{ "bench_version": 1, "track": "poisson_hodge_periodic", "model": "mlp_tiny", "metric_direction": "lower is better", "n_seeds": 8, "baseline": { "best_cfg": { "lr": 0.003 }, "sweep": [ { "cfg": { "lr": 0.001 }, "mean": 2.206587553024292 }, { "cfg": { "lr": 0.003 }, "mean": 1.1046047359704971 }, { "cfg": { "lr": 0.01 }, "mean": 1.2606632113456726 } ], "full": { "mean": 1.0800504088401794, "std": 0.10522868591444227, "per_seed": [ 1.1444686651229858, 0.8914604783058167, 1.1053142547607422, 1.2771755456924438, 1.091360092163086, 1.0986981391906738, 1.034430980682373, 0.9974951148033142 ], "n": 8 } }, "idea": { "mean": 0.4011378400027752, "std": 0.059436192075174005, "per_seed": [ 0.33402565121650696, 0.3543514013290405, 0.42588725686073303, 0.5025325417518616, 0.3978813886642456, 0.43913376331329346, 0.4413507878780365, 0.3139399290084839 ], "n": 8, "selected_cfg": { "lr": 0.01 } }, "comparison": { "delta_mean": -0.6789125688374043, "idea_wins": 8, "n_pairs": 8, "per_seed_diffs": [ -0.8104430139064789, -0.5371090769767761, -0.6794269979000092, -0.7746430039405823, -0.6934787034988403, -0.6595643758773804, -0.5930801928043365, -0.6835551857948303 ], "p_value": 0.0081, "mde": 0.07381216084595137, "mde_rel_pct": 6.834140355098345, "verdict": "idea better (significant)", "system_worked": true }, "mechanism_signature": { "mechanism_signature": { "prediction": "div(curl A)=0 for trained dual model", "baseline_observed_constraint_residual": 106.66156768798828, "idea_observed_div_curl_max": 2.384185791015625e-07, "confirmed": true }, "custom_track": { "name": "poisson_hodge_periodic", "file": "bench_stage2.py", "domain": "pde" }, "runtime_sec": 21.82808494567871 } }