{ "bench_version": 1, "track": "tabular", "model": "mlp_tiny", "metric_direction": "lower is better", "n_seeds": 8, "baseline": { "best_cfg": { "lr": 0.006, "weight_decay": 0.0 }, "sweep": [ { "cfg": { "lr": 0.001, "weight_decay": 0.0 }, "mean": 17.79831099510193 }, { "cfg": { "lr": 0.003, "weight_decay": 0.0 }, "mean": 13.153547525405884 }, { "cfg": { "lr": 0.006, "weight_decay": 0.0 }, "mean": 9.905518293380737 } ], "full": { "mean": 10.041840195655823, "std": 1.3433768404487412, "per_seed": [ 10.178184509277344, 11.6652193069458, 8.723758697509766, 9.054910659790039, 7.620545387268066, 10.61941909790039, 11.13137149810791, 11.341312408447266 ], "n": 8 } }, "idea": { "mean": 7.694764673709869, "std": 0.9183754203462169, "per_seed": [ 7.17905855178833, 8.86394214630127, 7.2537841796875, 6.873910903930664, 6.19173526763916, 8.16868782043457, 8.054282188415527, 8.972716331481934 ], "n": 8 }, "comparison": { "delta_mean": -2.3470755219459534, "idea_wins": 8, "n_pairs": 8, "per_seed_diffs": [ -2.9991259574890137, -2.8012771606445312, -1.4699745178222656, -2.180999755859375, -1.4288101196289062, -2.4507312774658203, -3.077089309692383, -2.368596076965332 ], "p_value": 0.0081, "mde": 0.5303101801167621, "mde_rel_pct": 5.281005968867921, "verdict": "idea better (significant)", "system_worked": true }, "mechanism_signature": { "predicted": "packet preparation makes common slow-direction projection near zero", "observed": { "initial_cancellation_ratio": 3.7172168874545825e-10, "observed_c_ratio_epoch1": 0.21678468534656278, "observed_c_ratio_final": 1.042262186528141, "v_norm": 1.0 }, "confirmed": true, "idea_sweep": [ { "cfg": { "lr": 0.001, "kappa": 0.01 }, "mean": 20.009164333343506, "result": { "mean": 20.009164333343506, "std": 1.230693031020796, "per_seed": [ 22.104595184326172, 19.132362365722656, 19.679386138916016, 19.12031364440918 ], "n": 4 } }, { "cfg": { "lr": 0.001, "kappa": 0.03 }, "mean": 19.979770183563232, "result": { "mean": 19.979770183563232, "std": 1.2766088175400236, "per_seed": [ 22.140043258666992, 18.95973014831543, 19.69390106201172, 19.12540626525879 ], "n": 4 } }, { "cfg": { "lr": 0.001, "kappa": 0.06 }, "mean": 19.88680124282837, "result": { "mean": 19.88680124282837, "std": 1.3482576598501705, "per_seed": [ 22.143774032592773, 18.91352653503418, 19.69554328918457, 18.794361114501953 ], "n": 4 } }, { "cfg": { "lr": 0.003, "kappa": 0.01 }, "mean": 13.156998634338379, "result": { "mean": 13.156998634338379, "std": 0.7376469596332139, "per_seed": [ 13.269169807434082, 13.964943885803223, 13.43444538116455, 11.95943546295166 ], "n": 4 } }, { "cfg": { "lr": 0.003, "kappa": 0.03 }, "mean": 13.096021890640259, "result": { "mean": 13.096021890640259, "std": 0.7681500483182941, "per_seed": [ 13.330429077148438, 13.886496543884277, 13.34359073638916, 11.82357120513916 ], "n": 4 } }, { "cfg": { "lr": 0.003, "kappa": 0.06 }, "mean": 13.155548334121704, "result": { "mean": 13.155548334121704, "std": 0.7771499510902515, "per_seed": [ 13.34993839263916, 13.988134384155273, 13.402823448181152, 11.88129711151123 ], "n": 4 } }, { "cfg": { "lr": 0.006, "kappa": 0.01 }, "mean": 7.5606971979141235, "result": { "mean": 7.5606971979141235, "std": 0.7941976381676852, "per_seed": [ 7.124575614929199, 8.919793128967285, 7.272003173828125, 6.926416873931885 ], "n": 4 } }, { "cfg": { "lr": 0.006, "kappa": 0.03 }, "mean": 7.542673945426941, "result": { "mean": 7.542673945426941, "std": 0.7759940585392692, "per_seed": [ 7.17905855178833, 8.86394214630127, 7.2537841796875, 6.873910903930664 ], "n": 4 } }, { "cfg": { "lr": 0.006, "kappa": 0.06 }, "mean": 7.578917741775513, "result": { "mean": 7.578917741775513, "std": 0.7888582333579148, "per_seed": [ 7.209147930145264, 8.925769805908203, 7.265168190002441, 6.915585041046143 ], "n": 4 } } ] } }