{ "bench_version": 1, "track": "sparse_cycle_compatibility", "model": "pair_mlp", "metric_direction": "lower is better", "n_seeds": 8, "baseline": { "best_cfg": { "lr": 0.01, "lambda": 0.0 }, "sweep": [ { "cfg": { "lr": 0.001, "lambda": 0.0 }, "mean": 0.572812482714653 }, { "cfg": { "lr": 0.003, "lambda": 0.0 }, "mean": 0.4990624710917473 }, { "cfg": { "lr": 0.01, "lambda": 0.0 }, "mean": 0.4959374815225601 } ], "full": { "mean": 0.4884374812245369, "std": 0.07308691848966371, "per_seed": [ 0.5362499952316284, 0.5862499475479126, 0.5299999713897705, 0.33125001192092896, 0.44374996423721313, 0.45749998092651367, 0.4962499737739563, 0.5262500047683716 ], "n": 8 } }, "idea": { "mean": 0.4884374812245369, "std": 0.07308691848966371, "per_seed": [ 0.5362499952316284, 0.5862499475479126, 0.5299999713897705, 0.33125001192092896, 0.44374996423721313, 0.45749998092651367, 0.4962499737739563, 0.5262500047683716 ], "n": 8 }, "comparison": { "delta_mean": 0.0, "idea_wins": 0, "n_pairs": 8, "per_seed_diffs": [ 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0 ], "p_value": 1.0, "mde": 0.0, "mde_rel_pct": 0.0, "verdict": "no measurable effect", "system_worked": false }, "custom_track": { "name": "sparse_cycle_compatibility", "file": "custom_cycle_track.py", "domain": "masked_categorical_compatibility" }, "idea_cfg": { "lr": 0.01, "lambda": 0.01 }, "math_check": { "basis_rank": 5, "expected_rank": 5, "compatible_max_residual": 2.220446049250313e-16 }, "mechanism_signature": { "prediction": "basis constraints span all cycle constraints; basis count equals cycle rank", "predicted_cycle_rank": 5, "observed_exhaustive_cycles": 28, "observed_basis_mean_abs": 0.055877745151519775, "observed_unseen_cycle_mean_abs": 0.1098224903856005, "observed_unseen_to_basis_ratio": 1.9654066227231812, "confirmed": true } }