{ "bench_version": 1, "track": "dynamics", "model": "rnn_small", "metric_direction": "lower is better", "n_seeds": 8, "baseline": { "best_cfg": { "lr": 0.01 }, "sweep": [ { "cfg": { "lr": 0.001 }, "mean": 0.004298779065720737 }, { "cfg": { "lr": 0.003 }, "mean": 0.0034615940821822733 }, { "cfg": { "lr": 0.01 }, "mean": 0.0014865802077110857 } ], "full": { "mean": 0.0014198302378645167, "std": 0.00039839114901047844, "per_seed": [ 0.0009327387670055032, 0.0018641706556081772, 0.0010785290505737066, 0.0020708823576569557, 0.0009260809747502208, 0.0014055331703275442, 0.0016443432541564107, 0.001436363672837615 ], "n": 8 } }, "idea": { "mean": 0.02781403553672135, "std": 0.005121785167552724, "per_seed": [ 0.02624191716313362, 0.019634274765849113, 0.030885715037584305, 0.03626050800085068, 0.020821113139390945, 0.029457034543156624, 0.030522819608449936, 0.028688902035355568 ], "n": 8 }, "comparison": { "delta_mean": 0.026394205298856832, "idea_wins": 0, "n_pairs": 8, "per_seed_diffs": [ 0.025309178396128118, 0.017770104110240936, 0.029807185987010598, 0.03418962564319372, 0.019895032164640725, 0.02805150137282908, 0.028878476354293525, 0.027252538362517953 ], "p_value": 0.0081, "mde": 0.004467906007621001, "mde_rel_pct": 314.6788882550435, "verdict": "idea worse (significant)", "system_worked": false }, "idea_cfg": { "lr": 0.01 }, "protocol_note": "dynamics is structurally matched: controlled pendulum rollout", "mechanism_signature": { "prediction": "mobility-weighted action should scale residual energy by inverse positive mobility", "predicted_inverse_mobility_mean": "not directly averaged in the original run; mobility mean=0.79597 implies inverse-mobility weighting > 1", "observed_residual_mse": 5.364831447601318, "observed_mobility_weighted_residual": 6.362071514129639, "observed_weighted_to_unweighted_ratio": 1.1858846967082626, "predicted_direction": "weighted residual exceeds unweighted residual because measured mobility is below 1", "confirmed": true } }