18c8f446e8f", "node_id": "1987ea4e11ea435692b0a18c8f446e8f", "transition_id": "6558a892a7f344be9cbe0d640c89e09d", "step": 124, "value": 0.9519853834836565, "stage": "evolution", "elapsed_seconds": 17290.74412059784}, {"event_id": "93b66fb3ed8b48db858507000773f81c", "node_id": "93b66fb3ed8b48db858507000773f81c", "transition_id": "0c8786f905eb43eea54fd72704bf35a4", "step": 125, "value": 0.8602899315550437, "stage": "evolution", "elapsed_seconds": 17734.363445997238}, {"event_id": "cab9ab076863433ba935c1b35f10e3bf", "node_id": "cab9ab076863433ba935c1b35f10e3bf", "transition_id": "779c228f41b64c84894b0013113e0d08", "step": 126, "value": 0.9541346830422824, "stage": "evolution", "elapsed_seconds": 18053.390075445175}, {"event_id": "fbaf44cba21244e99ece47a61bb7f435", "node_id": "fbaf44cba21244e99ece47a61bb7f435", "transition_id": "790f83f6277a43cd8fe3686c7333dda2", "step": 127, "value": 0.9049566621889592, "stage": "debug", "elapsed_seconds": 18104.885359287262}, {"event_id": "6a86396bb63644498854415fcdf6426b", "node_id": "6a86396bb63644498854415fcdf6426b", "transition_id": "ebcfba24e1a040cd978190b04c55307d", "step": 128, "value": 0.9401450457365828, "stage": "evolution", "elapsed_seconds": 18605.357462644577}, {"event_id": "cbd837f8e21747c3a6395c5dd70ccabe", "node_id": "cbd837f8e21747c3a6395c5dd70ccabe", "transition_id": "927a72e670df4e5f8eb7d6e97f01a74e", "step": 129, "value": 0.8789060001279345, "stage": "evolution", "elapsed_seconds": 18888.856446027756}, {"event_id": "c0c3cc1f14934fc581068acb0b914ba1", "node_id": "c0c3cc1f14934fc581068acb0b914ba1", "transition_id": "f0c6398d3b1547ffabef889d5474c1b1", "step": 130, "value": 0.9582613701784686, "stage": "evolution", "elapsed_seconds": 18952.654463529587}, {"event_id": "a97bf53b42c34a58a0f652dade083076", "node_id": "a97bf53b42c34a58a0f652dade083076", "transition_id": "78dc4a13a8e343ecb509d611c54ea2f8", "step": 132, "value": 0.8420888505085395, "stage": "evolution", "elapsed_seconds": 19697.18854856491}, {"event_id": "7c61b88ec03946de80d45bb8567fbba7", "node_id": "7c61b88ec03946de80d45bb8567fbba7", "transition_id": "db113f9101f94c8294559c2bdd15d25e", "step": 133, "value": 0.9085955990532847, "stage": "evolution", "elapsed_seconds": 19735.204214811325}, {"event_id": "90a98067ff5d4a3190f64049a6145443", "node_id": "90a98067ff5d4a3190f64049a6145443", "transition_id": "86c29f2e69b64534b8ec40ad9d090370", "step": 134, "value": 0.9541514744450841, "stage": "evolution", "elapsed_seconds": 19977.47001194954}, {"event_id": "c8a7b2f1e3e948ce9bf9e37811be8234", "node_id": "c8a7b2f1e3e948ce9bf9e37811be8234", "transition_id": "50e82c98630e4a17b51d35d0298afef1", "step": 137, "value": 0.9456574233992194, "stage": "evolution", "elapsed_seconds": 20398.068897247314}, {"event_id": "30222e4ea8e84d3c977e87231c874ab1", "node_id": "30222e4ea8e84d3c977e87231c874ab1", "transition_id": "460e9371137b41e08f024de26ced08b1", "step": 138, "value": 0.9423359240069085, "stage": "debug", "elapsed_seconds": 20503.561453580856}, {"event_id": "e94fcbf541ed4d6ca4c0b324df987e80", "node_id": "e94fcbf541ed4d6ca4c0b324df987e80", "transition_id": "643f1d5b0c994ca4a2b14024f388da5d", "step": 139, "value": 0.8423087379261818, "stage": "debug", "elapsed_seconds": 20820.607702493668}, {"event_id": "23019d45d263498cad6ff4c144d43e87", "node_id": "23019d45d263498cad6ff4c144d43e87", "transition_id": "e02e430d4bcc4378b9b1c14fc17ed4a6", "step": 140, "value": 0.9604858312543978, "stage": "evolution", "elapsed_seconds": 21246.444954395294}, {"event_id": "f225c48975814152aac789e1d6098cfc", "node_id": "f225c48975814152aac789e1d6098cfc", "transition_id": "131fc7a1c38b4e9b87e34f9e92397453", "step": 141, "value": 0.9442237574361927, "stage": "evolution", "elapsed_seconds": 21413.49243593216}, {"event_id": "df83e91b8cb4488e800c3b935f1b9c8d", "node_id": "df83e91b8cb4488e800c3b935f1b9c8d", "transition_id": "8b09ece040b442f1bf8714913711bd53", "step": 142, "value": 0.8726827864133564, "stage": "evolution", "elapsed_seconds": 21560.76914191246}, {"event_id": "898f259cef7a43d8a1bcec20d240c749", "node_id": "898f259cef7a43d8a1bcec20d240c749", "transition_id": "4518c52fb2c54d7c92eba3854517f950", "step": 144, "value": 0.9545804548071388, "stage": "evolution", "elapsed_seconds": 21967.20076394081}, {"event_id": "e4d84fbee9d140e88658d08fae997813", "node_id": "e4d84fbee9d140e88658d08fae997813", "transition_id": "610a16fa01604ac9ae81b922d061a43c", "step": 146, "value": 0.9596334676645558, "stage": "evolution", "elapsed_seconds": 22480.171637773514}, {"event_id": "63d2cb69b0fd4edf84435d06b06a3316", "node_id": "63d2cb69b0fd4edf84435d06b06a3316", "transition_id": "abc70762f9444f4dadf92964ba938aa6", "step": 147, "value": 0.9371042026482441, "stage": "debug", "elapsed_seconds": 22490.890048742294}, {"event_id": "a84210286b094da39abf41132ad3316c", "node_id": "a84210286b094da39abf41132ad3316c", "transition_id": "0925f8dd12ac4e75940d223753c4674a", "step": 148, "value": 0.7209480745858121, "stage": "evolution", "elapsed_seconds": 22702.36200761795}, {"event_id": "c5669f0c8dd84957b51255168f0f0e76", "node_id": "c5669f0c8dd84957b51255168f0f0e76", "transition_id": "cf73220c148746028353f917b97cf05f", "step": 151, "value": 0.891262073818205, "stage": "evolution", "elapsed_seconds": 23457.287007331848}, {"event_id": "acf79019b6bf4a3298be39f329fe4cdc", "node_id": "acf79019b6bf4a3298be39f329fe4cdc", "transition_id": "30ffc021c78040e890f0fd3b5a801003", "step": 152, "value": 0.9218759994882619, "stage": "evolution", "elapsed_seconds": 23619.76185488701}, {"event_id": "1f2fdb055b5446e4953f33cb820770ad", "node_id": "1f2fdb055b5446e4953f33cb820770ad", "transition_id": "c9059bec2d314bcba0cf162456b17a6d", "step": 154, "value": 0.9566941725836371, "stage": "evolution", "elapsed_seconds": 24185.177226305008}, {"event_id": "d230faf8538a493ea94b62c43c342093", "node_id": "d230faf8538a493ea94b62c43c342093", "transition_id": "624017d8106f4db59957a9cee220d5f5", "step": 155, "value": 0.8271189151154608, "stage": "evolution", "elapsed_seconds": 24363.194556951523}, {"event_id": "84b74ee2d3634578ab1d5d56edbff796", "node_id": "84b74ee2d3634578ab1d5d56edbff796", "transition_id": "029acf178f4a4019b65475220467ec19", "step": 157, "value": 0.9535757692061664, "stage": "debug", "elapsed_seconds": 24510.779304027557}, {"event_id": "06a66c13eaec4bf6b6e31c79bcf416f2", "node_id": "06a66c13eaec4bf6b6e31c79bcf416f2", "transition_id": "f5e5b7b576ff4f2a8ac592250eb27b34", "step": 158, "value": 0.9363669801061855, "stage": "debug", "elapsed_seconds": 24994.397656917572}, {"event_id": "856a90e3d26d461db13c395e31ba6653", "node_id": "856a90e3d26d461db13c395e31ba6653", "transition_id": "a00c9f4d04834a53aec390546e1101a0", "step": 159, "value": 0.9528385466641082, "stage": "evolution", "elapsed_seconds": 25077.776258707047}, {"event_id": "c7ddce8bb8124437a3a11aff3fb649c0", "node_id": "c7ddce8bb8124437a3a11aff3fb649c0", "transition_id": "3bed802162394aebbf934b3fe8aad19f", "step": 160, "value": 0.9435001279344976, "stage": "evolution", "elapsed_seconds": 25376.998059034348}, {"event_id": "d38900daa7604b48a6233fc96339a670", "node_id": "d38900daa7604b48a6233fc96339a670", "transition_id": "b095ef99526643ff90908b6e8252f4b8", "step": 161, "value": 0.9418121921576152, "stage": "evolution", "elapsed_seconds": 25667.7713971138}, {"event_id": "671c59291f4f4d8c858eb099dcfd733f", "node_id": "671c59291f4f4d8c858eb099dcfd733f", "transition_id": "f35380280e804a60a87ffff6c87a50d2", "step": 162, "value": 0.9424902449945628, "stage": "evolution", "elapsed_seconds": 26757.736329078674}, {"event_id": "4e50775a1315491dbbed28039910a5dd", "node_id": "4e50775a1315491dbbed28039910a5dd", "transition_id": "3a3c9bc7fe2a454fb4f7e56319918d87", "step": 163, "value": 0.9570995650227082, "stage": "fusion", "elapsed_seconds": 27226.654265642166}, {"event_id": "21c1787fc8ba441f83694bf8190eef3c", "node_id": "21c1787fc8ba441f83694bf8190eef3c", "transition_id": "8bdf39c1553e4875a8b78826000a4a56", "step": 164, "value": 0.9552509115332949, "stage": "evolution", "elapsed_seconds": 27263.704040288925}, {"event_id": "b59cc389b5504e3f8c9a309fe4876fb7", "node_id": "b59cc389b5504e3f8c9a309fe4876fb7", "transition_id": "0f6da65b94cf42b4b6b7906083da8607", "step": 165, "value": 0.9305107784814176, "stage": "fusion", "elapsed_seconds": 27328.103739261627}, {"event_id": "d7a244a1285a46f08a4cfb3ea4b7862e", "node_id": "d7a244a1285a46f08a4cfb3ea4b7862e", "transition_id": "3428a4c741154d2c842514785d34ca0a", "step": 166, "value": 0.9305683490053094, "stage": "fusion", "elapsed_seconds": 27825.025778770447}, {"event_id": "1004a28019ee4a5195a1945ebb514e7f", "node_id": "1004a28019ee4a5195a1945ebb514e7f", "transition_id": "7bd0b48d096e4868819cd1674c543d6a", "step": 167, "value": 0.9371873600716433, "stage": "fusion", "elapsed_seconds": 28030.04019856453}, {"event_id": "012720b90a8140b999b966114bf0476b", "node_id": "012720b90a8140b999b966114bf0476b", "transition_id": "16fa236321724d95b1f74c49ae0f730e", "step": 168, "value": 0.9393998272884283, "stage": "fusion", "elapsed_seconds": 28078.499125003815}, {"event_id": "aeb7367b2c9f40deb0cf5b452a681aee", "node_id": "aeb7367b2c9f40deb0cf5b452a681aee", "transition_id": "c3d98a3926734caa8bd71abaf5730560", "step": 170, "value": 0.9577296424230793, "stage": "evolution", "elapsed_seconds": 28869.39146232605}, {"event_id": "d682de18e5604497ba8014cbd2ec3a67", "node_id": "d682de18e5604497ba8014cbd2ec3a67", "transition_id": "5f3a7720f09046a894b9e1bf81d3676b", "step": 171, "value": 0.8930051813471502, "stage": "fusion", "elapsed_seconds": 28959.349330186844}, {"event_id": "5fc9c240462f444ba05bd2b010b05196", "node_id": "5fc9c240462f444ba05bd2b010b05196", "transition_id": "f210a1921eba4ebf89b767dd3f42b894", "step": 172, "value": 0.959795784558306, "stage": "evolution", "elapsed_seconds": 29555.195011377335}, {"event_id": "3de059bfacef493b8be381c2f78688d7", "node_id": "3de059bfacef493b8be381c2f78688d7", "transition_id": "fa8f42fe14b8481191d8b39b66db0f56", "step": 173, "value": 0.9528385466641082, "stage": "evolution", "elapsed_seconds": 29626.255353212357}, {"event_id": "03b6bddf9b3a4e0e80e5abc67d61ca4f", "node_id": "03b6bddf9b3a4e0e80e5abc67d61ca4f", "transition_id": "d86774199a4b494681b7a334e818af56", "step": 174, "value": 0.9589450201496834, "stage": "fusion", "elapsed_seconds": 29823.811017513275}, {"event_id": "12fa97369dfc497f97fdb9d4404eceb5", "node_id": "12fa97369dfc497f97fdb9d4404eceb5", "transition_id": "479942570ad64529b4b20997879243ee", "step": 176, "value": 0.9615205015032302, "stage": "evolution", "elapsed_seconds": 30551.133722782135}, {"event_id": "f142b63a571a457cac9a0cf467cccc9d", "node_id": "f142b63a571a457cac9a0cf467cccc9d", "transition_id": "e294fe29d3a44c3f871efa8b8729bdb2", "step": 177, "value": 0.9430371649715346, "stage": "evolution", "elapsed_seconds": 30975.405729055405}, {"event_id": "42253031f7d9428896c24eb798cec6ce", "node_id": "42253031f7d9428896c24eb798cec6ce", "transition_id": "3272d0b812bc48158de51576e019fd46", "step": 179, "value": 0.8376767095247233, "stage": "fusion", "elapsed_seconds": 31190.20681333542}, {"event_id": "9076c49fec3343cba3230b00803f5982", "node_id": "9076c49fec3343cba3230b00803f5982", "transition_id": "55777f4cd50b4d84ab07cdee06e6a49c", "step": 180, "value": 0.9492755709076952, "stage": "fusion", "elapsed_seconds": 31777.497732162476}, {"event_id": "77cff366c2364a6babe2199c1a3348e5", "node_id": "77cff366c2364a6babe2199c1a3348e5", "transition_id": "00539a9f9e8146f58ec90341df57dd35", "step": 181, "value": 0.8394717904432931, "stage": "debug", "elapsed_seconds": 31935.77740597725}, {"event_id": "a86ae417c35641a1b120602356e1f5ec", "node_id": "a86ae417c35641a1b120602356e1f5ec", "transition_id": "23654e45824845c5a09671e7bbbc2bd1", "step": 182, "value": 0.9248128957973518, "stage": "evolution", "elapsed_seconds": 31958.354774475098}, {"event_id": "3fc98c9e5d264e40b34e8e9df93d9de7", "node_id": "3fc98c9e5d264e40b34e8e9df93d9de7", "transition_id": "7114bc5a343f48aaa04e107d6f55b38a", "step": 184, "value": 0.8854786349389112, "stage": "evolution", "elapsed_seconds": 32715.06037592888}, {"event_id": "0b4cea5b501e476b93124d7fe0f6e689", "node_id": "0b4cea5b501e476b93124d7fe0f6e689", "transition_id": "4fb15775c64048328a12182e091aa6e7", "step": 185, "value": 0.9308609991684259, "stage": "evolution", "elapsed_seconds": 32959.48103618622}, {"event_id": "519147843332476f9aea7e31d05153a6", "node_id": "519147843332476f9aea7e31d05153a6", "transition_id": "56846f1a1bfa4d78ad71879b1f1d9849", "step": 186, "value": 0.794806259195292, "stage": "evolution", "elapsed_seconds": 33511.66039323807}, {"event_id": "03cc41157eea4bb5bc020a1b2e94cbd5", "node_id": "03cc41157eea4bb5bc020a1b2e94cbd5", "transition_id": "0600275fcdec4284ae7e0eb8f6607771", "step": 187, "value": 0.9512505597134268, "stage": "evolution", "elapsed_seconds": 33636.92321586609}, {"event_id": "9d3db45436054f41894a871a5efe3baa", "node_id": "9d3db45436054f41894a871a5efe3baa", "transition_id": "0434b14e7318463184d905090344f789", "step": 188, "value": 0.8442581398324058, "stage": "evolution", "elapsed_seconds": 33840.61569738388}, {"event_id": "fd0ce45a8e2a4946abd7806b7ca14cb2", "node_id": "fd0ce45a8e2a4946abd7806b7ca14cb2", "transition_id": "66026f71b2034a9d8ed54d3d587ce8f9", "step": 189, "value": 0.9637761466129342, "stage": "evolution", "elapsed_seconds": 34189.26375627518}, {"event_id": "cdc4ec4988a34ab09009f7aa7b8bf416", "node_id": "cdc4ec4988a34ab09009f7aa7b8bf416", "transition_id": "5a1ffca352a847e4a0ef576c10fb9bfb", "step": 191, "value": 0.8431914859591887, "stage": "fusion", "elapsed_seconds": 34525.89520096779}, {"event_id": "99358995ee654368925a1be9318f130c", "node_id": "99358995ee654368925a1be9318f130c", "transition_id": "acc0663958dd4402876e0677ebfd5ed9", "step": 193, "value": 0.9455094991364422, "stage": "fusion", "elapsed_seconds": 35167.776883363724}, {"event_id": "24ae516f68cc4f4da4292bd3ec98fff9", "node_id": "24ae516f68cc4f4da4292bd3ec98fff9", "transition_id": "0ac92a9970a24f42884a76a66e6f5e94", "step": 194, "value": 0.8595491108552422, "stage": "fusion", "elapsed_seconds": 35183.450325489044}, {"event_id": "4bba2a5d7fd54f9facbf96f12fcc576c", "node_id": "4bba2a5d7fd54f9facbf96f12fcc576c", "transition_id": "faeacff7ecbe426491f38e676f2e2835", "step": 195, "value": 0.9066102155696284, "stage": "evolution", "elapsed_seconds": 35393.68742465973}, {"event_id": "6b431a7e313449b1a47ba79e3e16151d", "node_id": "6b431a7e313449b1a47ba79e3e16151d", "transition_id": "330fc28903c446389f25fe01cf34ba9a", "step": 197, "value": 0.9067989189534957, "stage": "evolution", "elapsed_seconds": 36061.422802209854}, {"event_id": "a54df7d0a08449ca8e4b05e9d2eca6d9", "node_id": "a54df7d0a08449ca8e4b05e9d2eca6d9", "transition_id": "3c4c7e3902b04767be5e26b106f7c3cf", "step": 198, "value": 0.9303456630205336, "stage": "evolution", "elapsed_seconds": 36179.58699417114}, {"event_id": "cf3a2bf207fd42f0afd1e7a08a6d9a52", "node_id": "cf3a2bf207fd42f0afd1e7a08a6d9a52", "transition_id": "99364f716d0a4867b5144b8786b2a526", "step": 199, "value": 0.9231425510138809, "stage": "evolution", "elapsed_seconds": 36679.31901264191}, {"event_id": "c4755704808f4952915c4b0485f06d78", "node_id": "c4755704808f4952915c4b0485f06d78", "transition_id": "9edf322067024eb198b6305625825652", "step": 200, "value": 0.9548711059937312, "stage": "fusion", "elapsed_seconds": 36845.84924554825}, {"event_id": "1a4366258b4e4a7eb155eb8e555e7d91", "node_id": "1a4366258b4e4a7eb155eb8e555e7d91", "transition_id": "63510b8715c14892bf8043b829ee18c5", "step": 201, "value": 0.9225724429092305, "stage": "evolution", "elapsed_seconds": 37300.8322057724}, {"event_id": "fb860bb9f892427290c9b771557f6058", "node_id": "fb860bb9f892427290c9b771557f6058", "transition_id": "983cede0e74c42959919616826660a27", "step": 202, "value": 0.9490045096910381, "stage": "fusion", "elapsed_seconds": 37421.251344680786}, {"event_id": "0704a9e47525443dbf8b12f0682e7e2e", "node_id": "0704a9e47525443dbf8b12f0682e7e2e", "transition_id": "5d455157312e4d2ab35bdb783062cd86", "step": 203, "value": 0.9535365892662956, "stage": "fusion", "elapsed_seconds": 37953.29104375839}, {"event_id": "8a223bb7400c411cac37baa187688180", "node_id": "8a223bb7400c411cac37baa187688180", "transition_id": "5615504f3c6749879ff7e46c6fd5b697", "step": 204, "value": 0.949944828247937, "stage": "evolution", "elapsed_seconds": 38350.516688108444}, {"event_id": "3fceff257ede4331984a6fb0c45c16e8", "node_id": "3fceff257ede4331984a6fb0c45c16e8", "transition_id": "3e4323918ea4455ca2ec41d27f9ea9d7", "step": 206, "value": 0.9454703191965713, "stage": "evolution", "elapsed_seconds": 38724.96153688431}, {"event_id": "598512fd3a77452080418043c0c60222", "node_id": "598512fd3a77452080418043c0c60222", "transition_id": "fc24b88a24484f5081c98390c77abd58", "step": 207, "value": 0.7144286125503742, "stage": "evolution", "elapsed_seconds": 39091.19328761101}, {"event_id": "171f8e4fe0b14610ba0b513a46fe16bf", "node_id": "171f8e4fe0b14610ba0b513a46fe16bf", "transition_id": "9b74880f462945a2a151fa29f10a014e", "step": 208, "value": 0.9406224013305188, "stage": "evolution", "elapsed_seconds": 39296.44937443733}, {"event_id": "cea2cccdfe434717b7df49cf61d23470", "node_id": "cea2cccdfe434717b7df49cf61d23470", "transition_id": "7466da6c44bb4f6e8eb1323c49a74cf8", "step": 209, "value": 0.9619314910765687, "stage": "fusion", "elapsed_seconds": 39651.26561355591}, {"event_id": "59c667c326df4857aea51100c4c29906", "node_id": "59c667c326df4857aea51100c4c29906", "transition_id": "4739edb0b5424a9493e2dc8169979451", "step": 210, "value": 0.93179012345679, "stage": "evolution", "elapsed_seconds": 39711.84259343147}, {"event_id": "91b5a3e697f8423786df1b66bbb3d71f", "node_id": "91b5a3e697f8423786df1b66bbb3d71f", "transition_id": "e071856e0c904f0d96394ff33623e017", "step": 211, "value": 0.9586395765368131, "stage": "evolution", "elapsed_seconds": 40419.808326244354}, {"event_id": "ab375cae11734e58a36feb636e1a8326", "node_id": "ab375cae11734e58a36feb636e1a8326", "transition_id": "b3cc94b914e44cc1a05469c696bae5a6", "step": 212, "value": 0.8419905008635578, "stage": "fusion", "elapsed_seconds": 40619.723254442215}, {"event_id": "16f324c979f449feba988e5d9c86208e", "node_id": "16f324c979f449feba988e5d9c86208e", "transition_id": "648572cecd0047f896b8acb092288915", "step": 214, "value": 0.9565710356297575, "stage": "fusion", "elapsed_seconds": 40683.432181835175}, {"event_id": "0d8e1d39b4294ddd966c218bc612d1cd", "node_id": "0d8e1d39b4294ddd966c218bc612d1cd", "transition_id": "d8e0f1ac5eb1448e8ebcbb551e97689c", "step": 215, "value": 0.9480745858120643, "stage": "evolution", "elapsed_seconds": 41241.53305077553}, {"event_id": "bfd6472fe3e34309b4e5c5490d688e13", "node_id": "bfd6472fe3e34309b4e5c5490d688e13", "transition_id": "058015269452497281b2e8489c701a5a", "step": 216, "value": 0.9556267191198106, "stage": "evolution", "elapsed_seconds": 41404.48577928543}, {"event_id": "ee91c789ea4f48439e7311e418bc40a8", "node_id": "ee91c789ea4f48439e7311e418bc40a8", "transition_id": "f0f9359dcb3c414bb515987a8b96154a", "step": 218, "value": 0.8816533934625473, "stage": "evolution", "elapsed_seconds": 41847.584711551666}, {"event_id": "72692cd4fc854741a87bd1761d0b0431", "node_id": "72692cd4fc854741a87bd1761d0b0431", "transition_id": "c0317a85ae274e419cc88d3b099f9832", "step": 219, "value": 0.9515703959572699, "stage": "evolution", "elapsed_seconds": 42044.22301483154}, {"event_id": "36c625db71b345ada1079b9e493f46ad", "node_id": "36c625db71b345ada1079b9e493f46ad", "transition_id": "02a0d95d0af6420a9dfdcfc5d164c290", "step": 220, "value": 0.9585540203415851, "stage": "debug", "elapsed_seconds": 42202.399930238724}, {"event_id": "65b1c3193fd54877b0252076f0635a83", "node_id": "65b1c3193fd54877b0252076f0635a83", "transition_id": "20e702ee1d4d4015a4c5d3f42e2cd9f7", "step": 221, "value": 0.9609096662847574, "stage": "fusion", "elapsed_seconds": 42515.386323690414}, {"event_id": "942f4fc3180a4d1bb04b765e13f38d13", "node_id": "942f4fc3180a4d1bb04b765e13f38d13", "transition_id": "24ec14c6c82743f3935bf3651288ef05", "step": 222, "value": 0.7668993475340625, "stage": "evolution", "elapsed_seconds": 42679.1501083374}, {"event_id": "7540e3e41d1549cb80500acdd22516e3", "node_id": "7540e3e41d1549cb80500acdd22516e3", "transition_id": "136b0b45f60c4c90a7c98e23cb8b28cd", "step": 223, "value": 0.9581558242180004, "stage": "evolution", "elapsed_seconds": 42784.54396224022}, {"event_id": "cfeb86eca3ad436f82a4ebb657dd9d9d", "node_id": "cfeb86eca3ad436f82a4ebb657dd9d9d", "transition_id": "97c00eac572b4b4db12ea963cfe1853e", "step": 224, "value": 0.9475028785261945, "stage": "evolution", "elapsed_seconds": 43168.22784781456}], "maximize": true, "metric_name": "native public validation metric", "official_score": 0.91801, "valid_submission": true, "medal": "silver", "thresholds": {"gold": 0.93527, "silver": 0.90038, "bronze": 0.87372}, "formal_result": false, "full_agent_budget_used": true, "note": "从 2026-09-21 首轮断点续跑；续跑使用独占 A100 80GB，仅补原 12h 剩余时间。 已保存评分来自本次续跑最终提交。 原首轮格式校验任务 ID 有误；续跑已修正。原全局记忆缺失，按保存记录重建；详情见 provenance。", "artifacts": [{"bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/experiments/mlebench-aq04-12h-20260921/continuations/liux-mila-20260924/runs/harry123.aq04-20260921.mlsp-2013-birds", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/experiments/mlebench-aq04-12h-20260921/continuations/liux-mila-20260924/runs/harry123.aq04-20260921.mlsp-2013-birds/live.json", "member": "live.json; immutable metric events and continuation archive index", "files": 1, "bytes": 0}, {"bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/experiments/mlebench-aq04-12h-20260921/continuations/liux-mila-20260924/runs/harry123.aq04-20260921.mlsp-2013-birds/final", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/experiments/mlebench-aq04-12h-20260921/continuations/liux-mila-20260924/runs/harry123.aq04-20260921.mlsp-2013-birds/final/submission-51f9270ed5bbb6ca75be42050bb9dfacd9b6bc3b71c5f89b80814691dde54781.csv", "member": "Sealed final submission.csv; SHA256 51f9270ed5bbb6ca75be42050bb9dfacd9b6bc3b71c5f89b80814691dde54781", "files": 1, "bytes": 30925}, {"bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/experiments/mlebench-aq04-12h-20260921/continuations/liux-mila-20260924/runs/harry123.aq04-20260921.mlsp-2013-birds/artifacts", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/experiments/mlebench-aq04-12h-20260921/continuations/liux-mila-20260924/runs/harry123.aq04-20260921.mlsp-2013-birds/artifacts/logs-aaea02644ebd4bd436081f110ccd944be9017f152f635bac2f16e2285b15e61b.tar.gz", "member": "experiments/mlebench-aq04-12h-20260921/continuations/liux-mila-20260924/runs/harry123.aq04-20260921.mlsp-2013-birds/artifacts/logs-aaea02644ebd4bd436081f110ccd944be9017f152f635bac2f16e2285b15e61b.tar.gz", "files": 408, "bytes": 162953443}, {"bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/experiments/mlebench-aq04-12h-20260921/runs/harry123.aq04-20260921.mlsp-2013-birds/artifacts/logs", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/experiments/mlebench-aq04-12h-20260921/runs/harry123.aq04-20260921.mlsp-2013-birds/live.json", "member": "live.json; persisted native/wrapper logs", "files": 100, "bytes": 248626774}], "logs_scope": "完整可用日志、候选代码及提交 CSV 已上传；日志快照时间 2026-09-25T17:04:24.035876+00:00；排除数据集、模型缓存及凭据。", "curve_scope": "保留原始指标点；续跑使用已提交的有效原生观察。仅有原生 active 时间的点参与时间曲线。", "source_grade": {"competition_id": "mlsp-2013-birds", "score": 0.91801, "gold_threshold": 0.93527, "silver_threshold": 0.90038, "bronze_threshold": 0.87372, "median_threshold": 0.86572, "any_medal": true, "gold_medal": false, "silver_medal": true, "bronze_medal": false, "above_median": true, "submission_exists": true, "valid_submission": true, "is_lower_better": false, "created_at": "2026-09-25T13:01:35.630937", "submission_path": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/runs/aq04-mlebench-lite-20260921-resume-mila-20260924/tasks/mlsp-2013-birds/20260921_003318_AQ04_mlsp-2013-birds/workspace/ensembles_csv/top6ens-total_run_time0.46h.csv"}, "source_wrapper": {"task": "mlsp-2013-birds", "job_id": "22372432", "owner": "harry123", "host": "g4.nibi.sharcnet", "commit": "3a0479c4e597b3515697d776c2768736cea8c4d6", "source_sha256": "efedc394766bff346ee7a3f98737fe3cf912cd3da7c397456e86e844d3c7046b", "started_at": "2026-09-21T04:32:13.502422+00:00", "agent_budget_seconds": 43200, "state": "failed", "workspace_is_node_local": true, "formal_result": false, "gpu": "NVIDIA H100 80GB HBM3", "gpu_uuid": "0ee7b952-9184-5699-76a9-8eaca8731ee5", "cpu_ids": [68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86, 87, 88], "grading_port": 32432, "grading_server_id": 27427, "search_started_at": "2026-09-21T04:32:56.845805+00:00", "search_exit_code": 1, "search_finished_at": "2026-09-21T07:43:31.656401+00:00", "fusion_exit_code": 0, "final_submission": "/scratch/harry123/EvolveFold/MLEvolve_BO/runs/aq04-mlebench-lite-20260921/tasks/mlsp-2013-birds/22372432/native/20260921_003318_AQ04_mlsp-2013-birds/final_submission.json", "log_dir": "/scratch/harry123/EvolveFold/MLEvolve_BO/runs/aq04-mlebench-lite-20260921/tasks/mlsp-2013-birds/22372432/native/20260921_003318_AQ04_mlsp-2013-birds", "journal_active_seconds": 10972.428212165833, "full_agent_budget_used": false, "outer_search_timeout_reached": false, "official_grade": "/scratch/harry123/EvolveFold/MLEvolve_BO/runs/aq04-mlebench-lite-20260921/tasks/mlsp-2013-birds/22372432/official-grade.json", "finished_at": "2026-09-21T07:43:36.671047+00:00", "elapsed_seconds": 11483.130267293192}, "score_phase": "continuation-final", "final_submission_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/experiments/mlebench-aq04-12h-20260921/continuations/liux-mila-20260924/runs/harry123.aq04-20260921.mlsp-2013-birds/final/submission-51f9270ed5bbb6ca75be42050bb9dfacd9b6bc3b71c5f89b80814691dde54781.csv", "hardware": "A100 80GB (continuation); H100 80GB (first segment)", "model": "muse-spark-1.3-contributor", "provider": "codex://opencode-go", "scheduler": {"job_id": "10929807", "partition": "short-unkillable", "observed_at": "2026-09-25T17:05:53.228316+00:00", "allocation": null}, "completed_candidates": 266, "pending_decisions": 3, "remaining_seconds": 0, "continuation_source_status": {"state": "complete", "active_elapsed_seconds": 43209.06550979614, "updated_at": "2026-09-25T17:01:35.765323+00:00", "source_updated_at": "2026-09-21T07:43:36.671047+00:00", "imported_first_run": true, "run_root": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/runs/aq04-mlebench-lite-20260921-resume-mila-20260924/tasks/mlsp-2013-birds/20260921_003318_AQ04_mlsp-2013-birds", "previous_job_id": "22372432", "job_id": "10929807", "attempt": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/runs/aq04-mlebench-lite-20260921-resume-mila-20260924/tasks/mlsp-2013-birds/attempt-05-10929807", "gpu": "NVIDIA A100-SXM4-80GB", "host": "cn-g025.server.mila.quebec", "started_at": "2026-09-24T17:57:18.697130+00:00", "search_pid": 3293023, "attempt_started_epoch": 1790348628.3271806, "search_stopped_epoch": 1790355687.4876122, "search_exit_code": 75, "budget_complete": true, "completed_transitions": 266, "release_receipt": {"job_id": "10927555", "state": "COMPLETED", "end": "2026-09-25T07:15:38", "exit_code": "0:0", "end_epoch": 1790334938.0, "verified_at": "2026-09-25T11:15:42.854257+00:00"}, "stop_history": [{"stop_reason": "user_request", "stop_requested_at": "2026-09-24T19:15:09.692440+00:00", "stopped_at": "2026-09-24T19:15:16.423637+00:00", "job_id": "10919452", "active_elapsed_seconds": 15894.91823220253}], "resume_requested_at": "2026-09-25T05:30:03.052522+00:00", "resume_reason": "explicit_user_request", "error": null, "search_finished_at": "2026-09-25T17:01:30.893665+00:00", "finished_at": "2026-09-25T17:01:35.763102+00:00", "submission": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/runs/aq04-mlebench-lite-20260921-resume-mila-20260924/tasks/mlsp-2013-birds/20260921_003318_AQ04_mlsp-2013-birds/workspace/ensembles_csv/top6ens-total_run_time0.46h.csv", "official_grade": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/runs/aq04-mlebench-lite-20260921-resume-mila-20260924/tasks/mlsp-2013-birds/20260921_003318_AQ04_mlsp-2013-birds/logs/official-grade.json", "final_submission_sha256": "51f9270ed5bbb6ca75be42050bb9dfacd9b6bc3b71c5f89b80814691dde54781"}, "config_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/experiments/mlebench-aq04-12h-20260921/continuations/liux-mila-20260924/runs/harry123.aq04-20260921.mlsp-2013-birds/config.yaml"}, {"id": "harry123.aq04-20260921.new-york-city-taxi-fare-prediction", "experiment_id": "mlebench-aq04-12h-20260921", "family": "MLEBench", "method": "AQ04", "dataset": "new-york-city-taxi-fare-prediction", "seed": 42, "status": "completed", "source_status": "completed", "wrapper_status": "completed", "source_updated_at": "2026-09-21T16:32:55.795841+00:00", "uploaded_at": "2026-09-22T04:54:57.361781+00:00", "elapsed_seconds": 42163.669632434845, "budget_seconds": 43200.0, "metrics": [{"event_id": "9672bfbbf785457c81f4108312f46408", "step": 2, "value": 3.6136824077690086, "stage": "draft"}, {"event_id": "bab106c2684e47749ab5d91a65ed9547", "step": 3, "value": 3.5241523827668737, "stage": "debug"}, {"event_id": "eb2d3ef723514094bc805737e39ac324", "step": 4, "value": 3.170718375159446, "stage": "draft"}, {"event_id": "dc0695079b1544858d9a1415d928178d", "step": 5, "value": 3.233288190335029, "stage": "improve"}, {"event_id": "6821fada675b4dbcb73c09761858d5f0", "step": 6, "value": 2.7853321383102996, "stage": "improve"}, {"event_id": "b1fa8fe7c6de4629b8ddbd5d772f587c", "step": 7, "value": 2.7079916463316738, "stage": "improve"}, {"event_id": "a5a02cb5a4464c67a3b61cbced82502e", "step": 8, "value": 2.6861804574625046, "stage": "improve"}, {"event_id": "3774a969844346be81418e0437dd829c", "step": 10, "value": 2.7774267174504916, "stage": "improve"}, {"event_id": "2d9d1794fd534303a0940a125c57c84b", "step": 11, "value": 2.7631243376991788, "stage": "debug"}, {"event_id": "481baa0d932f4835b264a9e6a5f92a22", "step": 12, "value": 2.7130744815955734, "stage": "improve"}, {"event_id": "4df2195c00344429b7bd08e7471aedfb", "step": 