{ "bench_version": 1, "track": "stochastic_intervention_scm", "model": "mlp_tiny", "metric_direction": "lower is better", "n_seeds": 8, "baseline": { "best_cfg": { "lr": 0.003 }, "sweep": [ { "cfg": { "lr": 0.003 }, "mean": 2.497592270374298 }, { "cfg": { "lr": 0.01 }, "mean": 2.5648475885391235 }, { "cfg": { "lr": 0.03 }, "mean": 2.6781041622161865 } ], "full": { "mean": 2.414719134569168, "std": 0.23689432610640407, "per_seed": [ 2.342486619949341, 2.4945199489593506, 2.7365739345550537, 2.4167885780334473, 2.2174108028411865, 2.058196783065796, 2.258479356765747, 2.793297052383423 ], "n": 8 } }, "idea": { "mean": 2.2138066589832306, "std": 0.5331661449712295, "per_seed": [ 2.4092166423797607, 2.4376542568206787, 2.0347108840942383, 1.5852525234222412, 1.881182074546814, 1.8407953977584839, 3.4355263710021973, 2.0861151218414307 ], "n": 8, "best_cfg": { "lr": 0.03 }, "sweep": [ { "cfg": { "lr": 0.003 }, "mean": 7.919645547866821, "std": 2.5149207407136784, "per_seed": [ 10.004054069519043, 5.846197605133057, 7.366078853607178, 4.32836389541626, 7.836812496185303, 5.4305877685546875, 11.452704429626465, 11.092365264892578 ], "n": 8 }, { "cfg": { "lr": 0.01 }, "mean": 3.1929454803466797, "std": 0.8334051410010931, "per_seed": [ 3.184743642807007, 3.0707268714904785, 3.08829665184021, 2.054521322250366, 2.8313469886779785, 2.428166151046753, 4.886856555938721, 3.998905658721924 ], "n": 8 }, { "cfg": { "lr": 0.03 }, "mean": 2.2138066589832306, "std": 0.5331661449712295, "per_seed": [ 2.4092166423797607, 2.4376542568206787, 2.0347108840942383, 1.5852525234222412, 1.881182074546814, 1.8407953977584839, 3.4355263710021973, 2.0861151218414307 ], "n": 8 } ] }, "comparison": { "delta_mean": -0.2009124755859375, "idea_wins": 6, "n_pairs": 8, "per_seed_diffs": [ 0.06673002243041992, -0.056865692138671875, -0.7018630504608154, -0.831536054611206, -0.33622872829437256, -0.217401385307312, 1.1770470142364502, -0.7071819305419922 ], "p_value": 0.41835, "mde": 0.5395513694218982, "mde_rel_pct": 22.34427025891624, "verdict": "no significant win", "system_worked": false }, "custom_track": { "name": "stochastic_intervention_scm", "file": "custom_stochastic_intervention_track.py", "domain": "causal-world-model" }, "mechanism_signature": { "baseline_predicted_selected_mean": 1.6279271692037582, "idea_predicted_selected_mean": 1.8218559473752975, "observed_selected_mean": 1.7572368532419205, "baseline_abs_error": 0.12930968403816223, "idea_abs_error": 0.06461909413337708, "confirmed": true } }