{ "bench_version": 1, "track": "tabular", "model": "mlp_tiny", "metric_direction": "lower is better", "n_seeds": 8, "baseline": { "best_cfg": { "lr": 0.006 }, "sweep": [ { "cfg": { "lr": 0.0015 }, "mean": 6.50612199306488 }, { "cfg": { "lr": 0.003 }, "mean": 5.869555473327637 }, { "cfg": { "lr": 0.006 }, "mean": 4.962810158729553 } ], "full": { "mean": 5.057340204715729, "std": 0.5639876094204693, "per_seed": [ 5.718886852264404, 5.579864501953125, 4.7256927490234375, 3.826796531677246, 5.060815811157227, 5.323063373565674, 4.853731155395508, 5.369870662689209 ], "n": 8 } }, "idea": { "mean": 4.5547012984752655, "std": 0.8416642558828814, "per_seed": [ 5.184708118438721, 5.024646759033203, 4.222005367279053, 4.777006149291992, 5.235812664031982, 4.5309157371521, 4.969952583312988, 2.492563009262085 ], "n": 8 }, "comparison": { "delta_mean": -0.5026389062404633, "idea_wins": 5, "n_pairs": 8, "per_seed_diffs": [ -0.5341787338256836, -0.5552177429199219, -0.5036873817443848, 0.9502096176147461, 0.17499685287475586, -0.7921476364135742, 0.11622142791748047, -2.877307653427124 ], "p_value": 0.2491, "mde": 0.9310786105933415, "mde_rel_pct": 18.4104405261318, "verdict": "no significant win", "system_worked": false }, "idea_sweep": [ { "cfg": { "lr": 0.0015, "delta": 0.02, "ema": 0.15 }, "result": { "mean": 6.439422070980072, "std": 0.22122740568514504, "per_seed": [ 6.449733257293701, 6.59368371963501, 6.736842155456543, 6.062600612640381, 6.195968151092529, 6.431543350219727, 6.701443672180176, 6.34356164932251 ], "n": 8 } }, { "cfg": { "lr": 0.003, "delta": 0.02, "ema": 0.15 }, "result": { "mean": 5.547695994377136, "std": 0.3737932778729164, "per_seed": [ 5.546213150024414, 6.377541542053223, 5.3842549324035645, 5.396069526672363, 5.144563674926758, 5.520054817199707, 5.180293083190918, 5.832577228546143 ], "n": 8 } }, { "cfg": { "lr": 0.006, "delta": 0.01, "ema": 0.1 }, "result": { "mean": 4.5547012984752655, "std": 0.8416642558828814, "per_seed": [ 5.184708118438721, 5.024646759033203, 4.222005367279053, 4.777006149291992, 5.235812664031982, 4.5309157371521, 4.969952583312988, 2.492563009262085 ], "n": 8 } } ], "selected_cfg": { "lr": 0.006, "delta": 0.01, "ema": 0.1 }, "custom_track": null, "mechanism_signature": { "f2_hat": 0.12070295963746307, "f3_hat": -1.2520681114060102, "sigma2_hat": 6.631455711858227e-06, "predicted_displacement": -3.4351747621157183e-11, "observed_displacement": 5.153735449760493e-08, "n_obs": 480, "confirmed": false } }