{ "bench_version": 1, "track": "dynamics", "model": "rnn_small", "metric_direction": "lower is better", "n_seeds": 8, "baseline": { "best_cfg": { "lr": 0.01, "weight_decay": 0.0 }, "sweep": [ { "cfg": { "lr": 0.001, "weight_decay": 0.0 }, "mean": 0.0006648988055530936 }, { "cfg": { "lr": 0.003, "weight_decay": 0.0 }, "mean": 0.00014707197260577232 }, { "cfg": { "lr": 0.01, "weight_decay": 0.0 }, "mean": 2.476238842064049e-05 } ], "full": { "mean": 2.4103710074996343e-05, "std": 9.965204787101785e-06, "per_seed": [ 4.82606228615623e-05, 1.8373453713138588e-05, 1.6678590327501297e-05, 1.5736886780359782e-05, 1.8623857613420114e-05, 2.8347380066406913e-05, 2.4800614482956007e-05, 2.2008274754625745e-05 ], "n": 8 } }, "idea": { "mean": 3.29756971950701e-05, "std": 8.53505931418874e-06, "per_seed": [ 3.491392271826044e-05, 3.567166277207434e-05, 1.5284425899153575e-05, 3.08263479382731e-05, 3.304120764369145e-05, 4.200598777970299e-05, 4.4804033677792177e-05, 2.7257989131612703e-05 ], "n": 8, "selected_cfg": { "lr": 0.01, "strength": 0.1 } }, "comparison": { "delta_mean": 8.871987120073754e-06, "idea_wins": 2, "n_pairs": 8, "per_seed_diffs": [ -1.334670014330186e-05, 1.7298209058935754e-05, -1.3941644283477217e-06, 1.508946115791332e-05, 1.4417350030271336e-05, 1.3658607713296078e-05, 2.000341919483617e-05, 5.249714376986958e-06 ], "p_value": 0.06005, "mde": 9.478008368122907e-06, "mde_rel_pct": 39.32178215981278, "verdict": "no significant win", "system_worked": false }, "config": { "epochs": 16, "n_train": 2000, "n_test": 500, "idea_grid": [ { "lr": 0.001, "strength": 0.02 }, { "lr": 0.003, "strength": 0.05 }, { "lr": 0.01, "strength": 0.1 } ] }, "mechanism_signature": { "baseline": { "prediction_abs": 0.005701124202460051, "koopman_abs": 0.03589034453034401, "rho_capped": 0.9499999284744263, "rho_raw": 0.993781371389095 }, "idea": { "prediction_abs": 0.004197320435196161, "koopman_abs": 0.03153369948267937, "rho_capped": 0.9499999284744263, "rho_raw": 0.993781371389095 }, "predicted_effect": "spectral cap keeps fitted transition rho <= 0.95 and lowers NN deviation from the fitted stable forecast", "confirmed": true } }