{ "bench_version": 1, "track": "dynamics", "model": "rnn_small", "metric_direction": "lower is better", "n_seeds": 8, "baseline": { "best_cfg": { "lr": 0.01, "wbar": 0.05 }, "sweep": [ { "cfg": { "lr": 0.001, "wbar": 0.05 }, "mean": 0.004298779065720737 }, { "cfg": { "lr": 0.001, "wbar": 0.15 }, "mean": 0.004298779065720737 }, { "cfg": { "lr": 0.001, "wbar": 0.3 }, "mean": 0.004298779065720737 }, { "cfg": { "lr": 0.003, "wbar": 0.05 }, "mean": 0.0034615940821822733 }, { "cfg": { "lr": 0.003, "wbar": 0.15 }, "mean": 0.0034615940821822733 }, { "cfg": { "lr": 0.003, "wbar": 0.3 }, "mean": 0.0034615940821822733 }, { "cfg": { "lr": 0.01, "wbar": 0.05 }, "mean": 0.0014865802077110857 }, { "cfg": { "lr": 0.01, "wbar": 0.15 }, "mean": 0.0014865802077110857 }, { "cfg": { "lr": 0.01, "wbar": 0.3 }, "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": 0.005354407912818715, "std": 0.0011548517240013176, "per_seed": [ 0.0045272172428667545, 0.004973915405571461, 0.006366239860653877, 0.007458276581019163, 0.005999961402267218, 0.0034331066999584436, 0.005241193808615208, 0.004835352301597595 ], "n": 8 }, "comparison": { "delta_mean": 0.003934577674954198, "idea_wins": 0, "n_pairs": 8, "per_seed_diffs": [ 0.0035944784758612514, 0.0031097447499632835, 0.005287710810080171, 0.005387394223362207, 0.005073880427516997, 0.0020275735296308994, 0.003596850554458797, 0.00339898862875998 ], "p_value": 0.0081, "mde": 0.0010030486525361333, "mde_rel_pct": 70.6456747987534, "verdict": "idea worse (significant)", "system_worked": false }, "mechanism_signature": { "chosen_cfg": { "lr": 0.01, "wbar": 0.05 }, "cV": 0.4, "predicted_envelope": "Vdot <= -cV V + disturbance margin", "signature": { "quantity": "mean robust CLF residual versus disturbance", "predicted_slope_abs_theta": 0.7278081178665161, "observed_slope": 0.27696520090103144, "relative_error": 0.6194529845209034, "confirmed": false } }, "idea_sweep": [ { "cfg": { "lr": 0.01, "wbar": 0.05 }, "result": { "mean": 0.005354407912818715, "std": 0.0011548517240013176, "per_seed": [ 0.0045272172428667545, 0.004973915405571461, 0.006366239860653877, 0.007458276581019163, 0.005999961402267218, 0.0034331066999584436, 0.005241193808615208, 0.004835352301597595 ], "n": 8 } }, { "cfg": { "lr": 0.001, "wbar": 0.15 }, "result": { "mean": 0.005414883635239676, "std": 0.0011777990905441577, "per_seed": [ 0.004449672531336546, 0.0050073061138391495, 0.006440161261707544, 0.007577271666377783, 0.006071907002478838, 0.0035233551170676947, 0.005342461168766022, 0.004906934220343828 ], "n": 8 } }, { "cfg": { "lr": 0.01, "wbar": 0.3 }, "result": { "mean": 0.005623006261885166, "std": 0.0012009004828101744, "per_seed": [ 0.004604719579219818, 0.005171346943825483, 0.006618546321988106, 0.007910414598882198, 0.006261724047362804, 0.003785517066717148, 0.005539596080780029, 0.005092185456305742 ], "n": 8 } } ] }