13, "value": 2.869787261743665, "stage": "improve"}, {"event_id": "d63c46df11124deeafc131c76e500e18", "step": 15, "value": 3.03374033931216, "stage": "debug"}, {"event_id": "6a9dfee185584aaab34bf27ae5308663", "step": 16, "value": 3.17306229332411, "stage": "improve"}, {"event_id": "b5f3ff6ba7fc46bf9546bb5679e0987f", "step": 17, "value": 2.9037918889696446, "stage": "improve"}, {"event_id": "05c84d6a2c9e4630ba59f656519df956", "step": 18, "value": 2.7101679725987577, "stage": "improve"}, {"event_id": "ee11ea31698244d88e7f5b010e9df024", "step": 20, "value": 2.2969513143738856, "stage": "improve"}, {"event_id": "0efe93f3e1bc4617b23268bcf9c9c2d5", "step": 21, "value": 2.6806401435690956, "stage": "evolution"}, {"event_id": "330756d1383d4b1a9a637901699c1374", "step": 22, "value": 2.8229698458280468, "stage": "debug"}, {"event_id": "a24bd0ac4d554bd19f5122ad0c71aa90", "step": 23, "value": 2.770089712857665, "stage": "improve"}, {"event_id": "a1eb4d217eff4fd6835cfc296a2c4475", "step": 27, "value": 2.780127470366825, "stage": "debug"}, {"event_id": "435fc5b6431443a1a7d0a71ed94e3050", "step": 28, "value": 2.2892891416792938, "stage": "improve"}, {"event_id": "929fb51eae4b439a93f181133df81118", "step": 29, "value": 2.3029426921737306, "stage": "debug"}, {"event_id": "0d3bc9fa3852467ab42a09b85e65a169", "step": 30, "value": 2.4073504244744885, "stage": "improve"}, {"event_id": "92f17ec01f114f408e63114251cd4e80", "step": 31, "value": 2.2774623084275842, "stage": "improve"}, {"event_id": "48adaa21186f411ebe31aaa7bf4eda70", "step": 32, "value": 2.30455879813799, "stage": "improve"}, {"event_id": "1cf95bbdd86a4ccc96a3af07a9ba906b", "step": 33, "value": 2.3290913532331996, "stage": "improve"}, {"event_id": "933ca83908154cb9ab320f2539f51c01", "step": 34, "value": 3.6325374575383, "stage": "improve"}, {"event_id": "0859aedf437e4686af0dc1ff23fc9205", "step": 35, "value": 2.7695415754401136, "stage": "improve"}, {"event_id": "24c94f0441424cb1a86a46c4bdb69448", "step": 36, "value": 2.5111921637207644, "stage": "evolution"}, {"event_id": "377ddeba2b304939a40e64582a80c02c", "step": 37, "value": 2.4747555487888957, "stage": "fusion"}, {"event_id": "18ef6f81323c4bdc932b56117c1f80ab", "step": 38, "value": 2.6798719143119074, "stage": "evolution"}, {"event_id": "26bf78bcb3ed44aaadfa1609d85e11f1", "step": 39, "value": 2.2788956724995497, "stage": "improve"}, {"event_id": "b10d166a4a9b450abe84f4bb2f5513ba", "step": 40, "value": 2.2885366219170926, "stage": "evolution"}, {"event_id": "243f27292f6940b0a6db8cf349a7bc92", "step": 41, "value": 2.2756287991263355, "stage": "evolution"}, {"event_id": "aee0717f6ff24471834d983c349d05c0", "step": 42, "value": 2.4732917347697425, "stage": "evolution"}, {"event_id": "ae882dd0362a4db4a48eb4de6c972bcc", "step": 43, "value": 2.2917165465211458, "stage": "evolution"}, {"event_id": "0a53c0e04bb345fea6415685693b4e45", "step": 44, "value": 2.478007996001091, "stage": "improve"}, {"event_id": "f1d02c0320f7422fbe2c21635f3a90a7", "step": 45, "value": 2.2947780490081975, "stage": "improve"}, {"event_id": "5191dd3497a048fda1c582d0d618ba2d", "step": 46, "value": 2.829818515833339, "stage": "improve"}, {"event_id": "99e3c912cb3b45f9907a0d87337b62eb", "step": 47, "value": 2.6815354485090945, "stage": "improve"}, {"event_id": "4c5513945b724b16a340388631d35569", "step": 48, "value": 2.281225420514652, "stage": "evolution"}, {"event_id": "284c8c4c05b24e67ab82da7d034e9b30", "step": 49, "value": 2.275665814466754, "stage": "evolution"}, {"event_id": "2482762ae0894d7fbbcc8915308d2804", "step": 50, "value": 2.496636023704976, "stage": "evolution"}, {"event_id": "c150cde15c8949aa8abef61742948215", "step": 51, "value": 2.273599997505847, "stage": "evolution"}, {"event_id": "b01d5acdceeb4717a4bd74a45a0dd68b", "step": 52, "value": 2.3353813369592924, "stage": "evolution"}, {"event_id": "38e348caafab48ddbac1c4aef0068b7b", "step": 53, "value": 2.7116750249801664, "stage": "evolution"}], "maximize": false, "metric_name": "native public validation metric", "official_score": 9.06377, "valid_submission": true, "medal": "none", "thresholds": {"gold": 2.83377, "silver": 2.88191, "bronze": 2.92371}, "formal_result": true, "full_agent_budget_used": false, "note": "", "artifacts": [{"bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/experiments/mlebench-aq04-12h-20260921/runs/harry123.aq04-20260921.new-york-city-taxi-fare-prediction/artifacts/logs", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/experiments/mlebench-aq04-12h-20260921/runs/harry123.aq04-20260921.new-york-city-taxi-fare-prediction/live.json", "member": "live.json; persisted native/wrapper logs", "files": 73, "bytes": 73734084}], "logs_scope": "已存在 persisted wrapper/native logs；原上传者排除了 node-local workspaces、datasets、submissions、checkpoints。", "curve_scope": "上传者 live.json 验证指标；官方 grade 为另一条证据。", "source_grade": {"competition_id": "new-york-city-taxi-fare-prediction", "score": 9.06377, "gold_threshold": 2.83377, "silver_threshold": 2.88191, "bronze_threshold": 2.92371, "median_threshold": 3.59741, "any_medal": false, "gold_medal": false, "silver_medal": false, "bronze_medal": false, "above_median": false, "submission_exists": true, "valid_submission": true, "is_lower_better": true, "created_at": "2026-09-21T12:32:50.649826", "submission_path": "/scratch/harry123/EvolveFold/MLEvolve_BO/runs/aq04-mlebench-lite-20260921/tasks/new-york-city-taxi-fare-prediction/22372433/submission.csv"}, "source_wrapper": {"task": "new-york-city-taxi-fare-prediction", "job_id": "22372433", "owner": "harry123", "host": "g10.nibi.sharcnet", "commit": "3a0479c4e597b3515697d776c2768736cea8c4d6", "source_sha256": "efedc394766bff346ee7a3f98737fe3cf912cd3da7c397456e86e844d3c7046b", "started_at": "2026-09-21T04:32:13.302980+00:00", "agent_budget_seconds": 43200, "state": "completed", "workspace_is_node_local": true, "formal_result": true, "gpu": "NVIDIA H100 80GB HBM3", "gpu_uuid": "a1798eaf-30eb-8652-d8c4-8240260c5bd0", "cpu_ids": [56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 76], "grading_port": 32433, "grading_server_id": 27428, "search_started_at": "2026-09-21T04:32:45.472580+00:00", "search_exit_code": 124, "search_finished_at": "2026-09-21T16:32:46.005493+00:00", "fusion_exit_code": 0, "final_submission": "/scratch/harry123/EvolveFold/MLEvolve_BO/runs/aq04-mlebench-lite-20260921/tasks/new-york-city-taxi-fare-prediction/22372433/native/20260921_003302_AQ04_new-york-city-taxi-fare-prediction/final_submission.json", "log_dir": "/scratch/harry123/EvolveFold/MLEvolve_BO/runs/aq04-mlebench-lite-20260921/tasks/new-york-city-taxi-fare-prediction/22372433/native/20260921_003302_AQ04_new-york-city-taxi-fare-prediction", "journal_active_seconds": 42163.669632434845, "full_agent_budget_used": false, "outer_search_timeout_reached": true, "official_grade": "/scratch/harry123/EvolveFold/MLEvolve_BO/runs/aq04-mlebench-lite-20260921/tasks/new-york-city-taxi-fare-prediction/22372433/official-grade.json", "finished_at": "2026-09-21T16:32:55.784681+00:00", "elapsed_seconds": 43242.45767917484}}, {"id": "harry123.aq04-20260921.nomad2018-predict-transparent-conductors", "experiment_id": "mlebench-aq04-12h-20260921", "family": "MLEBench", "method": "AQ04", "dataset": "nomad2018-predict-transparent-conductors", "seed": 42, "status": "completed", "source_status": "complete", "wrapper_status": "complete", "source_updated_at": "2026-09-25T06:12:00.018027+00:00", "uploaded_at": "2026-09-25T17:05:51.509723+00:00", "elapsed_seconds": 43207.26385140419, "budget_seconds": 43200, "metrics": [{"event_id": "0d2b692e619c44c79ece5bcf1a739ea9", "node_id": "0d2b692e619c44c79ece5bcf1a739ea9", "transition_id": "1a4557e312944724825c3d5b0dcfe896", "step": 6, "value": 0.059062896055247414, "stage": "debug", "elapsed_seconds": 804.2758479118347}, {"event_id": "1a31cbbfc629447e83c66b717a390fb7", "node_id": "1a31cbbfc629447e83c66b717a390fb7", "transition_id": "9fc8a077986b4130bf9c3b80075e07d3", "step": 7, "value": 0.18472336681913948, "stage": "debug", "elapsed_seconds": 838.5178532600403}, {"event_id": "56445598641c45a88fe6393660a03f43", "node_id": "56445598641c45a88fe6393660a03f43", "transition_id": "19db38cfb718454d93ada0af677b3d78", "step": 10, "value": 0.059062896055247414, "stage": "improve", "elapsed_seconds": 953.8084530830383}, {"event_id": "c572319ef5bb4078a7120e5a0410a206", "node_id": "c572319ef5bb4078a7120e5a0410a206", "transition_id": "14ede72cd221474891c3644ae65e3c94", "step": 11, "value": 0.059062896055247414, "stage": "improve", "elapsed_seconds": 959.3242745399475}, {"event_id": "d443c8da4f0149b6935022ca00112e84", "node_id": "d443c8da4f0149b6935022ca00112e84", "transition_id": "ce92ecd83b444e47b274c91708e96576", "step": 13, "value": 0.059062896055247414, "stage": "debug", "elapsed_seconds": 1208.1480903625488}, {"event_id": "af7e7e13472344e99cfffdd3b693a021", "node_id": "af7e7e13472344e99cfffdd3b693a021", "transition_id": "0d48e5b6f9a74790880967975925948d", "step": 14, "value": 0.059062896055247414, "stage": "improve", "elapsed_seconds": 1249.162994146347}, {"event_id": "55e1697381254c6986da3f3a542e143b", "node_id": "55e1697381254c6986da3f3a542e143b", "transition_id": "3ac58141918e4c4cbb3a6c9fe49478c2", "step": 15, "value": 0.059062896055247414, "stage": "improve", "elapsed_seconds": 1273.7208104133606}, {"event_id": "4cf958c68d604269bf15f9e7cc869f69", "node_id": "4cf958c68d604269bf15f9e7cc869f69", "transition_id": "f343c7c3e1cc477cb1fa3d2e34ea36da", "step": 16, "value": 0.059062896055247414, "stage": "improve", "elapsed_seconds": 1350.2821290493011}, {"event_id": "a348f7104a7c4ff38350378a702cf877", "node_id": "a348f7104a7c4ff38350378a702cf877", "transition_id": "871181fe7f2b4b0ab25dce18c74bfc26", "step": 17, "value": 0.05896306786984114, "stage": "improve", "elapsed_seconds": 1414.267713546753}, {"event_id": "9db2adc9b7b047f7b5a8d1270dcbd095", "node_id": "9db2adc9b7b047f7b5a8d1270dcbd095", "transition_id": "3c5fd79a06af4ac59156aba2f3557a94", "step": 18, "value": 0.05875377801546852, "stage": "improve", "elapsed_seconds": 1417.0907101631165}, {"event_id": "6664ab0b0a6e499a9f7c70d6e7355d2e", "node_id": "6664ab0b0a6e499a9f7c70d6e7355d2e", "transition_id": "d0440701c90140748a89e596862d386f", "step": 19, "value": 0.06070418452091418, "stage": "improve", "elapsed_seconds": 1537.8339567184448}, {"event_id": "6cd95eeca014494b9c316fa38d3339ce", "node_id": "6cd95eeca014494b9c316fa38d3339ce", "transition_id": "191933b870984611b5b5829b3d257ed4", "step": 20, "value": 0.059062896055247414, "stage": "improve", "elapsed_seconds": 1598.8579640388489}, {"event_id": "c5b16d1ad80140969fc74127652b6a5c", "node_id": "c5b16d1ad80140969fc74127652b6a5c", "transition_id": "ef75112962384d3c8d5a36d10936332c", "step": 21, "value": 0.059062896055247414, "stage": "improve", "elapsed_seconds": 1665.4344036579132}, {"event_id": "b3da86009d374b1bb3c7613957be8478", "node_id": "b3da86009d374b1bb3c7613957be8478", "transition_id": "75a0f50715c94bec97ace34eda557abc", "step": 22, "value": 0.06070418452091418, "stage": "improve", "elapsed_seconds": 1686.4044404029846}, {"event_id": "d0da105b83d14f25bd0c1d9783af86ba", "node_id": "d0da105b83d14f25bd0c1d9783af86ba", "transition_id": "afc3b4dda58a46bc8b21323cd3319a39", "step": 23, "value": 0.06070418452091418, "stage": "improve", "elapsed_seconds": 1776.5510921478271}, {"event_id": "749686ced3e148b2a0d20229bba13202", "node_id": "749686ced3e148b2a0d20229bba13202", "transition_id": "d2395ae3a43d474e83d44514a88a2fdc", "step": 24, "value": 0.05973960223257353, "stage": "evolution", "elapsed_seconds": 1782.3302664756775}, {"event_id": "b2da36a2689a4c88b97ae7a56ab14868", "node_id": "b2da36a2689a4c88b97ae7a56ab14868", "transition_id": "6e927993b7b34634bbf08a1ebcbcefa8", "step": 25, "value": 0.06097680166326443, "stage": "evolution", "elapsed_seconds": 1827.6181700229645}, {"event_id": "e6513b89f42d42aeb1bbee5c5799e14b", "node_id": "e6513b89f42d42aeb1bbee5c5799e14b", "transition_id": "636c47866fc74b06ba013a411dcc31d9", "step": 27, "value": 0.058942602759074564, "stage": "evolution", "elapsed_seconds": 1948.955684185028}, {"event_id": "89a2b8f25c7c44d1b1960bcdd102468d", "node_id": "89a2b8f25c7c44d1b1960bcdd102468d", "transition_id": "55a39ee0ae944524b9df934cb2897d5f", "step": 28, "value": 0.05850686390031541, "stage": "evolution", "elapsed_seconds": 1954.2927396297455}, {"event_id": "40bb2300fe254ad0b8ea37d72652840f", "node_id": "40bb2300fe254ad0b8ea37d72652840f", "transition_id": "1cb15747c10c437d92f5a2de3077e04e", "step": 30, "value": 0.06169115919573251, "stage": "evolution", "elapsed_seconds": 2105.3832335472107}, {"event_id": "8cac13bdac724795b9e314a1b0907080", "node_id": "8cac13bdac724795b9e314a1b0907080", "transition_id": "0f4fad73eee344b5b058834029194068", "step": 31, "value": 0.05867616770084251, "stage": "debug", "elapsed_seconds": 2143.578711271286}, {"event_id": "911647042d974c08882f63f330aa2ab2", "node_id": "911647042d974c08882f63f330aa2ab2", "transition_id": "e7cb175ed18b42ca8988a6c4296a6592", "step": 32, "value": 0.05875377801546852, "stage": "improve", "elapsed_seconds": 2179.3688402175903}, {"event_id": "145ac2ee427642f38a0cb90788b64938", "node_id": "145ac2ee427642f38a0cb90788b64938", "transition_id": "16d767e11ec247d0b3b3829c606d4871", "step": 33, "value": 0.05891531486673707, "stage": "improve", "elapsed_seconds": 2312.629141807556}, {"event_id": "be87c945d143483d9fe00c4e8e4b522d", "node_id": "be87c945d143483d9fe00c4e8e4b522d", "transition_id": "456f3ccbf37d4e859cb4df5eae613f94", "step": 34, "value": 0.058909465957727766, "stage": "evolution", "elapsed_seconds": 2372.3105721473694}, {"event_id": "20e78c8abcf843388f4e12d468209b3f", "node_id": "20e78c8abcf843388f4e12d468209b3f", "transition_id": "370f0eeb473e40309257440afbf52659", "step": 35, "value": 0.05867616770084251, "stage": "improve", "elapsed_seconds": 2372.633719444275}, {"event_id": "5b7339b86f9a4a3ca2f796f0ef79f158", "node_id": "5b7339b86f9a4a3ca2f796f0ef79f158", "transition_id": "883ae62a3bf34fc7a22d1a77f99b9e85", "step": 36, "value": 0.05820417648241884, "stage": "evolution", "elapsed_seconds": 2526.5162494182587}, {"event_id": "7ce94610e325478d82d9a442fc86c3ab", "node_id": "7ce94610e325478d82d9a442fc86c3ab", "transition_id": "57dd0ff6688445eaab33bf055479dc36", "step": 37, "value": 0.057998010440341786, "stage": "evolution", "elapsed_seconds": 2528.5693171024323}, {"event_id": "944f080ae0a44c6782df5bacffbb72b8", "node_id": "944f080ae0a44c6782df5bacffbb72b8", "transition_id": "b118270a458a4f3fb44ed8cb8e99a8a2", "step": 38, "value": 0.05949953692466268, "stage": "evolution", "elapsed_seconds": 2553.1149151325226}, {"event_id": "d315a5586308417b9f0e14d5100af6e5", "node_id": "d315a5586308417b9f0e14d5100af6e5", "transition_id": "1075ebb64c8e44c98636fe1c539eafc7", "step": 39, "value": 0.059062637174718664, "stage": "improve", "elapsed_seconds": 2685.620212316513}, {"event_id": "dd136c57eab24e129a50986e6cefee0a", "node_id": "dd136c57eab24e129a50986e6cefee0a", "transition_id": "13dce37639dc4071b8e0b2ee92528915", "step": 40, "value": 0.05850686390031541, "stage": "improve", "elapsed_seconds": 2705.2534744739532}, {"event_id": "b0fc51c7d9484c77820d345e3ec7e6fa", "node_id": "b0fc51c7d9484c77820d345e3ec7e6fa", "transition_id": "6fd87c7c8279433d9589b7f38598b1a7", "step": 41, "value": 0.057998010440341786, "stage": "improve", "elapsed_seconds": 2706.992560863495}, {"event_id": "864d5c3afdd645b09cf5e68568e5fb52", "node_id": "864d5c3afdd645b09cf5e68568e5fb52", "transition_id": "974bbda4605e4dfab24cce666eeb65da", "step": 43, "value": 0.058179562373204326, "stage": "evolution", "elapsed_seconds": 2925.894437789917}, {"event_id": "b5717be23e26413485630e7f1594ae48", "node_id": "b5717be23e26413485630e7f1594ae48", "transition_id": "5a8882e43d264b27930edb7e3a8880e8", "step": 44, "value": 0.057998010440341786, "stage": "improve", "elapsed_seconds": 2938.6012761592865}, {"event_id": "00cbb41fec5a41d8aef67ebaddb4651b", "node_id": "00cbb41fec5a41d8aef67ebaddb4651b", "transition_id": "8f60949c50834739abdd43e8369a7f84", "step": 45, "value": 0.062115658023245576, "stage": "debug", "elapsed_seconds": 2972.2735764980316}, {"event_id": "7b0699ba840c4244bc0f606033223f30", "node_id": "7b0699ba840c4244bc0f606033223f30", "transition_id": "770db0edaaf44ddc9140b717c482e38f", "step": 47, "value": 0.05865630239899651, "stage": "improve", "elapsed_seconds": 3144.043901205063}, {"event_id": "d407be6d59234978876121b9048b2be6", "node_id": "d407be6d59234978876121b9048b2be6", "transition_id": "73b84095d2914d999212f18b1f55ae4a", "step": 48, "value": 0.05850686390031541, "stage": "improve", "elapsed_seconds": 3168.0857644081116}, {"event_id": "76f9f9612c994d5f81f7ef5431220ec4", "node_id": "76f9f9612c994d5f81f7ef5431220ec4", "transition_id": "cf58d53c3dda401d8976bea07d6520dd", "step": 49, "value": 0.0584182494698013, "stage": "debug", "elapsed_seconds": 3275.471893310547}, {"event_id": "b30f26af6d8640cca0e468d9be2ae8ef", "node_id": "b30f26af6d8640cca0e468d9be2ae8ef", "transition_id": "ec3e4945681a449988e9c1f5c5197564", "step": 50, "value": 0.06010675302389764, "stage": "evolution", "elapsed_seconds": 3319.9120931625366}, {"event_id": "2a93c7fe883c4d75a2c20b4445b1b20c", "node_id": "2a93c7fe883c4d75a2c20b4445b1b20c", "transition_id": "83dfc8ffc03d44efb0c5381e4ee3c4c8", "step": 51, "value": 0.05788904056234061, "stage": "improve", "elapsed_seconds": 3405.0638830661774}, {"event_id": "8a146fe1433f45ac9c8fc8ce21422915", "node_id": "8a146fe1433f45ac9c8fc8ce21422915", "transition_id": "300f5237236f4722966f73764827588c", "step": 52, "value": 0.058561315250873415, "stage": "evolution", "elapsed_seconds": 3469.1471400260925}, {"event_id": "83e15b985b0248eb8f73c9b1d3cdcfda", "node_id": "83e15b985b0248eb8f73c9b1d3cdcfda", "transition_id": "65cbcd08b3a4409dae1c6455a9cd89ad", "step": 53, "value": 0.059671155689473065, "stage": "evolution", "elapsed_seconds": 3511.5345072746277}, {"event_id": "3b9660b80b4e44d6b6759c858fbadc37", "node_id": "3b9660b80b4e44d6b6759c858fbadc37", "transition_id": "4f5d24e2afcf4581acb6e2005a5eea62", "step": 54, "value": 0.057998010440341786, "stage": "improve", "elapsed_seconds": 3644.3415429592133}, {"event_id": "a49b4629dba24107a464b4acc4710fb1", "node_id": "a49b4629dba24107a464b4acc4710fb1", "transition_id": "63a87afe7ae44e1abff6fb761995bb0d", "step": 56, "value": 0.05813887748931437, "stage": "debug", "elapsed_seconds": 3774.683509349823}, {"event_id": "00a6228e493d44029cb166f8a3b0aaf8", "node_id": "00a6228e493d44029cb166f8a3b0aaf8", "transition_id": "7ba8e11511784797a2c2c4e3e72c1281", "step": 57, "value": 0.058529432601570584, "stage": "evolution", "elapsed_seconds": 3778.2567014694214}, {"event_id": "c730dee533164e9cb546fdcf159ba20f", "node_id": "c730dee533164e9cb546fdcf159ba20f", "transition_id": "948e9f3891d644eeb5562740b7c5f89c", "step": 58, "value": 0.060574270052154724, "stage": "improve", "elapsed_seconds": 3852.5919501781464}, {"event_id": "6793284ee0f54dd4b6035944b4ab530c", "node_id": "6793284ee0f54dd4b6035944b4ab530c", "transition_id": "60cfe8abca294dda9db14144ba8b15e4", "step": 59, "value": 0.05872346525298161, "stage": "evolution", "elapsed_seconds": 3993.9441273212433}, {"event_id": "4976663388214c1ab5328cb23b765c39", "node_id": "4976663388214c1ab5328cb23b765c39", "transition_id": "4b4c0ee2dddb4e6ab652dac895fd84f7", "step": 60, "value": 0.05756151006278091, "stage": "evolution", "elapsed_seconds": 4045.280958175659}, {"event_id": "2d756d472ef54d7aad7b541abcafeb54", "node_id": "2d756d472ef54d7aad7b541abcafeb54", "transition_id": "bb699b6f39824d06bc49e19978a83ffe", "step": 61, "value": 0.06562118304417859, "stage": "evolution", "elapsed_seconds": 4048.942635536194}, {"event_id": "12466e07da2446e190feaa5af5af05a2", "node_id": "12466e07da2446e190feaa5af5af05a2", "transition_id": "240d73b5936d4e0faaa0ff45c43b2fb1", "step": 62, "value": 0.058909465957727766, "stage": "improve", "elapsed_seconds": 4207.942778587341}, {"event_id": "9a54287b24f3416dbcbfa8ad8dfe21d5", "node_id": "9a54287b24f3416dbcbfa8ad8dfe21d5", "transition_id": "13fb0f02e51b4cdea98bddf52661603f", "step": 63, "value": 0.05858814793361794, "stage": "evolution", "elapsed_seconds": 4210.051030158997}, {"event_id": "20a441b16cd548cbb2cabf7e26b5e3f7", "node_id": "20a441b16cd548cbb2cabf7e26b5e3f7", "transition_id": "2df722332d414469ae157db4a921cbd2", "step": 64, "value": 0.058179562373204326, "stage": "improve", "elapsed_seconds": 4280.655403375626}, {"event_id": "f066ead745a34fb9b1a1dcc98d199ce1", "node_id": "f066ead745a34fb9b1a1dcc98d199ce1", "transition_id": "021bbba864814566a8185fea4ff93300", "step": 65, "value": 0.05926467695510455, "stage": "evolution", "elapsed_seconds": 4395.133469104767}, {"event_id": "5b98c1918d4349408d53c28a0f586e37", "node_id": "5b98c1918d4349408d53c28a0f586e37", "transition_id": "47160987b04c46b8a9c6fa55c8723a7e", "step": 66, "value": 0.058700832182998694, "stage": "evolution", "elapsed_seconds": 4477.614907979965}, {"event_id": "dbb301f5cf044649adea4af5cb2f1c05", "node_id": "dbb301f5cf044649adea4af5cb2f1c05", "transition_id": "33cbb23ea7ab407693e0e321f65a3b7f", "step": 67, "value": 0.0588821578350763, "stage": "evolution", "elapsed_seconds": 4635.258791685104}, {"event_id": "e1f45bbb56f94221937566cbe80b06ce", "node_id": "e1f45bbb56f94221937566cbe80b06ce", "transition_id": "391a9c005fb341fb9e1d593b610379ba", "step": 69, "value": 0.05853853630576848, "stage": "debug", "elapsed_seconds": 4744.4389979839325}, {"event_id": "20db18ac43a241829f907272ff057bb3", "node_id": "20db18ac43a241829f907272ff057bb3", "transition_id": "ffee7b21d3ae40fca47157df170c46cd", "step": 70, "value": 0.05839698162183564, "stage": "evolution", "elapsed_seconds": 4756.934463024139}, {"event_id": "5b0aec7cc6134531b4a1edda95a5e853", "node_id": "5b0aec7cc6134531b4a1edda95a5e853", "transition_id": "c01f4fe6ca6c4ec19e20c26c7373d509", "step": 71, "value": 0.05980076698002061, "stage": "evolution", "elapsed_seconds": 4832.148787736893}, {"event_id": "27dc88f1ba1b4e5786bd30d489605164", "node_id": "27dc88f1ba1b4e5786bd30d489605164", "transition_id": "6c0424f5e09a497e8c706fca4bc9fc01", "step": 72, "value": 0.05854794384491964, "stage": "evolution", "elapsed_seconds": 4951.146710157394}, {"event_id": "b0799879337d4abd9343b78c0e9328b2", "node_id": "b0799879337d4abd9343b78c0e9328b2", "transition_id": "4502aff4a6144dafb52fa45c8869bf4a", "step": 73, "value": 0.0590076105602934, "stage": "evolution", "elapsed_seconds": 5050.262581110001}, {"event_id": "ef0ba5d7c7fc41cbaa948ab5a41bd207", "node_id": "ef0ba5d7c7fc41cbaa948ab5a41bd207", "transition_id": "a2cd695fd5884b00814b1aee9bf88609", "step": 74, "value": 0.0594995008825327, "stage": "evolution", "elapsed_seconds": 5054.05938911438}, {"event_id": "4571186e8616415485bad7dc723d6b47", "node_id": "4571186e8616415485bad7dc723d6b47", "transition_id": "ed0b929c69524cbe8a8b5024433eb825", "step": 75, "value": 0.058710621931525736, "stage": "evolution", "elapsed_seconds": 5085.149014234543}, {"event_id": "086dbcc226524b17a1db0c83f81a64d2", "node_id": "086dbcc226524b17a1db0c83f81a64d2", "transition_id": "a6aac047808b487489f657f29b5d60e9", "step": 76, "value": 0.05890673824426777, "stage": "evolution", "elapsed_seconds": 5291.2348392009735}, {"event_id": "fb75211f6ae64d2493d48aee307c2cea", "node_id": "fb75211f6ae64d2493d48aee307c2cea", "transition_id": "fb13365d341f4555921d9993e37d36c4", "step": 77, "value": 0.05932456977999712, "stage": "evolution", "elapsed_seconds": 5298.700202226639}, {"event_id": "f018e315be7e4670af36df412b83dec0", "node_id": "f018e315be7e4670af36df412b83dec0", "transition_id": "ec3675f875954cd5a0813849783a29a9", "step": 78, "value": 0.05816711069116126, "stage": "evolution", "elapsed_seconds": 5339.919898509979}, {"event_id": "7959d153a48e407d92f9855ffa871f30", "node_id": "7959d153a48e407d92f9855ffa871f30", "transition_id": "fd61234ff71c4048b15e4f9ed7227f8d", "step": 79, "value": 0.05914791642060301, "stage": "evolution", "elapsed_seconds": 5493.730443477631}, {"event_id": "5a519c444f8e40ceb842ab65aeb3d24c", "node_id": "5a519c444f8e40ceb842ab65aeb3d24c", "transition_id": "b782aac2ea624851be7050ff6d815047", "step": 80, "value": 0.061203059334597375, "stage": "evolution", "elapsed_seconds": 5534.310822725296}, {"event_id": "649789f543ab466681623fee69044284", "node_id": "649789f543ab466681623fee69044284", "transition_id": "4d21cda1b5b3485d929c631937d518f6", "step": 83, "value": 0.057396733649789616, "stage": "debug", "elapsed_seconds": 5878.437828779221}, {"event_id": "46959002106b45b3a260cd55c6a68428", "node_id": "46959002106b45b3a260cd55c6a68428", "transition_id": "e227e1687e5e49af8f64196c7be3c600", "step": 84, "value": 0.05820475983173086, "stage": "debug", "elapsed_seconds": 5973.82116985321}, {"event_id": "06f583c208ec4e18aa91aea70ce9f2ba", "node_id": "06f583c208ec4e18aa91aea70ce9f2ba", "transition_id": "96bf44e312dc40029adafc032d55a9d5", "step": 85, "value": 0.053194290192539226, "stage": "improve", "elapsed_seconds": 6152.542186975479}, {"event_id": "66d4d099512b4932a9a118c15891711f", "node_id": "66d4d099512b4932a9a118c15891711f", "transition_id": "7d04bc1cdf484d9396b8db7ff4603073", "step": 86, "value": 0.05841876472228416, "stage": "improve", "elapsed_seconds": 6198.805866479874}, {"event_id": "891ea125f5ab4d0095a8fd14daf1d037", "node_id": "891ea125f5ab4d0095a8fd14daf1d037", "transition_id": "a96e6dee21f64fc0ac67efdde2da0423", "step": 87, "value": 0.053194290192539226, "stage": "improve", "elapsed_seconds": 6365.777250528336}, {"event_id": "5802457487184c24b55c93fd4dcbe45a", "node_id": "5802457487184c24b55c93fd4dcbe45a", "transition_id": "c8bdc606c1c34109b962d517bcf27295", "step": 88, "value": 0.05315121051376638, "stage": "improve", "elapsed_seconds": 6558.189961433411}, {"event_id": "8bdcaccbb1a3469abcf18530825bc8a9", "node_id": "8bdcaccbb1a3469abcf18530825bc8a9", "transition_id": "859d783ca4de4032abfe17240f14e4d4", "step": 89, "value": 0.05820475983173086, "stage": "improve", "elapsed_seconds": 6572.573055267334}, {"event_id": "71c8f7e7c2524fd1a8922dad48bae5bf", "node_id": "71c8f7e7c2524fd1a8922dad48bae5bf", "transition_id": "7c81bcef4e8748bfbd48902a682e70ad", "step": 90, "value": 0.05315121051376638, "stage": "improve", "elapsed_seconds": 6818.979568243027}, {"event_id": "b8e395d71dc9450981612bca7e8215e1", "node_id": "b8e395d71dc9450981612bca7e8215e1", "transition_id": "322912536124400e80a374356d998383", "step": 91, "value": 0.053194290192539226, "stage": "improve", "elapsed_seconds": 6832.071240663528}, {"event_id": "0d666250e8fd4da9955cc46935d2b3da", "node_id": "0d666250e8fd4da9955cc46935d2b3da", "transition_id": "ccbf73b0de4f41e3b09dfb2b0c15a254", "step": 92, "value": 0.053124508416508134, "stage": "improve", "elapsed_seconds": 7105.286625146866}, {"event_id": "5d6e436c73da42eaa0c597d8abc8ea58", "node_id": "5d6e436c73da42eaa0c597d8abc8ea58", "transition_id": "638feb5493074069919f618e0530d794", "step": 93, "value": 0.052867522491494005, "stage": "improve", "elapsed_seconds": 7111.106235027313}, {"event_id": "0a33ce939c2c4596bf987873f70fb6cc", "node_id": "0a33ce939c2c4596bf987873f70fb6cc", "transition_id": "eb4bd2e6cd354b8e91f6ac48c5a30cf9", "step": 94, "value": 0.05315121051376638, "stage": "improve", "elapsed_seconds": 7309.6597855091095}, {"event_id": "0261f34a399042d99218fe0d59458390", "node_id": "0261f34a399042d99218fe0d59458390", "transition_id": "867d5fe4d15740b6b7b829fd727dd241", "step": 95, "value": 0.05315121051376638, "stage": "improve", "elapsed_seconds": 7322.426417589188}, {"event_id": "d84732d87f4342f497ac31a877cee230", "node_id": "d84732d87f4342f497ac31a877cee230", "transition_id": "abdcdac06fa04215b4bc3e0e05a0fec6", "step": 96, "value": 0.053271688843901904, "stage": "improve", "elapsed_seconds": 7483.296676397324}, {"event_id": "f326e1acccf549859800cabb416bb712", "node_id": "f326e1acccf549859800cabb416bb712", "transition_id": "35497a010df5496e9e926c43d7006c67", "step": 97, "value": 0.05362599583205785, "stage": "evolution", "elapsed_seconds": 7637.387590408325}, {"event_id": "0c63d94a71c04e2881a2b62ced5f32c0", "node_id": "0c63d94a71c04e2881a2b62ced5f32c0", "transition_id": "9f01a9068c9045eba57cceb8d1da171a", "step": 98, "value": 0.052867522491494005, "stage": "improve", "elapsed_seconds": 7678.227438926697}, {"event_id": "e51fcfd9c25145319025de13f32d3df6", "node_id": "e51fcfd9c25145319025de13f32d3df6", "transition_id": "83daf19e9a8b4b0c8794d11c93cc43fb", "step": 99, "value": 0.053425148523894316, "stage": "improve", "elapsed_seconds": 7896.78968501091}, {"event_id": "0b83234766474076be9c5c891eda2a6c", "node_id": "0b83234766474076be9c5c891eda2a6c", "transition_id": "f18014cd31614a27bcfa1f8fbe1dbb5b", "step": 100, "value": 0.05324222193939266, "stage": "evolution", "elapsed_seconds": 7914.190088033676}, {"event_id": "c7bc6ddc79c34c1aa6e481e21186e5a2", "node_id": "c7bc6ddc79c34c1aa6e481e21186e5a2", "transition_id": "e7dee25f21b042a1ad220a0f1332b2cc", "step": 101, "value": 0.052867522491494005, "stage": "improve", "elapsed_seconds": 8135.490691423416}, {"event_id": "d4c52884d54e48509ddea278782ee985", "node_id": "d4c52884d54e48509ddea278782ee985", "transition_id": "f2ebb1d039d741e397efbdf3f52bfa65", "step": 102, "value": 0.05805016402373211, "stage": "improve", "elapsed_seconds": 8210.069627523422}, {"event_id": "5d416ca9cbc248f69a2c3006a3668cac", "node_id": "5d416ca9cbc248f69a2c3006a3668cac", "transition_id": "e8ffc77a2ee54065a6d3773b06ebcbd4", "step": 103, "value": 0.05293591400763193, "stage": "improve", "elapsed_seconds": 8376.357012271881}, {"event_id": "8150c9efc4414ae391f931112ea96850", "node_id": "8150c9efc4414ae391f931112ea96850", "transition_id": "4cb62d6276d24e9592067be54760a2d4", "step": 104, "value": 0.05362599583205785, "stage": "improve", "elapsed_seconds": 8415.177331447601}, {"event_id": "05eb56ebe30b408e86b5448a1de2a026", "node_id": "05eb56ebe30b408e86b5448a1de2a026", "transition_id": "42adbc94d4cc43faac1ee5b0d211c91d", "step": 105, "value": 0.05362599583205785, "stage": "improve", "elapsed_seconds": 8580.50103712082}, {"event_id": "6d301540b249491386e2ad977d4f8410", "node_id": "6d301540b249491386e2ad977d4f8410", "transition_id": "7c6c21ce1ab940febe652d7f15261572", "step": 