{ "bench_version": 1, "track": "tabular", "model": "mlp_tiny", "metric_direction": "lower is better", "n_seeds": 8, "baseline": { "sweep": { "best_cfg": { "lr": 0.01 }, "sweep": [ { "cfg": { "lr": 0.001 }, "mean": 32.33934259414673 }, { "cfg": { "lr": 0.003 }, "mean": 16.37940740585327 }, { "cfg": { "lr": 0.01 }, "mean": 10.050109148025513 } ], "full": { "mean": 10.512850999832153, "std": 1.6350143489482907, "per_seed": [ 8.558663368225098, 10.783540725708008, 9.733381271362305, 11.12485122680664, 8.562338829040527, 12.776362419128418, 9.492801666259766, 13.070868492126465 ], "n": 8 } }, "best_config": { "lr": 0.01 }, "full": { "per_seed": [ 8.558663368225098, 10.783540725708008, 9.733381271362305, 11.12485122680664, 8.562338829040527, 12.776362419128418, 9.492801666259766, 13.070868492126465 ], "aux": [ { "upward_fraction": 0.5784375071525574, "mean_left_gap": 0.009560184553265572, "codes": 16 }, { "upward_fraction": 0.5663281083106995, "mean_left_gap": 0.03742143139243126, "codes": 16 }, { "upward_fraction": 0.5204687118530273, "mean_left_gap": 0.07099631428718567, "codes": 16 }, { "upward_fraction": 0.5039452910423279, "mean_left_gap": 0.08094017207622528, "codes": 16 }, { "upward_fraction": 0.5638671517372131, "mean_left_gap": 0.05500025674700737, "codes": 16 }, { "upward_fraction": 0.19499999284744263, "mean_left_gap": 0.03867589682340622, "codes": 16 }, { "upward_fraction": 0.3338281214237213, "mean_left_gap": 0.015087975189089775, "codes": 16 }, { "upward_fraction": 0.2247656136751175, "mean_left_gap": 0.09521723538637161, "codes": 16 } ], "mean": 10.512850999832153 } }, "idea": { "config": { "lr": 0.01 }, "per_seed": [ 9.773167610168457, 11.56466007232666, 13.178303718566895, 14.895204544067383, 10.585610389709473, 15.57695484161377, 10.29378890991211, 14.999134063720703 ], "aux": [ { "upward_fraction": 0.0, "mean_left_gap": 0.09891153126955032, "codes": 16 }, { "upward_fraction": 0.0, "mean_left_gap": 0.1319166123867035, "codes": 16 }, { "upward_fraction": 0.0, "mean_left_gap": 0.20265933871269226, "codes": 16 }, { "upward_fraction": 0.0, "mean_left_gap": 0.20551525056362152, "codes": 16 }, { "upward_fraction": 0.0, "mean_left_gap": 0.1258753538131714, "codes": 16 }, { "upward_fraction": 0.0, "mean_left_gap": 0.14724649488925934, "codes": 16 }, { "upward_fraction": 0.0, "mean_left_gap": 0.09176831692457199, "codes": 16 }, { "upward_fraction": 0.0, "mean_left_gap": 0.2208053320646286, "codes": 16 } ], "mean": 12.608353018760681, "sweep": [ { "lr": 0.003, "per_seed": [ 17.26456069946289, 16.607093811035156, 19.64568328857422, 18.041486740112305, 17.236543655395508, 19.011493682861328, 15.007841110229492, 20.771881103515625 ], "aux": [ { "upward_fraction": 0.0, "mean_left_gap": 0.11044175922870636, "codes": 16 }, { "upward_fraction": 0.0, "mean_left_gap": 0.13866443932056427, "codes": 16 }, { "upward_fraction": 0.0, "mean_left_gap": 0.18446868658065796, "codes": 16 }, { "upward_fraction": 0.0, "mean_left_gap": 0.20145590603351593, "codes": 16 }, { "upward_fraction": 0.0, "mean_left_gap": 0.14068220555782318, "codes": 16 }, { "upward_fraction": 0.0, "mean_left_gap": 0.13724036514759064, "codes": 16 }, { "upward_fraction": 0.0, "mean_left_gap": 0.10448167473077774, "codes": 16 }, { "upward_fraction": 0.0, "mean_left_gap": 0.22862808406352997, "codes": 16 } ], "mean": 17.948323011398315 }, { "lr": 0.001, "per_seed": [ 27.97640609741211, 42.11697006225586, 70.37665557861328, 48.89053726196289, 47.3976936340332, 83.98968505859375, 23.241455078125, 54.805789947509766 ], "aux": [ { "upward_fraction": 0.0, "mean_left_gap": 0.09334667772054672, "codes": 16 }, { "upward_fraction": 0.0, "mean_left_gap": 0.1060170829296112, "codes": 16 }, { "upward_fraction": 0.0, "mean_left_gap": 0.10366649180650711, "codes": 16 }, { "upward_fraction": 0.0, "mean_left_gap": 0.13664911687374115, "codes": 16 }, { "upward_fraction": 0.0, "mean_left_gap": 0.09772422909736633, "codes": 16 }, { "upward_fraction": 0.0, "mean_left_gap": 0.07773704826831818, "codes": 16 }, { "upward_fraction": 0.0, "mean_left_gap": 0.09394310414791107, "codes": 16 }, { "upward_fraction": 0.0, "mean_left_gap": 0.15413281321525574, "codes": 16 } ], "mean": 49.84939908981323 }, { "lr": 0.01, "per_seed": [ 9.773167610168457, 11.56466007232666, 13.178303718566895, 14.895204544067383, 10.585610389709473, 15.57695484161377, 10.29378890991211, 14.999134063720703 ], "aux": [ { "upward_fraction": 0.0, "mean_left_gap": 0.09891153126955032, "codes": 16 }, { "upward_fraction": 0.0, "mean_left_gap": 0.1319166123867035, "codes": 16 }, { "upward_fraction": 0.0, "mean_left_gap": 0.20265933871269226, "codes": 16 }, { "upward_fraction": 0.0, "mean_left_gap": 0.20551525056362152, "codes": 16 }, { "upward_fraction": 0.0, "mean_left_gap": 0.1258753538131714, "codes": 16 }, { "upward_fraction": 0.0, "mean_left_gap": 0.14724649488925934, "codes": 16 }, { "upward_fraction": 0.0, "mean_left_gap": 0.09176831692457199, "codes": 16 }, { "upward_fraction": 0.0, "mean_left_gap": 0.2208053320646286, "codes": 16 } ], "mean": 12.608353018760681 } ] }, "comparison": { "delta_mean": 2.095502018928528, "idea_wins": 0, "n_pairs": 8, "per_seed_diffs": [ 1.2145042419433594, 0.7811193466186523, 3.44492244720459, 3.770353317260742, 2.0232715606689453, 2.8005924224853516, 0.8009872436523438, 1.9282655715942383 ], "p_value": 0.0081, "mde": 0.9656413775288165, "mde_rel_pct": 9.185342563537082, "verdict": "idea worse (significant)", "system_worked": false }, "mechanism_signature": { "predicted": { "upward_fraction": 0.0, "left_gap_nonnegative": true }, "observed": { "mean_upward_fraction": 0.0, "mean_left_gap": 0.15308727882802486 }, "confirmed": true } }