{ "bench_version": 1, "track": "dynamics", "model": "rnn_small", "metric_direction": "lower is better", "n_seeds": 8, "baseline": { "best_cfg": { "lr": 0.006 }, "sweep": [ { "cfg": { "lr": 0.001 }, "mean": 0.47112278640270233 }, { "cfg": { "lr": 0.003 }, "mean": 0.08337884861975908 }, { "cfg": { "lr": 0.006 }, "mean": 0.05978757236152887 } ], "full": { "mean": 0.04506447445601225, "std": 0.01812126155730088, "per_seed": [ 0.06423857063055038, 0.039343297481536865, 0.05935552343726158, 0.07621289789676666, 0.028351932764053345, 0.038264982402324677, 0.0202757827937603, 0.03447280824184418 ], "n": 8 } }, "idea": { "mean": 0.05070888949558139, "std": 0.008596224148366128, "per_seed": [ 0.05224335566163063, 0.03554942458868027, 0.061948955059051514, 0.04569929093122482, 0.05899675190448761, 0.05897253751754761, 0.04991588369011879, 0.042344916611909866 ], "n": 8 }, "comparison": { "delta_mean": 0.0056444150395691395, "idea_wins": 3, "n_pairs": 8, "per_seed_diffs": [ -0.011995214968919754, -0.003793872892856598, 0.0025934316217899323, -0.03051360696554184, 0.030644819140434265, 0.02070755511522293, 0.02964010089635849, 0.007872108370065689 ], "p_value": 0.49005, "mde": 0.01773643806217156, "mde_rel_pct": 39.35791613299345, "verdict": "no significant win", "system_worked": false }, "mechanism_signature": { "predicted_budget": 0.537269855031944, "observed_budget_at_exit": 0.0, "observed_crossing_epoch": null, "observed_exit_epoch": null, "post_crossing_epochs": null, "relative_budget_error": Infinity, "confirmed": false }, "idea_sweep": [ { "cfg": { "lr": 0.001, "budget_scale": 1.0 }, "result": { "mean": 0.38905996084213257, "std": 0.06823595036576088, "per_seed": [ 0.4037257730960846, 0.27306991815567017, 0.47476810216903687, 0.4277902841567993, 0.4180760383605957, 0.460550993680954, 0.35112857818603516, 0.30336999893188477 ], "n": 8 } }, { "cfg": { "lr": 0.003, "budget_scale": 1.0 }, "result": { "mean": 0.07632979797199368, "std": 0.02907599907859665, "per_seed": [ 0.07722286134958267, 0.03422033414244652, 0.11100310832262039, 0.061097800731658936, 0.10502404719591141, 0.11226481199264526, 0.0710601806640625, 0.03874523937702179 ], "n": 8 } }, { "cfg": { "lr": 0.006, "budget_scale": 0.7 }, "result": { "mean": 0.05070888949558139, "std": 0.008596224148366128, "per_seed": [ 0.05224335566163063, 0.03554942458868027, 0.061948955059051514, 0.04569929093122482, 0.05899675190448761, 0.05897253751754761, 0.04991588369011879, 0.042344916611909866 ], "n": 8 } }, { "cfg": { "lr": 0.006, "budget_scale": 1.0 }, "result": { "mean": 0.05070888949558139, "std": 0.008596224148366128, "per_seed": [ 0.05224335566163063, 0.03554942458868027, 0.061948955059051514, 0.04569929093122482, 0.05899675190448761, 0.05897253751754761, 0.04991588369011879, 0.042344916611909866 ], "n": 8 } }, { "cfg": { "lr": 0.006, "budget_scale": 1.3 }, "result": { "mean": 0.05070888949558139, "std": 0.008596224148366128, "per_seed": [ 0.05224335566163063, 0.03554942458868027, 0.061948955059051514, 0.04569929093122482, 0.05899675190448761, 0.05897253751754761, 0.04991588369011879, 0.042344916611909866 ], "n": 8 } } ], "track_justification": "Dynamics track directly matches stability/control and bifurcation monitoring; shared rnn_small and task MSE.", "budget": { "n_train": 400, "n_test": 200, "epochs": 6, "batch": 128, "lr_union": [ 0.001, 0.003, 0.006 ], "paired_seeds": [ 0, 1, 2, 3, 4, 5, 6, 7 ] }, "runtime_sec": 64.41141510009766 }