106, "value": 0.054021096106826066, "stage": "evolution", "elapsed_seconds": 8584.593918800354}, {"event_id": "092ce5e180554e839edffba9dc036c0e", "node_id": "092ce5e180554e839edffba9dc036c0e", "transition_id": "c3f871c6283846e496fab92a56e3e866", "step": 107, "value": 0.05354946767207068, "stage": "evolution", "elapsed_seconds": 8793.551929712296}, {"event_id": "46adc01603044b97bdaced02ccd985db", "node_id": "46adc01603044b97bdaced02ccd985db", "transition_id": "f85a3bab46d04e54a18de867a4bbd5a2", "step": 108, "value": 0.05467009822415447, "stage": "evolution", "elapsed_seconds": 9020.068097829819}, {"event_id": "b940d0104b944237bef021a548604842", "node_id": "b940d0104b944237bef021a548604842", "transition_id": "7ab43b9e399340dc84c8e0735ebb9c7a", "step": 109, "value": 0.05310714375787329, "stage": "evolution", "elapsed_seconds": 9097.591964960098}, {"event_id": "59ec4ca8ddfb44648e28be0b5abc6aee", "node_id": "59ec4ca8ddfb44648e28be0b5abc6aee", "transition_id": "d74e7d05018e4bb09271aeffb4c3a531", "step": 110, "value": 0.053297999315886725, "stage": "evolution", "elapsed_seconds": 9248.012118339539}, {"event_id": "115c625c11f844d2b44161a773a2bdd4", "node_id": "115c625c11f844d2b44161a773a2bdd4", "transition_id": "ecedc6e2c5014720afd4d868df395f2a", "step": 111, "value": 0.059130577272991036, "stage": "evolution", "elapsed_seconds": 9346.260673046112}, {"event_id": "f593fde2947c4fcf870a6c6cb4b705c8", "node_id": "f593fde2947c4fcf870a6c6cb4b705c8", "transition_id": "e43855053fed4b389b8f79f5abe7f137", "step": 112, "value": 0.053096283074787934, "stage": "evolution", "elapsed_seconds": 9465.284211874008}, {"event_id": "22245a817c0343d8833f1a91bb24be49", "node_id": "22245a817c0343d8833f1a91bb24be49", "transition_id": "c776435685b5484bab423f89c18e4e58", "step": 114, "value": 0.053015282823624985, "stage": "evolution", "elapsed_seconds": 9728.90609717369}, {"event_id": "b949d97604b344d88649043a463f1c76", "node_id": "b949d97604b344d88649043a463f1c76", "transition_id": "6c3f6f1bdc3548f8b8f9181e77f69a97", "step": 115, "value": 0.05307483628401212, "stage": "debug", "elapsed_seconds": 9787.382037878036}, {"event_id": "a155325086e34330bb842ee5d9905711", "node_id": "a155325086e34330bb842ee5d9905711", "transition_id": "bd97597ac4ce4c7d842e45bbd27b96ae", "step": 117, "value": 0.052865353619621455, "stage": "debug", "elapsed_seconds": 10047.20513010025}, {"event_id": "dcd4b8c72fca4656b8f5c272fbc52dcd", "node_id": "dcd4b8c72fca4656b8f5c272fbc52dcd", "transition_id": "f2e061caf1c7477798a1f8003077a450", "step": 119, "value": 0.05836019850975778, "stage": "debug", "elapsed_seconds": 10190.019339561462}, {"event_id": "6140fddebab449ec806027c1d80454d2", "node_id": "6140fddebab449ec806027c1d80454d2", "transition_id": "ea5e8bc10c1b427da0f0459dd181102e", "step": 120, "value": 0.05362599583205785, "stage": "improve", "elapsed_seconds": 10265.688932180405}, {"event_id": "22e4315819d841f19d7b962ab8601b04", "node_id": "22e4315819d841f19d7b962ab8601b04", "transition_id": "9bf05e6b5d6043a9beda1ae3c391b05f", "step": 122, "value": 0.052863627534066565, "stage": "improve", "elapsed_seconds": 10536.315770149231}, {"event_id": "f98a2b6892c54c59ba335c3607c7f1ca", "node_id": "f98a2b6892c54c59ba335c3607c7f1ca", "transition_id": "b59c182a613b4b4fb7289ef4afd50909", "step": 123, "value": 0.05822283268070956, "stage": "debug", "elapsed_seconds": 10539.904000997543}, {"event_id": "325c227f28c44f23b886cb2836bf9762", "node_id": "325c227f28c44f23b886cb2836bf9762", "transition_id": "28d3c03d91e14c61b250bf0c89b1ce66", "step": 124, "value": 0.05819698132156684, "stage": "improve", "elapsed_seconds": 10756.250514268875}, {"event_id": "626063d5df58482782849a98417000dc", "node_id": "626063d5df58482782849a98417000dc", "transition_id": "09b3faf6bcb54377b6d531a02ad95e30", "step": 125, "value": 0.05354946767207068, "stage": "improve", "elapsed_seconds": 10821.99234867096}, {"event_id": "16b0555906724de0a4ad688316aaf615", "node_id": "16b0555906724de0a4ad688316aaf615", "transition_id": "fab9e9065fe74980946133d5ce5c4e5d", "step": 126, "value": 0.058664415982745216, "stage": "evolution", "elapsed_seconds": 11024.767662763596}, {"event_id": "e2a53e27167b4237967ba4ec9a290644", "node_id": "e2a53e27167b4237967ba4ec9a290644", "transition_id": "ba17edcee64c468bb3be21cc84f87cf6", "step": 127, "value": 0.052863627534066565, "stage": "improve", "elapsed_seconds": 11100.983324766159}, {"event_id": "f0ea3cc4c48d4a1cb9216e7696241605", "node_id": "f0ea3cc4c48d4a1cb9216e7696241605", "transition_id": "8e0ef81023f7448da3afb41c52971cd9", "step": 128, "value": 0.05320461357412966, "stage": "evolution", "elapsed_seconds": 11277.355247974396}, {"event_id": "3540f2b5fce84cc3bf808a731603bbef", "node_id": "3540f2b5fce84cc3bf808a731603bbef", "transition_id": "986fb9ad410e4421a313e49177e2f45c", "step": 129, "value": 0.05823163927444486, "stage": "improve", "elapsed_seconds": 11384.766350507736}, {"event_id": "62936d0e834a4de8bb6047ead9922c77", "node_id": "62936d0e834a4de8bb6047ead9922c77", "transition_id": "80fb2949a765498cbe86363c55a76a97", "step": 130, "value": 0.053397888081329975, "stage": "improve", "elapsed_seconds": 11522.31139421463}, {"event_id": "80d62e6d45de433a80546aaba73bfe96", "node_id": "80d62e6d45de433a80546aaba73bfe96", "transition_id": "d823e7bcced44c3891259955b54799a4", "step": 131, "value": 0.05307483628401212, "stage": "improve", "elapsed_seconds": 11669.123916387558}, {"event_id": "0e670124dae548fda05a138fde7dc687", "node_id": "0e670124dae548fda05a138fde7dc687", "transition_id": "bba9712d6e314261870ca9f8ef9a5053", "step": 132, "value": 0.053281723779827386, "stage": "evolution", "elapsed_seconds": 11786.108758687973}, {"event_id": "61d278b8c72442a88aa548296d2a8763", "node_id": "61d278b8c72442a88aa548296d2a8763", "transition_id": "572e54a3a5414a1ba3c452c5ccf03bfe", "step": 134, "value": 0.05307483628401212, "stage": "evolution", "elapsed_seconds": 12105.89666724205}, {"event_id": "3ff47801ec9c4d4c87e38fa8755fdc0c", "node_id": "3ff47801ec9c4d4c87e38fa8755fdc0c", "transition_id": "b1fd62f364c24ffa9a9dd433414aef1d", "step": 135, "value": 0.05939177187529865, "stage": "debug", "elapsed_seconds": 12220.894756793976}, {"event_id": "4160d100f7f346679b9037a804dcda4d", "node_id": "4160d100f7f346679b9037a804dcda4d", "transition_id": "bfae802e57ab4c2c8488822b469b499b", "step": 136, "value": 0.055700293043729074, "stage": "evolution", "elapsed_seconds": 12453.838712215424}, {"event_id": "7fd05719413d4e4d9a822375cfe6bed2", "node_id": "7fd05719413d4e4d9a822375cfe6bed2", "transition_id": "fa502e19358d4425a0dac10997fc5d03", "step": 137, "value": 0.05326416339338148, "stage": "evolution", "elapsed_seconds": 12666.01813673973}, {"event_id": "2578ed5e1f6146fba9ce366038a7443f", "node_id": "2578ed5e1f6146fba9ce366038a7443f", "transition_id": "accbda8d8da5447a8a5f0e4d183a6b5a", "step": 138, "value": 0.05330629674141642, "stage": "evolution", "elapsed_seconds": 12787.049718379974}, {"event_id": "3a8573277ccc498ea743fda2beabac61", "node_id": "3a8573277ccc498ea743fda2beabac61", "transition_id": "f4dc3953275c4036bc658a5f66c1fc1b", "step": 139, "value": 0.05384672587984431, "stage": "evolution", "elapsed_seconds": 12867.093112707138}, {"event_id": "20e263d2dd2f4a51871cf61f0d660697", "node_id": "20e263d2dd2f4a51871cf61f0d660697", "transition_id": "e94b8529b6ad487d874625c6e16f7295", "step": 140, "value": 0.0525095375262992, "stage": "evolution", "elapsed_seconds": 13058.609502315521}, {"event_id": "fe422b4f3ad34224a9f6f07cf9e6ee87", "node_id": "fe422b4f3ad34224a9f6f07cf9e6ee87", "transition_id": "e1a9a6db010d4fa883040794237f3643", "step": 141, "value": 0.05247725413679258, "stage": "evolution", "elapsed_seconds": 13122.08707165718}, {"event_id": "5d87e3e1466841a386a2885dc0adba25", "node_id": "5d87e3e1466841a386a2885dc0adba25", "transition_id": "6f72cf458671490a9718032b629d5fac", "step": 142, "value": 0.05328675238812111, "stage": "improve", "elapsed_seconds": 13341.973846673965}, {"event_id": "b3915b3715cc4aea9a048b4702d96545", "node_id": "b3915b3715cc4aea9a048b4702d96545", "transition_id": "d61379ab0cfa4e8792d32a0ba94fa01c", "step": 143, "value": 0.0525095375262992, "stage": "improve", "elapsed_seconds": 13443.814836025238}, {"event_id": "24d0601a2b764c11ada648ba8dd9b71a", "node_id": "24d0601a2b764c11ada648ba8dd9b71a", "transition_id": "0a6a5b43aa4845de8eb76aa13b01948d", "step": 144, "value": 0.05299820648501581, "stage": "improve", "elapsed_seconds": 13574.934746265411}, {"event_id": "4735d6bbcf994255b1b9b419319655de", "node_id": "4735d6bbcf994255b1b9b419319655de", "transition_id": "614a14c211cf4a2594f2e90f8c2fa89a", "step": 145, "value": 0.05843884348937915, "stage": "improve", "elapsed_seconds": 13720.531985759735}, {"event_id": "5ef2e301eeb145a5a83d9efa8bac3729", "node_id": "5ef2e301eeb145a5a83d9efa8bac3729", "transition_id": "afa0c4d27c1c4609a092efd90a1533f4", "step": 146, "value": 0.05245972839656782, "stage": "evolution", "elapsed_seconds": 13840.16809630394}, {"event_id": "78f937e73a7248028518410cbaf635bb", "node_id": "78f937e73a7248028518410cbaf635bb", "transition_id": "04504ac914e846599284e720caeecff8", "step": 147, "value": 0.05285356882568884, "stage": "evolution", "elapsed_seconds": 14029.996827840805}, {"event_id": "ee96ccd1ae8a412886e96502c70b4258", "node_id": "ee96ccd1ae8a412886e96502c70b4258", "transition_id": "6c0205486e2849c9af910b63a1c6fb37", "step": 148, "value": 0.05317503051356061, "stage": "improve", "elapsed_seconds": 14085.296924591064}, {"event_id": "e0b0227ffaa241b0ac204d357b410fe5", "node_id": "e0b0227ffaa241b0ac204d357b410fe5", "transition_id": "3eb2ef4811c540209b8f0df47ca28b96", "step": 149, "value": 0.052900641014592326, "stage": "improve", "elapsed_seconds": 14242.640567779541}, {"event_id": "583a1ae7139547caa61681735dba019b", "node_id": "583a1ae7139547caa61681735dba019b", "transition_id": "d6c44dafa987467bb8984370ea115641", "step": 151, "value": 0.05882103537092154, "stage": "debug", "elapsed_seconds": 14509.45580458641}, {"event_id": "0066966f922b40c196e6ac46bb19dc18", "node_id": "0066966f922b40c196e6ac46bb19dc18", "transition_id": "13ee4ea782e7452c93821943ae9f732e", "step": 153, "value": 0.05326062742576185, "stage": "evolution", "elapsed_seconds": 14704.761275291443}, {"event_id": "0a2cfb9481a44f40b37ec7748460461e", "node_id": "0a2cfb9481a44f40b37ec7748460461e", "transition_id": "3b4d12978c2c4d7ab8311abae284e7b1", "step": 154, "value": 0.054614530844427016, "stage": "debug", "elapsed_seconds": 14753.508951187134}, {"event_id": "42035597a4dc4f8b8fbeb76e08f29346", "node_id": "42035597a4dc4f8b8fbeb76e08f29346", "transition_id": "1131ed8380cf4e3dbef91b295cec263f", "step": 156, "value": 0.053281723779827386, "stage": "evolution", "elapsed_seconds": 14950.497596263885}, {"event_id": "93aabb410cf74266a841273026687b27", "node_id": "93aabb410cf74266a841273026687b27", "transition_id": "d54fd550f70143a482f4d36d0c5f3a26", "step": 157, "value": 0.054192496531943454, "stage": "debug", "elapsed_seconds": 15051.376297950745}, {"event_id": "8d0e87a9ee4e4d6888b2fc51d0349366", "node_id": "8d0e87a9ee4e4d6888b2fc51d0349366", "transition_id": "1d004c0562584591aa966fef769a8d22", "step": 158, "value": 0.05298245933743616, "stage": "evolution", "elapsed_seconds": 15149.691519021988}, {"event_id": "8ba714adf0d74a969c620f7853e47207", "node_id": "8ba714adf0d74a969c620f7853e47207", "transition_id": "c6c1ba850e224869b5010f59824e633f", "step": 159, "value": 0.05335861654247301, "stage": "evolution", "elapsed_seconds": 15226.346016168594}, {"event_id": "4d8a4e3f39fd4e6fa0169931880abcaa", "node_id": "4d8a4e3f39fd4e6fa0169931880abcaa", "transition_id": "f8648e39036347dba782ff5ad34dab62", "step": 162, "value": 0.059124103042751265, "stage": "evolution", "elapsed_seconds": 37126.112557411194}, {"event_id": "bc933d9bf60742c7998c2b82967e5dc4", "node_id": "bc933d9bf60742c7998c2b82967e5dc4", "transition_id": "2deeba181b23489b814a08fa8f1d8f2b", "step": 163, "value": 0.05339148336390545, "stage": "evolution", "elapsed_seconds": 37143.10801458359}, {"event_id": "70bbd088a98a4c38af8fff618f439bb2", "node_id": "70bbd088a98a4c38af8fff618f439bb2", "transition_id": "ff843df2a5fd420ba53c380352887fa9", "step": 164, "value": 0.05246084271996549, "stage": "fusion", "elapsed_seconds": 37303.03513646126}, {"event_id": "5ceeee4560584ca2bd1e93d0ca08412b", "node_id": "5ceeee4560584ca2bd1e93d0ca08412b", "transition_id": "197c6dcf1cad4ca1a3a097ee89135e89", "step": 165, "value": 0.053177563979427765, "stage": "evolution", "elapsed_seconds": 37337.56690239906}, {"event_id": "ff661eed20ed4d7da25eb49526a6def3", "node_id": "ff661eed20ed4d7da25eb49526a6def3", "transition_id": "06c5366664f742eca0ec9454f29ec689", "step": 166, "value": 0.05310622281946739, "stage": "evolution", "elapsed_seconds": 37512.167862415314}, {"event_id": "89f0e9aa4ee24338b9e2f8769f651a29", "node_id": "89f0e9aa4ee24338b9e2f8769f651a29", "transition_id": "256be355955b4a1ea87201c749ea7f69", "step": 167, "value": 0.053779865359494125, "stage": "evolution", "elapsed_seconds": 37521.811868190765}, {"event_id": "0d047608b74f4962bec0da55b7509dca", "node_id": "0d047608b74f4962bec0da55b7509dca", "transition_id": "2177c6af41b048238a077854b91e01ef", "step": 168, "value": 0.05418115877390306, "stage": "evolution", "elapsed_seconds": 37692.30262255669}, {"event_id": "e18f48cbf9df417ea61f01a415bebb94", "node_id": "e18f48cbf9df417ea61f01a415bebb94", "transition_id": "d99d19106f454691984fdd7dd554c4cd", "step": 169, "value": 0.05249611543330921, "stage": "evolution", "elapsed_seconds": 37814.53197789192}, {"event_id": "1c5c195e02af4fc1b0a457edd6c52612", "node_id": "1c5c195e02af4fc1b0a457edd6c52612", "transition_id": "f6b86ee91a164ab58ad1953165ba6a59", "step": 170, "value": 0.057354892065879175, "stage": "evolution", "elapsed_seconds": 37877.901821136475}, {"event_id": "9f802375acb74ff39cd7723ef000ea21", "node_id": "9f802375acb74ff39cd7723ef000ea21", "transition_id": "8162f6e13f6044cebc3b77fd8a3b27a8", "step": 171, "value": 0.05366368473758606, "stage": "evolution", "elapsed_seconds": 37922.82579112053}, {"event_id": "d13e7cf4aac742e7860b1b168c37b22b", "node_id": "d13e7cf4aac742e7860b1b168c37b22b", "transition_id": "d29bd7e6b1724eb9bd7f3e412a81d511", "step": 172, "value": 0.05871185253332982, "stage": "evolution", "elapsed_seconds": 38150.941886901855}, {"event_id": "8e87854ec76f472faf7398026f23c37e", "node_id": "8e87854ec76f472faf7398026f23c37e", "transition_id": "b54af26b06f14acb863fa380db7047bf", "step": 173, "value": 0.05924424602367198, "stage": "evolution", "elapsed_seconds": 38151.04359483719}, {"event_id": "84e8de87dace4cd7a549549a702b0c37", "node_id": "84e8de87dace4cd7a549549a702b0c37", "transition_id": "611ae5bc15fa467087a687d4bbb9e706", "step": 174, "value": 0.05333340578000466, "stage": "evolution", "elapsed_seconds": 38398.57768559456}, {"event_id": "04805787693d4948ac09a4aa23052da3", "node_id": "04805787693d4948ac09a4aa23052da3", "transition_id": "c1a5d1e36b664555a1e680a897acf572", "step": 175, "value": 0.05268474520299466, "stage": "evolution", "elapsed_seconds": 38517.3936817646}, {"event_id": "c403bb9afbf446dfaae25ea93e2bf4ae", "node_id": "c403bb9afbf446dfaae25ea93e2bf4ae", "transition_id": "bfb479bbc3bd4965a2f5f2d582fd6b24", "step": 176, "value": 0.05249396624764119, "stage": "evolution", "elapsed_seconds": 38543.67910194397}, {"event_id": "1de401f85d4c48db9b1b0f541daae095", "node_id": "1de401f85d4c48db9b1b0f541daae095", "transition_id": "c76bd82a869b48d4bb993d5bb2f2fc3f", "step": 177, "value": 0.05299040285410617, "stage": "fusion", "elapsed_seconds": 38590.13187646866}, {"event_id": "8d63d8396be74d2892d71d2fee96fc4c", "node_id": "8d63d8396be74d2892d71d2fee96fc4c", "transition_id": "96cff09c8bf4496cb0cbfe6c84fbd6a2", "step": 178, "value": 0.05309161131758093, "stage": "fusion", "elapsed_seconds": 38701.83340835571}, {"event_id": "16a74f6b52ec4797bf838a319f02c42d", "node_id": "16a74f6b52ec4797bf838a319f02c42d", "transition_id": "61b276f64d4c4f5a81267548fede0e6e", "step": 179, "value": 0.05246084271996549, "stage": "fusion", "elapsed_seconds": 38809.363609075546}, {"event_id": "b81e1f9839fa45aeb4b0916baca02b59", "node_id": "b81e1f9839fa45aeb4b0916baca02b59", "transition_id": "ec364ba26d5b411eaa5852341bbc8121", "step": 180, "value": 0.05286909197108946, "stage": "fusion", "elapsed_seconds": 38882.24571728706}, {"event_id": "1598d2c0231d463c8eac9daccaf53a82", "node_id": "1598d2c0231d463c8eac9daccaf53a82", "transition_id": "ab8312fda7c340868c408456622cb441", "step": 181, "value": 0.053199915465594175, "stage": "fusion", "elapsed_seconds": 38905.20683479309}, {"event_id": "a4528b9efb6640e9a2ac196604ce7890", "node_id": "a4528b9efb6640e9a2ac196604ce7890", "transition_id": "6e1e44340702496c9e3a2b1567d23ec4", "step": 185, "value": 0.05318558612548434, "stage": "fusion", "elapsed_seconds": 41381.403416633606}, {"event_id": "a895b35345c042558c94006c99fc3032", "node_id": "a895b35345c042558c94006c99fc3032", "transition_id": "80be1f9dc4cc4908b11d568c9ae04867", "step": 186, "value": 0.05407251174366917, "stage": "evolution", "elapsed_seconds": 41510.75722908974}, {"event_id": "0d66d9c6999042548a6c26faf2478243", "node_id": "0d66d9c6999042548a6c26faf2478243", "transition_id": "3a5aff6b89bc46c89ed63c42b5a758d3", "step": 187, "value": 0.05988147032181717, "stage": "evolution", "elapsed_seconds": 41660.39448714256}, {"event_id": "3ec5846d484c4e6eb70b035c33b0ead5", "node_id": "3ec5846d484c4e6eb70b035c33b0ead5", "transition_id": "952a6ab20443415fa86e872a4876aed2", "step": 188, "value": 0.05318558612548434, "stage": "evolution", "elapsed_seconds": 41795.02798175812}, {"event_id": "63252b7a3eca479baf9a33de7b0fc406", "node_id": "63252b7a3eca479baf9a33de7b0fc406", "transition_id": "8c7c9d36459a4b45941033c819d4c15e", "step": 189, "value": 0.0533039292344461, "stage": "evolution", "elapsed_seconds": 41856.02555727959}, {"event_id": "ebf3a2c3ba8e4a3ca3de38e4341ac8ef", "node_id": "ebf3a2c3ba8e4a3ca3de38e4341ac8ef", "transition_id": "3103faddbbf143ddad665bdcccf31bbf", "step": 190, "value": 0.05288642693878448, "stage": "fusion", "elapsed_seconds": 41971.934244155884}, {"event_id": "b48ad728e4574de98992642adb829f41", "node_id": "b48ad728e4574de98992642adb829f41", "transition_id": "2136409117d74e57a95ffed538ba59f4", "step": 191, "value": 0.059324350324528784, "stage": "evolution", "elapsed_seconds": 42150.853816986084}, {"event_id": "0f073f0ab11b458d8ef58280d72ee606", "node_id": "0f073f0ab11b458d8ef58280d72ee606", "transition_id": "f64d0564a38a4fa1a11e31a814141488", "step": 192, "value": 0.05246998907129674, "stage": "fusion", "elapsed_seconds": 42165.39934325218}, {"event_id": "1d2c4d4ec6a4431cbdadf1e19b1cd555", "node_id": "1d2c4d4ec6a4431cbdadf1e19b1cd555", "transition_id": "05e68493c6bd4828894f1bd61c741ab7", "step": 193, "value": 0.05318261431524196, "stage": "evolution", "elapsed_seconds": 42357.24153327942}, {"event_id": "84f3f9b2e17840c293978a38c43685f5", "node_id": "84f3f9b2e17840c293978a38c43685f5", "transition_id": "3cb42d941830449bbda6d30918243e96", "step": 195, "value": 0.05362599583205786, "stage": "evolution", "elapsed_seconds": 42383.712561130524}, {"event_id": "56fe29524942414fab78368c1e08137a", "node_id": "56fe29524942414fab78368c1e08137a", "transition_id": "e00f8d5473c3486ea47750d98bbd3fb7", "step": 196, "value": 0.053071278486101714, "stage": "fusion", "elapsed_seconds": 42656.36372256279}, {"event_id": "3b16e5cdda884bc8a544f5d171aa4470", "node_id": "3b16e5cdda884bc8a544f5d171aa4470", "transition_id": "2bc6553eeeea4e38b0dfbfb22d477110", "step": 197, "value": 0.058840901511512986, "stage": "evolution", "elapsed_seconds": 42706.03460144997}, {"event_id": "bb47b5751d0d4b008b02560dcc90dc17", "node_id": "bb47b5751d0d4b008b02560dcc90dc17", "transition_id": "c617aa8e751447c2bc93c2667108fed6", "step": 198, "value": 0.053302201941186386, "stage": "evolution", "elapsed_seconds": 42899.50653171539}, {"event_id": "7231b3e1c5dd4896830d4967cc0bbedc", "node_id": "7231b3e1c5dd4896830d4967cc0bbedc", "transition_id": "bd6be9cdbf9f410a93feff78202baebc", "step": 199, "value": 0.05294866613346404, "stage": "evolution", "elapsed_seconds": 42972.38202166557}, {"event_id": "f456e35574d04452905faf783c80ae9d", "node_id": "f456e35574d04452905faf783c80ae9d", "transition_id": "bd0ad64c140c45b2961512df8971e308", "step": 200, "value": 0.052937343775440134, "stage": "evolution", "elapsed_seconds": 43145.07902884483}, {"event_id": "9c2b8a2dd36a47eb8ffc66553341d340", "node_id": "9c2b8a2dd36a47eb8ffc66553341d340", "transition_id": "337068de1b094561a1ae89ef26c40e54", "step": 201, "value": 0.05299040285410617, "stage": "fusion", "elapsed_seconds": 43151.2680618763}], "maximize": false, "metric_name": "native public validation metric", "official_score": 0.06086, "valid_submission": true, "medal": "silver", "thresholds": {"gold": 0.05589, "silver": 0.06229, "bronze": 0.06582}, "formal_result": false, "full_agent_budget_used": true, "note": "从 2026-09-21 首轮断点续跑；续跑使用独占 A100 80GB，仅补原 12h 剩余时间。 已保存评分来自本次续跑最终提交。 原首轮格式校验任务 ID 有误；续跑已修正。原全局记忆缺失，按保存记录重建；详情见 provenance。", "artifacts": [{"bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/experiments/mlebench-aq04-12h-20260921/continuations/liux-mila-20260924/runs/harry123.aq04-20260921.nomad2018-predict-transparent-conductors", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/experiments/mlebench-aq04-12h-20260921/continuations/liux-mila-20260924/runs/harry123.aq04-20260921.nomad2018-predict-transparent-conductors/live.json", "member": "live.json; immutable metric events and continuation archive index", "files": 1, "bytes": 0}, {"bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/experiments/mlebench-aq04-12h-20260921/continuations/liux-mila-20260924/runs/harry123.aq04-20260921.nomad2018-predict-transparent-conductors/final", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/experiments/mlebench-aq04-12h-20260921/continuations/liux-mila-20260924/runs/harry123.aq04-20260921.nomad2018-predict-transparent-conductors/final/submission-f9bd07cc4ec04722f90c67a3d884fb27038c727c75e4ce4a3d5f333be9276645.csv", "member": "Sealed final submission.csv; SHA256 f9bd07cc4ec04722f90c67a3d884fb27038c727c75e4ce4a3d5f333be9276645", "files": 1, "bytes": 10100}, {"bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/experiments/mlebench-aq04-12h-20260921/continuations/liux-mila-20260924/runs/harry123.aq04-20260921.nomad2018-predict-transparent-conductors/artifacts", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/experiments/mlebench-aq04-12h-20260921/continuations/liux-mila-20260924/runs/harry123.aq04-20260921.nomad2018-predict-transparent-conductors/artifacts/logs-8b7ec2944467700c5b1ca398686a09f9ec124da82fb639583ee7a0f7c5151751.tar.gz", "member": "experiments/mlebench-aq04-12h-20260921/continuations/liux-mila-20260924/runs/harry123.aq04-20260921.nomad2018-predict-transparent-conductors/artifacts/logs-8b7ec2944467700c5b1ca398686a09f9ec124da82fb639583ee7a0f7c5151751.tar.gz", "files": 318, "bytes": 141902881}, {"bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/experiments/mlebench-aq04-12h-20260921/runs/harry123.aq04-20260921.nomad2018-predict-transparent-conductors/artifacts/logs", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/experiments/mlebench-aq04-12h-20260921/runs/harry123.aq04-20260921.nomad2018-predict-transparent-conductors/live.json", "member": "live.json; persisted native/wrapper logs", "files": 163, "bytes": 371585933}], "logs_scope": "完整可用日志、候选代码及提交 CSV 已上传；日志快照时间 2026-09-25T06:21:42.578296+00:00；排除数据集、模型缓存及凭据。", "curve_scope": "保留原始指标点；续跑使用已提交的有效原生观察。仅有原生 active 时间的点参与时间曲线。", "source_grade": {"competition_id": "nomad2018-predict-transparent-conductors", "score": 0.06086, "gold_threshold": 0.05589, "silver_threshold": 0.06229, "bronze_threshold": 0.06582, "median_threshold": 0.06988, "any_medal": true, "gold_medal": false, "silver_medal": true, "bronze_medal": false, "above_median": true, "submission_exists": true, "valid_submission": true, "is_lower_better": true, "created_at": "2026-09-25T02:11:59.895428", "submission_path": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/runs/aq04-mlebench-lite-20260921-resume-mila-20260924/tasks/nomad2018-predict-transparent-conductors/20260921_003637_AQ04_nomad2018-predict-transparent-conductors/workspace/ensembles_csv/top6ens-total_run_time0.19h.csv"}, "source_wrapper": {"task": "nomad2018-predict-transparent-conductors", "job_id": "22372438", "owner": "harry123", "host": "g10.nibi.sharcnet", "commit": "3a0479c4e597b3515697d776c2768736cea8c4d6", "source_sha256": "efedc394766bff346ee7a3f98737fe3cf912cd3da7c397456e86e844d3c7046b", "started_at": "2026-09-21T04:36:21.848012+00:00", "agent_budget_seconds": 43200, "state": "failed", "workspace_is_node_local": true, "formal_result": false, "gpu": "NVIDIA H100 80GB HBM3", "gpu_uuid": "5c3d3eab-e338-fbf2-cb9e-5e0e9d9dc836", "cpu_ids": [77, 78, 79, 80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90, 91, 92, 93, 94, 95, 96, 97], "grading_port": 32438, "grading_server_id": 27433, "search_started_at": "2026-09-21T04:36:30.529842+00:00", "search_exit_code": -2, "search_finished_at": "2026-09-21T14:52:14.013100+00:00", "fusion_exit_code": 0, "final_submission": "/scratch/harry123/EvolveFold/MLEvolve_BO/runs/aq04-mlebench-lite-20260921/tasks/nomad2018-predict-transparent-conductors/22372438/native/20260921_003637_AQ04_nomad2018-predict-transparent-conductors/final_submission.json", "log_dir": "/scratch/harry123/EvolveFold/MLEvolve_BO/runs/aq04-mlebench-lite-20260921/tasks/nomad2018-predict-transparent-conductors/22372438/native/20260921_003637_AQ04_nomad2018-predict-transparent-conductors", "journal_active_seconds": 15227.911437988281, "full_agent_budget_used": false, "outer_search_timeout_reached": false, "official_grade": "/scratch/harry123/EvolveFold/MLEvolve_BO/runs/aq04-mlebench-lite-20260921/tasks/nomad2018-predict-transparent-conductors/22372438/official-grade.json", "finished_at": "2026-09-21T14:52:19.826063+00:00", "elapsed_seconds": 36957.965941321105}, "score_phase": "continuation-final", "final_submission_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/experiments/mlebench-aq04-12h-20260921/continuations/liux-mila-20260924/runs/harry123.aq04-20260921.nomad2018-predict-transparent-conductors/final/submission-f9bd07cc4ec04722f90c67a3d884fb27038c727c75e4ce4a3d5f333be9276645.csv", "hardware": "A100 80GB (continuation); H100 80GB (first segment)", "model": "muse-spark-1.3-contributor", "provider": "codex://opencode-go", "scheduler": {"job_id": "10927028", "partition": "main", "observed_at": "2026-09-25T17:05:51.509769+00:00", "allocation": null}, "completed_candidates": 249, "pending_decisions": 3, "remaining_seconds": 0, "continuation_source_status": {"state": "complete", "active_elapsed_seconds": 43207.26385140419, "updated_at": "2026-09-25T06:12:00.018027+00:00", "source_updated_at": "2026-09-21T14:52:19.826063+00:00", "imported_first_run": true, "run_root": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/runs/aq04-mlebench-lite-20260921-resume-mila-20260924/tasks/nomad2018-predict-transparent-conductors/20260921_003637_AQ04_nomad2018-predict-transparent-conductors", "previous_job_id": "22372438", "job_id": "10927028", "attempt": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/runs/aq04-mlebench-lite-20260921-resume-mila-20260924/tasks/nomad2018-predict-transparent-conductors/attempt-03-10927028", "gpu": "NVIDIA A100-SXM4-80GB", "host": "cn-g019.server.mila.quebec", "started_at": "2026-09-24T17:57:20.254476+00:00", "search_pid": 1881379, "attempt_started_epoch": 1790314658.1993206, "search_stopped_epoch": 1790316713.057169, "search_exit_code": 75, "budget_complete": true, "completed_transitions": 249, "error": null, "repair_id": "memory-lock-v1", "release_receipt": {"job_id": "10919451", "state": "COMPLETED", "end": "2026-09-24T15:15:25", "exit_code": "0:0", "end_epoch": 1790277325.0, "verified_at": "2026-09-25T05:30:03.102563+00:00"}, "stop_history": [{"stop_reason": "user_request", "stop_requested_at": "2026-09-24T19:15:09.692440+00:00", "stopped_at": "2026-09-24T19:15:16.474721+00:00", "job_id": "10919451", "active_elapsed_seconds": 41190.669416189194}], "resume_requested_at": "2026-09-25T05:30:03.052522+00:00", "resume_reason": "explicit_user_request", "search_finished_at": "2026-09-25T06:11:55.723317+00:00", "finished_at": "2026-09-25T06:12:00.016515+00:00", "submission": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/runs/aq04-mlebench-lite-20260921-resume-mila-20260924/tasks/nomad2018-predict-transparent-conductors/20260921_003637_AQ04_nomad2018-predict-transparent-conductors/workspace/ensembles_csv/top6ens-total_run_time0.19h.csv", "official_grade": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/runs/aq04-mlebench-lite-20260921-resume-mila-20260924/tasks/nomad2018-predict-transparent-conductors/20260921_003637_AQ04_nomad2018-predict-transparent-conductors/logs/official-grade.json", "final_submission_sha256": "f9bd07cc4ec04722f90c67a3d884fb27038c727c75e4ce4a3d5f333be9276645"}, "config_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/experiments/mlebench-aq04-12h-20260921/continuations/liux-mila-20260924/runs/harry123.aq04-20260921.nomad2018-predict-transparent-conductors/config.yaml"}, {"id": "harry123.aq04-20260921.random-acts-of-pizza", "experiment_id": "mlebench-aq04-12h-20260921", "family": "MLEBench", "method": "AQ04", "dataset": "random-acts-of-pizza", "seed": 42, "status": "completed", "source_status": "complete", "wrapper_status": "complete", "source_updated_at": "2026-09-25T06:07:52.543310+00:00", "uploaded_at": "2026-09-25T17:05:52.180983+00:00", "elapsed_seconds": 43209.153702259064, "budget_seconds": 43200, "metrics": [{"event_id": "79a12385f98d493fa9e7fb7b99102592", "node_id": "79a12385f98d493fa9e7fb7b99102592", "transition_id": "15e5ae9c0d9c41c5a43aa3316d97b3c4", "step": 2, "value": 0.7036664270309131, "stage": "draft", "elapsed_seconds": 620.3162324428558}, {"event_id": "e23435a46f3349f6a9022feb83667bb2", "node_id": "e23435a46f3349f6a9022feb83667bb2", "transition_id": "5ba330a04a2444a880763805030e9fa8", "step": 