{ "bench_version": 1, "track": "tabular", "model": "mlp_tiny", "metric_direction": "lower is better", "n_seeds": 8, "baseline": { "best_cfg": { "lr": 0.01 }, "sweep": [ { "cfg": { "lr": 0.001 }, "mean": 18.315088629722595 }, { "cfg": { "lr": 0.003 }, "mean": 13.52312970161438 }, { "cfg": { "lr": 0.01 }, "mean": 8.00898426771164 } ], "full": { "per_seed": [ 7.518021106719971, 7.098003387451172, 7.579931259155273, 8.855631828308105, 7.726285457611084, 7.675883769989014, 9.252959251403809, 8.365158081054688 ], "mean": 8.00898426771164 }, "diagnostics": [ { "metric": 7.518021106719971, "test_rank": 1.0162361860275269, "minmax_sv_ratio": 0.0, "seed": 0 }, { "metric": 7.098003387451172, "test_rank": 1.0113472938537598, "minmax_sv_ratio": 0.0, "seed": 1 }, { "metric": 7.579931259155273, "test_rank": 1.016098141670227, "minmax_sv_ratio": 0.0, "seed": 2 }, { "metric": 8.855631828308105, "test_rank": 1.0101362466812134, "minmax_sv_ratio": 0.0, "seed": 3 }, { "metric": 7.726285457611084, "test_rank": 1.0102609395980835, "minmax_sv_ratio": 0.0, "seed": 4 }, { "metric": 7.675883769989014, "test_rank": 1.0237842798233032, "minmax_sv_ratio": 0.0, "seed": 5 }, { "metric": 9.252959251403809, "test_rank": 1.0102062225341797, "minmax_sv_ratio": 0.0, "seed": 6 }, { "metric": 8.365158081054688, "test_rank": 1.0161538124084473, "minmax_sv_ratio": 0.0, "seed": 7 } ] }, "idea": { "per_seed": [ 7.499464988708496, 7.094777584075928, 7.588492393493652, 8.855938911437988, 7.727814674377441, 7.682166576385498, 9.250493049621582, 8.36063003540039 ], "mean": 8.007472276687622, "diagnostics": [ { "metric": 7.499464988708496, "test_rank": 1.016357183456421, "minmax_sv_ratio": 0.0, "seed": 0 }, { "metric": 7.094777584075928, "test_rank": 1.0115842819213867, "minmax_sv_ratio": 0.0, "seed": 1 }, { "metric": 7.588492393493652, "test_rank": 1.016180396080017, "minmax_sv_ratio": 0.0, "seed": 2 }, { "metric": 8.855938911437988, "test_rank": 1.0104186534881592, "minmax_sv_ratio": 0.0, "seed": 3 }, { "metric": 7.727814674377441, "test_rank": 1.0103423595428467, "minmax_sv_ratio": 0.0, "seed": 4 }, { "metric": 7.682166576385498, "test_rank": 1.023997187614441, "minmax_sv_ratio": 0.0, "seed": 5 }, { "metric": 9.250493049621582, "test_rank": 1.0103188753128052, "minmax_sv_ratio": 0.0, "seed": 6 }, { "metric": 8.36063003540039, "test_rank": 1.0162674188613892, "minmax_sv_ratio": 0.0, "seed": 7 } ] }, "comparison": { "delta_mean": -0.001511991024017334, "idea_wins": 4, "n_pairs": 8, "per_seed_diffs": [ -0.01855611801147461, -0.0032258033752441406, 0.008561134338378906, 0.0003070831298828125, 0.0015292167663574219, 0.006282806396484375, -0.0024662017822265625, -0.004528045654296875 ], "p_value": 0.69225, "mde": 0.006911241884516106, "mde_rel_pct": 0.08629361294139257, "verdict": "no measurable effect", "system_worked": false }, "idea_grid": [ { "lr": 0.001, "mean": 18.320167779922485 }, { "lr": 0.003, "mean": 13.5223867893219 }, { "lr": 0.01, "mean": 8.007472276687622 } ], "paired_deltas": [ -0.01855611801147461, -0.0032258033752441406, 0.008561134338378906, 0.0003070831298828125, 0.0015292167663574219, 0.006282806396484375, -0.0024662017822265625, -0.004528045654296875 ], "paired_p_value": 0.69225, "mechanism_signature": { "prediction": "span regularization increases held-out effective rank", "predicted_direction": "idea rank > baseline rank", "baseline_mean_rank": 1.0142778903245926, "idea_mean_rank": 1.0144332945346832, "baseline_mean_sv_ratio": 0.0, "idea_mean_sv_ratio": 0.0, "confirmed": true }, "elapsed_sec": 31.53953456878662 }