{ "bench_version": 1, "track": "dynamics", "model": "rnn_small", "metric_direction": "lower is better", "n_seeds": 8, "baseline": { "best_cfg": { "lr": 0.01, "weight_decay": 0.0001 }, "sweep": [ { "cfg": { "lr": 0.001, "weight_decay": 0.0 }, "mean": 0.0035823711077682674 }, { "cfg": { "lr": 0.001, "weight_decay": 0.0001 }, "mean": 0.0035786936641670763 }, { "cfg": { "lr": 0.003, "weight_decay": 0.0 }, "mean": 0.0033184013445861638 }, { "cfg": { "lr": 0.003, "weight_decay": 0.0001 }, "mean": 0.0032864113454706967 }, { "cfg": { "lr": 0.01, "weight_decay": 0.0 }, "mean": 0.0015948790241964161 }, { "cfg": { "lr": 0.01, "weight_decay": 0.0001 }, "mean": 0.0015534490812569857 } ], "full": { "mean": 0.0013736290202359669, "std": 0.0004336284119124816, "per_seed": [ 0.0022530313581228256, 0.0016054200241342187, 0.0008981260471045971, 0.0014572188956663013, 0.0016656755469739437, 0.0009697971981950104, 0.000995026552118361, 0.0011447365395724773 ], "n": 8 } }, "idea": { "mean": 0.4975068047642708, "std": 0.06142691120766916, "per_seed": [ 0.39669302105903625, 0.551139771938324, 0.4963032305240631, 0.5875324010848999, 0.44322699308395386, 0.4858019948005676, 0.45647817850112915, 0.5628788471221924 ], "n": 8 }, "comparison": { "delta_mean": 0.4961331757440348, "idea_wins": 0, "n_pairs": 8, "per_seed_diffs": [ 0.39443998970091343, 0.5495343519141898, 0.4954051044769585, 0.5860751821892336, 0.4415613175369799, 0.4848321976023726, 0.4554831519490108, 0.5617341105826199 ], "p_value": 0.0081, "mde": 0.055052955593549176, "mde_rel_pct": 4007.847445163323, "verdict": "idea worse (significant)", "system_worked": false }, "mechanism_signature": { "signature": { "quantity": "W2^2/(D*dt*Sigma)", "predicted": "<= 1 in stable intervals", "observed_mean_ratio": 12911.468078824939, "observed_max_ratio_mean": 18444.135724120242, "observed_final_eta_mean": 0.0025, "confirmed": false }, "idea_grid": [ 0.001, 0.003, 0.01 ], "baseline_grid": [ { "lr": 0.001, "weight_decay": 0.0 }, { "lr": 0.001, "weight_decay": 0.0001 }, { "lr": 0.003, "weight_decay": 0.0 }, { "lr": 0.003, "weight_decay": 0.0001 }, { "lr": 0.01, "weight_decay": 0.0 }, { "lr": 0.01, "weight_decay": 0.0001 } ], "protocol": "8 paired seeds; 4-seed baseline/idea selection" }, "idea_configs_considered": [ { "lr": 0.001 }, { "lr": 0.003 }, { "lr": 0.01 } ] }