5, "value": 0.6186196980589505, "stage": "debug", "elapsed_seconds": 872.9084477424622}, {"event_id": "6e95f25a95634c689d06a8e9bd7b9b0c", "node_id": "6e95f25a95634c689d06a8e9bd7b9b0c", "transition_id": "3c13e0ef72554441aba84d4798a52f60", "step": 6, "value": 0.6450323508267434, "stage": "improve", "elapsed_seconds": 882.4276509284973}, {"event_id": "3966cb2c5f8c479dafd0da7b3b8e02e2", "node_id": "3966cb2c5f8c479dafd0da7b3b8e02e2", "transition_id": "68efd3d7da9e4f43930af41c5bf1b721", "step": 7, "value": 0.6454349388928828, "stage": "debug", "elapsed_seconds": 904.1624426841736}, {"event_id": "3c7744e4bc01410e8540470d3f6c39e5", "node_id": "3c7744e4bc01410e8540470d3f6c39e5", "transition_id": "370a0d1f3f11405bbe256adcb2c7e3c2", "step": 9, "value": 0.6287562904385334, "stage": "improve", "elapsed_seconds": 1162.0462973117828}, {"event_id": "19dd9f4ebba34ed69b7910608cd4e10a", "node_id": "19dd9f4ebba34ed69b7910608cd4e10a", "transition_id": "1741d3b47d8042d1897feefbc8afad04", "step": 10, "value": 0.6370524802300503, "stage": "improve", "elapsed_seconds": 1228.513235092163}, {"event_id": "c678bd61bb55440ab205af9a55cf8dde", "node_id": "c678bd61bb55440ab205af9a55cf8dde", "transition_id": "e294297e07e348c3bbf3eeb01f422524", "step": 11, "value": 0.7000718907260963, "stage": "improve", "elapsed_seconds": 1312.481373310089}, {"event_id": "b1256c25a54b44cb87483d1a31297c14", "node_id": "b1256c25a54b44cb87483d1a31297c14", "transition_id": "f7e5be7950b84324b0fe7acb0f86f0b3", "step": 17, "value": 0.6914162473040977, "stage": "debug", "elapsed_seconds": 1982.6877036094666}, {"event_id": "e268b82c72ee46f7a719dc7ec10a4890", "node_id": "e268b82c72ee46f7a719dc7ec10a4890", "transition_id": "c10e08a77c75439fa9b9fb105a454287", "step": 18, "value": 0.6287419122933141, "stage": "improve", "elapsed_seconds": 2000.375415802002}, {"event_id": "32f51d304a4041fba0765ec0ffec79a4", "node_id": "32f51d304a4041fba0765ec0ffec79a4", "transition_id": "1424ccdbe81f4b7c8373a64fe781adc2", "step": 19, "value": 0.6774982027318476, "stage": "debug", "elapsed_seconds": 2001.0758247375488}, {"event_id": "c147bb2876c54a05aa013f19f936b756", "node_id": "c147bb2876c54a05aa013f19f936b756", "transition_id": "37022c72dba04db1b2a39b6b2dcc977e", "step": 21, "value": 0.6939481230743365, "stage": "debug", "elapsed_seconds": 2229.975255012512}, {"event_id": "ed1ac039aed046ffabe8d9914558d882", "node_id": "ed1ac039aed046ffabe8d9914558d882", "transition_id": "eded443c5e084480b91cf4feca4be836", "step": 22, "value": 0.705391804457225, "stage": "improve", "elapsed_seconds": 2322.0789861679077}, {"event_id": "eb2b69d7339248229008338c21c36ffa", "node_id": "eb2b69d7339248229008338c21c36ffa", "transition_id": "0f90b4d5032a4f398bda5a5e2bc74398", "step": 23, "value": 0.686959022286125, "stage": "improve", "elapsed_seconds": 2387.6465423107147}, {"event_id": "7171ee0f47874b7894aba914f42fb66d", "node_id": "7171ee0f47874b7894aba914f42fb66d", "transition_id": "32519e16aabd4ee79df81acf88ffd5b6", "step": 24, "value": 0.7014577655354354, "stage": "evolution", "elapsed_seconds": 2472.8424458503723}, {"event_id": "f2cd11532d29489db95d8b9a58f09744", "node_id": "f2cd11532d29489db95d8b9a58f09744", "transition_id": "7bb729a5975e49feb5501448edac2d44", "step": 25, "value": 0.6931128684399712, "stage": "improve", "elapsed_seconds": 2553.384384393692}, {"event_id": "308760f6c7654564a5df569e06b95696", "node_id": "308760f6c7654564a5df569e06b95696", "transition_id": "53e9bdb21da249e29229a9f93e54c849", "step": 26, "value": 0.700339789660178, "stage": "evolution", "elapsed_seconds": 2655.3018686771393}, {"event_id": "a0a11920a03042249a2fcfddfbf1c6fe", "node_id": "a0a11920a03042249a2fcfddfbf1c6fe", "transition_id": "14c89891c46a4b898ed3b01e3045d196", "step": 27, "value": 0.699651157903585, "stage": "evolution", "elapsed_seconds": 2708.587319135666}, {"event_id": "ab2aa6f3c27a4532a537417224f6fe5b", "node_id": "ab2aa6f3c27a4532a537417224f6fe5b", "transition_id": "455a7aee7efc414c9ab9372c12c97114", "step": 29, "value": 0.6837670740474479, "stage": "improve", "elapsed_seconds": 2989.329975128174}, {"event_id": "6b885218453c446e95a36debb1bd6925", "node_id": "6b885218453c446e95a36debb1bd6925", "transition_id": "6ccfec3a19e749b0b6b633ff6fe8dd50", "step": 30, "value": 0.6908698777857657, "stage": "improve", "elapsed_seconds": 2998.1495654582977}, {"event_id": "dbe2da2f021243188ebfc15a72c2a224", "node_id": "dbe2da2f021243188ebfc15a72c2a224", "transition_id": "a36a3e0d3c674183a2c59c57949822a1", "step": 31, "value": 0.7016310550291133, "stage": "evolution", "elapsed_seconds": 3181.6916546821594}, {"event_id": "26c20de0fa10474db72b900cb6eca045", "node_id": "26c20de0fa10474db72b900cb6eca045", "transition_id": "615fb80c638946b0864d4ee77b43cefa", "step": 32, "value": 0.6836128273021477, "stage": "debug", "elapsed_seconds": 3202.4901037216187}, {"event_id": "7f8cca780ef84638a2d024271381f32c", "node_id": "7f8cca780ef84638a2d024271381f32c", "transition_id": "a995b95d991e492d97f756fcf1812a6b", "step": 33, "value": 0.6932494689776243, "stage": "evolution", "elapsed_seconds": 3350.857971906662}, {"event_id": "be295e7216ce44da9c7dee3cdd9673d6", "node_id": "be295e7216ce44da9c7dee3cdd9673d6", "transition_id": "1d45d55dcc5a45a6bda612df5ef41f86", "step": 36, "value": 0.7427749820273184, "stage": "evolution", "elapsed_seconds": 3586.7318477630615}, {"event_id": "48e2f54dd0214b75bd2086a41de70bf1", "node_id": "48e2f54dd0214b75bd2086a41de70bf1", "transition_id": "2a583aa5f4ae4f8f982bd76ccee1ac03", "step": 37, "value": 0.6973492526890586, "stage": "evolution", "elapsed_seconds": 3600.4101214408875}, {"event_id": "d0aabd11c7e5491c873b125e9c485198", "node_id": "d0aabd11c7e5491c873b125e9c485198", "transition_id": "1873315638cc4f0b94f7700e1cb12ad7", "step": 39, "value": 0.697551315997918, "stage": "debug", "elapsed_seconds": 3739.0613944530487}, {"event_id": "a0dea0923aa04fa08ca0a685900adf85", "node_id": "a0dea0923aa04fa08ca0a685900adf85", "transition_id": "e68e5a85b92146cc9f8438cad334fa28", "step": 42, "value": 0.7078360891445004, "stage": "improve", "elapsed_seconds": 4142.21213889122}, {"event_id": "4f7278c17dfa437cba9f7ae191c29ce7", "node_id": "4f7278c17dfa437cba9f7ae191c29ce7", "transition_id": "13cdd8852cfc4981a52f730f059381d4", "step": 43, "value": 0.6868727534148095, "stage": "debug", "elapsed_seconds": 4221.489376783371}, {"event_id": "7f4f65cbaadd403caf4afb3d2e574394", "node_id": "7f4f65cbaadd403caf4afb3d2e574394", "transition_id": "c0c1df7b0f124f1da80e90f315b96f60", "step": 44, "value": 0.6815501650453107, "stage": "debug", "elapsed_seconds": 4271.331611394882}, {"event_id": "0760f39581314ad4b7ba0a7d5d51bd2f", "node_id": "0760f39581314ad4b7ba0a7d5d51bd2f", "transition_id": "56f391118385468eb5314763d2f41a43", "step": 45, "value": 0.6970977242821903, "stage": "evolution", "elapsed_seconds": 4473.02837562561}, {"event_id": "2402b1cf7160415f93118fd73979146e", "node_id": "2402b1cf7160415f93118fd73979146e", "transition_id": "39cd241c4fb6476ebc73365a874ee423", "step": 46, "value": 0.6862946351869882, "stage": "evolution", "elapsed_seconds": 4474.739961862564}, {"event_id": "2ad89f55aa3b4014939382256260c976", "node_id": "2ad89f55aa3b4014939382256260c976", "transition_id": "1913f1b4852048fca9c39c1042f771b7", "step": 48, "value": 0.7003152187618207, "stage": "evolution", "elapsed_seconds": 4626.503701686859}, {"event_id": "65e357888cca43b6ad8a42514bc67478", "node_id": "65e357888cca43b6ad8a42514bc67478", "transition_id": "8b812bdbdbbd480a959ba851052aadbb", "step": 49, "value": 0.9484667436123747, "stage": "evolution", "elapsed_seconds": 4823.339883327484}, {"event_id": "88b97599866944698973d7a2a77a17d0", "node_id": "88b97599866944698973d7a2a77a17d0", "transition_id": "c589f152d26c497399ba59eba183c49c", "step": 50, "value": 0.6497771387491014, "stage": "debug", "elapsed_seconds": 4851.365503072739}, {"event_id": "9a4a73ec93374171b34141f683e97972", "node_id": "9a4a73ec93374171b34141f683e97972", "transition_id": "c2789f0ef0214d06838fdbdf6a43c32c", "step": 51, "value": 0.655344008742067, "stage": "evolution", "elapsed_seconds": 5076.915439605713}, {"event_id": "1c99efd623a94501826532fa0471fc51", "node_id": "1c99efd623a94501826532fa0471fc51", "transition_id": "d5fcd5d067da4867966735c53b1561f9", "step": 52, "value": 0.6620273184759167, "stage": "improve", "elapsed_seconds": 5269.220474481583}, {"event_id": "bfcccda6b5464ba987a9144bbc9c7d8e", "node_id": "bfcccda6b5464ba987a9144bbc9c7d8e", "transition_id": "caedc90eb7074604a49c91959f4e0740", "step": 54, "value": 0.5668008626887131, "stage": "improve", "elapsed_seconds": 5466.857314109802}, {"event_id": "ceda932549d34fccaecb4301b02bb897", "node_id": "ceda932549d34fccaecb4301b02bb897", "transition_id": "0409a5fe4fdd4b95821515263de13539", "step": 55, "value": 0.7045886152682269, "stage": "debug", "elapsed_seconds": 5510.749295473099}, {"event_id": "729e17d244714bf48f58dbc9895c6c57", "node_id": "729e17d244714bf48f58dbc9895c6c57", "transition_id": "51eb7d67c4ce4c5fb7dccca6818ad06e", "step": 56, "value": 0.685576236061673, "stage": "improve", "elapsed_seconds": 5769.804472208023}, {"event_id": "19982ba0dde045e5b23ca794ad80186a", "node_id": "19982ba0dde045e5b23ca794ad80186a", "transition_id": "c7050370eae149d39e7b0c700b9a7f22", "step": 57, "value": 0.6958749987876203, "stage": "improve", "elapsed_seconds": 5853.21028137207}, {"event_id": "6559a5d8b83645b9a10f0a950a11731e", "node_id": "6559a5d8b83645b9a10f0a950a11731e", "transition_id": "f3a678ed4ae744a784c7483c8d0fa53b", "step": 58, "value": 0.7027057085309513, "stage": "evolution", "elapsed_seconds": 6187.573148012161}, {"event_id": "88fdc4697fad4630af44d684fc19921c", "node_id": "88fdc4697fad4630af44d684fc19921c", "transition_id": "a4d06d0d582e40ae80d77f17547e6491", "step": 59, "value": 0.7043998073124287, "stage": "evolution", "elapsed_seconds": 6211.580918073654}, {"event_id": "55cba3ce81a94321a97d1ede883a88a3", "node_id": "55cba3ce81a94321a97d1ede883a88a3", "transition_id": "71d6f11ef94241a4aa41102956c816a7", "step": 60, "value": 0.6882586668994436, "stage": "improve", "elapsed_seconds": 6258.6817173957825}, {"event_id": "0243d029de2e480aaa62b27628bc0640", "node_id": "0243d029de2e480aaa62b27628bc0640", "transition_id": "a5b3063079844fc1b5c5c23503063137", "step": 62, "value": 0.7013371675053917, "stage": "evolution", "elapsed_seconds": 6655.52786231041}, {"event_id": "e8c85ab2041b4914ac143926d35fecdb", "node_id": "e8c85ab2041b4914ac143926d35fecdb", "transition_id": "83b258c8c2c24d8bb81cd79c709a43c5", "step": 63, "value": 0.6368149649703048, "stage": "debug", "elapsed_seconds": 6689.1807498931885}, {"event_id": "c9c8500405ce481180708edb7da50f49", "node_id": "c9c8500405ce481180708edb7da50f49", "transition_id": "fb89bac00f6c48c69331ef414f0973e3", "step": 64, "value": 0.685576236061673, "stage": "evolution", "elapsed_seconds": 6761.24455165863}, {"event_id": "e26eb18460614a19b971710493f93c77", "node_id": "e26eb18460614a19b971710493f93c77", "transition_id": "513d3973a79145138d0b12fd6c419961", "step": 65, "value": 0.6549825578951792, "stage": "evolution", "elapsed_seconds": 6878.044605970383}, {"event_id": "3b8238ee16c14b23b4336ab7478cf40e", "node_id": "3b8238ee16c14b23b4336ab7478cf40e", "transition_id": "cc95713e3f534bf9a0dbf67a2feaa686", "step": 68, "value": 0.9444775289435483, "stage": "debug", "elapsed_seconds": 7258.0232763290405}, {"event_id": "82deaff8d9bb44ccb23c0a9f21246771", "node_id": "82deaff8d9bb44ccb23c0a9f21246771", "transition_id": "5db6c73e89f24787ab131fbe4a382e9f", "step": 69, "value": 0.6899892987271626, "stage": "debug", "elapsed_seconds": 7336.806393623352}, {"event_id": "cca7d6748b1447b5b2cf8b0bfa6985a1", "node_id": "cca7d6748b1447b5b2cf8b0bfa6985a1", "transition_id": "d17a3c511a3c429586ea9d5da88e3c91", "step": 70, "value": 0.69061941294951, "stage": "improve", "elapsed_seconds": 7457.003409385681}, {"event_id": "c5fab8fba62e4fff83981a2177596345", "node_id": "c5fab8fba62e4fff83981a2177596345", "transition_id": "8a0b94e6557e4f26bef79efeba82b0ec", "step": 73, "value": 0.6994967649173256, "stage": "evolution", "elapsed_seconds": 7635.979614019394}, {"event_id": "f03da011e62e4cb58612a3841725d6f9", "node_id": "f03da011e62e4cb58612a3841725d6f9", "transition_id": "2888e244a47648839c57ac637acdb6d3", "step": 77, "value": 0.950980411174586, "stage": "evolution", "elapsed_seconds": 8022.685943841934}, {"event_id": "1ccf03d937734a6e8d42b2dff39e13bd", "node_id": "1ccf03d937734a6e8d42b2dff39e13bd", "transition_id": "b2eeb3798a0049e982faccd3265276e9", "step": 78, "value": 0.9492882522008737, "stage": "debug", "elapsed_seconds": 8224.116713047028}, {"event_id": "0592eb44fb104a93afed105487128fa2", "node_id": "0592eb44fb104a93afed105487128fa2", "transition_id": "02b53d4c159f4bd796042f6ab3b5146a", "step": 81, "value": 0.7037771290198476, "stage": "evolution", "elapsed_seconds": 8519.038439273834}, {"event_id": "ae6f571bb49543deafb65ced14a20f4f", "node_id": "ae6f571bb49543deafb65ced14a20f4f", "transition_id": "f7e13a47cbd6499f89901d6c4d24be91", "step": 82, "value": 0.6807476635514019, "stage": "improve", "elapsed_seconds": 8650.178590297699}, {"event_id": "cb1e03f37aa545439ccad5df5f8d41fd", "node_id": "cb1e03f37aa545439ccad5df5f8d41fd", "transition_id": "1b41dc6748de46c9a0e93c3119b8d105", "step": 83, "value": 0.6782314881380301, "stage": "improve", "elapsed_seconds": 8942.219026088715}, {"event_id": "4dd3a4f8d42642c98563e6aeb5d864f1", "node_id": "4dd3a4f8d42642c98563e6aeb5d864f1", "transition_id": "ed539d307a984c70b2d52ce54326dff7", "step": 84, "value": 0.6815110455887154, "stage": "improve", "elapsed_seconds": 9039.271400213242}, {"event_id": "81cbbe0256114b93b6ac50efb9863371", "node_id": "81cbbe0256114b93b6ac50efb9863371", "transition_id": "e793d74eb45241f08c044d18f711b6a6", "step": 85, "value": 0.6979609387376378, "stage": "debug", "elapsed_seconds": 9353.512027025223}, {"event_id": "6aaacd9fe8294397ae644fd2420e0568", "node_id": "6aaacd9fe8294397ae644fd2420e0568", "transition_id": "aafa16fde9114e138b8db2a7cf15b390", "step": 86, "value": 0.9486713933315877, "stage": "evolution", "elapsed_seconds": 9388.739849567413}, {"event_id": "d609e157e36a463eaacae6c274d69084", "node_id": "d609e157e36a463eaacae6c274d69084", "transition_id": "c2de51dc13c04faa969467f663d293f1", "step": 87, "value": 0.5701509705248022, "stage": "evolution", "elapsed_seconds": 9537.176439285278}, {"event_id": "7a47889ca9f244568e945a5af1fb202e", "node_id": "7a47889ca9f244568e945a5af1fb202e", "transition_id": "4c448a48866642e98f9bd30b6109ffdd", "step": 89, "value": 0.49708123652048875, "stage": "debug", "elapsed_seconds": 9967.667095184326}, {"event_id": "6d7cca69a914483abf15279ec9d97184", "node_id": "6d7cca69a914483abf15279ec9d97184", "transition_id": "3629354c283f4a32b293a83ae7788db5", "step": 90, "value": 0.6160460100647016, "stage": "evolution", "elapsed_seconds": 10392.7308781147}, {"event_id": "c9c3f63baefb43d3b3d580235512a7a0", "node_id": "c9c3f63baefb43d3b3d580235512a7a0", "transition_id": "77f89172bb4e4a90841b13da2aa65dbc", "step": 91, "value": 0.9696491211054317, "stage": "evolution", "elapsed_seconds": 10662.847176790237}, {"event_id": "142ea36f375e46ba9e9e16a89b646003", "node_id": "142ea36f375e46ba9e9e16a89b646003", "transition_id": "25e4f4a3828d488a88e365abc47154f1", "step": 92, "value": 0.6794765105444717, "stage": "evolution", "elapsed_seconds": 10982.754979133606}, {"event_id": "e5e6a04d047b4ae2ab6909278a5bdfc7", "node_id": "e5e6a04d047b4ae2ab6909278a5bdfc7", "transition_id": "f542d21508874bdbbc14730028d7c6e5", "step": 93, "value": 0.6874646389209496, "stage": "evolution", "elapsed_seconds": 10985.963119268417}, {"event_id": "5d95a771f11d4e98a708243a8a29b68f", "node_id": "5d95a771f11d4e98a708243a8a29b68f", "transition_id": "3e4fcbea10a34fe4b857709060cb043a", "step": 94, "value": 0.7070696293997266, "stage": "evolution", "elapsed_seconds": 11135.12655711174}, {"event_id": "82818b9a23b94d11b5a8a084308efb1f", "node_id": "82818b9a23b94d11b5a8a084308efb1f", "transition_id": "1a87203cfa9c4e63adbddfe7a657bfb0", "step": 95, "value": 0.6761794839464742, "stage": "evolution", "elapsed_seconds": 11264.19240617752}, {"event_id": "36eaa5c6324642c3980ee8bec501cce3", "node_id": "36eaa5c6324642c3980ee8bec501cce3", "transition_id": "ccf3339fac8640d0be461130016d5b36", "step": 97, "value": 0.6276568501920615, "stage": "improve", "elapsed_seconds": 11427.860195875168}, {"event_id": "6c16fb01366f49cfbe550d65bd0ebadf", "node_id": "6c16fb01366f49cfbe550d65bd0ebadf", "transition_id": "1ecd60a39a1840e2a3cb0abe449cb3d5", "step": 98, "value": 0.6911819572013748, "stage": "debug", "elapsed_seconds": 11519.32127046585}, {"event_id": "86999ac836b8473e8be12d472fdcf9da", "node_id": "86999ac836b8473e8be12d472fdcf9da", "transition_id": "c996082263ae41908e782753dd6f2a4d", "step": 101, "value": 0.5977684287543442, "stage": "improve", "elapsed_seconds": 12485.944063425064}, {"event_id": "4ac28c480b874a629c6643d0fa5430e1", "node_id": "4ac28c480b874a629c6643d0fa5430e1", "transition_id": "4f85f4cf617d46dc81e1b31f6ca8eff0", "step": 102, "value": 0.6840596296906977, "stage": "debug", "elapsed_seconds": 12713.925709724426}, {"event_id": "29bde454b4304a2c9f1ead1a68b0ea31", "node_id": "29bde454b4304a2c9f1ead1a68b0ea31", "transition_id": "25370a7625b94deb808ab1a82b7e8c1c", "step": 103, "value": 0.9696491211054317, "stage": "debug", "elapsed_seconds": 12907.61427617073}, {"event_id": "332714a0218149c296cb00b01cbbc584", "node_id": "332714a0218149c296cb00b01cbbc584", "transition_id": "cd2c589f6bf545d88ade0486a11bac8c", "step": 104, "value": 0.680843428416244, "stage": "evolution", "elapsed_seconds": 12916.991431474686}, {"event_id": "db0acff493b44167b3ecfeb36947b227", "node_id": "db0acff493b44167b3ecfeb36947b227", "transition_id": "a9a733e141724addb041f65f2f1a7430", "step": 105, "value": 0.6975438800681519, "stage": "evolution", "elapsed_seconds": 13040.457790136337}, {"event_id": "b1c487ea6af146ea99eaff0a8e33a344", "node_id": "b1c487ea6af146ea99eaff0a8e33a344", "transition_id": "98343c127760407bb038b54fab928fdc", "step": 107, "value": 0.6944644140905822, "stage": "debug", "elapsed_seconds": 13541.847087621689}, {"event_id": "09ff525cb8f14012b59f496f8e1e9794", "node_id": "09ff525cb8f14012b59f496f8e1e9794", "transition_id": "85731968659c4635af77db321358d2bf", "step": 108, "value": 0.6913798175934098, "stage": "improve", "elapsed_seconds": 13603.897242546082}, {"event_id": "255a575d6d644023ae2971c1ee881b85", "node_id": "255a575d6d644023ae2971c1ee881b85", "transition_id": "dfa2cb58450248318e81866519f106b1", "step": 109, "value": 0.5632339491494421, "stage": "evolution", "elapsed_seconds": 13953.16627573967}, {"event_id": "cd3f72faf72c497fb514a64755a30f30", "node_id": "cd3f72faf72c497fb514a64755a30f30", "transition_id": "cd88b40599c440999b60df2702aea31a", "step": 110, "value": 0.9898561253363665, "stage": "improve", "elapsed_seconds": 14440.248223781586}, {"event_id": "bb08e586e4cf4005ac1665b9e9c38a8a", "node_id": "bb08e586e4cf4005ac1665b9e9c38a8a", "transition_id": "3d454e9753654c399766a8702ab48ccd", "step": 111, "value": 0.6873495436602233, "stage": "evolution", "elapsed_seconds": 14509.733548879623}, {"event_id": "1e7054f6eaae4c639b953f920d630c2b", "node_id": "1e7054f6eaae4c639b953f920d630c2b", "transition_id": "8be754b27a4d4aa4ada4f1c4d67c4108", "step": 113, "value": 0.6029632339491494, "stage": "evolution", "elapsed_seconds": 14824.62804722786}, {"event_id": "a2606a1e6b014d359d11a69c4979d215", "node_id": "a2606a1e6b014d359d11a69c4979d215", "transition_id": "393d808f704642c88665f112d2ca1fc0", "step": 116, "value": 0.9889735969706217, "stage": "improve", "elapsed_seconds": 15792.924751758575}, {"event_id": "88328215620b41b780ad7632d2d0395a", "node_id": "88328215620b41b780ad7632d2d0395a", "transition_id": "047f50aed66e4e7899ab9976b86d7b88", "step": 118, "value": 0.9893775834327405, "stage": "debug", "elapsed_seconds": 16270.339214086533}, {"event_id": "6a5dd44fd1cb42c6b4ad8a614066b8d6", "node_id": "6a5dd44fd1cb42c6b4ad8a614066b8d6", "transition_id": "b6d27741460d4e74962e69a954d223a4", "step": 120, "value": 0.9920867201154048, "stage": "evolution", "elapsed_seconds": 16878.56217098236}, {"event_id": "5167dba696844b3e92dd92bb7cde7787", "node_id": "5167dba696844b3e92dd92bb7cde7787", "transition_id": "52dc8a3570a34592a0fca8ee72ca184e", "step": 121, "value": 0.9932869760312925, "stage": "debug", "elapsed_seconds": 17313.38082408905}, {"event_id": "66b355bc50954b82aa87e9fe2fd3bed3", "node_id": "66b355bc50954b82aa87e9fe2fd3bed3", "transition_id": "b6a1cec68cbf4054aa4c4776e942bd35", "step": 122, "value": 0.9896350597830609, "stage": "debug", "elapsed_seconds": 17481.278014183044}, {"event_id": "f20a65959ea64cff9ea6b9ebe057fc6b", "node_id": "f20a65959ea64cff9ea6b9ebe057fc6b", "transition_id": "033c418300bc4a22b3025b5c0e9a08eb", "step": 123, "value": 0.5748490945674044, "stage": "improve", "elapsed_seconds": 18038.298372030258}, {"event_id": "b21d195ff6ac45958e45ce8c29597f29", "node_id": "b21d195ff6ac45958e45ce8c29597f29", "transition_id": "d79b14aef5624d3bb22f1f26da077ab9", "step": 125, "value": 0.5643863179074446, "stage": "improve", "elapsed_seconds": 18463.43128347397}, {"event_id": "9e13eb4e704f4f2ba610f2d6d663d31e", "node_id": "9e13eb4e704f4f2ba610f2d6d663d31e", "transition_id": "4d86ec20e6494d0eb48b7aeeec2519ee", "step": 127, "value": 0.5775745381379185, "stage": "improve", "elapsed_seconds": 18809.44767522812}, {"event_id": "705b02ba7d58467595127fef9b586ef7", "node_id": "705b02ba7d58467595127fef9b586ef7", "transition_id": "86bfad7ab0a94e1ba3124216bc868ab2", "step": 128, "value": 0.5477044082677885, "stage": "evolution", "elapsed_seconds": 19080.774358034134}, {"event_id": "38397dc9f7604ae5a7a9d0c758694414", "node_id": "38397dc9f7604ae5a7a9d0c758694414", "transition_id": "ea3f95e79d914d1a8292fa325788c9df", "step": 129, "value": 0.989581310511277, "stage": "improve", "elapsed_seconds": 19659.801650047302}, {"event_id": "17074bb9952d4b0094b1460b22391d16", "node_id": "17074bb9952d4b0094b1460b22391d16", "transition_id": "a10e4ac558ff4efabc8bd64b829a05d7", "step": 132, "value": 0.6318248094947123, "stage": "debug", "elapsed_seconds": 19905.5263607502}, {"event_id": "2d7aef79553c49219a2622d426fc4255", "node_id": "2d7aef79553c49219a2622d426fc4255", "transition_id": "ced3dcf9875d4ba9bf9660c0e7bb21ad", "step": 135, "value": 0.605538151169219, "stage": "evolution", "elapsed_seconds": 20235.207804203033}, {"event_id": "542d778bd1c14f9b88afb7b8a97a80a1", "node_id": "542d778bd1c14f9b88afb7b8a97a80a1", "transition_id": "2451eb6db8504bd09d46bd8f0036e36b", "step": 136, "value": 0.6515458651380981, "stage": "evolution", "elapsed_seconds": 20242.363530158997}, {"event_id": "9a778f198caf44dbbfbf1b8bf4cbc9ae", "node_id": "9a778f198caf44dbbfbf1b8bf4cbc9ae", "transition_id": "76587f1d999a49eaaafdf662f0ffe352", "step": 139, "value": 0.98943393347574, "stage": "evolution", "elapsed_seconds": 20807.852429389954}, {"event_id": "d20329d17af34f0591915fcc7af5bbd2", "node_id": "d20329d17af34f0591915fcc7af5bbd2", "transition_id": "87e802fb250e4c9ba4e163f27e738bea", "step": 140, "value": 0.5838668373879642, "stage": "evolution", "elapsed_seconds": 20945.7795214653}, {"event_id": "2ec75f7e470c42eab9bff481e718309a", "node_id": "2ec75f7e470c42eab9bff481e718309a", "transition_id": "5cd480148bac42b0928ea7cb24d6644e", "step": 142, "value": 0.6638102084831057, "stage": "improve", "elapsed_seconds": 21071.642267227173}, {"event_id": "3c5fc8aeb52047c78127a778a5efc2b1", "node_id": "3c5fc8aeb52047c78127a778a5efc2b1", "transition_id": "38c39a4c8f2449e6b76898c54f0483a4", "step": 143, "value": 0.6990881696118957, "stage": "debug", "elapsed_seconds": 21235.71378660202}, {"event_id": "9cf4d07a72b04309916931b674973178", "node_id": "9cf4d07a72b04309916931b674973178", "transition_id": "6ea880a3f01a4f39867be5d5bcbca0b7", "step": 144, "value": 0.7002356866434536, "stage": "evolution", "elapsed_seconds": 21355.6210398674}, {"event_id": "d4351768294f44ab932772a6922877a8", "node_id": "d4351768294f44ab932772a6922877a8", "transition_id": "433256e7f9f74b62bb9fb55177bd2771", "step": 145, "value": 0.7001419292681429, "stage": "evolution", "elapsed_seconds": 21439.63478422165}, {"event_id": "e0965ec54312450ab25612b9d97a4900", "node_id": "e0965ec54312450ab25612b9d97a4900", "transition_id": "4e2d13d3844444a39ff4d23fff8e6b3e", "step": 147, "value": 0.6939959716658746, "stage": "evolution", "elapsed_seconds": 21668.96025443077}, {"event_id": "8eb95f6f885e4383b1370ec3e5733597", "node_id": "8eb95f6f885e4383b1370ec3e5733597", "transition_id": "f2f68f7b8eb443de866fe2cbae51ce1e", "step": 148, "value": 0.6834227261411728, "stage": "debug", "elapsed_seconds": 21687.78156018257}, {"event_id": "713772ab1c854ccb98e05f934bbc26f8", "node_id": "713772ab1c854ccb98e05f934bbc26f8", "transition_id": "193fc3a87b574480a2a9a619cc065eb1", "step": 149, "value": 0.7016013113100492, "stage": "evolution", "elapsed_seconds": 21998.146517276764}, {"event_id": "d69877a9cece4817a02631ecf95a35bb", "node_id": "d69877a9cece4817a02631ecf95a35bb", "transition_id": "f325d8a0d5354721bc25c93bf99c0245", "step": 150, "value": 0.9909961300524316, "stage": "evolution", "elapsed_seconds": 22616.17812848091}, {"event_id": "7dfc775987a342f2917f42a52cd847a2", "node_id": "7dfc775987a342f2917f42a52cd847a2", "transition_id": "64b30a78a8314180b46ee3ee2f5ed954", "step": 151, "value": 0.5737333089445766, "stage": "fusion", "elapsed_seconds": 22797.38984489441}, {"event_id": "df457b4c146946158788380523fbf2f9", "node_id": "df457b4c146946158788380523fbf2f9", "transition_id": "4153debf0ef74a39afa87f05f6f2e95d", "step": 152, "value": 0.6948543366019093, "stage": "evolution", "elapsed_seconds": 22860.9289894104}, {"event_id": "baf34fee81714defaa6b2d99dae39bd3", "node_id": "baf34fee81714defaa6b2d99dae39bd3", "transition_id": "43c54e2691d44b73a06a13afe6955524", "step": 153, "value": 0.6919552938970415, "stage": "evolution", "elapsed_seconds": 22948.11130309105}, {"event_id": "a44ea86146c74313b14782ddfd52a65f", "node_id": "a44ea86146c74313b14782ddfd52a65f", "transition_id": "b36131a4b04743748561e97eb0652cdc", "step": 155, "value": 0.7044179121849025, "stage": "evolution", "elapsed_seconds": 23060.21007657051}, {"event_id": "13f4b907b27a428eb4214f5d32751ad5", "node_id": "13f4b907b27a428eb4214f5d32751ad5", "transition_id": "2eb5a81fecf54f89bcf5516ee5607fd9", "step": 156, "value": 0.6846700225341003, "stage": "fusion_draft", "elapsed_seconds": 23164.71719765663}, {"event_id": "276982a0bc5b4049b953aa94f4e8b0a4", "node_id": "276982a0bc5b4049b953aa94f4e8b0a4", "transition_id": "700163337da441d78dea9495520ec52b", "step": 157, "value": 0.6937742631200575, "stage": "improve", "elapsed_seconds": 23473.01433110237}, {"event_id": "95cfc9ffd8d7411c85aea787861f8060", "node_id": "95cfc9ffd8d7411c85aea787861f8060", "transition_id": "e43497489fb142cd846aafaf92591f05", "step": 158, "value": 0.9952683302355259, "stage": "evolution", "elapsed_seconds": 23694.68026804924}, {"event_id": "c1c33e1350dd4f968973843a1684a862", "node_id": "c1c33e1350dd4f968973843a1684a862", "transition_id": "b7ca41148ee747889ee9f71590184557", "step": 159, "value": 0.7007045291157441, "stage": "improve", "elapsed_seconds": 24074.717812776566}, {"event_id": "e9979518773849fe82f2b6b47070abc4", "node_id": "e9979518773849fe82f2b6b47070abc4", "transition_id": "add3e116fe05454fb361be27e2a1c1a4", "step": 160, "value": 0.611086971281146, "stage": "evolution", "elapsed_seconds": 24328.634773015976}, {"event_id": "dc6cdc37ff09456f92dd578af79b9c8a", "node_id": "dc6cdc37ff09456f92dd578af79b9c8a", "transition_id": "d4c289dd9dfd4f2c959435ab4f23f071", "step": 161, "value": 0.590378635449058, "stage": "improve", "elapsed_seconds": 24408.161437749863}, {"event_id": "f383199225c448939c50e115d04c7084", "node_id": "f383199225c448939c50e115d04c7084", "transition_id": "fed0a162b100418da715738e6d3ded09", "step": 162, "value": 0.688301989272863, "stage": "evolution", "elapsed_seconds": 24680.783231258392}, {"event_id": "1fc7f8e333d34a4ba588f91179210887", "node_id": "1fc7f8e333d34a4ba588f91179210887", "transition_id": "50f47a3cda5445259caa9efc0b6a29b0", "step": 163, "value": 0.6640498659916135, "stage": "evolution", "elapsed_seconds": 24762.350275993347}, {"event_id": "46c2657d768c47f487a89129101ef873", "node_id": "46c2657d768c47f487a89129101ef873", "transition_id": "30ed9f1f7276401aa82371cff349f592", "step": 166, "value": 0.6952120776419841, "stage": "improve", "elapsed_seconds": 25153.823101997375}, {"event_id": "fff78e25fd504b53baf4b2bd23c1d5a1", "node_id": "fff78e25fd504b53baf4b2bd23c1d5a1", "transition_id": "77fdd0f05a3440a3930bcf730a437b24", "step": 167, "value": 0.6357422512762317, "stage": "debug", "elapsed_seconds": 25233.040313720703}, {"event_id": "5ba8e961a23946e3a0a1f04155591b40", "node_id": "5ba8e961a23946e3a0a1f04155591b40", "transition_id": "482ed3fbf40c47e2991f1c1d028a32fb", "step": 168, "value": 0.6958016093938424, "stage": "debug", "elapsed_seconds": 25450.54918885231}, {"event_id": "c9ea5684133d47f89f0f66284677187b", "node_id": "c9ea5684133d47f89f0f66284677187b", "transition_id": "a84221b4cbbb4868bc424da71204a75d", "step": 169, "value": 0.4528443387598317, "stage": "fusion", "elapsed_seconds": 25944.920989513397}, {"event_id": "29b68d52bf7148ad8c52338e3c629a2c", "node_id": "29b68d52bf7148ad8c52338e3c629a2c", "transition_id": "db9c45dc481942c49cdfdc0b2e81dfc6", "step": 170, "value": 0.7066402852810619, "stage": "evolution", "elapsed_seconds": 26031.399666547775}, {"event_id": "061c18ad5fee4714b398b5bbe30c243b", "node_id": "061c18ad5fee4714b398b5bbe30c243b", "transition_id": "97d7350aedd4427bb8df8e96aa9c0fd6", "step": 171, "value": 0.5687945856959942, "stage": "fusion", "elapsed_seconds": 26594.495619297028}, {"event_id": "20af8e545ac049c8bac4ebc3c32c1861", "node_id": "20af8e545ac049c8bac4ebc3c32c1861", "transition_id": "7d9c53a567f84262b61f228f5da375b5", "step": 172, "value": 0.6781595974119339, "stage": "fusion", "elapsed_seconds": 26876.273499250412}, {"event_id": "29c354689ca14eb3905020fd1f193bd3", "node_id": "29c354689ca14eb3905020fd1f193bd3", "transition_id": "aa29fcba865e4f4f83530e7e09db10e6", "step": 173, "value": 0.6825491660443117, "stage": "fusion", "elapsed_seconds": 27097.429468154907}, {"event_id": "ac201e98fda441cb921c01a08b8903aa", "node_id": "ac201e98fda441cb921c01a08b8903aa", "transition_id": "e64f1dc6194e4f2db717a6365b20bf28", "step": 174, "value": 0.6665341131360549, "stage": "fusion", "elapsed_seconds": 27235.260571718216}, {"event_id": "101becffa44d4a7b9ddd44ed57ed608b", "node_id": "101becffa44d4a7b9ddd44ed57ed608b", "transition_id": "11f417977538451fa76e44f8bff03698", "step": 175, "value": 0.7066098949594095, "stage": "fusion", "elapsed_seconds": 27486.886933088303}, {"event_id": "c72ea7794c184a09a0c2ff9438d965ce", "node_id": "c72ea7794c184a09a0c2ff9438d965ce", "transition_id": "8e884da618ed47ae8b0975efc83f0c9f", "step": 177, "value": 0.6954999692863771, "stage": "fusion", "elapsed_seconds": 37810.15899562836}, {"event_id": "7f2176f34eac45cdbefc5e27c99d897e", "node_id": "7f2176f34eac45cdbefc5e27c99d897e", "transition_id": "6157591fed25492089f287c83b2298bb", "step": 178, "value": 0.9965288373512359, "stage": "evolution", "elapsed_seconds": 38249.547642469406}, {"event_id": "4ae2641252eb4e28b444c6f9c36d5e2a", "node_id": "4ae2641252eb4e28b444c6f9c36d5e2a", "transition_id": "44f8ce1ae72b4430ae578cb656946806", "step": 179, "value": 0.6745938173975556, "stage": "improve", "elapsed_seconds": 38283.58892440796}, {"event_id": "398ccd257cdf46509937d84d53406a83", "node_id": "398ccd257cdf46509937d84d53406a83", "transition_id": "e3c056c3288148a386031fb8a4913e14", "step": 180, "value": 0.6826743350107836, "stage": "improve", "elapsed_seconds": 38689.378100156784}, {"event_id": "d7ee244b10bb497a9f183ce5b8d14b74", "node_id": "d7ee244b10bb497a9f183ce5b8d14b74", "transition_id": "d357d0e5290445c99a16697860fdc157", "step": 184, "value": 0.5882933967441009, "stage": "debug", "elapsed_seconds": 42053.227380275726}, {"event_id": "f31212da1de34a28a2e13b36826f3e85", "node_id": "f31212da1de34a28a2e13b36826f3e85", "transition_id": "fdf289b161a548df82f2f7b5915064b7", "step": 185, "value": 0.5810865191146881, "stage": "improve", "elapsed_seconds": 42412.61899161339}, {"event_id": "402832f4ee3445c885736c3942eead26", "node_id": "402832f4ee3445c885736c3942eead26", "transition_id": "931431eaeed04735bb0ba39778a5a1f0", "step": 189, "value": 0.6889673433362754, "stage": "evolution", "elapsed_seconds": 42986.96405386925}], "maximize": true, "metric_name": "native public validation metric", "official_score": 0.58546, "valid_submission": true, "medal": "none", "thresholds": {"gold": 0.97908, "silver": 0.76482, "bronze": 0.6921}, "formal_result": false, "full_agent_budget_used": true, "note": "从 2026-09-21 首轮断点续跑；续跑使用独占 A100 80GB，仅补原 12h 剩余时间。 