{ "bench_version": 1, "track": "dynamics", "model": "rnn_small", "metric_direction": "lower is better", "n_seeds": 8, "baseline": { "best_cfg": { "lr": 0.01, "h": 0.025 }, "sweep": [ { "cfg": { "lr": 0.001, "h": 0.025 }, "mean": 1.4525697110912006e-05 }, { "cfg": { "lr": 0.001, "h": 0.05 }, "mean": 1.4545178487423982e-05 }, { "cfg": { "lr": 0.001, "h": 0.1 }, "mean": 1.4584162499886588e-05 }, { "cfg": { "lr": 0.003, "h": 0.025 }, "mean": 8.580010785408376e-06 }, { "cfg": { "lr": 0.003, "h": 0.05 }, "mean": 8.575699666835135e-06 }, { "cfg": { "lr": 0.003, "h": 0.1 }, "mean": 8.567132681491785e-06 }, { "cfg": { "lr": 0.01, "h": 0.025 }, "mean": 5.892069680157874e-06 }, { "cfg": { "lr": 0.01, "h": 0.05 }, "mean": 5.897995151826763e-06 }, { "cfg": { "lr": 0.01, "h": 0.1 }, "mean": 5.909915387292131e-06 } ], "full": { "mean": 5.681601408014103e-06, "std": 2.730715161483723e-06, "per_seed": [ 2.3133106878958642e-06, 4.037152848468395e-06, 1.1316467862343416e-05, 5.901347321923822e-06, 5.3298954298952594e-06, 3.4796667023329064e-06, 8.45680187921971e-06, 4.618168532033451e-06 ], "n": 8 } }, "idea": { "mean": 5.6799913750182895e-06, "std": 2.7279983370928816e-06, "per_seed": [ 2.3146424155129353e-06, 4.040079147671349e-06, 1.1296857337583788e-05, 5.893076377105899e-06, 5.312819212122122e-06, 3.484348098936607e-06, 8.480390533804893e-06, 4.617717877408722e-06 ], "n": 8 }, "comparison": { "delta_mean": -1.6100329958135262e-09, "idea_wins": 4, "n_pairs": 8, "per_seed_diffs": [ 1.3317276170710102e-09, 2.9262992029543966e-09, -1.961052475962788e-08, -8.27094481792301e-09, -1.7076217773137614e-08, 4.681396603700705e-09, 2.3588654585182667e-08, -4.5065462472848594e-10 ], "p_value": 0.78145, "mde": 1.1450469552506787e-08, "mde_rel_pct": 0.20153595316199915, "verdict": "no measurable effect", "system_worked": false }, "mechanism_signature": { "signature": { "prediction": "two-derivative correction should improve finite-step rollout", "predicted": { "order": 4, "correction_coefficient": 0.5 }, "observed": { "mean_abs_field": 0.08425881783477962, "mean_abs_ph_correction": 7.20391401642928e-07 }, "confirmed": true }, "idea_sweep": [ { "cfg": { "lr": 0.001, "h": 0.025 }, "mean": 1.4506283719128987e-05 }, { "cfg": { "lr": 0.001, "h": 0.05 }, "mean": 1.4506301454275672e-05 }, { "cfg": { "lr": 0.001, "h": 0.1 }, "mean": 1.4506304410133453e-05 }, { "cfg": { "lr": 0.003, "h": 0.025 }, "mean": 8.584338502259925e-06 }, { "cfg": { "lr": 0.003, "h": 0.05 }, "mean": 8.584342822359758e-06 }, { "cfg": { "lr": 0.003, "h": 0.1 }, "mean": 8.58435225836729e-06 }, { "cfg": { "lr": 0.01, "h": 0.025 }, "mean": 5.886169105906447e-06 }, { "cfg": { "lr": 0.01, "h": 0.05 }, "mean": 5.886163819468493e-06 }, { "cfg": { "lr": 0.01, "h": 0.1 }, "mean": 5.886164046842168e-06 } ] } }