{ "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": 0.001 }, "mean": 128.04924488067627 }, { "cfg": { "lr": 0.003 }, "mean": 17.483699202537537 }, { "cfg": { "lr": 0.006 }, "mean": 15.365184903144836 } ], "full": { "mean": 15.365184903144836, "std": 2.415935250017397, "per_seed": [ 14.475372314453125, 12.608717918395996, 13.87478256225586, 14.577168464660645, 13.041308403015137, 17.592876434326172, 16.508373260498047, 20.24287986755371 ], "n": 8 } }, "idea": { "mean": 15.514657378196716, "std": 1.759501310100533, "per_seed": [ 14.62114143371582, 13.303616523742676, 15.129264831542969, 15.524860382080078, 13.418356895446777, 15.95352840423584, 17.32539176940918, 18.84109878540039 ], "n": 8, "stats_per_seed": [ { "rank_mean": 3.0, "orth_mean": 2.0764549699434394e-07, "projection_ratio": 1.0 }, { "rank_mean": 3.0, "orth_mean": 2.2836561377717305e-07, "projection_ratio": 1.0 }, { "rank_mean": 3.0, "orth_mean": 2.202748265271263e-07, "projection_ratio": 1.0 }, { "rank_mean": 3.0, "orth_mean": 2.2073787706331257e-07, "projection_ratio": 1.0 }, { "rank_mean": 3.0, "orth_mean": 2.6148559885265223e-07, "projection_ratio": 1.0 }, { "rank_mean": 3.0, "orth_mean": 2.169296318873156e-07, "projection_ratio": 1.0 }, { "rank_mean": 3.0, "orth_mean": 2.209224932375125e-07, "projection_ratio": 1.0 }, { "rank_mean": 3.0, "orth_mean": 2.2133620220583023e-07, "projection_ratio": 1.0 } ] }, "comparison": { "delta_mean": 0.14947247505187988, "idea_wins": 2, "n_pairs": 8, "per_seed_diffs": [ 0.1457691192626953, 0.6948986053466797, 1.2544822692871094, 0.9476919174194336, 0.3770484924316406, -1.639348030090332, 0.8170185089111328, -1.4017810821533203 ], "p_value": 0.7055, "mde": 0.9082613543107244, "mde_rel_pct": 5.911164493209762, "verdict": "no measurable effect", "system_worked": false }, "mechanism_signature": { "track_rationale": "optimizer modification matches the tabular optimizer track", "idea_trials": [ { "cfg": { "lr": 0.001, "rel_tol": 0.3, "block": 4, "kmax": 16 }, "mean": 128.22543716430664, "std": 14.557069548048865 }, { "cfg": { "lr": 0.003, "rel_tol": 0.3, "block": 4, "kmax": 16 }, "mean": 17.355298161506653, "std": 1.848799316741261 }, { "cfg": { "lr": 0.006, "rel_tol": 0.3, "block": 4, "kmax": 16 }, "mean": 15.514657378196716, "std": 1.759501310100533 } ], "mechanism_signature": { "prediction": "adaptive Householder subspaces retain fewer than kmax dimensions while maintaining orthogonality", "observed_rank_mean": 3.0, "observed_orthogonality_mean": 2.247122175681583e-07, "observed_projected_gradient_norm_ratio": 1.0, "confirmed": true }, "runtime_sec": 14.900958776473999 }, "custom_track": null }