已保存评分来自本次续跑最终提交。 原首轮格式校验任务 ID 有误；续跑已修正。原全局记忆缺失，按保存记录重建；详情见 provenance。", "artifacts": [{"bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/experiments/mlebench-aq04-12h-20260921/continuations/liux-mila-20260924/runs/harry123.aq04-20260921.random-acts-of-pizza", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/experiments/mlebench-aq04-12h-20260921/continuations/liux-mila-20260924/runs/harry123.aq04-20260921.random-acts-of-pizza/live.json", "member": "live.json; immutable metric events and continuation archive index", "files": 1, "bytes": 0}, {"bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/experiments/mlebench-aq04-12h-20260921/continuations/liux-mila-20260924/runs/harry123.aq04-20260921.random-acts-of-pizza/final", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/experiments/mlebench-aq04-12h-20260921/continuations/liux-mila-20260924/runs/harry123.aq04-20260921.random-acts-of-pizza/final/submission-039bf4dd0217a01ff1806abf40c64ae55ea864d49aac732903432a4e6aace0b2.csv", "member": "Sealed final submission.csv; SHA256 039bf4dd0217a01ff1806abf40c64ae55ea864d49aac732903432a4e6aace0b2", "files": 1, "bytes": 34062}, {"bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/experiments/mlebench-aq04-12h-20260921/continuations/liux-mila-20260924/runs/harry123.aq04-20260921.random-acts-of-pizza/artifacts", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/experiments/mlebench-aq04-12h-20260921/continuations/liux-mila-20260924/runs/harry123.aq04-20260921.random-acts-of-pizza/artifacts/logs-b06a2eb947529a36c1901bfba2f5244f2e016e7a73ff3794aeb77aebed2d087b.tar.gz", "member": "experiments/mlebench-aq04-12h-20260921/continuations/liux-mila-20260924/runs/harry123.aq04-20260921.random-acts-of-pizza/artifacts/logs-b06a2eb947529a36c1901bfba2f5244f2e016e7a73ff3794aeb77aebed2d087b.tar.gz", "files": 295, "bytes": 101028227}, {"bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/experiments/mlebench-aq04-12h-20260921/runs/harry123.aq04-20260921.random-acts-of-pizza/artifacts/logs", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/experiments/mlebench-aq04-12h-20260921/runs/harry123.aq04-20260921.random-acts-of-pizza/live.json", "member": "live.json; persisted native/wrapper logs", "files": 157, "bytes": 493101181}], "logs_scope": "完整可用日志、候选代码及提交 CSV 已上传；日志快照时间 2026-09-25T06:12:12.094975+00:00；排除数据集、模型缓存及凭据。", "curve_scope": "保留原始指标点；续跑使用已提交的有效原生观察。仅有原生 active 时间的点参与时间曲线。", "source_grade": {"competition_id": "random-acts-of-pizza", "score": 0.58546, "gold_threshold": 0.97908, "silver_threshold": 0.76482, "bronze_threshold": 0.6921, "median_threshold": 0.5995950000000001, "any_medal": false, "gold_medal": false, "silver_medal": false, "bronze_medal": false, "above_median": false, "submission_exists": true, "valid_submission": true, "is_lower_better": false, "created_at": "2026-09-25T02:07:52.418528", "submission_path": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/runs/aq04-mlebench-lite-20260921-resume-mila-20260924/tasks/random-acts-of-pizza/20260921_003637_AQ04_random-acts-of-pizza/workspace/ensembles_csv/top6ens-total_run_time0.91h.csv"}, "source_wrapper": {"task": "random-acts-of-pizza", "job_id": "22372439", "owner": "harry123", "host": "g10.nibi.sharcnet", "commit": "3a0479c4e597b3515697d776c2768736cea8c4d6", "source_sha256": "efedc394766bff346ee7a3f98737fe3cf912cd3da7c397456e86e844d3c7046b", "started_at": "2026-09-21T04:36:21.852605+00:00", "agent_budget_seconds": 43200, "state": "failed", "workspace_is_node_local": true, "formal_result": false, "gpu": "NVIDIA H100 80GB HBM3", "gpu_uuid": "29022a50-d24d-6ed5-3744-70beb54c2e23", "cpu_ids": [33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108], "grading_port": 32439, "grading_server_id": 27434, "search_started_at": "2026-09-21T04:36:31.240912+00:00", "search_exit_code": -2, "search_finished_at": "2026-09-21T14:52:15.383182+00:00", "fusion_exit_code": 0, "final_submission": "/scratch/harry123/EvolveFold/MLEvolve_BO/runs/aq04-mlebench-lite-20260921/tasks/random-acts-of-pizza/22372439/native/20260921_003637_AQ04_random-acts-of-pizza/final_submission.json", "log_dir": "/scratch/harry123/EvolveFold/MLEvolve_BO/runs/aq04-mlebench-lite-20260921/tasks/random-acts-of-pizza/22372439/native/20260921_003637_AQ04_random-acts-of-pizza", "journal_active_seconds": 27237.30201292038, "full_agent_budget_used": false, "outer_search_timeout_reached": false, "official_grade": "/scratch/harry123/EvolveFold/MLEvolve_BO/runs/aq04-mlebench-lite-20260921/tasks/random-acts-of-pizza/22372439/official-grade.json", "finished_at": "2026-09-21T14:52:20.631851+00:00", "elapsed_seconds": 36958.76670267014}, "score_phase": "continuation-final", "final_submission_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/experiments/mlebench-aq04-12h-20260921/continuations/liux-mila-20260924/runs/harry123.aq04-20260921.random-acts-of-pizza/final/submission-039bf4dd0217a01ff1806abf40c64ae55ea864d49aac732903432a4e6aace0b2.csv", "hardware": "A100 80GB (continuation); H100 80GB (first segment)", "model": "muse-spark-1.3-contributor", "provider": "codex://opencode-go", "scheduler": {"job_id": "10927028", "partition": "main", "observed_at": "2026-09-25T17:05:52.181027+00:00", "allocation": null}, "completed_candidates": 216, "pending_decisions": 3, "remaining_seconds": 0, "continuation_source_status": {"state": "complete", "active_elapsed_seconds": 43209.153702259064, "updated_at": "2026-09-25T06:07:52.543310+00:00", "source_updated_at": "2026-09-21T14:52:20.631851+00:00", "imported_first_run": true, "run_root": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/runs/aq04-mlebench-lite-20260921-resume-mila-20260924/tasks/random-acts-of-pizza/20260921_003637_AQ04_random-acts-of-pizza", "previous_job_id": "22372439", "job_id": "10927028", "attempt": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/runs/aq04-mlebench-lite-20260921-resume-mila-20260924/tasks/random-acts-of-pizza/attempt-03-10927028", "gpu": "NVIDIA A100-SXM4-80GB", "host": "cn-g019.server.mila.quebec", "started_at": "2026-09-24T17:57:20.590956+00:00", "search_pid": 1881381, "attempt_started_epoch": 1790314658.4748812, "search_stopped_epoch": 1790316465.057111, "search_exit_code": 75, "budget_complete": true, "completed_transitions": 216, "release_receipt": {"job_id": "10919451", "state": "COMPLETED", "end": "2026-09-24T15:15:25", "exit_code": "0:0", "end_epoch": 1790277325.0, "verified_at": "2026-09-25T05:30:03.102563+00:00"}, "stop_history": [{"stop_reason": "user_request", "stop_requested_at": "2026-09-24T19:15:09.692440+00:00", "stopped_at": "2026-09-24T19:15:17.721951+00:00", "job_id": "10919451", "active_elapsed_seconds": 41441.326315164566}], "resume_requested_at": "2026-09-25T05:30:03.052522+00:00", "resume_reason": "explicit_user_request", "error": null, "search_finished_at": "2026-09-25T06:07:47.930003+00:00", "finished_at": "2026-09-25T06:07:52.541669+00:00", "submission": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/runs/aq04-mlebench-lite-20260921-resume-mila-20260924/tasks/random-acts-of-pizza/20260921_003637_AQ04_random-acts-of-pizza/workspace/ensembles_csv/top6ens-total_run_time0.91h.csv", "official_grade": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/runs/aq04-mlebench-lite-20260921-resume-mila-20260924/tasks/random-acts-of-pizza/20260921_003637_AQ04_random-acts-of-pizza/logs/official-grade.json", "final_submission_sha256": "039bf4dd0217a01ff1806abf40c64ae55ea864d49aac732903432a4e6aace0b2"}, "config_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/experiments/mlebench-aq04-12h-20260921/continuations/liux-mila-20260924/runs/harry123.aq04-20260921.random-acts-of-pizza/config.yaml"}, {"id": "harry123.aq04-20260921.ranzcr-clip-catheter-line-classification", "experiment_id": "mlebench-aq04-12h-20260921", "family": "MLEBench", "method": "AQ04", "dataset": "ranzcr-clip-catheter-line-classification", "seed": 42, "status": "completed", "source_status": "complete", "wrapper_status": "complete", "source_updated_at": "2026-09-25T08:49:40.931694+00:00", "uploaded_at": "2026-09-25T17:05:53.320034+00:00", "elapsed_seconds": 43202.401245355606, "budget_seconds": 43200, "metrics": [{"event_id": "31d0eac5a8084c0890478ed01b032cc5", "node_id": "31d0eac5a8084c0890478ed01b032cc5", "transition_id": "718c6759213a4c289fa300ab3b13c7a8", "step": 2, "value": 0.8693649819039305, "stage": "draft", "elapsed_seconds": 2337.914084672928}, {"event_id": "31c9517ea6f44ab7bee94b3cc3be4044", "node_id": "31c9517ea6f44ab7bee94b3cc3be4044", "transition_id": "a31f39bf99e14d9da3a8f8b8f3dc6df8", "step": 3, "value": 0.8426358740239972, "stage": "draft", "elapsed_seconds": 3327.530036211014}, {"event_id": "abb547cf40d646c4ba4dc0990f07bda7", "node_id": "abb547cf40d646c4ba4dc0990f07bda7", "transition_id": "dfd71c26df974549a3c50677111029bc", "step": 7, "value": 0.7595996839817043, "stage": "improve", "elapsed_seconds": 5137.158398866653}, {"event_id": "4bf274d048174c86848ca71822a5a0cb", "node_id": "4bf274d048174c86848ca71822a5a0cb", "transition_id": "44f81a131fbf48abb6436ed5b756f459", "step": 9, "value": 0.8598558751318418, "stage": "improve", "elapsed_seconds": 8769.21480178833}, {"event_id": "6f9eaed40b9e4940a564d554083e4b8b", "node_id": "6f9eaed40b9e4940a564d554083e4b8b", "transition_id": "7441e7135d954d9b8ee121d254e3ea21", "step": 11, "value": 0.8076425761729363, "stage": "improve", "elapsed_seconds": 9906.182265520096}, {"event_id": "6dfccdb60a5344c7bc88afd94fc09f6c", "node_id": "6dfccdb60a5344c7bc88afd94fc09f6c", "transition_id": "46655c13b16b45108dce6dbd3cc82716", "step": 12, "value": 0.8561454769161396, "stage": "improve", "elapsed_seconds": 11734.62534403801}, {"event_id": "5ee13d60c7a74d17ac06e24520dbb16e", "node_id": "5ee13d60c7a74d17ac06e24520dbb16e", "transition_id": "7af0b34f8f8a49e48e29c080c708664c", "step": 14, "value": 0.8534554346653835, "stage": "debug", "elapsed_seconds": 12290.200774669647}, {"event_id": "544b7358ae1d4a9283cc84682b4fd3c8", "node_id": "544b7358ae1d4a9283cc84682b4fd3c8", "transition_id": "7b1714366b78479db650d567c6ea8ca3", "step": 16, "value": 0.8337536317034132, "stage": "debug", "elapsed_seconds": 14621.467616558075}, {"event_id": "43b2cec399ac436d8d21530eabf3dab2", "node_id": "43b2cec399ac436d8d21530eabf3dab2", "transition_id": "ea0142b35a5a4d52b4b044019327ba8c", "step": 19, "value": 0.9051117766742257, "stage": "debug", "elapsed_seconds": 20156.170156002045}, {"event_id": "78fa4d321fec4c9b80a59faec1be9018", "node_id": "78fa4d321fec4c9b80a59faec1be9018", "transition_id": "a52704407e1548cdb1dede16c384dfcb", "step": 21, "value": 0.8451650077188809, "stage": "evolution", "elapsed_seconds": 22786.81841659546}, {"event_id": "bed4111be5ac4ad684fc3a029fa3c2e7", "node_id": "bed4111be5ac4ad684fc3a029fa3c2e7", "transition_id": "5ebfd0c4fe0a45dbbebd5b7e9d421b21", "step": 23, "value": 0.8644092165558825, "stage": "debug", "elapsed_seconds": 24714.8622944355}, {"event_id": "12414e23a08f4f42acb47708fa620ae3", "node_id": "12414e23a08f4f42acb47708fa620ae3", "transition_id": "f7efff7c832348babc5d4fadece8e3f8", "step": 25, "value": 0.8102091907005772, "stage": "debug", "elapsed_seconds": 26027.584914445877}, {"event_id": "38daee33889247b99478294fabebf2b2", "node_id": "38daee33889247b99478294fabebf2b2", "transition_id": "482a3fb2eb984124a2c71a2783d87715", "step": 27, "value": 0.8676, "stage": "debug", "elapsed_seconds": 27097.451078653336}, {"event_id": "818ed617cef643adbaf765269bcfb0f0", "node_id": "818ed617cef643adbaf765269bcfb0f0", "transition_id": "24c5576fb95048a99c5abf593febe4fe", "step": 35, "value": 0.8391, "stage": "debug", "elapsed_seconds": 36874.18313193321}], "maximize": true, "metric_name": "native public validation metric", "official_score": 0.88141, "valid_submission": true, "medal": "none", "thresholds": {"gold": 0.97357, "silver": 0.97152, "bronze": 0.9709}, "formal_result": false, "full_agent_budget_used": true, "note": "从 2026-09-21 首轮断点续跑；续跑使用独占 A100 80GB，仅补原 12h 剩余时间。 已保存评分来自本次续跑最终提交。 原首轮格式校验任务 ID 有误；续跑已修正。原全局记忆缺失，按保存记录重建；详情见 provenance。", "artifacts": [{"bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/experiments/mlebench-aq04-12h-20260921/continuations/liux-mila-20260924/runs/harry123.aq04-20260921.ranzcr-clip-catheter-line-classification", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/experiments/mlebench-aq04-12h-20260921/continuations/liux-mila-20260924/runs/harry123.aq04-20260921.ranzcr-clip-catheter-line-classification/live.json", "member": "live.json; immutable metric events and continuation archive index", "files": 1, "bytes": 0}, {"bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/experiments/mlebench-aq04-12h-20260921/continuations/liux-mila-20260924/runs/harry123.aq04-20260921.ranzcr-clip-catheter-line-classification/final", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/experiments/mlebench-aq04-12h-20260921/continuations/liux-mila-20260924/runs/harry123.aq04-20260921.ranzcr-clip-catheter-line-classification/final/submission-6f2e937ca0da4ca5982ebc63499c3e6a4f891615f6c21c00f7d1e3a45e0560d9.csv", "member": "Sealed final submission.csv; SHA256 6f2e937ca0da4ca5982ebc63499c3e6a4f891615f6c21c00f7d1e3a45e0560d9", "files": 1, "bytes": 747298}, {"bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/experiments/mlebench-aq04-12h-20260921/continuations/liux-mila-20260924/runs/harry123.aq04-20260921.ranzcr-clip-catheter-line-classification/artifacts", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/experiments/mlebench-aq04-12h-20260921/continuations/liux-mila-20260924/runs/harry123.aq04-20260921.ranzcr-clip-catheter-line-classification/artifacts/logs-a79aa64b638d818d359910de1ece3dd929211fbef77c7cdbb80a5ca8f5709c2b.tar.gz", "member": "experiments/mlebench-aq04-12h-20260921/continuations/liux-mila-20260924/runs/harry123.aq04-20260921.ranzcr-clip-catheter-line-classification/artifacts/logs-a79aa64b638d818d359910de1ece3dd929211fbef77c7cdbb80a5ca8f5709c2b.tar.gz", "files": 152, "bytes": 18153986}, {"bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/experiments/mlebench-aq04-12h-20260921/runs/harry123.aq04-20260921.ranzcr-clip-catheter-line-classification/artifacts/logs", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/experiments/mlebench-aq04-12h-20260921/runs/harry123.aq04-20260921.ranzcr-clip-catheter-line-classification/live.json", "member": "live.json; persisted native/wrapper logs", "files": 42, "bytes": 32431369}], "logs_scope": "完整可用日志、候选代码及提交 CSV 已上传；日志快照时间 2026-09-25T08:58:54.821190+00:00；排除数据集、模型缓存及凭据。", "curve_scope": "保留原始指标点；续跑使用已提交的有效原生观察。仅有原生 active 时间的点参与时间曲线。", "source_grade": {"competition_id": "ranzcr-clip-catheter-line-classification", "score": 0.88141, "gold_threshold": 0.97357, "silver_threshold": 0.97152, "bronze_threshold": 0.9709, "median_threshold": 0.9675, "any_medal": false, "gold_medal": false, "silver_medal": false, "bronze_medal": false, "above_median": false, "submission_exists": true, "valid_submission": true, "is_lower_better": false, "created_at": "2026-09-25T04:49:40.800908", "submission_path": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/runs/aq04-mlebench-lite-20260921-resume-mila-20260924/tasks/ranzcr-clip-catheter-line-classification/20260921_003258_AQ04_ranzcr-clip-catheter-line-classification/workspace/ensembles_csv/top6ens-total_run_time5.16h.csv"}, "source_wrapper": {"task": "ranzcr-clip-catheter-line-classification", "job_id": "22372434", "owner": "harry123", "host": "g17.nibi.sharcnet", "commit": "3a0479c4e597b3515697d776c2768736cea8c4d6", "source_sha256": "efedc394766bff346ee7a3f98737fe3cf912cd3da7c397456e86e844d3c7046b", "started_at": "2026-09-21T04:32:12.843389+00:00", "agent_budget_seconds": 43200, "state": "failed", "workspace_is_node_local": true, "formal_result": false, "gpu": "NVIDIA H100 80GB HBM3", "gpu_uuid": "c01e30d0-bdb2-9c87-91b7-a87daf8bab8f", "cpu_ids": [72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90, 91, 92], "grading_port": 32434, "grading_server_id": 27429, "search_started_at": "2026-09-21T04:32:43.195822+00:00", "search_exit_code": 1, "search_finished_at": "2026-09-21T12:05:50.066061+00:00", "fusion_exit_code": 0, "final_submission": "/scratch/harry123/EvolveFold/MLEvolve_BO/runs/aq04-mlebench-lite-20260921/tasks/ranzcr-clip-catheter-line-classification/22372434/native/20260921_003258_AQ04_ranzcr-clip-catheter-line-classification/final_submission.json", "log_dir": "/scratch/harry123/EvolveFold/MLEvolve_BO/runs/aq04-mlebench-lite-20260921/tasks/ranzcr-clip-catheter-line-classification/22372434/native/20260921_003258_AQ04_ranzcr-clip-catheter-line-classification", "journal_active_seconds": 27098.111396312714, "full_agent_budget_used": false, "outer_search_timeout_reached": false, "official_grade": "/scratch/harry123/EvolveFold/MLEvolve_BO/runs/aq04-mlebench-lite-20260921/tasks/ranzcr-clip-catheter-line-classification/22372434/official-grade.json", "finished_at": "2026-09-21T12:05:56.529505+00:00", "elapsed_seconds": 27223.677676087245}, "score_phase": "continuation-final", "final_submission_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/experiments/mlebench-aq04-12h-20260921/continuations/liux-mila-20260924/runs/harry123.aq04-20260921.ranzcr-clip-catheter-line-classification/final/submission-6f2e937ca0da4ca5982ebc63499c3e6a4f891615f6c21c00f7d1e3a45e0560d9.csv", "hardware": "A100 80GB (continuation); H100 80GB (first segment)", "model": "muse-spark-1.3-contributor", "provider": "codex://opencode-go", "scheduler": {"job_id": "10927555", "partition": "short-unkillable", "observed_at": "2026-09-25T17:05:53.320059+00:00", "allocation": null}, "completed_candidates": 37, "pending_decisions": 3, "remaining_seconds": 0, "continuation_source_status": {"state": "complete", "active_elapsed_seconds": 43202.401245355606, "updated_at": "2026-09-25T08:49:40.931694+00:00", "source_updated_at": "2026-09-21T12:05:56.529505+00:00", "imported_first_run": true, "run_root": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/runs/aq04-mlebench-lite-20260921-resume-mila-20260924/tasks/ranzcr-clip-catheter-line-classification/20260921_003258_AQ04_ranzcr-clip-catheter-line-classification", "previous_job_id": "22372434", "job_id": "10927555", "attempt": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/runs/aq04-mlebench-lite-20260921-resume-mila-20260924/tasks/ranzcr-clip-catheter-line-classification/attempt-04-10927555", "gpu": "NVIDIA A100-SXM4-80GB", "host": "cn-g008.server.mila.quebec", "started_at": "2026-09-24T17:57:18.717072+00:00", "search_pid": 235128, "attempt_started_epoch": 1790324729.1032274, "search_stopped_epoch": 1790326173.9460003, "search_exit_code": 75, "budget_complete": true, "completed_transitions": 37, "release_receipt": {"job_id": "10927029", "state": "COMPLETED", "end": "2026-09-25T04:24:35", "exit_code": "0:0", "end_epoch": 1790324675.0, "verified_at": "2026-09-25T08:25:00.641637+00:00"}, "stop_history": [{"stop_reason": "user_request", "stop_requested_at": "2026-09-24T19:15:09.692440+00:00", "stopped_at": "2026-09-24T19:15:12.546155+00:00", "job_id": "10919452", "active_elapsed_seconds": 31663.870396375656}], "resume_requested_at": "2026-09-25T05:30:03.052522+00:00", "resume_reason": "explicit_user_request", "error": null, "search_finished_at": "2026-09-25T08:49:36.054111+00:00", "finished_at": "2026-09-25T08:49:40.928589+00:00", "submission": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/runs/aq04-mlebench-lite-20260921-resume-mila-20260924/tasks/ranzcr-clip-catheter-line-classification/20260921_003258_AQ04_ranzcr-clip-catheter-line-classification/workspace/ensembles_csv/top6ens-total_run_time5.16h.csv", "official_grade": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/runs/aq04-mlebench-lite-20260921-resume-mila-20260924/tasks/ranzcr-clip-catheter-line-classification/20260921_003258_AQ04_ranzcr-clip-catheter-line-classification/logs/official-grade.json", "final_submission_sha256": "6f2e937ca0da4ca5982ebc63499c3e6a4f891615f6c21c00f7d1e3a45e0560d9"}, "config_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/experiments/mlebench-aq04-12h-20260921/continuations/liux-mila-20260924/runs/harry123.aq04-20260921.ranzcr-clip-catheter-line-classification/config.yaml"}, {"id": "harry123.aq04-20260921.siim-isic-melanoma-classification", "experiment_id": "mlebench-aq04-12h-20260921", "family": "MLEBench", "method": "AQ04", "dataset": "siim-isic-melanoma-classification", "seed": 42, "status": "completed", "source_status": "complete", "wrapper_status": "complete", "source_updated_at": "2026-09-24T18:19:54.410806+00:00", "uploaded_at": "2026-09-25T17:05:50.973526+00:00", "elapsed_seconds": 43206.7769408226, "budget_seconds": 43200, "metrics": [{"event_id": "c247676f39214f5b8d29cf0663f2ef42", "node_id": "c247676f39214f5b8d29cf0663f2ef42", "transition_id": "71d34a71339b46508afed4ae32ed35bc", "step": 5, "value": 0.8582185969377916, "stage": "debug", "elapsed_seconds": 5866.564488172531}, {"event_id": "dbbfb0c8f98945268bfb1e7679c8536a", "node_id": "dbbfb0c8f98945268bfb1e7679c8536a", "transition_id": "c6ff598970bc4f4f8f6ef55342aa5c16", "step": 6, "value": 0.9328175675675676, "stage": "debug", "elapsed_seconds": 7021.533565759659}, {"event_id": "7554289b2a2a4ed48c3282a81704d857", "node_id": "7554289b2a2a4ed48c3282a81704d857", "transition_id": "a2993cd2f6d94d1382d3a0c7689b1b37", "step": 7, "value": 0.9170945945945945, "stage": "draft", "elapsed_seconds": 8562.528449058533}, {"event_id": "5c5e5984affb4bc8a13956f30420855c", "node_id": "5c5e5984affb4bc8a13956f30420855c", "transition_id": "a0e297e58f1f4fb59be0f251d2314527", "step": 8, "value": 0.9324847972972974, "stage": "improve", "elapsed_seconds": 12858.039629936218}, {"event_id": "0705f98943a24613b0c299d8f1a6e30f", "node_id": "0705f98943a24613b0c299d8f1a6e30f", "transition_id": "e41a23aad7df4f9c8b1e2cec32cb32b3", "step": 9, "value": 0.8973108108108108, "stage": "improve", "elapsed_seconds": 16288.685093641281}, {"event_id": "ec64c0203e8e46e6ab9ff9b10a0545e6", "node_id": "ec64c0203e8e46e6ab9ff9b10a0545e6", "transition_id": "d4fbfd5cd38f491b8eda00abb850e457", "step": 10, "value": 0.9488310810810812, "stage": "improve", "elapsed_seconds": 16911.66443681717}, {"event_id": "a2beb17c95d649cf89d1611c9add6ebd", "node_id": "a2beb17c95d649cf89d1611c9add6ebd", "transition_id": "439d13f366194130bfbeb03e70a80f65", "step": 12, "value": 0.8627510789954387, "stage": "improve", "elapsed_seconds": 20764.257603168488}, {"event_id": "04e6bb64fd6a43729a733dfbd4ebfcb1", "node_id": "04e6bb64fd6a43729a733dfbd4ebfcb1", "transition_id": "788dfaab0116479193dc35404a5ab9ca", "step": 13, "value": 0.9290692567567569, "stage": "debug", "elapsed_seconds": 25331.732031822205}, {"event_id": "b0f63d62cce04948acbb67e1f8926304", "node_id": "b0f63d62cce04948acbb67e1f8926304", "transition_id": "09495ba59d2f44f9885b7c77dcdd6ae0", "step": 14, "value": 0.9463614864864864, "stage": "improve", "elapsed_seconds": 26330.911470890045}, {"event_id": "62f869bf9200459282337b021f4b5dfb", "node_id": "62f869bf9200459282337b021f4b5dfb", "transition_id": "0b506192d2fb4535a53301b415b4b2e0", "step": 15, "value": 0.9322195945945946, "stage": "improve", "elapsed_seconds": 28604.695251464844}, {"event_id": "2ae6743649714afd8ca7f27749e9cae7", "node_id": "2ae6743649714afd8ca7f27749e9cae7", "transition_id": "5deaa53d1e5b4d6897f90c2cb9fa9be4", "step": 16, "value": 0.9174138513513513, "stage": "improve", "elapsed_seconds": 29559.116199970245}, {"event_id": "fe2c42354a674245978b5eb796474a44", "node_id": "fe2c42354a674245978b5eb796474a44", "transition_id": "2a77ce6ce82b4f12a8fb0b93e30cace1", "step": 19, "value": 0.9275827702702704, "stage": "fusion", "elapsed_seconds": 35404.084725141525}, {"event_id": "b3360007da814bf1a22fbcf903252f48", "node_id": "b3360007da814bf1a22fbcf903252f48", "transition_id": "08a88ac1259a418ba27a36b3006bad85", "step": 20, "value": 0.9195084459459459, "stage": "improve", "elapsed_seconds": 36608.72508740425}, {"event_id": "67e24ae8354846e48f7baa0585a2b4ea", "node_id": "67e24ae8354846e48f7baa0585a2b4ea", "transition_id": "99d6a231cb914629ad486d8dbbfe4023", "step": 21, "value": 0.9391621621621622, "stage": "debug", "elapsed_seconds": 41786.80153155327}], "maximize": true, "metric_name": "native public validation metric", "official_score": 0.91188, "valid_submission": true, "medal": "none", "thresholds": {"gold": 0.9455, "silver": 0.9401, "bronze": 0.937}, "formal_result": false, "full_agent_budget_used": true, "note": "从 2026-09-21 首轮断点续跑；续跑使用独占 A100 80GB，仅补原 12h 剩余时间。 已保存评分来自本次续跑最终提交。 原首轮格式校验任务 ID 有误；续跑已修正。原全局记忆缺失，按保存记录重建；详情见 provenance。", "artifacts": [{"bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/experiments/mlebench-aq04-12h-20260921/continuations/liux-mila-20260924/runs/harry123.aq04-20260921.siim-isic-melanoma-classification", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/experiments/mlebench-aq04-12h-20260921/continuations/liux-mila-20260924/runs/harry123.aq04-20260921.siim-isic-melanoma-classification/live.json", "member": "live.json; immutable metric events and continuation archive index", "files": 1, "bytes": 0}, {"bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/experiments/mlebench-aq04-12h-20260921/continuations/liux-mila-20260924/runs/harry123.aq04-20260921.siim-isic-melanoma-classification/final", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/experiments/mlebench-aq04-12h-20260921/continuations/liux-mila-20260924/runs/harry123.aq04-20260921.siim-isic-melanoma-classification/final/submission-713415370d4dc1383aadf35aefc8bb2cd9150be181392da294a39cac06aa3775.csv", "member": "Sealed final submission.csv; SHA256 713415370d4dc1383aadf35aefc8bb2cd9150be181392da294a39cac06aa3775", "files": 1, "bytes": 135620}, {"bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/experiments/mlebench-aq04-12h-20260921/continuations/liux-mila-20260924/runs/harry123.aq04-20260921.siim-isic-melanoma-classification/artifacts", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/experiments/mlebench-aq04-12h-20260921/continuations/liux-mila-20260924/runs/harry123.aq04-20260921.siim-isic-melanoma-classification/artifacts/logs-9e8c65a1fb07710673975bbaaed8ce53c332cfed2befe8370af98fd3dafda06f.tar.gz", "member": "experiments/mlebench-aq04-12h-20260921/continuations/liux-mila-20260924/runs/harry123.aq04-20260921.siim-isic-melanoma-classification/artifacts/logs-9e8c65a1fb07710673975bbaaed8ce53c332cfed2befe8370af98fd3dafda06f.tar.gz", "files": 130, "bytes": 7753404}, {"bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/experiments/mlebench-aq04-12h-20260921/runs/harry123.aq04-20260921.siim-isic-melanoma-classification/artifacts/logs", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/experiments/mlebench-aq04-12h-20260921/runs/harry123.aq04-20260921.siim-isic-melanoma-classification/live.json", "member": "live.json; persisted native/wrapper logs", "files": 41, "bytes": 20669028}], "logs_scope": "完整可用日志、候选代码及提交 CSV 已上传；日志快照时间 2026-09-24T18:21:13.811994+00:00；排除数据集、模型缓存及凭据。", "curve_scope": "保留原始指标点；续跑使用已提交的有效原生观察。