{ "bench_version": 1, "track": "sequence", "model": "transformer_tiny", "metric_direction": "lower is better", "n_seeds": 8, "baseline": { "best_cfg": { "lr": 0.0015, "weight_decay": 0.0 }, "sweep": [ { "cfg": { "lr": 0.0015, "weight_decay": 0.0 }, "mean": 0.3047138750553131 }, { "cfg": { "lr": 0.003, "weight_decay": 0.0 }, "mean": 0.347607359290123 }, { "cfg": { "lr": 0.006, "weight_decay": 0.0 }, "mean": 0.47413551807403564 }, { "cfg": { "lr": 0.003, "weight_decay": 0.0001 }, "mean": 0.34758908301591873 } ], "full": { "mean": 0.3249584026634693, "std": 0.05372834754753049, "per_seed": [ 0.2926701307296753, 0.2746025025844574, 0.2790817320346832, 0.3725011348724365, 0.32657936215400696, 0.2697966992855072, 0.43131738901138306, 0.35311827063560486 ], "n": 8 } }, "idea": { "best_cfg": { "lr": 0.0015, "weight_decay": 0.0 }, "sweep": [ { "cfg": { "lr": 0.0015, "weight_decay": 0.0 }, "mean": 1.981750339269638 }, { "cfg": { "lr": 0.0015, "weight_decay": 0.0 }, "mean": 1.981750339269638 }, { "cfg": { "lr": 0.006, "weight_decay": 0.0 }, "mean": 20.26469349861145 } ], "mean": 1.7784757614135742, "std": 0.4284677525253833, "per_seed": [ 2.11492919921875, 2.2909317016601562, 1.8699382543563843, 1.6512022018432617, 2.2055816650390625, 1.2742841243743896, 1.835213541984558, 0.9857254028320312 ], "n": 8 }, "comparison": { "delta_mean": 1.453517358750105, "idea_wins": 0, "n_pairs": 8, "per_seed_diffs": [ 1.8222590684890747, 2.016329199075699, 1.590856522321701, 1.2787010669708252, 1.8790023028850555, 1.0044874250888824, 1.403896152973175, 0.6326071321964264 ], "p_value": 0.0081, "mde": 0.3948775559757818, "mde_rel_pct": 121.51633954968739, "verdict": "idea worse (significant)", "system_worked": false }, "mechanism_signature": { "predicted_rho": 0.9985000165639166, "observed_local_perturbation_ratio": 1.0000219345092773, "relative_gap_pct": 0.15242042264536065, "selected_order": [ 0, 1, 2 ], "trained_test_mse": 0.2926701307296753, "confirmed": true } }