{ "bench_version": 1, "track": "dynamics", "model": "rnn_small", "metric_direction": "lower is better", "n_seeds": 8, "baseline": { "best_cfg": { "lr": 0.005, "weight_decay": 0.0 }, "sweep": [ { "cfg": { "lr": 0.001, "weight_decay": 0.0 }, "mean": 0.7906209975481033 }, { "cfg": { "lr": 0.003, "weight_decay": 0.0 }, "mean": 0.6789352595806122 }, { "cfg": { "lr": 0.005, "weight_decay": 0.0 }, "mean": 0.5756678730249405 } ], "full": { "mean": 0.5096767991781235, "std": 0.09851907442454794, "per_seed": [ 0.49524950981140137, 0.5737435817718506, 0.5768014788627625, 0.6568769216537476, 0.31393858790397644, 0.5531363487243652, 0.47284379601478577, 0.4348241686820984 ], "n": 8 } }, "idea": { "mean": 0.8012284114956856, "std": 0.20420508185800218, "per_seed": [ 0.7726240158081055, 1.0544251203536987, 1.041422724723816, 0.9839093685150146, 0.5845463275909424, 0.789264976978302, 0.7381134629249573, 0.4455212950706482 ], "n": 8 }, "comparison": { "delta_mean": 0.2915516123175621, "idea_wins": 0, "n_pairs": 8, "per_seed_diffs": [ 0.2773745059967041, 0.48068153858184814, 0.46462124586105347, 0.3270324468612671, 0.27060773968696594, 0.23612862825393677, 0.2652696669101715, 0.010697126388549805 ], "p_value": 0.0081, "mde": 0.12250781647639007, "mde_rel_pct": 24.03637298655528, "verdict": "idea worse (significant)", "system_worked": false }, "mechanism_signature": { "track_match": "stability/control -> dynamics", "math_sanity": { "max_skew": 0.0, "min_R_eig": 0.03000270389020443, "max_identity_residual": 3.725290298461914e-09, "max_dHdt": -0.000846284267026931 }, "mechanism_signature": { "trained_model_samples": 8, "max_skew_residual": 0.0, "min_R_eigenvalue": 0.030000008642673492, "max_energy_identity_residual": 1.4901161193847656e-08, "max_observed_dHdt": -0.0005119751440361142, "predicted": { "skew_zero": true, "R_eigenvalue_ge_epsilon": true, "dHdt_le_zero": true }, "confirmed": true }, "idea_sweep": [ { "cfg": { "lr": 0.001, "weight_decay": 0.0 }, "result": { "mean": 0.8644205369055271, "std": 0.20784380092323357, "per_seed": [ 0.8139765858650208, 1.1354857683181763, 1.0707145929336548, 1.0692869424819946, 0.6739808320999146, 0.8699936866760254, 0.7972943186759949, 0.48463156819343567 ], "n": 8 } }, { "cfg": { "lr": 0.003, "weight_decay": 0.0 }, "result": { "mean": 0.8342878073453903, "std": 0.20629487017615392, "per_seed": [ 0.792961597442627, 1.0980685949325562, 1.055668830871582, 1.029300332069397, 0.6329599618911743, 0.8318073749542236, 0.7700064182281494, 0.4635293483734131 ], "n": 8 } }, { "cfg": { "lr": 0.005, "weight_decay": 0.0 }, "result": { "mean": 0.8012284114956856, "std": 0.20420508185800218, "per_seed": [ 0.7726240158081055, 1.0544251203536987, 1.041422724723816, 0.9839093685150146, 0.5845463275909424, 0.789264976978302, 0.7381134629249573, 0.4455212950706482 ], "n": 8 } } ], "selected_cfg": { "lr": 0.005, "weight_decay": 0.0 }, "parameter_counts": { "baseline": 13313, "idea": 3142 } } }