仅有原生 active 时间的点参与时间曲线。", "source_grade": {"competition_id": "siim-isic-melanoma-classification", "score": 0.91188, "gold_threshold": 0.9455, "silver_threshold": 0.9401, "bronze_threshold": 0.937, "median_threshold": 0.9128, "any_medal": false, "gold_medal": false, "silver_medal": false, "bronze_medal": false, "above_median": false, "submission_exists": true, "valid_submission": true, "is_lower_better": false, "created_at": "2026-09-24T14:19:54.273739", "submission_path": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/runs/aq04-mlebench-lite-20260921-resume-mila-20260924/tasks/siim-isic-melanoma-classification/20260921_003709_AQ04_siim-isic-melanoma-classification/workspace/ensembles_csv/top4ens-total_run_time8.55h.csv"}, "source_wrapper": {"task": "siim-isic-melanoma-classification", "job_id": "22372440", "owner": "harry123", "host": "g26.nibi.sharcnet", "commit": "3a0479c4e597b3515697d776c2768736cea8c4d6", "source_sha256": "efedc394766bff346ee7a3f98737fe3cf912cd3da7c397456e86e844d3c7046b", "started_at": "2026-09-21T04:36:23.395689+00:00", "agent_budget_seconds": 43200, "state": "failed", "workspace_is_node_local": true, "formal_result": false, "gpu": "NVIDIA H100 80GB HBM3", "gpu_uuid": "f72a8abf-3efe-f284-aa6a-4bc2757cc88c", "cpu_ids": [72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86, 87, 92, 93, 94, 95, 96], "grading_port": 32440, "grading_server_id": 27435, "search_started_at": "2026-09-21T04:36:54.500483+00:00", "search_exit_code": 1, "search_finished_at": "2026-09-21T16:14:49.591512+00:00", "fusion_exit_code": 0, "final_submission": "/scratch/harry123/EvolveFold/MLEvolve_BO/runs/aq04-mlebench-lite-20260921/tasks/siim-isic-melanoma-classification/22372440/native/20260921_003709_AQ04_siim-isic-melanoma-classification/final_submission.json", "log_dir": "/scratch/harry123/EvolveFold/MLEvolve_BO/runs/aq04-mlebench-lite-20260921/tasks/siim-isic-melanoma-classification/22372440/native/20260921_003709_AQ04_siim-isic-melanoma-classification", "journal_active_seconds": 41787.30876207352, "full_agent_budget_used": false, "outer_search_timeout_reached": false, "official_grade": "/scratch/harry123/EvolveFold/MLEvolve_BO/runs/aq04-mlebench-lite-20260921/tasks/siim-isic-melanoma-classification/22372440/official-grade.json", "finished_at": "2026-09-21T16:14:54.919728+00:00", "elapsed_seconds": 41911.50937386416}, "score_phase": "continuation-final", "final_submission_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/experiments/mlebench-aq04-12h-20260921/continuations/liux-mila-20260924/runs/harry123.aq04-20260921.siim-isic-melanoma-classification/final/submission-713415370d4dc1383aadf35aefc8bb2cd9150be181392da294a39cac06aa3775.csv", "hardware": "A100 80GB (continuation); H100 80GB (first segment)", "model": "muse-spark-1.3-contributor", "provider": "codex://opencode-go", "scheduler": {"job_id": "10919450", "partition": "unkillable", "observed_at": "2026-09-25T17:05:50.973923+00:00", "allocation": null}, "completed_candidates": 23, "pending_decisions": 3, "remaining_seconds": 0, "continuation_source_status": {"state": "complete", "active_elapsed_seconds": 43206.7769408226, "updated_at": "2026-09-24T18:19:54.410806+00:00", "source_updated_at": "2026-09-21T16:14:54.919728+00:00", "imported_first_run": true, "run_root": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/runs/aq04-mlebench-lite-20260921-resume-mila-20260924/tasks/siim-isic-melanoma-classification/20260921_003709_AQ04_siim-isic-melanoma-classification", "previous_job_id": "22372440", "job_id": "10919450", "attempt": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/runs/aq04-mlebench-lite-20260921-resume-mila-20260924/tasks/siim-isic-melanoma-classification/attempt-02-10919450", "gpu": "NVIDIA A100-SXM4-80GB", "host": "cn-g017.server.mila.quebec", "started_at": "2026-09-24T17:54:16.140336+00:00", "search_pid": 1329308, "attempt_started_epoch": 1790273176.3408701, "search_stopped_epoch": 1790273982.9927173, "search_exit_code": 75, "budget_complete": true, "completed_transitions": 23, "release_receipt": {"job_id": "10919298", "state": "COMPLETED", "end": "2026-09-24T14:05:32", "exit_code": "0:0", "end_epoch": 1790273132.0, "verified_at": "2026-09-24T18:05:50.138475+00:00"}, "search_finished_at": "2026-09-24T18:19:45.066999+00:00", "finished_at": "2026-09-24T18:19:54.408522+00:00", "submission": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/runs/aq04-mlebench-lite-20260921-resume-mila-20260924/tasks/siim-isic-melanoma-classification/20260921_003709_AQ04_siim-isic-melanoma-classification/workspace/ensembles_csv/top4ens-total_run_time8.55h.csv", "official_grade": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/runs/aq04-mlebench-lite-20260921-resume-mila-20260924/tasks/siim-isic-melanoma-classification/20260921_003709_AQ04_siim-isic-melanoma-classification/logs/official-grade.json", "final_submission_sha256": "713415370d4dc1383aadf35aefc8bb2cd9150be181392da294a39cac06aa3775"}, "config_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/experiments/mlebench-aq04-12h-20260921/continuations/liux-mila-20260924/runs/harry123.aq04-20260921.siim-isic-melanoma-classification/config.yaml"}, {"id": "harry123.aq04-20260921.tabular-playground-series-may-2022", "experiment_id": "mlebench-aq04-12h-20260921", "family": "MLEBench", "method": "AQ04", "dataset": "tabular-playground-series-may-2022", "seed": 42, "status": "completed", "source_status": "completed", "wrapper_status": "completed", "source_updated_at": "2026-09-21T16:37:25.416673+00:00", "uploaded_at": "2026-09-22T04:52:49.916898+00:00", "elapsed_seconds": 42668.98822712898, "budget_seconds": 43200.0, "metrics": [{"event_id": "f5f87d15b77c4c9a9eba213683d4751a", "step": 1, "value": 0.9656721786654808, "stage": "draft"}, {"event_id": "fa30d97be1f94ed6836c9f93ff54a3a1", "step": 3, "value": 0.8254046020702492, "stage": "debug"}, {"event_id": "1121c9d0e184426da409876e606bfd18", "step": 4, "value": 0.9914560615452683, "stage": "draft"}, {"event_id": "f7a66e43f37143ecaeab62d8562e1dd5", "step": 7, "value": 0.8351198275053575, "stage": "improve"}, {"event_id": "f6ecc6fd06b64d598eb28542c6cb97b9", "step": 8, "value": 0.9641611889232462, "stage": "debug"}, {"event_id": "3d924ce63ae1495d9de5a455ed0b8f85", "step": 9, "value": 0.992026683136927, "stage": "improve"}, {"event_id": "35c2055d63584aac8989c2491e0f6139", "step": 10, "value": 0.8493787739474259, "stage": "improve"}, {"event_id": "6467b23adf984bd3b8e2638049ec26a0", "step": 12, "value": 0.972459428671621, "stage": "debug"}, {"event_id": "da5afa2021d942d79bd2db223c047211", "step": 14, "value": 0.9917556723957011, "stage": "improve"}, {"event_id": "8b3e6839831f43c9ab4d279e76d622af", "step": 15, "value": 0.9916523887071722, "stage": "improve"}, {"event_id": "8accd579403748b1b586c8c0ba9a5b45", "step": 16, "value": 0.9916067033555809, "stage": "debug"}, {"event_id": "b7f6a2b2a23243e6a80cc2a0be2889ce", "step": 19, "value": 0.9667703862683965, "stage": "improve"}, {"event_id": "ea01c07e9a1a45e8bf43d311054db003", "step": 20, "value": 0.9919096973118591, "stage": "improve"}, {"event_id": "21d62db31321448997a25153523389d0", "step": 21, "value": 0.9917297844493929, "stage": "debug"}, {"event_id": "3ad44700a28b4ff79751884c5dbbbe0b", "step": 23, "value": 0.991752194409758, "stage": "improve"}, {"event_id": "122eed24a3fe42f79120338cf7a866ab", "step": 24, "value": 0.9917582790087159, "stage": "debug"}, {"event_id": "248fb7ed5f03455892f15d427b85d6cc", "step": 25, "value": 0.9919589878981221, "stage": "evolution"}, {"event_id": "7055eac8ae3e4fb19ab8fdc4168a408a", "step": 26, "value": 0.9911195904637711, "stage": "evolution"}, {"event_id": "fdd55225ddfd48cb91b8630911ce28da", "step": 28, "value": 0.9916253788828786, "stage": "improve"}, {"event_id": "8f094fb5e9a44f99b0a4557f5eaa79b0", "step": 29, "value": 0.991885304846853, "stage": "fusion"}, {"event_id": "e64434af798140a5aa457c6e2fa155d9", "step": 32, "value": 0.990991707154691, "stage": "improve"}, {"event_id": "77691528584a4783be1a2952e99865f8", "step": 34, "value": 0.9779052896098879, "stage": "fusion_draft"}, {"event_id": "5e9046331e22407d8da77dee719029da", "step": 35, "value": 0.9940493382150833, "stage": "evolution"}, {"event_id": "d7b6d288431b4086bd076916c5c7a5bb", "step": 36, "value": 0.9919566421105972, "stage": "improve"}, {"event_id": "ed4e3c414e5b4584ae433ff032be9381", "step": 37, "value": 0.9914785963672367, "stage": "debug"}, {"event_id": "15d58bd4bc3e4ec583658706fd19780e", "step": 38, "value": 0.9875156856540814, "stage": "improve"}, {"event_id": "867e3258486e46bebaea7dfd93bbfbfc", "step": 39, "value": 0.9870551407127104, "stage": "improve"}, {"event_id": "746ec2c962f9475085e91254c15c611f", "step": 40, "value": 0.9915140024111245, "stage": "improve"}, {"event_id": "5f05a61b9dcb4930b223a121ab48dc78", "step": 41, "value": 0.988535353030325, "stage": "improve"}, {"event_id": "fbcb3323ff344cd6925e70552ff9827d", "step": 42, "value": 0.986538042397067, "stage": "improve"}, {"event_id": "3536dd022dcc46ffbd22be7b3e417525", "step": 43, "value": 0.9936038711435705, "stage": "improve"}, {"event_id": "ccffd03ac4aa48a4a8f8279f63fa1d42", "step": 44, "value": 0.9889091028226804, "stage": "improve"}, {"event_id": "11838610a83e4be8a0b5b7af4843c326", "step": 45, "value": 0.994070865387496, "stage": "evolution"}, {"event_id": "3378b95b2ed54e6396ac8b01e279fa33", "step": 46, "value": 0.9936935605186902, "stage": "improve"}, {"event_id": "d265eae4e45a45d19ebe2ccb747c3da6", "step": 48, "value": 0.9888233902969261, "stage": "improve"}, {"event_id": "f7c676b0f73e408699509dad470627db", "step": 49, "value": 0.98879720383991, "stage": "improve"}], "maximize": true, "metric_name": "native public validation metric", "official_score": 0.99409, "valid_submission": true, "medal": "none", "thresholds": {"gold": 0.99823, "silver": 0.99822, "bronze": 0.99818}, "formal_result": true, "full_agent_budget_used": false, "note": "", "artifacts": [{"bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/experiments/mlebench-aq04-12h-20260921/runs/harry123.aq04-20260921.tabular-playground-series-may-2022/artifacts/logs", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/experiments/mlebench-aq04-12h-20260921/runs/harry123.aq04-20260921.tabular-playground-series-may-2022/live.json", "member": "live.json; persisted native/wrapper logs", "files": 63, "bytes": 75138406}], "logs_scope": "已存在 persisted wrapper/native logs；原上传者排除了 node-local workspaces、datasets、submissions、checkpoints。", "curve_scope": "上传者 live.json 验证指标；官方 grade 为另一条证据。", "source_grade": {"competition_id": "tabular-playground-series-may-2022", "score": 0.99409, "gold_threshold": 0.99823, "silver_threshold": 0.99822, "bronze_threshold": 0.99818, "median_threshold": 0.972675, "any_medal": false, "gold_medal": false, "silver_medal": false, "bronze_medal": false, "above_median": true, "submission_exists": true, "valid_submission": true, "is_lower_better": false, "created_at": "2026-09-21T12:37:01.361353", "submission_path": "/scratch/harry123/EvolveFold/MLEvolve_BO/runs/aq04-mlebench-lite-20260921/tasks/tabular-playground-series-may-2022/22372441/submission.csv"}, "source_wrapper": {"task": "tabular-playground-series-may-2022", "job_id": "22372441", "owner": "harry123", "host": "g26.nibi.sharcnet", "commit": "3a0479c4e597b3515697d776c2768736cea8c4d6", "source_sha256": "efedc394766bff346ee7a3f98737fe3cf912cd3da7c397456e86e844d3c7046b", "started_at": "2026-09-21T04:36:23.387969+00:00", "agent_budget_seconds": 43200, "state": "completed", "workspace_is_node_local": true, "formal_result": true, "gpu": "NVIDIA H100 80GB HBM3", "gpu_uuid": "25209aa2-e883-f363-9572-89833dcd93b6", "cpu_ids": [4, 5, 10, 11, 12, 13, 14, 15, 19, 21, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107], "grading_port": 32441, "grading_server_id": 27436, "search_started_at": "2026-09-21T04:36:54.713931+00:00", "search_exit_code": 124, "search_finished_at": "2026-09-21T16:36:55.111666+00:00", "fusion_exit_code": 0, "final_submission": "/scratch/harry123/EvolveFold/MLEvolve_BO/runs/aq04-mlebench-lite-20260921/tasks/tabular-playground-series-may-2022/22372441/native/20260921_003709_AQ04_tabular-playground-series-may-2022/final_submission.json", "log_dir": "/scratch/harry123/EvolveFold/MLEvolve_BO/runs/aq04-mlebench-lite-20260921/tasks/tabular-playground-series-may-2022/22372441/native/20260921_003709_AQ04_tabular-playground-series-may-2022", "journal_active_seconds": 42668.98822712898, "full_agent_budget_used": false, "outer_search_timeout_reached": true, "official_grade": "/scratch/harry123/EvolveFold/MLEvolve_BO/runs/aq04-mlebench-lite-20260921/tasks/tabular-playground-series-may-2022/22372441/official-grade.json", "finished_at": "2026-09-21T16:37:25.409244+00:00", "elapsed_seconds": 43262.00971622998}}, {"id": "harry123.aq04-20260921.text-normalization-challenge-english-language", "experiment_id": "mlebench-aq04-12h-20260921", "family": "MLEBench", "method": "AQ04", "dataset": "text-normalization-challenge-english-language", "seed": 42, "status": "completed", "source_status": "complete", "wrapper_status": "complete", "source_updated_at": "2026-09-25T09:46:01.791618+00:00", "uploaded_at": "2026-09-25T17:05:53.413284+00:00", "elapsed_seconds": 43201.53254914284, "budget_seconds": 43200, "metrics": [{"event_id": "1d7d6793567641d4b8210537b635ceac", "node_id": "1d7d6793567641d4b8210537b635ceac", "transition_id": "0169327def5145ae9018852fee5179f0", "step": 2, "value": 0.9598352792006328, "stage": "draft", "elapsed_seconds": 1294.8919234275818}, {"event_id": "66ec7cb817764206bc615715e26be6a0", "node_id": "66ec7cb817764206bc615715e26be6a0", "transition_id": "367d6aba7cf6447bae6328385ba39d59", "step": 3, "value": 0.9854613703848956, "stage": "debug", "elapsed_seconds": 1310.9363858699799}, {"event_id": "52f28363e32845b58e2e17da8b16dab6", "node_id": "52f28363e32845b58e2e17da8b16dab6", "transition_id": "8fd2e1a3619b4420a4b88f9826d93c01", "step": 4, "value": 0.9867931620670889, "stage": "draft", "elapsed_seconds": 1906.882798910141}, {"event_id": "9f78bf664db84031a68f3b05f8e906d3", "node_id": "9f78bf664db84031a68f3b05f8e906d3", "transition_id": "ab14b2ff376c413ea2e8fc3f7b50b4fd", "step": 5, "value": 0.9864642276878256, "stage": "improve", "elapsed_seconds": 2385.3846020698547}, {"event_id": "57d4f805a50a4232ba1dfea08bfdb183", "node_id": "57d4f805a50a4232ba1dfea08bfdb183", "transition_id": "46d7346efcd04ea4943ada28563de5f3", "step": 6, "value": 0.9598352792006328, "stage": "improve", "elapsed_seconds": 2454.9078555107117}, {"event_id": "66168a576cc64322a698b09442b07111", "node_id": "66168a576cc64322a698b09442b07111", "transition_id": "7882c14969cc422eb28f614032d8c4d8", "step": 7, "value": 0.9854109473920107, "stage": "improve", "elapsed_seconds": 3160.801308631897}, {"event_id": "eeda75a23ce14a849ab2f1518ab9bcd4", "node_id": "eeda75a23ce14a849ab2f1518ab9bcd4", "transition_id": "71318dbcd5ee4834bc8d1abcba48c4a3", "step": 8, "value": 0.9942998524469678, "stage": "improve", "elapsed_seconds": 3405.511703968048}, {"event_id": "000d25f2530d40ddaad9851e7d7e18d9", "node_id": "000d25f2530d40ddaad9851e7d7e18d9", "transition_id": "67237e109b1e49ee93a1e62d616ee3e4", "step": 9, "value": 0.9828169645358283, "stage": "improve", "elapsed_seconds": 3860.044179201126}, {"event_id": "c3085291ca474344b9ba9a4410b66abd", "node_id": "c3085291ca474344b9ba9a4410b66abd", "transition_id": "cdc47abf8b7d47479751502f85966753", "step": 10, "value": 0.9598352792006328, "stage": "improve", "elapsed_seconds": 4206.069164514542}, {"event_id": "84da2643b32542efa5d4d6a6e23385da", "node_id": "84da2643b32542efa5d4d6a6e23385da", "transition_id": "dd0699ef831445709caab3596776f9cc", "step": 13, "value": 0.9913048350047622, "stage": "debug", "elapsed_seconds": 5652.498278141022}, {"event_id": "8352a97826ed418ca74262beeefa0818", "node_id": "8352a97826ed418ca74262beeefa0818", "transition_id": "ea2af2292ca54cc9bfac36549238670f", "step": 14, "value": 0.987163447242778, "stage": "improve", "elapsed_seconds": 5741.2233510017395}, {"event_id": "524c1ae6e42d464caec0506ba0d37b5b", "node_id": "524c1ae6e42d464caec0506ba0d37b5b", "transition_id": "2a0f8fdbc57d40fa844a31218963ccfa", "step": 15, "value": 0.9598352792006328, "stage": "improve", "elapsed_seconds": 6527.676002502441}, {"event_id": "0eeeba5195bb431cadf6a46937613087", "node_id": "0eeeba5195bb431cadf6a46937613087", "transition_id": "c240f36665174c4ca882c8fa606dae40", "step": 17, "value": 0.9886782502342334, "stage": "improve", "elapsed_seconds": 8800.695502281189}, {"event_id": "7c1fc9c8a01a4cc983fdbb993da2b2b8", "node_id": "7c1fc9c8a01a4cc983fdbb993da2b2b8", "transition_id": "5e95b19f84104bf8a71cfee1dca9c76c", "step": 18, "value": 0.9888465616777284, "stage": "debug", "elapsed_seconds": 9704.733818292618}, {"event_id": "097ab637db4d489cb6c172edcf341f50", "node_id": "097ab637db4d489cb6c172edcf341f50", "transition_id": "368cba3146934b6b82fed6f2148acb41", "step": 19, "value": 0.980509534843274, "stage": "improve", "elapsed_seconds": 12119.896894216537}, {"event_id": "8052e67eb4b54c599df6c35a5b5a4e0c", "node_id": "8052e67eb4b54c599df6c35a5b5a4e0c", "transition_id": "fef7b4adc25f4329976d20e7e9e7e278", "step": 20, "value": 0.985976805423273, "stage": "improve", "elapsed_seconds": 12374.640382289886}, {"event_id": "36368407deae416685b7700fe6e4af34", "node_id": "36368407deae416685b7700fe6e4af34", "transition_id": "b90c9c7afa944acea3b6efe6a7a7f6e5", "step": 22, "value": 0.9967281080172559, "stage": "improve", "elapsed_seconds": 14232.908504247665}, {"event_id": "25554f5f84f642b49e6f22c2d5fb99e0", "node_id": "25554f5f84f642b49e6f22c2d5fb99e0", "transition_id": "e369846f425a4e8d90a8377f49f816b5", "step": 23, "value": 0.9854557678301306, "stage": "improve", "elapsed_seconds": 16120.458776950836}, {"event_id": "7b02aa3f33dd4d5c8fde7e6e8d9d80d6", "node_id": "7b02aa3f33dd4d5c8fde7e6e8d9d80d6", "transition_id": "bc8459c52674461dad6c4f04fabef2be", "step": 25, "value": 0.986383604221251, "stage": "evolution", "elapsed_seconds": 21339.568000793457}, {"event_id": "bc3533183bf14d02a1dd562181b728bb", "node_id": "bc3533183bf14d02a1dd562181b728bb", "transition_id": "c7ceae719105443f9037a2e51544f54e", "step": 28, "value": 0.99474, "stage": "debug", "elapsed_seconds": 23746.967980146408}, {"event_id": "d31b419da214460493b9fae710a9e223", "node_id": "d31b419da214460493b9fae710a9e223", "transition_id": "77d37c15b5bb412cbf22de631e5807a6", "step": 37, "value": 0.9969185948792649, "stage": "improve", "elapsed_seconds": 36055.14169335365}], "maximize": true, "metric_name": "native public validation metric", "official_score": 0.99796, "valid_submission": true, "medal": "gold", "thresholds": {"gold": 0.99724, "silver": 0.99135, "bronze": 0.99038}, "formal_result": false, "full_agent_budget_used": true, "note": "从 2026-09-21 首轮断点续跑；续跑使用独占 A100 80GB，仅补原 12h 剩余时间。 已保存评分来自本次续跑最终提交。 原首轮格式校验任务 ID 有误；续跑已修正。原全局记忆缺失，按保存记录重建；详情见 provenance。", "artifacts": [{"bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/experiments/mlebench-aq04-12h-20260921/continuations/liux-mila-20260924/runs/harry123.aq04-20260921.text-normalization-challenge-english-language", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/experiments/mlebench-aq04-12h-20260921/continuations/liux-mila-20260924/runs/harry123.aq04-20260921.text-normalization-challenge-english-language/live.json", "member": "live.json; immutable metric events and continuation archive index", "files": 1, "bytes": 0}, {"bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/experiments/mlebench-aq04-12h-20260921/continuations/liux-mila-20260924/runs/harry123.aq04-20260921.text-normalization-challenge-english-language/final", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/experiments/mlebench-aq04-12h-20260921/continuations/liux-mila-20260924/runs/harry123.aq04-20260921.text-normalization-challenge-english-language/final/submission-4aa686ab4c11735b175981593a9bc86cc39a586434ff31f736bda67b41ab7d7b.csv", "member": "Sealed final submission.csv; SHA256 4aa686ab4c11735b175981593a9bc86cc39a586434ff31f736bda67b41ab7d7b", "files": 1, "bytes": 14306460}, {"bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/experiments/mlebench-aq04-12h-20260921/continuations/liux-mila-20260924/runs/harry123.aq04-20260921.text-normalization-challenge-english-language/artifacts", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/experiments/mlebench-aq04-12h-20260921/continuations/liux-mila-20260924/runs/harry123.aq04-20260921.text-normalization-challenge-english-language/artifacts/logs-400fca48fbfd718f5fd576a18930ec76071a5697e21176af706a97af033882e6.tar.gz", "member": "experiments/mlebench-aq04-12h-20260921/continuations/liux-mila-20260924/runs/harry123.aq04-20260921.text-normalization-challenge-english-language/artifacts/logs-400fca48fbfd718f5fd576a18930ec76071a5697e21176af706a97af033882e6.tar.gz", "files": 183, "bytes": 291095055}, {"bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/experiments/mlebench-aq04-12h-20260921/runs/harry123.aq04-20260921.text-normalization-challenge-english-language/artifacts/logs", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/experiments/mlebench-aq04-12h-20260921/runs/harry123.aq04-20260921.text-normalization-challenge-english-language/live.json", "member": "live.json; persisted native/wrapper logs", "files": 47, "bytes": 32628535}], "logs_scope": "完整可用日志、候选代码及提交 CSV 已上传；日志快照时间 2026-09-25T09:48:53.944936+00:00；排除数据集、模型缓存及凭据。", "curve_scope": "保留原始指标点；续跑使用已提交的有效原生观察。仅有原生 active 时间的点参与时间曲线。", "source_grade": {"competition_id": "text-normalization-challenge-english-language", "score": 0.99796, "gold_threshold": 0.99724, "silver_threshold": 0.99135, "bronze_threshold": 0.99038, "median_threshold": 0.99037, "any_medal": true, "gold_medal": true, "silver_medal": false, "bronze_medal": false, "above_median": true, "submission_exists": true, "valid_submission": true, "is_lower_better": false, "created_at": "2026-09-25T05:46:01.542347", "submission_path": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/runs/aq04-mlebench-lite-20260921-resume-mila-20260924/tasks/text-normalization-challenge-english-language/20260921_003258_AQ04_text-normalization-challenge-english-language/workspace/ensembles_csv/top6ens-total_run_time4.71h.csv"}, "source_wrapper": {"task": "text-normalization-challenge-english-language", "job_id": "22372435", "owner": "harry123", "host": "g17.nibi.sharcnet", "commit": "3a0479c4e597b3515697d776c2768736cea8c4d6", "source_sha256": "efedc394766bff346ee7a3f98737fe3cf912cd3da7c397456e86e844d3c7046b", "started_at": "2026-09-21T04:32:12.843386+00:00", "agent_budget_seconds": 43200, "state": "failed", "workspace_is_node_local": true, "formal_result": false, "gpu": "NVIDIA H100 80GB HBM3", "gpu_uuid": "7b54dc26-f814-c38c-9ad0-3f80e0a3e536", "cpu_ids": [6, 7, 16, 17, 52, 53, 54, 55, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105], "grading_port": 32435, "grading_server_id": 27430, "search_started_at": "2026-09-21T04:32:43.367916+00:00", "search_exit_code": 1, "search_finished_at": "2026-09-21T11:09:41.194953+00:00", "fusion_exit_code": 0, "final_submission": "/scratch/harry123/EvolveFold/MLEvolve_BO/runs/aq04-mlebench-lite-20260921/tasks/text-normalization-challenge-english-language/22372435/native/20260921_003258_AQ04_text-normalization-challenge-english-language/final_submission.json", "log_dir": "/scratch/harry123/EvolveFold/MLEvolve_BO/runs/aq04-mlebench-lite-20260921/tasks/text-normalization-challenge-english-language/22372435/native/20260921_003258_AQ04_text-normalization-challenge-english-language", "journal_active_seconds": 23747.688903808594, "full_agent_budget_used": false, "outer_search_timeout_reached": false, "official_grade": "/scratch/harry123/EvolveFold/MLEvolve_BO/runs/aq04-mlebench-lite-20260921/tasks/text-normalization-challenge-english-language/22372435/official-grade.json", "finished_at": "2026-09-21T11:11:24.409642+00:00", "elapsed_seconds": 23951.55529646203}, "score_phase": "continuation-final", "final_submission_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/experiments/mlebench-aq04-12h-20260921/continuations/liux-mila-20260924/runs/harry123.aq04-20260921.text-normalization-challenge-english-language/final/submission-4aa686ab4c11735b175981593a9bc86cc39a586434ff31f736bda67b41ab7d7b.csv", "hardware": "A100 80GB (continuation); H100 80GB (first segment)", "model": "muse-spark-1.3-contributor", "provider": "codex://opencode-go", "scheduler": {"job_id": "10927555", "partition": "short-unkillable", "observed_at": "2026-09-25T17:05:53.413318+00:00", "allocation": null}, "completed_candidates": 67, "pending_decisions": 3, "remaining_seconds": 0, "continuation_source_status": {"state": "complete", "active_elapsed_seconds": 43201.53254914284, "updated_at": "2026-09-25T09:46:01.791618+00:00", "source_updated_at": "2026-09-21T11:11:24.409642+00:00", "imported_first_run": true, "run_root": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/runs/aq04-mlebench-lite-20260921-resume-mila-20260924/tasks/text-normalization-challenge-english-language/20260921_003258_AQ04_text-normalization-challenge-english-language", "previous_job_id": "22372435", "job_id": "10927555", "attempt": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/runs/aq04-mlebench-lite-20260921-resume-mila-20260924/tasks/text-normalization-challenge-english-language/attempt-04-10927555", "gpu": "NVIDIA A100-SXM4-80GB", "host": "cn-g026.server.mila.quebec", "started_at": "2026-09-24T17:57:19.385131+00:00", "search_pid": 856509, "attempt_started_epoch": 1790324729.395483, "search_stopped_epoch": 1790329536.4569597, "search_exit_code": 75, "budget_complete": true, "completed_transitions": 67, "release_receipt": {"job_id": "10927029", "state": "COMPLETED", "end": "2026-09-25T04:24:35", "exit_code": "0:0", "end_epoch": 1790324675.0, "verified_at": "2026-09-25T08:25:00.641637+00:00"}, "stop_history": [{"stop_reason": "user_request", "stop_requested_at": "2026-09-24T19:15:09.692440+00:00", "stopped_at": "2026-09-24T19:15:12.451027+00:00", "job_id": "10919452", "active_elapsed_seconds": 28300.934756994247}], "resume_requested_at": "2026-09-25T05:30:03.052522+00:00", "resume_reason": "explicit_user_request", "error": null, "search_finished_at": "2026-09-25T09:45:38.574218+00:00", "finished_at": "2026-09-25T09:46:01.758796+00:00", "submission": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/runs/aq04-mlebench-lite-20260921-resume-mila-20260924/tasks/text-normalization-challenge-english-language/20260921_003258_AQ04_text-normalization-challenge-english-language/workspace/ensembles_csv/top6ens-total_run_time4.71h.csv", "official_grade": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/runs/aq04-mlebench-lite-20260921-resume-mila-20260924/tasks/text-normalization-challenge-english-language/20260921_003258_AQ04_text-normalization-challenge-english-language/logs/official-grade.json", "final_submission_sha256": "4aa686ab4c11735b175981593a9bc86cc39a586434ff31f736bda67b41ab7d7b"}, "config_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/experiments/mlebench-aq04-12h-20260921/continuations/liux-mila-20260924/runs/harry123.aq04-20260921.text-normalization-challenge-english-language/config.yaml"}, {"id": "harry123.aq04-20260921.text-normalization-challenge-russian-language", "experiment_id": "mlebench-aq04-12h-20260921", "family": "MLEBench", "method": "AQ04", "dataset": "text-normalization-challenge-russian-language", "seed": 42, "status": "completed", "source_status": "completed", "wrapper_status": "completed", "source_updated_at": "2026-09-21T16:43:00.872387+00:00", "uploaded_at": "2026-09-22T04:53:01.045577+00:00", "elapsed_seconds": 41375.38422703743, "budget_seconds": 43200.0, "metrics": [{"event_id": "0a3ffea8f3ad44948068cd89f1fa62d8", "step": 2, "value": 0.8826165155650364, "stage": "draft"}, {"event_id": "9daac1c2469f4317b26bdbfead5c5b22", "step": 3, "value": 0.9514723154141496, "stage": "draft"}, {"event_id": "29502b9f185a421a9950030c3de21da8", "step": 4, "value": 0.9370601583168637, "stage": "improve"}, {"event_id": "a00f1652d9fb4ab8970e9b66035eff34", "step": 6, "value": 0.9492267151864981, "stage": "debug"}, {"event_id": "b303cf7d8620407b88d4571b34fa06bb", "step": 7, "value": 0.9773583116958356, "stage": "improve"}, {"event_id": "236c450822a445b2ae279ad185d31c24", "step": 8, "value": 0.9387698549633487, "stage": "improve"}, {"event_id": "18a4d5629fe44d29acc37ac5f81f501a", "step": 9, "value": 0.9376561993495833, "stage": "improve"}, {"event_id": "aa0517b05b56474b8146f324bfb0b9fe", "step": 10, "value": 0.9768537398960588, "stage": "improve"}, {"event_id": "28da0cb861ef4c538e4bfc9f11a84a24", "step": 11, "value": 0.9816928335554139, "stage": "improve"}, {"event_id": "e3828b49575a4c4e9b39c77e174db233", "step": 13, "value": 0.8874737271386893, "stage": "debug"}, {"event_id": "da866e415fed4c08b7426f985ba09d80", "step": 14, "value": 0.9827672472362815, "stage": "improve"}, {"event_id": "e318d932083d44e2906e25f7f18b1b1d", "step": 15, "value": 0.9787013287969201, "stage": "improve"}], "maximize": true, "metric_name": "native public validation metric", "official_score": 0.98397, "valid_submission": true, "medal": "silver", "thresholds": {"gold": 0.99012, "silver": 0.98232, "bronze": 0.97592}, "formal_result": true, "full_agent_budget_used": false, "note": "", "artifacts": [{"bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/experiments/mlebench-aq04-12h-20260921/runs/harry123.aq04-20260921.text-normalization-challenge-russian-language/artifacts/logs", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/experiments/mlebench-aq04-12h-20260921/runs/harry123.aq04-20260921.text-normalization-challenge-russian-language/live.json", "member": "live.json; persisted native/wrapper logs", "files": 40, "bytes": 16678699}], "logs_scope": "已存在 persisted wrapper/native logs；原上传者排除了 node-local workspaces、datasets、submissions、checkpoints。", "curve_scope": "上传者 live.json 验证指标；官方 grade 为另一条证据。", "source_grade": {"competition_id": "text-normalization-challenge-russian-language", "score": 0.98397, "gold_threshold": 0.99012, "silver_threshold": 0.98232, "bronze_threshold": 0.97592, "median_threshold": 