{ "bench_version": 1, "track": "dynamics", "model": "rnn_small", "metric_direction": "lower is better", "n_seeds": 8, "baseline": { "best_cfg": { "lr": 0.006, "step": 0.0 }, "sweep": [ { "cfg": { "lr": 0.001, "step": 0.0 }, "mean": 0.0013661633856827393 }, { "cfg": { "lr": 0.003, "step": 0.0 }, "mean": 0.0007308490021387115 }, { "cfg": { "lr": 0.006, "step": 0.0 }, "mean": 0.00039502444451500196 } ], "full": { "cfg": { "lr": 0.006, "step": 0.0 }, "mean": 0.00039502444451500196, "std": 0.00012923294272245648, "per_seed": [ 0.0004081559309270233, 0.0005658670561388135, 0.00031052311533130705, 0.0006247127312235534, 0.00027073538512922823, 0.00039440052933059633, 0.00022947481193114072, 0.00035632599610835314 ], "n": 8 } }, "idea": { "cfg": { "lr": 0.006, "step": 0.1 }, "mean": 0.00018664514300326118, "std": 6.30393270484372e-05, "per_seed": [ 0.0002500905538909137, 0.00021891914366278797, 0.0001631042396184057, 0.0002553996164351702, 9.480195876676589e-05, 0.00010218997340416536, 0.00015309224545489997, 0.00025556341279298067 ], "n": 8, "best_cfg": { "lr": 0.006, "step": 0.1 }, "sweep": [ { "cfg": { "lr": 0.006, "step": 0.1 }, "mean": 0.00018664514300326118 }, { "cfg": { "lr": 0.006, "step": 0.15 }, "mean": 0.0001907046962514869 }, { "cfg": { "lr": 0.006, "step": 0.22 }, "mean": 0.00020175300687697018 } ] }, "comparison": { "delta_mean": -0.00020837930151174078, "idea_wins": 8, "n_pairs": 8, "per_seed_diffs": [ -0.00015806537703610957, -0.0003469479124760255, -0.00014741887571290135, -0.00036931311478838325, -0.00017593342636246234, -0.00029221055592643097, -7.638256647624075e-05, -0.00010076258331537247 ], "p_value": 0.0081, "mde": 9.39821994106377e-05, "mde_rel_pct": 23.791489543394196, "verdict": "idea better (significant)", "system_worked": true }, "mechanism_signature": { "order_gap_mean": 0.012205412611365318, "steps": [ 0.009999999776482582, 0.019999999552965164, 0.03999999910593033 ], "gaps": [ 1.3433276762953028e-05, 0.00010710919741541147, 0.0008460786193609238 ], "predicted_exponent": 2.0, "observed_exponent": 2.9884542718353977, "confirmed": false } }