{ "bench_version": 1, "track": "tabular", "model": "mlp_tiny", "metric_direction": "lower is better", "n_seeds": 8, "baseline": { "best_cfg": { "lr": 0.006, "epochs": 12 }, "sweep": [ { "cfg": { "lr": 0.001, "epochs": 12 }, "mean": 133.94248580932617 }, { "cfg": { "lr": 0.003, "epochs": 12 }, "mean": 16.007279753684998 }, { "cfg": { "lr": 0.006, "epochs": 12 }, "mean": 14.950186729431152 } ], "full": { "mean": 14.950186729431152, "std": 1.5514200913682417, "per_seed": [ 14.034903526306152, 11.691411018371582, 14.283523559570312, 15.042709350585938, 16.13408851623535, 17.11699104309082, 15.280345916748047, 16.017520904541016 ], "n": 8 } }, "idea": { "config": { "lr": 0.001, "alpha": 0.2, "epochs": 12 }, "mean": 216.5899887084961, "std": 10.786054269508782, "per_seed": [ 230.07789611816406, 217.97207641601562, 221.4623565673828, 199.12059020996094, 223.05921936035156, 202.85182189941406, 209.7367706298828, 228.43917846679688 ], "n": 8, "grid": [ { "config": { "lr": 0.001, "alpha": 0.2, "epochs": 12 }, "mean": 216.5899887084961, "per_seed": [ 230.07789611816406, 217.97207641601562, 221.4623565673828, 199.12059020996094, 223.05921936035156, 202.85182189941406, 209.7367706298828, 228.43917846679688 ] }, { "config": { "lr": 0.003, "alpha": 0.2, "epochs": 12 }, "mean": 234.6817684173584, "per_seed": [ 249.0762176513672, 236.1846923828125, 239.8191375732422, 215.83428955078125, 241.5047607421875, 220.68380737304688, 227.49276733398438, 246.8584747314453 ] }, { "config": { "lr": 0.006, "alpha": 0.2, "epochs": 12 }, "mean": 232.99076080322266, "per_seed": [ 247.46762084960938, 234.6169891357422, 238.2631378173828, 213.9429931640625, 239.95175170898438, 219.12632751464844, 225.2731475830078, 245.28411865234375 ] } ] }, "comparison": { "delta_mean": 201.63980197906494, "idea_wins": 0, "n_pairs": 8, "per_seed_diffs": [ 216.0429925918579, 206.28066539764404, 207.1788330078125, 184.077880859375, 206.9251308441162, 185.73483085632324, 194.45642471313477, 212.42165756225586 ], "p_value": 0.0081, "mde": 10.077764526365558, "mde_rel_pct": 67.40895420741685, "verdict": "idea worse (significant)", "system_worked": false }, "mechanism_signature": { "predicted_mean_active": 3.9270833333333335, "observed_mean_active": 3.9270833333333335, "mean_iterations": 1.3046875, "one_iteration_fraction": 0.8307291666666666, "active_set_changes": 65, "max_violation": 0.8067416300048826, "confirmed": true }, "baseline_sweep": [ { "config": { "lr": 0.001, "epochs": 12 }, "mean": 133.94248580932617, "per_seed": [ 143.12049865722656, 131.5668487548828, 139.70982360839844, 120.17390441894531, 137.71632385253906, 123.82814025878906, 129.80224609375, 145.62210083007812 ] }, { "config": { "lr": 0.003, "epochs": 12 }, "mean": 16.007279753684998, "per_seed": [ 17.079910278320312, 13.425646781921387, 15.75783920288086, 16.13398551940918, 15.73672103881836, 15.811994552612305, 16.257793426513672, 17.854347229003906 ] }, { "config": { "lr": 0.006, "epochs": 12 }, "mean": 14.950186729431152, "per_seed": [ 14.034903526306152, 11.691411018371582, 14.283523559570312, 15.042709350585938, 16.13408851623535, 17.11699104309082, 15.280345916748047, 16.017520904541016 ] } ], "idea_grid": [ { "config": { "lr": 0.001, "alpha": 0.2, "epochs": 12 }, "mean": 216.5899887084961, "per_seed": [ 230.07789611816406, 217.97207641601562, 221.4623565673828, 199.12059020996094, 223.05921936035156, 202.85182189941406, 209.7367706298828, 228.43917846679688 ] }, { "config": { "lr": 0.003, "alpha": 0.2, "epochs": 12 }, "mean": 234.6817684173584, "per_seed": [ 249.0762176513672, 236.1846923828125, 239.8191375732422, 215.83428955078125, 241.5047607421875, 220.68380737304688, 227.49276733398438, 246.8584747314453 ] }, { "config": { "lr": 0.006, "alpha": 0.2, "epochs": 12 }, "mean": 232.99076080322266, "per_seed": [ 247.46762084960938, 234.6169891357422, 238.2631378173828, 213.9429931640625, 239.95175170898438, 219.12632751464844, 225.2731475830078, 245.28411865234375 ] } ], "search_space_parity": true }