0.97591, "any_medal": true, "gold_medal": false, "silver_medal": true, "bronze_medal": false, "above_median": true, "submission_exists": true, "valid_submission": true, "is_lower_better": false, "created_at": "2026-09-21T12:41:24.490670", "submission_path": "/scratch/harry123/EvolveFold/MLEvolve_BO/runs/aq04-mlebench-lite-20260921/tasks/text-normalization-challenge-russian-language/22372442/submission.csv"}, "source_wrapper": {"task": "text-normalization-challenge-russian-language", "job_id": "22372442", "owner": "harry123", "host": "g5.nibi.sharcnet", "commit": "3a0479c4e597b3515697d776c2768736cea8c4d6", "source_sha256": "efedc394766bff346ee7a3f98737fe3cf912cd3da7c397456e86e844d3c7046b", "started_at": "2026-09-21T04:40:31.334141+00:00", "agent_budget_seconds": 43200, "state": "completed", "workspace_is_node_local": true, "formal_result": true, "gpu": "NVIDIA H100 80GB HBM3", "gpu_uuid": "927fc9cb-96b1-72ab-7fea-19447dc7559b", "cpu_ids": [6, 7, 8, 9, 14, 15, 25, 26, 27, 28, 29, 30, 31, 32, 35, 36, 47, 48, 49, 50, 51], "grading_port": 32442, "grading_server_id": 27437, "search_started_at": "2026-09-21T04:40:58.830910+00:00", "search_exit_code": 124, "search_finished_at": "2026-09-21T16:41:00.237049+00:00", "fusion_exit_code": 0, "final_submission": "/scratch/harry123/EvolveFold/MLEvolve_BO/runs/aq04-mlebench-lite-20260921/tasks/text-normalization-challenge-russian-language/22372442/native/20260921_004111_AQ04_text-normalization-challenge-russian-language/final_submission.json", "log_dir": "/scratch/harry123/EvolveFold/MLEvolve_BO/runs/aq04-mlebench-lite-20260921/tasks/text-normalization-challenge-russian-language/22372442/native/20260921_004111_AQ04_text-normalization-challenge-russian-language", "journal_active_seconds": 41375.38422703743, "full_agent_budget_used": false, "outer_search_timeout_reached": true, "official_grade": "/scratch/harry123/EvolveFold/MLEvolve_BO/runs/aq04-mlebench-lite-20260921/tasks/text-normalization-challenge-russian-language/22372442/official-grade.json", "finished_at": "2026-09-21T16:43:00.851097+00:00", "elapsed_seconds": 43349.50716660172}}, {"id": "liux.aq04-rerun-20260925.jigsaw-toxic-comment-classification-challenge", "experiment_id": "mlebench-aq04-12h-rerun-20260925", "family": "MLEBench", "method": "AQ04", "dataset": "jigsaw-toxic-comment-classification-challenge", "seed": 42, "fresh_run": true, "status": "completed", "source_status": "complete", "wrapper_status": "complete", "source_updated_at": "2026-09-25T19:53:37.178143+00:00", "uploaded_at": "2026-09-25T20:02:51.860282+00:00", "elapsed_seconds": 43200.74638009071, "budget_seconds": 43200, "remaining_seconds": 0, "maximize": true, "metric_name": "native public validation metric", "metrics": [{"event_id": "3bfef2e10ef0401583f9d40286eb74dd", "node_id": "3bfef2e10ef0401583f9d40286eb74dd", "transition_id": "86a87b507ca14b01ad2c7ec65c97893c", "step": 1, "value": 0.9921663910509334, "stage": "draft", "elapsed_seconds": 3247.2903621196747}, {"event_id": "76a82edb66734fccbdc2cd9049a71607", "node_id": "76a82edb66734fccbdc2cd9049a71607", "transition_id": "9e0e26c790684e27b7d12021372a8b32", "step": 2, "value": 0.9918501597803582, "stage": "improve", "elapsed_seconds": 8834.871581792831}, {"event_id": "5e65dbc6bd2444899e9460701cbbfae5", "node_id": "5e65dbc6bd2444899e9460701cbbfae5", "transition_id": "446ea874170442538c2473419996bcfc", "step": 3, "value": 0.9932728136086252, "stage": "improve", "elapsed_seconds": 24883.68255352974}, {"event_id": "d2eaa282f88845ff8521d4c3c2e88e54", "node_id": "d2eaa282f88845ff8521d4c3c2e88e54", "transition_id": "82513c29d648443d828d2048bd5c035b", "step": 4, "value": 0.9920193536202997, "stage": "improve", "elapsed_seconds": 30575.75694489479}, {"event_id": "4ce96928ed7b4083a81a2c7c8e20b8c9", "node_id": "4ce96928ed7b4083a81a2c7c8e20b8c9", "transition_id": "8decc2b5d27d40b09d1e252cc87f6597", "step": 6, "value": 0.9908722083668889, "stage": "debug", "elapsed_seconds": 35893.142491579056}], "official_score": 0.9876, "valid_submission": true, "medal": "gold", "source_grade": {"competition_id": "jigsaw-toxic-comment-classification-challenge", "score": 0.9876, "gold_threshold": 0.9874, "silver_threshold": 0.98668, "bronze_threshold": 0.98639, "median_threshold": 0.98079, "any_medal": true, "gold_medal": true, "silver_medal": false, "bronze_medal": false, "above_median": true, "submission_exists": true, "valid_submission": true, "is_lower_better": false, "created_at": "2026-09-25T15:53:36.986150", "submission_path": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/runs/aq04-jigsaw-pizza-rerun-20260925/runs/20260925_034857_jigsaw-toxic-comment-classification-challenge/workspace/ensembles_csv/top4ens-total_run_time8.23h.csv"}, "score_phase": "rerun-final", "thresholds": {"gold": 0.9874, "silver": 0.98668, "bronze": 0.98639}, "full_agent_budget_used": true, "note": "2026-09-25 独立重跑；从空白工作目录、空 journal 和空全局记忆开始，每题独占 A100 80GB，累计搜索预算 12h。 main：8 CPU / 48 GiB RAM；AQ04、seed 42、模型及搜索参数保持一致。 已完成 MLE-bench 离线最终评分。", "hardware": "A100 80GB", "model": "muse-spark-1.3-contributor", "provider": "codex://opencode-go", "artifacts": [{"bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/experiments/mlebench-aq04-12h-rerun-20260925/contributors/liux/runs/liux.aq04-rerun-20260925.jigsaw-toxic-comment-classification-challenge", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/experiments/mlebench-aq04-12h-rerun-20260925/contributors/liux/runs/liux.aq04-rerun-20260925.jigsaw-toxic-comment-classification-challenge/live.json", "member": "live.json; independent rerun metrics and artifact index", "files": 1, "bytes": 0}, {"bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/experiments/mlebench-aq04-12h-rerun-20260925/contributors/liux/runs/liux.aq04-rerun-20260925.jigsaw-toxic-comment-classification-challenge/artifacts", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/experiments/mlebench-aq04-12h-rerun-20260925/contributors/liux/runs/liux.aq04-rerun-20260925.jigsaw-toxic-comment-classification-challenge/artifacts/logs-74e9ec1ed466e4929bf472ae1e18edb0cf30f62f1056b1c5ea1e59109b00cd27.tar.gz", "member": "experiments/mlebench-aq04-12h-rerun-20260925/contributors/liux/runs/liux.aq04-rerun-20260925.jigsaw-toxic-comment-classification-challenge/artifacts/logs-74e9ec1ed466e4929bf472ae1e18edb0cf30f62f1056b1c5ea1e59109b00cd27.tar.gz", "files": 93, "bytes": 75475021}, {"bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/experiments/mlebench-aq04-12h-rerun-20260925/contributors/liux/runs/liux.aq04-rerun-20260925.jigsaw-toxic-comment-classification-challenge/final", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/experiments/mlebench-aq04-12h-rerun-20260925/contributors/liux/runs/liux.aq04-rerun-20260925.jigsaw-toxic-comment-classification-challenge/final/submission-42e370ee2fab34051ba64170253689691fbff58307fdbf6dcf1f6cee1546f8c0.csv", "member": "Sealed final submission; SHA256 42e370ee2fab34051ba64170253689691fbff58307fdbf6dcf1f6cee1546f8c0", "files": 1, "bytes": 20844035}], "final_submission_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/experiments/mlebench-aq04-12h-rerun-20260925/contributors/liux/runs/liux.aq04-rerun-20260925.jigsaw-toxic-comment-classification-challenge/final/submission-42e370ee2fab34051ba64170253689691fbff58307fdbf6dcf1f6cee1546f8c0.csv", "config_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/experiments/mlebench-aq04-12h-rerun-20260925/contributors/liux/runs/liux.aq04-rerun-20260925.jigsaw-toxic-comment-classification-challenge/config.yaml", "scheduler": {"job_id": "10931622", "partition": "main", "observed_at": "2026-09-25T20:02:51.860826+00:00", "allocation": null}, "completed_candidates": 8, "pending_decisions": 3, "source_wrapper": {"state": "complete", "updated_at": "2026-09-25T19:53:37.178143+00:00", "active_elapsed_seconds": 43200.74638009071, "completed_transitions": 8, "fresh_run": true, "resume_from_previous_experiment": false, "job_id": "10931622", "attempt": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/runs/aq04-jigsaw-pizza-rerun-20260925/tasks/jigsaw-toxic-comment-classification-challenge/attempt-02-10931622", "gpu": "NVIDIA A100-SXM4-80GB", "host": "cn-g011.server.mila.quebec", "started_at": "2026-09-25T07:48:27.633462+00:00", "search_pid": 444067, "attempt_started_epoch": 1790360476.5164192, "search_stopped_epoch": 1790366002.9851348, "search_exit_code": 75, "budget_complete": true, "run_root": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/runs/aq04-jigsaw-pizza-rerun-20260925/runs/20260925_034857_jigsaw-toxic-comment-classification-challenge", "release_receipt": {"job_id": "10927456", "state": "PREEMPTED", "end": "2026-09-25T14:17:54", "exit_code": "0:0", "end_epoch": 1790360274.0, "verified_at": "2026-09-25T18:18:16.653190+00:00"}, "search_finished_at": "2026-09-25T19:53:25.048087+00:00", "finished_at": "2026-09-25T19:53:37.139629+00:00", "submission": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/runs/aq04-jigsaw-pizza-rerun-20260925/runs/20260925_034857_jigsaw-toxic-comment-classification-challenge/workspace/ensembles_csv/top4ens-total_run_time8.23h.csv", "official_grade": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/runs/aq04-jigsaw-pizza-rerun-20260925/runs/20260925_034857_jigsaw-toxic-comment-classification-challenge/logs/official-grade.json", "final_submission_sha256": "42e370ee2fab34051ba64170253689691fbff58307fdbf6dcf1f6cee1546f8c0"}, "logs_scope": "完整可用日志快照已上传：2026-09-25T20:02:29.789893+00:00 排除数据集、工作模型缓存和凭据。", "curve_scope": "独立重跑的原生有效观察；没有继承首轮或续跑曲线。时间横轴仅使用已保存的 active 时间。"}, {"id": "liux.aq04-rerun-20260925.random-acts-of-pizza", "experiment_id": "mlebench-aq04-12h-rerun-20260925", "family": "MLEBench", "method": "AQ04", "dataset": "random-acts-of-pizza", "seed": 42, "fresh_run": true, "status": "completed", "source_status": "complete", "wrapper_status": "complete", "source_updated_at": "2026-09-25T19:48:50.520318+00:00", "uploaded_at": "2026-09-25T20:02:52.115367+00:00", "elapsed_seconds": 43202.43855237961, "budget_seconds": 43200, "remaining_seconds": 0, "maximize": true, "metric_name": "native public validation metric", "metrics": [{"event_id": "dacfbd345d204855b1c8facf246ecc6c", "node_id": "dacfbd345d204855b1c8facf246ecc6c", "transition_id": "c4ca17bd3a4c478a88dd525995f13a13", "step": 1, "value": 0.6234219985621855, "stage": "draft", "elapsed_seconds": 854.5678427219391}, {"event_id": "36dd473a8ea04ff9aaa21c6714cea90a", "node_id": "36dd473a8ea04ff9aaa21c6714cea90a", "transition_id": "3e88d44ac37f4bf2bd0a93b5c5788ac2", "step": 2, "value": 0.6375557153127246, "stage": "improve", "elapsed_seconds": 1159.365530014038}, {"event_id": "2c78742da7a74d8fa09a616498affd89", "node_id": "2c78742da7a74d8fa09a616498affd89", "transition_id": "439b75c449e74a7d863c8ddb0dff528d", "step": 3, "value": 0.6428756290438533, "stage": "improve", "elapsed_seconds": 1472.580569267273}, {"event_id": "2c79405c2f804594a12939319d063be9", "node_id": "2c79405c2f804594a12939319d063be9", "transition_id": "e094297146f84b1baaf1df428a541620", "step": 4, "value": 0.6308123652048885, "stage": "improve", "elapsed_seconds": 1767.1066353321075}, {"event_id": "6cafa789076f4530b36a624a920fd1bf", "node_id": "6cafa789076f4530b36a624a920fd1bf", "transition_id": "306dcdc359d34ecb90406672e715bbc8", "step": 5, "value": 0.6865851905104241, "stage": "improve", "elapsed_seconds": 2178.668765306473}, {"event_id": "667ae2f337e54f2c8e7d4315a5ed9ed9", "node_id": "667ae2f337e54f2c8e7d4315a5ed9ed9", "transition_id": "ee3d96a9291a4db2881015e579bb4640", "step": 6, "value": 0.682703091301222, "stage": "improve", "elapsed_seconds": 2564.1083199977875}, {"event_id": "5a9efe1c4630470b9ddf04b8e289d758", "node_id": "5a9efe1c4630470b9ddf04b8e289d758", "transition_id": "61deddfed7e4443f80daf033891597c2", "step": 7, "value": 0.6825017972681523, "stage": "improve", "elapsed_seconds": 3007.8729968070984}, {"event_id": "b77e237f290f403bbf817986541071c4", "node_id": "b77e237f290f403bbf817986541071c4", "transition_id": "6fe3b55532c042ea98b413d6630003fc", "step": 8, "value": 0.6865522826687875, "stage": "improve", "elapsed_seconds": 3967.4824295043945}, {"event_id": "5391bd1538e4488780a6dacbf744ea78", "node_id": "5391bd1538e4488780a6dacbf744ea78", "transition_id": "d793d7abc8de468581254ba6c2e2b173", "step": 9, "value": 0.695189600043969, "stage": "evolution", "elapsed_seconds": 4217.20386838913}, {"event_id": "e8acdab1c8184a60bc7ec6cba70b4f0d", "node_id": "e8acdab1c8184a60bc7ec6cba70b4f0d", "transition_id": "e88048f3051b41239446ebbbb98cee45", "step": 10, "value": 0.7239683680805176, "stage": "improve", "elapsed_seconds": 4585.49214720726}, {"event_id": "78e6558aab034fa3acdc611718baca8b", "node_id": "78e6558aab034fa3acdc611718baca8b", "transition_id": "ea18befc439c461ea066a82d185f27b9", "step": 11, "value": 0.701375647006715, "stage": "improve", "elapsed_seconds": 5433.524262666702}, {"event_id": "795bd941acce47dca2ae8d5b1cc52087", "node_id": "795bd941acce47dca2ae8d5b1cc52087", "transition_id": "0012762cbb634145bad4405684e03507", "step": 12, "value": 0.6947453840657724, "stage": "improve", "elapsed_seconds": 6426.092919826508}, {"event_id": "9d6b9c37f0874715ab195b762d30c5ff", "node_id": "9d6b9c37f0874715ab195b762d30c5ff", "transition_id": "4c0d22e7b4f640cf9dd2d58e81c0f94a", "step": 13, "value": 0.6880287996792851, "stage": "improve", "elapsed_seconds": 7307.922039031982}, {"event_id": "447f6ce55fd0459fa329b0304af6f04d", "node_id": "447f6ce55fd0459fa329b0304af6f04d", "transition_id": "2429a8710c4c4cdd865f954822842ec3", "step": 14, "value": 0.6750608614686285, "stage": "improve", "elapsed_seconds": 7668.65491938591}, {"event_id": "4e7efa340cc84c888df3cbff12847a2c", "node_id": "4e7efa340cc84c888df3cbff12847a2c", "transition_id": "97d2bc26d6ec4032b56f34df772ded0d", "step": 15, "value": 0.7099447478088254, "stage": "evolution", "elapsed_seconds": 9622.932360887527}, {"event_id": "e2b29126e6284a41977b624cbca47a6e", "node_id": "e2b29126e6284a41977b624cbca47a6e", "transition_id": "e8569aa2c51541c6bc0965e4d3be05cd", "step": 16, "value": 0.685233644859813, "stage": "evolution", "elapsed_seconds": 9958.978753089905}, {"event_id": "ead010cc085a4249be1ca2bbda4306aa", "node_id": "ead010cc085a4249be1ca2bbda4306aa", "transition_id": "7bfa2a7c190140278f60bd9030b02559", "step": 18, "value": 0.7013536625187111, "stage": "debug", "elapsed_seconds": 10765.207839488983}, {"event_id": "95b702eb536e470f93a9ae4655227eeb", "node_id": "95b702eb536e470f93a9ae4655227eeb", "transition_id": "7e9c622aff0540e6824f19e43f66e680", "step": 19, "value": 0.7100346255686061, "stage": "evolution", "elapsed_seconds": 11426.544209241867}, {"event_id": "470503e04b834f1c8d66218578987dcc", "node_id": "470503e04b834f1c8d66218578987dcc", "transition_id": "d95380d3b57f49888fae1fefec7cca6e", "step": 21, "value": 0.705720816400428, "stage": "debug", "elapsed_seconds": 12757.954502344131}, {"event_id": "713e739d8a8e46ffb679b7db75532326", "node_id": "713e739d8a8e46ffb679b7db75532326", "transition_id": "673b5e27aad04ab884990a0e5dc2a1c2", "step": 22, "value": 0.692949768677924, "stage": "evolution", "elapsed_seconds": 13110.54541683197}, {"event_id": "5dc0b4b2761c48adaf7ba6a11564e394", "node_id": "5dc0b4b2761c48adaf7ba6a11564e394", "transition_id": "7fb55b3daad64184857ab4efb4f3ba63", "step": 23, "value": 0.7068772651296923, "stage": "evolution", "elapsed_seconds": 13685.526378154755}, {"event_id": "b478e8d635d8492f93021573d7a2bba0", "node_id": "b478e8d635d8492f93021573d7a2bba0", "transition_id": "4ae062ba08ff45019f89a7652da21e96", "step": 24, "value": 0.6766592630670301, "stage": "evolution", "elapsed_seconds": 14130.738598108292}, {"event_id": "3b7c6e9c130a420d97979cf00cd46113", "node_id": "3b7c6e9c130a420d97979cf00cd46113", "transition_id": "8a1008f2d2e94e33bd4763a7e7845c1c", "step": 25, "value": 0.7005460558858617, "stage": "evolution", "elapsed_seconds": 15152.1650557518}, {"event_id": "6aef0d74a243488d97d379df85eb657e", "node_id": "6aef0d74a243488d97d379df85eb657e", "transition_id": "4194c57eeac24f7cb26b2fbeef8633e0", "step": 26, "value": 0.7095422376975775, "stage": "evolution", "elapsed_seconds": 16266.358960151672}, {"event_id": "db6ee02147af4782a3ee16103d438b36", "node_id": "db6ee02147af4782a3ee16103d438b36", "transition_id": "304fa03bda454813aa7b74f4dfdacb49", "step": 28, "value": 0.7003068129281722, "stage": "debug", "elapsed_seconds": 17127.8845641613}, {"event_id": "3fff989611fd47d1948ad844a6539f3e", "node_id": "3fff989611fd47d1948ad844a6539f3e", "transition_id": "052ddbcd6a304d68b55ea04372a4bc8b", "step": 29, "value": 0.7133833803736717, "stage": "evolution", "elapsed_seconds": 17740.462648391724}, {"event_id": "151f103ee60e407e8081c996f29689bc", "node_id": "151f103ee60e407e8081c996f29689bc", "transition_id": "3828c02da9484659a247e4ff0ee95b38", "step": 31, "value": 0.7120568751636712, "stage": "debug", "elapsed_seconds": 18658.404007196426}, {"event_id": "54ce1c96f9914561aa9347bc42a413ed", "node_id": "54ce1c96f9914561aa9347bc42a413ed", "transition_id": "308947d26388454890bc0332714ac442", "step": 32, "value": 0.6980301941049605, "stage": "evolution", "elapsed_seconds": 19044.26305603981}, {"event_id": "e458cf74e5fc4a489432fcf1e892a22f", "node_id": "e458cf74e5fc4a489432fcf1e892a22f", "transition_id": "f0a4dc3c6e194b4c8f3056cc288feeb5", "step": 33, "value": 0.6978859328373891, "stage": "evolution", "elapsed_seconds": 19564.121500968933}, {"event_id": "49c624bc42f947e4a814431342729671", "node_id": "49c624bc42f947e4a814431342729671", "transition_id": "9316f265d4d54a41a99f77b65f80c4d4", "step": 34, "value": 0.695189600043969, "stage": "evolution", "elapsed_seconds": 19975.415311574936}, {"event_id": "f8ff891df87a4229ab0951e0b30ca20a", "node_id": "f8ff891df87a4229ab0951e0b30ca20a", "transition_id": "0cf1c4b7a16440619ffdc54e22734681", "step": 35, "value": 0.6970298310104135, "stage": "evolution", "elapsed_seconds": 20954.026335716248}, {"event_id": "bb47abaede824a619eb4f7dc0a5fa435", "node_id": "bb47abaede824a619eb4f7dc0a5fa435", "transition_id": "f104738f25cc4d95bdf56eaff1da0c82", "step": 37, "value": 0.695658710221817, "stage": "debug", "elapsed_seconds": 21517.45953631401}, {"event_id": "2be7ab8daa3840538f3bae6b04927bdd", "node_id": "2be7ab8daa3840538f3bae6b04927bdd", "transition_id": "0bdca4b744864698a0b081dd72d680c0", "step": 38, "value": 0.702764549366491, "stage": "evolution", "elapsed_seconds": 22412.963751077652}, {"event_id": "09b0c6eaf16a4508b0765b54fdc724ac", "node_id": "09b0c6eaf16a4508b0765b54fdc724ac", "transition_id": "dd42fe1674a045b6955c76b2c44dfe7b", "step": 39, "value": 0.6733572969086987, "stage": "fusion", "elapsed_seconds": 22810.93827867508}, {"event_id": "31d665a756724b3483d8749e85c55ba9", "node_id": "31d665a756724b3483d8749e85c55ba9", "transition_id": "fa82591d77194a278cfb55719e6db1d7", "step": 40, "value": 0.6639827462257368, "stage": "evolution", "elapsed_seconds": 23224.17821907997}, {"event_id": "f6ea0fa965f94ba780563f7c8c417bb8", "node_id": "f6ea0fa965f94ba780563f7c8c417bb8", "transition_id": "4b35ee94438d43a6b3808ca6db9ae587", "step": 41, "value": 0.6775557153127245, "stage": "evolution", "elapsed_seconds": 23630.975663900375}, {"event_id": "3551c62bfcb14d299d1a76815b151c63", "node_id": "3551c62bfcb14d299d1a76815b151c63", "transition_id": "c171876702134549989b26f79e5c9ed7", "step": 42, "value": 0.7025547268265715, "stage": "evolution", "elapsed_seconds": 24129.886618852615}, {"event_id": "44f6749100164713bc302dd3d1963ccd", "node_id": "44f6749100164713bc302dd3d1963ccd", "transition_id": "56685ef430194d2aa8155ea350129d21", "step": 43, "value": 0.7020028515174146, "stage": "evolution", "elapsed_seconds": 28786.72645330429}, {"event_id": "85379f2252b146a89191cec7639bcf54", "node_id": "85379f2252b146a89191cec7639bcf54", "transition_id": "04477025d4d04187ac11b5f932e2322c", "step": 44, "value": 0.7049077136455777, "stage": "evolution", "elapsed_seconds": 29370.852093458176}, {"event_id": "cffa230e84bc42158650cab4031fcddd", "node_id": "cffa230e84bc42158650cab4031fcddd", "transition_id": "5a5ac4f82fb7460e87f04144853b689b", "step": 45, "value": 0.7032918537772908, "stage": "evolution", "elapsed_seconds": 29937.214559316635}, {"event_id": "9878e2a019cd489bab6843afbe9e89dd", "node_id": "9878e2a019cd489bab6843afbe9e89dd", "transition_id": "92647251ff464926a1a416beffcc183e", "step": 47, "value": 0.7113886113886113, "stage": "evolution", "elapsed_seconds": 30612.926424264908}, {"event_id": "e63c7eb223c24ff9b8d5dbf105aab779", "node_id": "e63c7eb223c24ff9b8d5dbf105aab779", "transition_id": "caa010df0d9540d08690ca32598ee8ca", "step": 49, "value": 0.7118619244832838, "stage": "debug", "elapsed_seconds": 32135.9445104599}, {"event_id": "8181b5d4c32e4ee78c12d2797f11f227", "node_id": "8181b5d4c32e4ee78c12d2797f11f227", "transition_id": "e7d06395292a441388f64fe5b68e7c4a", "step": 50, "value": 0.7109253206340584, "stage": "evolution", "elapsed_seconds": 32702.47893333435}, {"event_id": "54c6bb52f27d4d90bf197f26d16278cf", "node_id": "54c6bb52f27d4d90bf197f26d16278cf", "transition_id": "4fa0cf879d3d4bb28a13c1ffdd97c89c", "step": 51, "value": 0.6185706948418814, "stage": "evolution", "elapsed_seconds": 33524.568353414536}, {"event_id": "5bbacd1a91dc451ca757440b2c2c90d0", "node_id": "5bbacd1a91dc451ca757440b2c2c90d0", "transition_id": "66a7dbcdace644fb856c7bd99ecf2843", "step": 53, "value": 0.7110969936212653, "stage": "debug", "elapsed_seconds": 34915.184307813644}, {"event_id": "784f0371e0904937a36e4503d8942173", "node_id": "784f0371e0904937a36e4503d8942173", "transition_id": "1af6ea7a2cde4bdc9f6ba774b4268a8a", "step": 54, "value": 0.711068219806084, "stage": "evolution", "elapsed_seconds": 35654.24842453003}, {"event_id": "05c921d658664b36a44b448ae78ecc27", "node_id": "05c921d658664b36a44b448ae78ecc27", "transition_id": "202ac634e4924e9bab716de31fac9eb0", "step": 55, "value": 0.6887827382973013, "stage": "fusion", "elapsed_seconds": 36103.70981311798}, {"event_id": "fcd958688d864e1389457424b39356d3", "node_id": "fcd958688d864e1389457424b39356d3", "transition_id": "7c18ef306ff54758aefdba2cef3a5c8c", "step": 56, "value": 0.7009075067327494, "stage": "fusion", "elapsed_seconds": 36350.506366968155}, {"event_id": "d230d1fc421c4b739af27265b6def11b", "node_id": "d230d1fc421c4b739af27265b6def11b", "transition_id": "5fe2e9daeb59412bb255968983fe85db", "step": 57, "value": 0.6966819588178812, "stage": "fusion", "elapsed_seconds": 36687.77090239525}, {"event_id": "c1ca659576b348d4af96f06579adbadf", "node_id": "c1ca659576b348d4af96f06579adbadf", "transition_id": "9d3a6ec4728d4a6cae107ed81f6f339a", "step": 58, "value": 0.7061352886595604, "stage": "fusion", "elapsed_seconds": 38007.142718315125}, {"event_id": "57fd4edde5464cc598b1ae1585b81bc0", "node_id": "57fd4edde5464cc598b1ae1585b81bc0", "transition_id": "178c21f6f8f74426874c1a19d1678a65", "step": 59, "value": 0.7123122831860694, "stage": "fusion", "elapsed_seconds": 38840.98360323906}, {"event_id": "726de329cf9640038f964f5366a5ca38", "node_id": "726de329cf9640038f964f5366a5ca38", "transition_id": "945e63395a774059a55b8f6f31ef1517", "step": 60, "value": 0.7085306279481036, "stage": "fusion", "elapsed_seconds": 39384.65947294235}, {"event_id": "a8b5dca5e86540349c94b796cbb025b7", "node_id": "a8b5dca5e86540349c94b796cbb025b7", "transition_id": "66dd0822b7fc4d95ab8fb48293603d83", "step": 61, "value": 0.6903623884206408, "stage": "fusion", "elapsed_seconds": 40146.95208358765}, {"event_id": "c9e7e6a427844c1f9c7c3b709c877377", "node_id": "c9e7e6a427844c1f9c7c3b709c877377", "transition_id": "485ae996fa3c4ebe97905b513ff316f8", "step": 62, "value": 0.669045517589207, "stage": "evolution", "elapsed_seconds": 40505.15394115448}, {"event_id": "335eff78906f44a9a76198ce2d7c97b6", "node_id": "335eff78906f44a9a76198ce2d7c97b6", "transition_id": "d21f21ac695e46609c546cf7d3032bfe", "step": 63, "value": 0.7157686973220955, "stage": "evolution", "elapsed_seconds": 41023.97852373123}, {"event_id": "b5ea95f548944c7688b153db881115c9", "node_id": "b5ea95f548944c7688b153db881115c9", "transition_id": "3e094b0186744d94b4839b89d80b5e92", "step": 64, "value": 0.7155986408413593, "stage": "evolution", "elapsed_seconds": 42256.994824409485}, {"event_id": "c8ab9b3cf7e640378853b746a04eb5de", "node_id": "c8ab9b3cf7e640378853b746a04eb5de", "transition_id": "35a35dc3954c43ad87e499f604b78ed5", "step": 65, "value": 0.7071342896585615, "stage": "fusion", "elapsed_seconds": 42945.19074511528}], "official_score": 0.69301, "valid_submission": true, "medal": "bronze", "source_grade": {"competition_id": "random-acts-of-pizza", "score": 0.69301, "gold_threshold": 0.97908, "silver_threshold": 0.76482, "bronze_threshold": 0.6921, "median_threshold": 0.5995950000000001, "any_medal": true, "gold_medal": false, "silver_medal": false, "bronze_medal": true, "above_median": true, "submission_exists": true, "valid_submission": true, "is_lower_better": false, "created_at": "2026-09-25T15:48:50.383189", "submission_path": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/runs/aq04-jigsaw-pizza-rerun-20260925/runs/20260925_034818_random-acts-of-pizza/workspace/ensembles_csv/top4ens-total_run_time0.58h.csv"}, "score_phase": "rerun-final", "thresholds": {"gold": 0.97908, "silver": 0.76482, "bronze": 0.6921}, "full_agent_budget_used": true, "note": "2026-09-25 独立重跑；从空白工作目录、空 journal 和空全局记忆开始，每题独占 A100 80GB，累计搜索预算 12h。 unkillable：4 CPU / 24 GiB RAM；AQ04、seed 42、模型及搜索参数保持一致。 已完成 MLE-bench 离线最终评分。", "hardware": "A100 80GB", "model": "muse-spark-1.3-contributor", "provider": "codex://opencode-go", "artifacts": [{"bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/experiments/mlebench-aq04-12h-rerun-20260925/contributors/liux/runs/liux.aq04-rerun-20260925.random-acts-of-pizza", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/experiments/mlebench-aq04-12h-rerun-20260925/contributors/liux/runs/liux.aq04-rerun-20260925.random-acts-of-pizza/live.json", "member": "live.json; independent rerun metrics and artifact index", "files": 1, "bytes": 0}, {"bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/experiments/mlebench-aq04-12h-rerun-20260925/contributors/liux/runs/liux.aq04-rerun-20260925.random-acts-of-pizza/artifacts", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/experiments/mlebench-aq04-12h-rerun-20260925/contributors/liux/runs/liux.aq04-rerun-20260925.random-acts-of-pizza/artifacts/logs-3e5e11ee315263f06a1615c1c2d609c84fdf8530fa1634aea4644f0e7d3ac784.tar.gz", "member": "experiments/mlebench-aq04-12h-rerun-20260925/contributors/liux/runs/liux.aq04-rerun-20260925.random-acts-of-pizza/artifacts/logs-3e5e11ee315263f06a1615c1c2d609c84fdf8530fa1634aea4644f0e7d3ac784.tar.gz", "files": 194, "bytes": 27471910}, {"bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/experiments/mlebench-aq04-12h-rerun-20260925/contributors/liux/runs/liux.aq04-rerun-20260925.random-acts-of-pizza/final", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/experiments/mlebench-aq04-12h-rerun-20260925/contributors/liux/runs/liux.aq04-rerun-20260925.random-acts-of-pizza/final/submission-2ae437437f1554f6884ea0ed7733a0456821930a6a724a0fb503c51d45ac4496.csv", "member": "Sealed final submission; SHA256 2ae437437f1554f6884ea0ed7733a0456821930a6a724a0fb503c51d45ac4496", "files": 1, "bytes": 33666}], "final_submission_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/experiments/mlebench-aq04-12h-rerun-20260925/contributors/liux/runs/liux.aq04-rerun-20260925.random-acts-of-pizza/final/submission-2ae437437f1554f6884ea0ed7733a0456821930a6a724a0fb503c51d45ac4496.csv", "config_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/experiments/mlebench-aq04-12h-rerun-20260925/contributors/liux/runs/liux.aq04-rerun-20260925.random-acts-of-pizza/config.yaml", "scheduler": {"job_id": "10927457", "partition": "unkillable", "observed_at": "2026-09-25T20:02:52.115713+00:00", "allocation": null}, "completed_candidates": 67, "pending_decisions": 1, "source_wrapper": {"state": "complete", "updated_at": "2026-09-25T19:48:50.520318+00:00", "active_elapsed_seconds": 43202.43855237961, "completed_transitions": 67, "fresh_run": true, "resume_from_previous_experiment": false, "job_id": "10927457", "attempt": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/runs/aq04-jigsaw-pizza-rerun-20260925/tasks/random-acts-of-pizza/attempt-01-10927457", "gpu": "NVIDIA A100-SXM4-80GB", "host": "cn-g022.server.mila.quebec", "started_at": "2026-09-25T07:47:55.288159+00:00", "search_pid": 1736289, "attempt_started_epoch": 1790322481.311243, "search_stopped_epoch": 1790365722.9820054, "search_exit_code": 75, "budget_complete": true, "run_root": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/runs/aq04-jigsaw-pizza-rerun-20260925/runs/20260925_034818_random-acts-of-pizza", "search_finished_at": "2026-09-25T19:48:45.273393+00:00", "finished_at": "2026-09-25T19:48:50.518481+00:00", "submission": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/runs/aq04-jigsaw-pizza-rerun-20260925/runs/20260925_034818_random-acts-of-pizza/workspace/ensembles_csv/top4ens-total_run_time0.58h.csv", "official_grade": "/network/scratch/l/liux/EvolveFold/MLEvolve_BO/runs/aq04-jigsaw-pizza-rerun-20260925/runs/20260925_034818_random-acts-of-pizza/logs/official-grade.json", "final_submission_sha256": "2ae437437f1554f6884ea0ed7733a0456821930a6a724a0fb503c51d45ac4496"}, "logs_scope": "完整可用日志快照已上传：2026-09-25T19:52:36.718405+00:00 排除数据集、工作模型缓存和凭据。", "curve_scope": "独立重跑的原生有效观察；没有继承首轮或续跑曲线。时间横轴仅使用已保存的 active 时间。"}, {"id": "liux.aq04-pizza-main-rerun2-20260925.random-acts-of-pizza", "experiment_id": "mlebench-aq04-12h-pizza-main-rerun2-20260925", "family": "MLEBench", "method": "AQ04", "dataset": "random-acts-of-pizza", "seed": 42, "fresh_run": true, "status": "stopped", "source_status": "stopped", "wrapper_status": "stopped", "source_updated_at": "2026-09-25T19:56:44.791196+00:00", "uploaded_at": "2026-09-25T19:57:40.748343+00:00", "elapsed_seconds": 0.0, "budget_seconds": 43200, "remaining_seconds": 43200.0, "maximize": true, "metric_name": "native public validation metric", "metrics": [], "official_score": null, "valid_submission": null, "medal": "none", "source_grade": null, "score_phase": "not-yet-graded", "thresholds": {}, "full_agent_budget_used": false, "note": "2026-09-25 Pizza main 第二轮独立重跑；从空白工作目录、空 journal 和空全局记忆开始，每题独占 A100 80GB，累计搜索预算 12h。 main：4 CPU / 24 GiB RAM；AQ04、seed 42、模型及搜索参数保持一致。 