{ "bench_version": 1, "track": "tabular", "model": "mlp_tiny", "metric_direction": "lower is better", "n_seeds": 8, "baseline": { "best_cfg": { "lr": 0.03 }, "sweep": [ { "cfg": { "lr": 0.001 }, "mean": 24.142436981201172 }, { "cfg": { "lr": 0.003 }, "mean": 13.75401242574056 }, { "cfg": { "lr": 0.01 }, "mean": 8.325917879740397 }, { "cfg": { "lr": 0.03 }, "mean": 6.865411599477132 } ], "full": { "mean": 7.418325066566467, "std": 0.9955428790176792, "per_seed": [ 6.716945648193359, 5.94451379776001, 7.934775352478027, 9.200451850891113, 7.416287899017334, 6.373697280883789, 8.270235061645508, 7.489693641662598 ], "n": 8 } }, "idea": { "mean": 124.02495861053467, "std": 19.888619557248344, "per_seed": [ 133.7542266845703, 95.59589385986328, 161.67819213867188, 123.55552673339844, 96.50812530517578, 130.4013214111328, 120.75763702392578, 129.94874572753906 ], "n": 8, "chosen_cfg": { "lr": 0.03 }, "trials": [ { "cfg": { "lr": 0.003 }, "mean": 235.4395955403646 }, { "cfg": { "lr": 0.01 }, "mean": 223.33053588867188 }, { "cfg": { "lr": 0.03 }, "mean": 130.3427708943685 } ] }, "comparison": { "delta_mean": 116.6066335439682, "idea_wins": 0, "n_pairs": 8, "per_seed_diffs": [ 127.03728103637695, 89.65138006210327, 153.74341678619385, 114.35507488250732, 89.09183740615845, 124.02762413024902, 112.48740196228027, 122.45905208587646 ], "p_value": 0.0081, "mde": 17.547701974609687, "mde_rel_pct": 236.54533627402162, "verdict": "idea worse (significant)", "system_worked": false }, "mechanism_signature": { "predicted": { "transport_error": 0.0, "call_reduction_fraction": 0.5 }, "observed": { "mean_transport_error": 1.59325485071804e-06, "mean_idea_grad_calls": 73.0, "mean_baseline_grad_calls": 72.0, "call_reduction_fraction": -0.013888888888888888 }, "confirmed": false } }