{ "bench_version": 1, "track": "tabular", "model": "mlp_tiny", "metric_direction": "lower is better", "n_seeds": 8, "baseline": { "best_cfg": { "lr": 0.006 }, "sweep": [ { "cfg": { "lr": 0.0015 }, "mean": 8.577727317810059 }, { "cfg": { "lr": 0.003 }, "mean": 6.8584965467453 }, { "cfg": { "lr": 0.006 }, "mean": 6.626367449760437 } ], "full": { "mean": 6.720197975635529, "std": 0.3792385031605589, "per_seed": [ 6.333833694458008, 7.1719770431518555, 6.258625507354736, 6.741033554077148, 6.219150543212891, 6.970664978027344, 6.840729713439941, 7.225568771362305 ], "n": 8 } }, "idea": { "best_cfg": { "lr": 0.006, "threshold": 0.02 }, "sweep": [ { "cfg": { "lr": 0.0015, "threshold": 0.02 }, "mean": 8.962467908859253, "per_seed": [ 7.58711051940918, 9.554247856140137, 8.6873140335083, 8.482236862182617, 8.62455940246582, 8.597721099853516, 10.342260360717773, 9.82429313659668 ] }, { "cfg": { "lr": 0.003, "threshold": 0.02 }, "mean": 7.0224193930625916, "per_seed": [ 6.4233717918396, 7.385267734527588, 6.821650505065918, 6.856407165527344, 7.057806015014648, 6.954143047332764, 7.078849792480469, 7.601859092712402 ] }, { "cfg": { "lr": 0.006, "threshold": 0.02 }, "mean": 6.847910106182098, "per_seed": [ 6.578519821166992, 7.120673179626465, 6.699369430541992, 6.741033554077148, 6.219150543212891, 6.990142345428467, 6.840729713439941, 7.593662261962891 ] } ], "per_seed": [ 6.578519821166992, 7.120673179626465, 6.699369430541992, 6.741033554077148, 6.219150543212891, 6.990142345428467, 6.840729713439941, 7.593662261962891 ], "mean": 6.847910106182098, "std": 0.3795102408701731, "n": 8 }, "comparison": { "delta_mean": 0.12771213054656982, "idea_wins": 1, "n_pairs": 8, "per_seed_diffs": [ 0.24468612670898438, -0.051303863525390625, 0.44074392318725586, 0.0, 0.0, 0.019477367401123047, 0.0, 0.36809349060058594 ], "p_value": 0.1856, "mde": 0.16181177964695484, "mde_rel_pct": 2.407842450975595, "verdict": "no significant win", "system_worked": false }, "mechanism_signature": { "quantity": "trained-model epoch displacement KL and held-out validation value/ledger", "prediction": "late low-value updates acquire positive KL and have eta near zero or negative", "observed_mean_info": 35.882227032415834, "observed_mean_late_eta": -0.5215707736578389, "observed_rollbacks": 1.25, "confirmed": true, "per_seed": [ { "seed": 0, "idea_info": 40.445681335271644, "idea_late_eta": -0.8021093204912924, "idea_rollbacks": 2 }, { "seed": 1, "idea_info": 30.49450051147865, "idea_late_eta": -5.761187156173132, "idea_rollbacks": 2 }, { "seed": 2, "idea_info": 37.59771323140545, "idea_late_eta": 0.012780262934585526, "idea_rollbacks": 2 }, { "seed": 3, "idea_info": 31.84697995765805, "idea_late_eta": 2.716472166477494, "idea_rollbacks": 0 }, { "seed": 4, "idea_info": 43.19129275120528, "idea_late_eta": 0.4035124075587761, "idea_rollbacks": 0 }, { "seed": 5, "idea_info": 33.22536463027882, "idea_late_eta": -2.2281370987865134, "idea_rollbacks": 2 }, { "seed": 6, "idea_info": 33.59606871616029, "idea_late_eta": 0.8177034771039023, "idea_rollbacks": 0 }, { "seed": 7, "idea_info": 36.66021512586849, "idea_late_eta": 0.668399072113469, "idea_rollbacks": 2 } ] }, "protocol_notes": { "n_train": 2000, "n_test": 500, "epochs": 15, "common_validation_fraction": 0.2, "track_match": "tabular is the built-in optimizer/scheduler track" } }