{ "bench_version": 1, "track": "categorical_energy", "model": "mlp_tiny", "metric_direction": "lower is better", "n_seeds": 8, "baseline": { "best_cfg": { "lr": 0.01 }, "sweep": [ { "cfg": { "lr": 0.001 }, "mean": 0.29375000298023224 }, { "cfg": { "lr": 0.003 }, "mean": 0.26999999582767487 }, { "cfg": { "lr": 0.01 }, "mean": 0.20749999955296516 } ], "full": { "mean": 0.2024999987334013, "std": 0.03614207525864678, "per_seed": [ 0.2199999988079071, 0.20000000298023224, 0.19499999284744263, 0.2150000035762787, 0.26499998569488525, 0.15000000596046448, 0.15000000596046448, 0.22499999403953552 ], "n": 8 }, "sweep_space": [ { "lr": 0.001 }, { "lr": 0.003 }, { "lr": 0.01 } ] }, "idea": { "mean": 0.21249999850988388, "std": 0.0482182497334198, "per_seed": [ 0.2549999952316284, 0.1850000023841858, 0.18000000715255737, 0.23000000417232513, 0.29499998688697815, 0.20499999821186066, 0.125, 0.22499999403953552 ], "n": 8 }, "comparison": { "delta_mean": 0.009999999776482582, "idea_wins": 3, "n_pairs": 8, "per_seed_diffs": [ 0.034999996423721313, -0.015000000596046448, -0.014999985694885254, 0.015000000596046448, 0.030000001192092896, 0.05499999225139618, -0.025000005960464478, 0.0 ], "p_value": 0.3679, "mde": 0.023755343439915824, "mde_rel_pct": 11.731033870864666, "verdict": "no significant win", "system_worked": false }, "mechanism_signature": { "custom_track": { "name": "categorical_energy", "file": "categorical_track.py", "domain": "discrete_energy_sampling" }, "idea_sweep": [ { "h": 0.02, "result": { "mean": 0.21249999850988388, "std": 0.0482182497334198, "per_seed": [ 0.2549999952316284, 0.1850000023841858, 0.18000000715255737, 0.23000000417232513, 0.29499998688697815, 0.20499999821186066, 0.125, 0.22499999403953552 ], "n": 8 } }, { "h": 0.05, "result": { "mean": 0.22187499795109034, "std": 0.045616437498093354, "per_seed": [ 0.2800000011920929, 0.20499999821186066, 0.2199999988079071, 0.23000000417232513, 0.26499998569488525, 0.20999999344348907, 0.11999999731779099, 0.24500000476837158 ], "n": 8 } }, { "h": 0.1, "result": { "mean": 0.24874999932944775, "std": 0.03927069276915124, "per_seed": [ 0.26499998569488525, 0.24500000476837158, 0.24500000476837158, 0.29499998688697815, 0.30000001192092896, 0.23499999940395355, 0.16500000655651093, 0.23999999463558197 ], "n": 8 } } ], "mechanism_signature": { "quantity": "per-leap active proposal count versus resolved coordinate updates", "predicted": 26.59152908809483, "observed": 26.3515625, "relative_error": 0.009024174100701296, "confirmed": true, "per_seed": [ { "seed": 0, "predicted_mean_counts": 26.762684151530266, "observed_updates": 25.84375 }, { "seed": 1, "predicted_mean_counts": 27.059062629938126, "observed_updates": 26.375 }, { "seed": 2, "predicted_mean_counts": 26.548943385481834, "observed_updates": 26.21875 }, { "seed": 3, "predicted_mean_counts": 26.508921772241592, "observed_updates": 26.78125 }, { "seed": 4, "predicted_mean_counts": 26.205237537622452, "observed_updates": 25.40625 }, { "seed": 5, "predicted_mean_counts": 26.47282662987709, "observed_updates": 25.3125 }, { "seed": 6, "predicted_mean_counts": 26.590720653533936, "observed_updates": 28.15625 }, { "seed": 7, "predicted_mean_counts": 26.583835944533348, "observed_updates": 26.71875 } ] } } }