{ "bench_version": 1, "track": "dynamics", "model": "rnn_small", "metric_direction": "lower is better", "n_seeds": 8, "baseline": { "best_cfg": { "lr": 0.01, "weight_decay": 0.0 }, "sweep": [ { "cfg": { "lr": 0.001, "weight_decay": 0.0 }, "mean": 0.0014035784406587481 }, { "cfg": { "lr": 0.001, "weight_decay": 0.0001 }, "mean": 0.0013894051662646234 }, { "cfg": { "lr": 0.003, "weight_decay": 0.0 }, "mean": 0.000857145045301877 }, { "cfg": { "lr": 0.003, "weight_decay": 0.0001 }, "mean": 0.0008355810859939083 }, { "cfg": { "lr": 0.01, "weight_decay": 0.0 }, "mean": 0.0004466182872420177 }, { "cfg": { "lr": 0.01, "weight_decay": 0.0001 }, "mean": 0.0004611926560755819 } ], "full": { "mean": 0.00039566773739352357, "std": 0.00014846719173678902, "per_seed": [ 0.0003142073401249945, 0.00040627806447446346, 0.0003180095227435231, 0.0007479782216250896, 0.00039004243444651365, 0.00019843246263917536, 0.000411077169701457, 0.00037931668339297175 ], "n": 8 } }, "idea": { "mean": 0.0003887512521032477, "std": 0.0001616191005487337, "per_seed": [ 0.0002601368469186127, 0.00042557879351079464, 0.00030667721875943244, 0.0007812847616150975, 0.0003697451902553439, 0.00021702404774259776, 0.0003767137532122433, 0.00037284940481185913 ], "n": 8 }, "comparison": { "delta_mean": -6.916485290275887e-06, "idea_wins": 5, "n_pairs": 8, "per_seed_diffs": [ -5.40704932063818e-05, 1.9300729036331177e-05, -1.1332303984090686e-05, 3.330653999000788e-05, -2.029724419116974e-05, 1.8591585103422403e-05, -3.4363416489213705e-05, -6.467278581112623e-06 ], "p_value": 0.51045, "mde": 2.474683454228356e-05, "mde_rel_pct": 6.254448418085408, "verdict": "no significant win", "system_worked": false }, "mechanism_signature": { "predicted": "feasibility weighting should reduce terminal-set error", "observed_event_mse_mean": 4.5046147988614393e-05, "observed_nonevent_mse_mean": 0.0004491949330258649, "confirmed": true, "idea_sweep": [ { "cfg": { "lr": 0.001, "weight_decay": 0.0, "alpha": 0.5 }, "mean": 0.0013711843639612198 }, { "cfg": { "lr": 0.001, "weight_decay": 0.0, "alpha": 1.0 }, "mean": 0.00134452705970034 }, { "cfg": { "lr": 0.001, "weight_decay": 0.0, "alpha": 2.0 }, "mean": 0.0013239112158771604 }, { "cfg": { "lr": 0.001, "weight_decay": 0.0001, "alpha": 0.5 }, "mean": 0.001358222885755822 }, { "cfg": { "lr": 0.001, "weight_decay": 0.0001, "alpha": 1.0 }, "mean": 0.0013323448947630823 }, { "cfg": { "lr": 0.001, "weight_decay": 0.0001, "alpha": 2.0 }, "mean": 0.001312095031607896 }, { "cfg": { "lr": 0.003, "weight_decay": 0.0, "alpha": 0.5 }, "mean": 0.0008442715043202043 }, { "cfg": { "lr": 0.003, "weight_decay": 0.0, "alpha": 1.0 }, "mean": 0.0008238502341555431 }, { "cfg": { "lr": 0.003, "weight_decay": 0.0, "alpha": 2.0 }, "mean": 0.0008038862433750182 }, { "cfg": { "lr": 0.003, "weight_decay": 0.0001, "alpha": 0.5 }, "mean": 0.0008234149281634018 }, { "cfg": { "lr": 0.003, "weight_decay": 0.0001, "alpha": 1.0 }, "mean": 0.0008033880876610056 }, { "cfg": { "lr": 0.003, "weight_decay": 0.0001, "alpha": 2.0 }, "mean": 0.000783455150667578 }, { "cfg": { "lr": 0.01, "weight_decay": 0.0, "alpha": 0.5 }, "mean": 0.00044341940520098433 }, { "cfg": { "lr": 0.01, "weight_decay": 0.0, "alpha": 1.0 }, "mean": 0.0004603777633747086 }, { "cfg": { "lr": 0.01, "weight_decay": 0.0, "alpha": 2.0 }, "mean": 0.0004929038841510192 }, { "cfg": { "lr": 0.01, "weight_decay": 0.0001, "alpha": 0.5 }, "mean": 0.00046618811757070944 }, { "cfg": { "lr": 0.01, "weight_decay": 0.0001, "alpha": 1.0 }, "mean": 0.0004956323173246346 }, { "cfg": { "lr": 0.01, "weight_decay": 0.0001, "alpha": 2.0 }, "mean": 0.000535586521436926 } ] } }