用户已取消此任务，自动重提已停用；本次没有开始搜索，也没有最终评分。", "hardware": "A100 80GB", "model": "muse-spark-1.3-contributor", "provider": "codex://opencode-go", "artifacts": [{"bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/experiments/mlebench-aq04-12h-pizza-main-rerun2-20260925/contributors/liux/runs/liux.aq04-pizza-main-rerun2-20260925.random-acts-of-pizza", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/experiments/mlebench-aq04-12h-pizza-main-rerun2-20260925/contributors/liux/runs/liux.aq04-pizza-main-rerun2-20260925.random-acts-of-pizza/live.json", "member": "live.json; independent rerun metrics and artifact index", "files": 1, "bytes": 0}, {"bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/experiments/mlebench-aq04-12h-pizza-main-rerun2-20260925/contributors/liux/runs/liux.aq04-pizza-main-rerun2-20260925.random-acts-of-pizza/artifacts", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/experiments/mlebench-aq04-12h-pizza-main-rerun2-20260925/contributors/liux/runs/liux.aq04-pizza-main-rerun2-20260925.random-acts-of-pizza/artifacts/logs-1421162ff9d3b8bb35e41e577a028d583be3353f932c32316890ab168037d192.tar.gz", "member": "experiments/mlebench-aq04-12h-pizza-main-rerun2-20260925/contributors/liux/runs/liux.aq04-pizza-main-rerun2-20260925.random-acts-of-pizza/artifacts/logs-1421162ff9d3b8bb35e41e577a028d583be3353f932c32316890ab168037d192.tar.gz", "files": 7, "bytes": 21285}], "final_submission_url": null, "config_url": null, "scheduler": {"job_id": "10933044", "partition": "main", "observed_at": "2026-09-25T19:57:40.748389+00:00", "allocation": null}, "completed_candidates": 0, "pending_decisions": 0, "source_wrapper": {"state": "stopped", "updated_at": "2026-09-25T19:56:44.791196+00:00", "active_elapsed_seconds": 0.0, "completed_transitions": 0, "fresh_run": true, "resume_from_previous_experiment": false, "stopped_at": "2026-09-25T19:56:44.791196+00:00", "job_id": "10933044", "reason": "User requested cancellation before the agent search started.", "automatic_submission_disabled": true, "release_receipt": {"job_id": "10933044", "state": "CANCELLED by 1500001736", "start": "2026-09-25T15:56:00", "end": "2026-09-25T15:56:04", "elapsed": "00:00:04", "exit_code": "0:0", "verified_at": "2026-09-25T19:56:44.791196+00:00"}}, "logs_scope": "完整可用日志快照已上传：2026-09-25T19:57:19.561928+00:00 排除数据集、工作模型缓存和凭据。", "curve_scope": "独立重跑的原生有效观察；没有继承首轮或续跑曲线。时间横轴仅使用已保存的 active 时间。"}], "bundles": [{"bundle_id": "bnvs-gpt-under-512mb", "source": "bnvs_gpt_under_512mb.zip", "source_archive_sha256": "33ecfd5de65e3cb205b3b781d1223c670ba038468c6845a05c7f2383a178b921", "path": "archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240", "bytes": 618918996, "files": 13757, "changes": [], "members_manifest": "archives/xixian/bnvs-gpt-under-512mb/members.json", "completeness": "All available local members except listed metadata/credential exclusions; credential values redacted where detected. Original packaging exclusions still apply.", "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/bnvs-gpt-under-512mb", "redacted_files": 0}, {"bundle_id": "gp6-gp6-draft-logs-with-private-scores", "source": "gp6_gp6-draft_logs_with_private_scores.zip", "source_archive_sha256": "3bc1e30def620a629deee8fea1356729abb22570786903f49fad84cbcad42b79", "path": "archives/xixian/gp6-gp6-draft-logs-with-private-scores/logs-7b2a3e058322.tar.zst", "sha256": "7b2a3e05832281a42f745f697155c42c6ef59359301c708d7b3496df1e02188f", "bytes": 16522885, "files": 1052, "changes": [], "members_manifest": "archives/xixian/gp6-gp6-draft-logs-with-private-scores/members.json", "completeness": "All available local members except listed metadata/credential exclusions; credential values redacted where detected. Original packaging exclusions still apply.", "format": "tar.zst", "archive_readback_verified": true, "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp6-gp6-draft-logs-with-private-scores/logs-7b2a3e058322.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp6-gp6-draft-logs-with-private-scores", "redacted_files": 0}, {"bundle_id": "gp7", "source": "gp7.zip", "source_archive_sha256": "ccfbd05e807bcae8b5e2800dbdef25e52cf77b524664a8adeba8ca3242f81c51", "path": "archives/xixian/gp7/logs-31ca423ebfab.tar.zst", "sha256": "31ca423ebfabbe5e7b019284026d4b5e56ffcf69cd0b4e76caf8bb4a870dae41", "bytes": 187937319, "files": 5599, "changes": [], "members_manifest": "archives/xixian/gp7/members.json", "completeness": "All available local members except listed metadata/credential exclusions; credential values redacted where detected. Original packaging exclusions still apply.", "format": "tar.zst", "archive_readback_verified": true, "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7/logs-31ca423ebfab.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7", "redacted_files": 0}, {"bundle_id": "gp7-ancestry-logei-hard14-full-logs-20260917", "source": "gp7_ancestry_logei_hard14_full_logs_20260917.zip", "source_archive_sha256": "98229b046bc80d045f33732f8796d3a0618f57abaa7193d7ce799cc8364d704d", "path": "archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917/logs-77c0e49ab8d6.tar.zst", "sha256": "77c0e49ab8d6df7268cefe20565a32eaa589661c5946ef2499c567afceab8104", "bytes": 43547152, "files": 2482, "changes": [], "members_manifest": "archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917/members.json", "completeness": "All available local members except listed metadata/credential exclusions; credential values redacted where detected. Original packaging exclusions still apply.", "format": "tar.zst", "archive_readback_verified": true, "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917/logs-77c0e49ab8d6.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917", "redacted_files": 0}, {"bundle_id": "gp7-no-ancestry-logei-hard14-full-logs-20260917", "source": "gp7_no_ancestry_logei_hard14_full_logs_20260917.zip", "source_archive_sha256": "7dd9546542a7c9f09ba10453dab245c1a35f0a59616e7955b2d11fbd605ac04f", "path": "archives/xixian/gp7-no-ancestry-logei-hard14-full-logs-20260917/logs-5cb1f19bf4da.tar.zst", "sha256": "5cb1f19bf4da2d6fd6b6aea2a936a5ebe2ad2c67f0a46cbfeed510ddf38aef8d", "bytes": 36592922, "files": 2427, "changes": [], "members_manifest": "archives/xixian/gp7-no-ancestry-logei-hard14-full-logs-20260917/members.json", "completeness": "All available local members except listed metadata/credential exclusions; credential values redacted where detected. Original packaging exclusions still apply.", "format": "tar.zst", "archive_readback_verified": true, "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-no-ancestry-logei-hard14-full-logs-20260917/logs-5cb1f19bf4da.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-no-ancestry-logei-hard14-full-logs-20260917", "redacted_files": 0}, {"bundle_id": "gp7-short-ucb-pibo-hard14-full-logs-20260917", "source": "gp7_short_ucb_pibo_hard14_full_logs_20260917.zip", "source_archive_sha256": "1b958de8ac19e8f5fae266de90d7ab9717950dd31b601aea5da82df2064bc1b1", "path": "archives/xixian/gp7-short-ucb-pibo-hard14-full-logs-20260917/logs-7d4a0bf30b9a.tar.zst", "sha256": "7d4a0bf30b9a2ab2c851ec14cd1b35edcbf277be29c9cdffb309d38ba56f821d", "bytes": 74057516, "files": 2426, "changes": [], "members_manifest": "archives/xixian/gp7-short-ucb-pibo-hard14-full-logs-20260917/members.json", "completeness": "All available local members except listed metadata/credential exclusions; credential values redacted where detected. Original packaging exclusions still apply.", "format": "tar.zst", "archive_readback_verified": true, "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-short-ucb-pibo-hard14-full-logs-20260917/logs-7d4a0bf30b9a.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-short-ucb-pibo-hard14-full-logs-20260917", "redacted_files": 0}, {"bundle_id": "gp7-three-bo-analysis-20260916", "source": "gp7_three_bo_analysis_20260916.zip", "source_archive_sha256": "4dbe66b67418575cd3e3e8761f62700f671e342107411206f3497e0a41e24454", "path": "archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f", "bytes": 195519661, "files": 8275, "changes": [], "members_manifest": "archives/xixian/gp7-three-bo-analysis-20260916/members.json", "completeness": "All available local members except listed metadata/credential exclusions; credential values redacted where detected. Original packaging exclusions still apply.", "format": "tar.zst", "archive_readback_verified": true, "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp7-three-bo-analysis-20260916", "redacted_files": 0}, {"bundle_id": "nanogpt-analysis-20260917-164244", "source": "nanogpt_analysis_20260917_164244.zip", "source_archive_sha256": "633d48c20287e8a1c4a79be0a169b2d9f9fd329bd0b13ecfe5afffa95ab15cb7", "path": "archives/xixian/nanogpt-analysis-20260917-164244/logs-dc6a57e6dbb8.tar.zst", "sha256": "dc6a57e6dbb82c6696661ad57415f89f08531979db0b6614f19ce12db58983a7", "bytes": 40911482, "files": 9073, "changes": [], "members_manifest": "archives/xixian/nanogpt-analysis-20260917-164244/members.json", "completeness": "All available local members except listed metadata/credential exclusions; credential values redacted where detected. Original packaging exclusions still apply.", "format": "tar.zst", "archive_readback_verified": true, "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/nanogpt-analysis-20260917-164244/logs-dc6a57e6dbb8.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/nanogpt-analysis-20260917-164244", "redacted_files": 0}, {"bundle_id": "study7-complete-for-gpt-20260919", "source": "study7_complete_for_gpt_20260919.zip", "source_archive_sha256": "57683315653fdfe811472abb3a0d6cccfe1cb22236e5e232e14b56d685219e08", "path": "archives/xixian/study7-complete-for-gpt-20260919/logs-ee645141ae41.tar.zst", "sha256": "ee645141ae417cc245c3e1412a8331050e8000178b3fca386cb53d5263f29def", "bytes": 52149039, "files": 4263, "changes": [], "members_manifest": "archives/xixian/study7-complete-for-gpt-20260919/members.json", "completeness": "All available local members except listed metadata/credential exclusions; credential values redacted where detected. Original packaging exclusions still apply.", "format": "tar.zst", "archive_readback_verified": true, "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/study7-complete-for-gpt-20260919/logs-ee645141ae41.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/study7-complete-for-gpt-20260919", "redacted_files": 0}, {"bundle_id": "01-read-first-and-final-states", "source": "nanoGPT/01_read_first_and_final_states.zip", "source_archive_sha256": "69a8d424e0f332bfbe69047b1dcf1a6632e5b2d20c9d5f909e20a3b296d8cfe6", "path": "archives/xixian/01-read-first-and-final-states/logs-c828e9f97191.tar.zst", "sha256": "c828e9f97191ffc3f6f4fa6f39045e6be494d2ab2ea3337eff18dfd2830908ba", "bytes": 39788916, "files": 24809, "changes": [], "members_manifest": "archives/xixian/01-read-first-and-final-states/members.json", "completeness": "All available local members except listed metadata/credential exclusions; credential values redacted where detected. Original packaging exclusions still apply.", "format": "tar.zst", "archive_readback_verified": true, "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/01-read-first-and-final-states/logs-c828e9f97191.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/01-read-first-and-final-states", "redacted_files": 0}, {"bundle_id": "02-study-run-logs", "source": "nanoGPT/02_study_run_logs.zip", "source_archive_sha256": "af5a9188db4240d9f4bd0c48d442547ae00c8aa6de578a711624e5d9a28640d5", "path": "archives/xixian/02-study-run-logs/logs-50a9df8a8a5a.tar.zst", "sha256": "50a9df8a8a5acb631814aa5ea6a0f2e8b7d47ec05bff989ffaa975aa9ca71d25", "bytes": 43122024, "files": 7983, "changes": [], "members_manifest": "archives/xixian/02-study-run-logs/members.json", "completeness": "All available local members except listed metadata/credential exclusions; credential values redacted where detected. Original packaging exclusions still apply.", "format": "tar.zst", "archive_readback_verified": true, "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/02-study-run-logs/logs-50a9df8a8a5a.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/02-study-run-logs", "redacted_files": 0}, {"bundle_id": "03-historical-run-logs", "source": "nanoGPT/03_historical_run_logs.zip", "source_archive_sha256": "075173b5e27944d91badd3e379b1e7d33ce9ced40a0bf6199c9f457674143d77", "path": "archives/xixian/03-historical-run-logs/logs-18799fb1fca5.tar.zst", "sha256": "18799fb1fca5aa0c206be70e600c8d13ba65086d8360620e18525cd877b72d9b", "bytes": 55967098, "files": 7045, "changes": [], "members_manifest": "archives/xixian/03-historical-run-logs/members.json", "completeness": "All available local members except listed metadata/credential exclusions; credential values redacted where detected. Original packaging exclusions still apply.", "format": "tar.zst", "archive_readback_verified": true, "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/03-historical-run-logs/logs-18799fb1fca5.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/03-historical-run-logs", "redacted_files": 0}, {"bundle_id": "analysis-20260917", "source": "analysis_20260917", "source_archive_sha256": null, "path": "archives/xixian/analysis-20260917/logs-fb5e34cb4c89.tar.zst", "sha256": "fb5e34cb4c899098d0665f1ae48ac848cb4ab22bbf5ebbeb41522f2f97c4e2c5", "bytes": 1683249, "files": 162, "changes": [{"path": ".DS_Store", "action": "excluded_metadata_or_credential_file"}], "members_manifest": "archives/xixian/analysis-20260917/members.json", "completeness": "All available local members except listed metadata/credential exclusions; credential values redacted where detected. Original packaging exclusions still apply.", "format": "tar.zst", "archive_readback_verified": true, "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/analysis-20260917/logs-fb5e34cb4c89.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/analysis-20260917", "redacted_files": 0}, {"bundle_id": "gp6-gp7-hard14-comparison", "source": "gp6_gp7_hard14_comparison", "source_archive_sha256": null, "path": "archives/xixian/gp6-gp7-hard14-comparison/logs-a5113cb33a02.tar.zst", "sha256": "a5113cb33a02103ecb8bdc89684c6560826708f79470a2596f572b11793e9a0c", "bytes": 2878599, "files": 154, "changes": [{"path": ".DS_Store", "action": "excluded_metadata_or_credential_file"}], "members_manifest": "archives/xixian/gp6-gp7-hard14-comparison/members.json", "completeness": "All available local members except listed metadata/credential exclusions; credential values redacted where detected. Original packaging exclusions still apply.", "format": "tar.zst", "archive_readback_verified": true, "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/gp6-gp7-hard14-comparison/logs-a5113cb33a02.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/gp6-gp7-hard14-comparison", "redacted_files": 0}, {"bundle_id": "setting-comparison-20260917", "source": "setting_comparison_20260917", "source_archive_sha256": null, "path": "archives/xixian/setting-comparison-20260917/logs-6045d721b392.tar.zst", "sha256": "6045d721b3922b63d1c7cf9ae3154a41a164af4a9aea4600cd88adc3c99624db", "bytes": 57039, "files": 34, "changes": [{"path": ".DS_Store", "action": "excluded_metadata_or_credential_file"}], "members_manifest": "archives/xixian/setting-comparison-20260917/members.json", "completeness": "All available local members except listed metadata/credential exclusions; credential values redacted where detected. Original packaging exclusions still apply.", "format": "tar.zst", "archive_readback_verified": true, "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/setting-comparison-20260917/logs-6045d721b392.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/setting-comparison-20260917", "redacted_files": 0}, {"bundle_id": "workflow-learning-curves-20260917", "source": "workflow_learning_curves_20260917", "source_archive_sha256": null, "path": "archives/xixian/workflow-learning-curves-20260917/logs-0d953a7358c3.tar.zst", "sha256": "0d953a7358c351f024f8fd6f8d3f2cc4cff52f1e7bf68fd97e58078dfb9725c9", "bytes": 28318882, "files": 144, "changes": [{"path": ".DS_Store", "action": "excluded_metadata_or_credential_file"}], "members_manifest": "archives/xixian/workflow-learning-curves-20260917/members.json", "completeness": "All available local members except listed metadata/credential exclusions; credential values redacted where detected. Original packaging exclusions still apply.", "format": "tar.zst", "archive_readback_verified": true, "download_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/resolve/archives/xixian/workflow-learning-curves-20260917/logs-0d953a7358c3.tar.zst", "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/archives/xixian/workflow-learning-curves-20260917", "redacted_files": 0}], "reports": [{"title": "MLEBench 全部 workflow 奖牌分析", "url": "reports/analysis-20260917-b3356305/index.html", "bundle_id": "analysis-20260917", "member": "README.md"}, {"title": "GP6 / GP7 hard14 对比", "url": "reports/gp6-gp7-hard14-comparison-d9ddfae8/index.html", "bundle_id": "gp6-gp7-hard14-comparison", "member": "REPORT.md"}, {"title": "实际配置差异", "url": "reports/setting-comparison-20260917-b3356305/index.html", "bundle_id": "setting-comparison-20260917", "member": "README.md"}, {"title": "学习曲线分析", "url": "reports/workflow-learning-curves-20260917-b21d0bb4/index.html", "bundle_id": "workflow-learning-curves-20260917", "member": "REPORT_zh.md"}, {"title": "BO advantage 分析", "url": "reports/workflow-learning-curves-20260917-f47f0b16/index.html", "bundle_id": "workflow-learning-curves-20260917", "member": "BO_ADVANTAGE_zh.md"}, {"title": "BO variance 分析", "url": "reports/workflow-learning-curves-20260917-0ca8db6c/index.html", "bundle_id": "workflow-learning-curves-20260917", "member": "BO_VARIANCE_zh.md"}, {"title": "GP6 学习分析", "url": "reports/workflow-learning-curves-20260917-09cb5fd0/index.html", "bundle_id": "workflow-learning-curves-20260917", "member": "GP6_LEARNING_zh.md"}, {"title": "nanoGPT 开发最终报告", "url": "reports/01-read-first-and-final-states-45cc30fd/index.html", "bundle_id": "01-read-first-and-final-states", "member": "MLEvolve_BO/research/nanogpt_bo_20260917/analysis/final_closeout_20260918/REPORT_zh.md"}, {"title": "Study7 正式实验分析", "url": "reports/study7-complete-for-gpt-20260919-251d3b7f/index.html", "bundle_id": "study7-complete-for-gpt-20260919", "member": "study7_complete_for_gpt_20260919/analysis_previous/REPORT_zh.md"}, {"title": "Study7 离线 β 重评分", "url": "reports/study7-complete-for-gpt-20260919-52d959b7/index.html", "bundle_id": "study7-complete-for-gpt-20260919", "member": "study7_complete_for_gpt_20260919/analysis_large_beta/REPORT_zh.md"}, {"title": "AQ04 已有结果与运行证据", "url": "reports/aq04/index.html", "member": "analyses/aq04-archive-20260922/REPORT.md"}], "aq04_summary": {"imported_at": "2026-09-22T05:20:46.029942+00:00", "run_count": 14, "valid_scores": 14, "medals": {"none": 9, "silver": 4, "gold": 1}, "snapshot_status": {"completed": 14}, "formal_result_count": 7, "full_budget_flag_count": 7, "files": 1108, "bytes": 1867392234, "note": "Snapshot, not a scheduler check. Scores exist for incomplete attempts. No remote logs were moved or overwritten.", "source_inventory_captured_at": "2026-09-22T04:55:11.180721+00:00"}, "verification": [{"check": "348 normalized grading policies versus original JSONL scores", "passed": true, "count": 348}], "cadence": "历史归档保留；AQ04 七题续跑：指标约 60 秒、完整日志约 10 分钟同步一次，最终结果自动归档。", "publication_complete": true, "publication_verification": {"verified_at": "2026-09-22T05:25:02.126592+00:00", "archives": [{"path": "archives/xixian/bnvs-gpt-under-512mb/logs-1e1b59643f21.zip", "bytes": 618918996, "sha256": "1e1b59643f21ab4bcaa99da2fe3678109d02706e15961e365d560c81a59b2240", "xet_hash": "22e8b0e9a0e28e378c8c56b7ff808b249dd41c16ef4e050d3328ac35d5f610a3"}, {"path": "archives/xixian/gp6-gp6-draft-logs-with-private-scores/logs-7b2a3e058322.tar.zst", "bytes": 16522885, "sha256": "7b2a3e05832281a42f745f697155c42c6ef59359301c708d7b3496df1e02188f", "xet_hash": "9952ec21c15d785efa3c852dc7901a2e5c8cb90994d687ef09e9eefc8ae512bc"}, {"path": "archives/xixian/gp7/logs-31ca423ebfab.tar.zst", "bytes": 187937319, "sha256": "31ca423ebfabbe5e7b019284026d4b5e56ffcf69cd0b4e76caf8bb4a870dae41", "xet_hash": "06a9e2029801f73f2c0f887b4683740b28ba4bb9aa5aeb514ace3e60ab770619"}, {"path": "archives/xixian/gp7-ancestry-logei-hard14-full-logs-20260917/logs-77c0e49ab8d6.tar.zst", "bytes": 43547152, "sha256": "77c0e49ab8d6df7268cefe20565a32eaa589661c5946ef2499c567afceab8104", "xet_hash": "daa2d2be1a20effe670564fa86ca0ab11c01ec5621a1d6729cb28656a34f8a45"}, {"path": "archives/xixian/gp7-no-ancestry-logei-hard14-full-logs-20260917/logs-5cb1f19bf4da.tar.zst", "bytes": 36592922, "sha256": "5cb1f19bf4da2d6fd6b6aea2a936a5ebe2ad2c67f0a46cbfeed510ddf38aef8d", "xet_hash": "7199f3515539defc2791e24f1541d825a59167bac56fce2a101cdde3cea8b931"}, {"path": "archives/xixian/gp7-short-ucb-pibo-hard14-full-logs-20260917/logs-7d4a0bf30b9a.tar.zst", "bytes": 74057516, "sha256": "7d4a0bf30b9a2ab2c851ec14cd1b35edcbf277be29c9cdffb309d38ba56f821d", "xet_hash": "612f6c4e1ffa8b5ca84f6b1e983a00329f548ac6b16c81de3b4ee0019d1e7488"}, {"path": "archives/xixian/gp7-three-bo-analysis-20260916/logs-599de92c4e3b.tar.zst", "bytes": 195519661, "sha256": "599de92c4e3b0df5fe60b55d755a88d6d484dad2c2299ff2fbbe8456d0fb6a1f", "xet_hash": "7ffc14ec722a8bf46509761b145c00f37eb139dcf64d2101ba42894d9d05f0a6"}, {"path": "archives/xixian/nanogpt-analysis-20260917-164244/logs-dc6a57e6dbb8.tar.zst", "bytes": 40911482, "sha256": "dc6a57e6dbb82c6696661ad57415f89f08531979db0b6614f19ce12db58983a7", "xet_hash": "7b023fb7b7432d2e0210a1d6fbe5bb2f1d701777ee72bf76c232f7d583c5563d"}, {"path": "archives/xixian/study7-complete-for-gpt-20260919/logs-ee645141ae41.tar.zst", "bytes": 52149039, "sha256": "ee645141ae417cc245c3e1412a8331050e8000178b3fca386cb53d5263f29def", "xet_hash": "065d43c854a99a600c53231ad87265d30b3f24bfec702e59cd3bbf989b738353"}, {"path": "archives/xixian/01-read-first-and-final-states/logs-c828e9f97191.tar.zst", "bytes": 39788916, "sha256": "c828e9f97191ffc3f6f4fa6f39045e6be494d2ab2ea3337eff18dfd2830908ba", "xet_hash": "be7fb12733f9324a23f8182de37062aa4d2e6f694b04f5823f547cf9c08855cd"}, {"path": "archives/xixian/02-study-run-logs/logs-50a9df8a8a5a.tar.zst", "bytes": 43122024, "sha256": "50a9df8a8a5acb631814aa5ea6a0f2e8b7d47ec05bff989ffaa975aa9ca71d25", "xet_hash": "9b864d8eda6abe42f3781c0deaf913607a1bec2c6daf77301ba9d5e2ceb1c5e8"}, {"path": "archives/xixian/03-historical-run-logs/logs-18799fb1fca5.tar.zst", "bytes": 55967098, "sha256": "18799fb1fca5aa0c206be70e600c8d13ba65086d8360620e18525cd877b72d9b", "xet_hash": "25a719180b4927c46f9de67ce1911eb64a37245d51b31a1c218aaeabc43526d1"}, {"path": "archives/xixian/analysis-20260917/logs-fb5e34cb4c89.tar.zst", "bytes": 1683249, "sha256": "fb5e34cb4c899098d0665f1ae48ac848cb4ab22bbf5ebbeb41522f2f97c4e2c5", "xet_hash": "4b055631bdd082fc57f0be78436a9be8c3adc53594ac94aa67bc2945bd237fbf"}, {"path": "archives/xixian/gp6-gp7-hard14-comparison/logs-a5113cb33a02.tar.zst", "bytes": 2878599, "sha256": "a5113cb33a02103ecb8bdc89684c6560826708f79470a2596f572b11793e9a0c", "xet_hash": "4b3df026d98b7826248e2c8add10ccfafa3806980d1c54a67dc606cb9ccb9273"}, {"path": "archives/xixian/setting-comparison-20260917/logs-6045d721b392.tar.zst", "bytes": 57039, "sha256": "6045d721b3922b63d1c7cf9ae3154a41a164af4a9aea4600cd88adc3c99624db", "xet_hash": "3e07318f028cd74030b3b5f4c6a81bce646c9ac434707425e17a81b6a775d4d5"}, {"path": "archives/xixian/workflow-learning-curves-20260917/logs-0d953a7358c3.tar.zst", "bytes": 28318882, "sha256": "0d953a7358c351f024f8fd6f8d3f2cc4cff52f1e7bf68fd97e58078dfb9725c9", "xet_hash": "5d70c2f21a75b5edb8bce1336acdbb8448e9007c8b65c839e0a757cceee16010"}], "archive_count": 16, "archive_bytes": 1437972779, "metadata_objects": 1248, "anonymous_manifest_readback": true, "anonymous_archive_sample_sha256": true, "all_tar_zst_members_locally_readback_verified": true, "source_logs_unchanged": true, "aq04_original_prefix_unchanged": true, "cadence": "one-shot", "active_services": []}, "aq04_continuation": {"updated_at": "2026-09-25T17:07:11.144832+00:00", "rows": 7, "states": {"completed": 7}, "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/experiments/mlebench-aq04-12h-20260921/continuations/liux-mila-20260924", "service": {"source": "Slurm shared AQ04 CPU services", "metrics_interval_seconds": 60, "artifacts_interval_seconds": 600, "expires_epoch": 1790521214.0, "resume_command": "sbatch /network/scratch/l/liux/EvolveFold/.staging/aq04-services-20260925/services.sbatch", "state": "running", "periodic_upload_enabled": true, "resumed_at": "2026-09-25T05:30:03.052522+00:00", "job_id": "10929806", "controller_job_id": "10929806", "previous_service": {"job_id": "10919510", "controller_job_id": "10919292", "state": "stopped_by_user", "one_shot_job_id": "10920767", "final_archives_uploaded_at": "2026-09-24T19:19:35.868424+00:00"}, "controller_submitted_at": "2026-09-25T05:30:33.605345+00:00", "publisher_submitted_at": "2026-09-25T05:30:35.153211+00:00", "verified_at": "2026-09-25T05:31:32.896572+00:00", "started_at": "2026-09-25T15:02:14.663370+00:00", "expires_at": "2026-09-27T15:00:14+00:00"}, "user_stop": null, "user_resume": {"requested_at": "2026-09-25T05:30:03.052522+00:00", "reason": "Explicit user request to finish the remaining AQ04 tasks with a replacement OpenCode token", "previous_stop_record": "history/user-stop-20260924.json", "tasks": {"aptos2019-blindness-detection": {"active_elapsed_seconds": 29588.684705495834, "remaining_seconds": 13611.315294504166, "completed_transitions": 57, "release_receipt": {"job_id": "10919452", "state": "COMPLETED", "end": "2026-09-24T15:15:24", "exit_code": "0:0", "end_epoch": 1790277324.0, "verified_at": "2026-09-25T05:30:03.128458+00:00"}}, "mlsp-2013-birds": {"active_elapsed_seconds": 15894.91823220253, "remaining_seconds": 27305.08176779747, "completed_transitions": 159, "release_receipt": {"job_id": "10919452", "state": "COMPLETED", "end": "2026-09-24T15:15:24", "exit_code": "0:0", "end_epoch": 1790277324.0, "verified_at": "2026-09-25T05:30:03.128458+00:00"}}, "nomad2018-predict-transparent-conductors": {"active_elapsed_seconds": 41190.669416189194, "remaining_seconds": 2009.3305838108063, "completed_transitions": 232, "release_receipt": {"job_id": "10919451", "state": "COMPLETED", "end": "2026-09-24T15:15:25", "exit_code": "0:0", "end_epoch": 1790277325.0, "verified_at": "2026-09-25T05:30:03.102563+00:00"}}, "random-acts-of-pizza": {"active_elapsed_seconds": 41441.326315164566, "remaining_seconds": 1758.673684835434, "completed_transitions": 209, "release_receipt": {"job_id": "10919451", "state": "COMPLETED", "end": "2026-09-24T15:15:25", "exit_code": "0:0", "end_epoch": 1790277325.0, "verified_at": "2026-09-25T05:30:03.102563+00:00"}}, "ranzcr-clip-catheter-line-classification": {"active_elapsed_seconds": 31663.870396375656, "remaining_seconds": 11536.129603624344, "completed_transitions": 34, "release_receipt": {"job_id": "10919452", "state": "COMPLETED", "end": "2026-09-24T15:15:24", "exit_code": "0:0", "end_epoch": 1790277324.0, "verified_at": "2026-09-25T05:30:03.128458+00:00"}}, "text-normalization-challenge-english-language": {"active_elapsed_seconds": 28300.934756994247, "remaining_seconds": 14899.065243005753, "completed_transitions": 65, "release_receipt": {"job_id": "10919452", "state": "COMPLETED", "end": "2026-09-24T15:15:24", "exit_code": "0:0", "end_epoch": 1790277324.0, "verified_at": "2026-09-25T05:30:03.128458+00:00"}}}, "gpu": "A100 80GB", "gpu_count": 6, "original_search_budget_seconds": 43200, "model": "muse-spark-1.3-contributor", "provider": "codex://opencode-go", "credential_rotated": true, "provider_check": {"model": "muse-spark-1.3-contributor", "provider": "codex://opencode-go", "reasoning": "high", "result": {"message": "AQ04_RESUME_OK", "ok": true}, "duration_seconds": 9.241989850997925, "checked_epoch": 1790314145.4014719}, "automatic_resubmission_enabled": true, "state": "running_verified", "controller_job_id": "10927026", "publisher_job_id": "10927027", "gpu_job_ids": {"main": "10927028", "short-unkillable": "10927029"}, "allocation_note": "Main allocation reduced from 4h to 1h30 for backfill; 12h cumulative search caps and saved remaining budgets are unchanged. Main tasks have 33.49 and 29.31 minutes of search left.", "runtime_verified_at": "2026-09-25T05:39:49.895050+00:00"}, "all_complete": true}, "aq04_reruns": {"mlebench-aq04-12h-rerun-20260925": {"updated_at": "2026-09-25T20:02:52.889703+00:00", "states": {"completed": 2}, "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/experiments/mlebench-aq04-12h-rerun-20260925/contributors/liux", "service": {"source": "Slurm shared AQ04 CPU services", "metrics_interval_seconds": 60, "artifacts_interval_seconds": 600, "state": "running", "periodic_upload_enabled": true, "expires_epoch": 1790521214.0, "job_id": "10929806", "controller_job_id": "10929806", "resume_command": "sbatch /network/scratch/l/liux/EvolveFold/.staging/aq04-services-20260925/services.sbatch", "started_at": "2026-09-25T15:02:14.666274+00:00", "expires_at": "2026-09-27T15:00:14+00:00"}, "all_complete": true}, "mlebench-aq04-12h-pizza-main-rerun2-20260925": {"updated_at": "2026-09-25T19:57:57.606387+00:00", "states": {"stopped": 1}, "bucket_url": "https://huggingface.co/buckets/jzshared/autoresearch-runs/tree/experiments/mlebench-aq04-12h-pizza-main-rerun2-20260925/contributors/liux", "service": {"source": "Dedicated Pizza main rerun CPU service", "state": "stopped", "metrics_interval_seconds": 60, "artifacts_interval_seconds": 600, "periodic_upload_enabled": false, "job_id": "10933043", "controller_job_id": "10933043", "resume_command": null, "started_at": "2026-09-25T19:11:34.507159+00:00", "expires_epoch": 1790536171.0, "expires_at": "2026-09-27T19:09:31+00:00", "stopped_at": "2026-09-25T19:56:44.791196+00:00", "automatic_submission_disabled": true, "stop_reason": "User requested cancellation of the new Pizza experiment; final one-shot publication only."}, "all_complete": false}}}