{ "bench_version": 1, "track": "dynamics", "model": "rnn_small", "metric_direction": "lower is better", "n_seeds": 8, "baseline": { "best_cfg": { "lr": 0.01, "tau": 0.01 }, "sweep": [ { "cfg": { "lr": 0.001, "tau": 0.01 }, "mean": 0.0034653106704354286 }, { "cfg": { "lr": 0.001, "tau": 0.001 }, "mean": 0.0034653106704354286 }, { "cfg": { "lr": 0.001, "tau": 0.0001 }, "mean": 0.0034653106704354286 }, { "cfg": { "lr": 0.003, "tau": 0.01 }, "mean": 0.002506730961613357 }, { "cfg": { "lr": 0.003, "tau": 0.001 }, "mean": 0.002506730961613357 }, { "cfg": { "lr": 0.003, "tau": 0.0001 }, "mean": 0.002506730961613357 }, { "cfg": { "lr": 0.01, "tau": 0.01 }, "mean": 0.0010691375500755385 }, { "cfg": { "lr": 0.01, "tau": 0.001 }, "mean": 0.0010691375500755385 }, { "cfg": { "lr": 0.01, "tau": 0.0001 }, "mean": 0.0010691375500755385 } ], "full": { "mean": 0.0011299664110993035, "std": 0.00033636016341449245, "per_seed": [ 0.0008199093863368034, 0.0008286746451631188, 0.0016839810414239764, 0.0009439851273782551, 0.001039800001308322, 0.0017109999898821115, 0.0009939224692061543, 0.0010184586280956864 ], "n": 8 } }, "idea": { "mean": 0.0010912194484262727, "std": 0.00044965589408538725, "per_seed": [ 0.0005372872692532837, 0.0008794514578767121, 0.001270528300665319, 0.0019876640290021896, 0.0010541900992393494, 0.0015042235609143972, 0.0008550031343474984, 0.0006414077361114323 ], "n": 8 }, "comparison": { "delta_mean": -3.8746962673030794e-05, "idea_wins": 5, "n_pairs": 8, "per_seed_diffs": [ -0.0002826221170835197, 5.0776812713593245e-05, -0.00041345274075865746, 0.0010436789016239345, 1.4390097931027412e-05, -0.0002067764289677143, -0.00013891933485865593, -0.0003770508919842541 ], "p_value": 0.8938, "mde": 0.0003915640556028904, "mde_rel_pct": 34.65271637782152, "verdict": "no significant win", "system_worked": false }, "mechanism_signature": { "idea_config": { "lr": 0.01, "tau": 0.01 }, "idea_sweep": [ { "cfg": { "lr": 0.001, "tau": 0.01 }, "result": { "mean": 0.004125978332012892, "std": 0.0021316471939702973, "per_seed": [ 0.0034050061367452145, 0.0024806063156574965, 0.0038227855693548918, 0.009371915832161903, 0.004681112710386515, 0.002079644240438938, 0.004045997746288776, 0.003120758105069399 ], "n": 8 } }, { "cfg": { "lr": 0.001, "tau": 0.001 }, "result": { "mean": 0.004125978332012892, "std": 0.0021316471939702973, "per_seed": [ 0.0034050061367452145, 0.0024806063156574965, 0.0038227855693548918, 0.009371915832161903, 0.004681112710386515, 0.002079644240438938, 0.004045997746288776, 0.003120758105069399 ], "n": 8 } }, { "cfg": { "lr": 0.001, "tau": 0.0001 }, "result": { "mean": 0.004125978332012892, "std": 0.0021316471939702973, "per_seed": [ 0.0034050061367452145, 0.0024806063156574965, 0.0038227855693548918, 0.009371915832161903, 0.004681112710386515, 0.002079644240438938, 0.004045997746288776, 0.003120758105069399 ], "n": 8 } }, { "cfg": { "lr": 0.003, "tau": 0.01 }, "result": { "mean": 0.002102683240082115, "std": 0.000509014269608427, "per_seed": [ 0.0013083082158118486, 0.002864542882889509, 0.0026755419094115496, 0.0018761787796393037, 0.0020888173021376133, 0.0016800755402073264, 0.002548397518694401, 0.0017796037718653679 ], "n": 8 } }, { "cfg": { "lr": 0.003, "tau": 0.001 }, "result": { "mean": 0.002102683240082115, "std": 0.000509014269608427, "per_seed": [ 0.0013083082158118486, 0.002864542882889509, 0.0026755419094115496, 0.0018761787796393037, 0.0020888173021376133, 0.0016800755402073264, 0.002548397518694401, 0.0017796037718653679 ], "n": 8 } }, { "cfg": { "lr": 0.003, "tau": 0.0001 }, "result": { "mean": 0.002102683240082115, "std": 0.000509014269608427, "per_seed": [ 0.0013083082158118486, 0.002864542882889509, 0.0026755419094115496, 0.0018761787796393037, 0.0020888173021376133, 0.0016800755402073264, 0.002548397518694401, 0.0017796037718653679 ], "n": 8 } }, { "cfg": { "lr": 0.01, "tau": 0.01 }, "result": { "mean": 0.0010912194484262727, "std": 0.00044965589408538725, "per_seed": [ 0.0005372872692532837, 0.0008794514578767121, 0.001270528300665319, 0.0019876640290021896, 0.0010541900992393494, 0.0015042235609143972, 0.0008550031343474984, 0.0006414077361114323 ], "n": 8 } }, { "cfg": { "lr": 0.01, "tau": 0.001 }, "result": { "mean": 0.0010912194484262727, "std": 0.00044965589408538725, "per_seed": [ 0.0005372872692532837, 0.0008794514578767121, 0.001270528300665319, 0.0019876640290021896, 0.0010541900992393494, 0.0015042235609143972, 0.0008550031343474984, 0.0006414077361114323 ], "n": 8 } }, { "cfg": { "lr": 0.01, "tau": 0.0001 }, "result": { "mean": 0.0010912194484262727, "std": 0.00044965589408538725, "per_seed": [ 0.0005372872692532837, 0.0008794514578767121, 0.001270528300665319, 0.0019876640290021896, 0.0010541900992393494, 0.0015042235609143972, 0.0008550031343474984, 0.0006414077361114323 ], "n": 8 } } ], "mechanism_signature": { "prediction": "causal lifted ambient width 9 has deterministic duplicate directions and SVD rank 6", "predicted_intrinsic_rank": 6, "observed_rank_tau_1e-3": 6, "ambient_coordinate_width": 9, "trained_model_behavior": { "baseline": { "metric": 0.00200747512280941, "prediction_rms_under_input_perturbation": 0.0009409512858837843 }, "idea": { "metric": 0.0012641767971217632, "prediction_rms_under_input_perturbation": 0.0011408096179366112 } }, "confirmed": true } } }