{ "track": { "name": "stochastic_intervention_scm", "domain": "causal-world-model", "description": "Random intervention X causes mediator M and outcome Y; tests joint modeling under intervention shift and mediator selection." }, "official_bench_available": false, "infrastructure_note": "Specified /home/maxwelhelp/all/math2nn/bench and README.md were absent; this is the required-contract local fallback, not bench.make_report output.", "math_check": { "selected_m_equals_1": { "sigma1": [ 1.483637689390105, 1.5, 2617 ], "sigma2": [ 1.7395092655751987, 1.8, 1897 ] }, "shift_observed": true }, "budget": { "seeds": [ 0, 1, 2, 3, 4, 5, 6, 7 ], "epochs": 90, "batch": 128, "lr_union": [ 0.003, 0.01, 0.03 ] }, "baseline_sweep": { "0.003": 2.854752391576767, "0.01": 2.711322247982025, "0.03": 2.849326878786087 }, "idea_sweep": { "0.003": 1.5709003955125809, "0.01": 1.6843366771936417, "0.03": 1.821063444018364 }, "best_baseline_lr": 0.01, "best_idea_lr": 0.003, "baseline_per_seed": [ { "seed": 0, "lr": 0.01, "mse": 2.560922861099243, "selected_pred": 1.608640432357788, "selected_obs": 1.8415178060531616, "n_selected": 145 }, { "seed": 1, "lr": 0.01, "mse": 2.782212495803833, "selected_pred": 1.5625216960906982, "selected_obs": 2.0218238830566406, "n_selected": 117 }, { "seed": 2, "lr": 0.01, "mse": 2.7840850353240967, "selected_pred": 1.3886590003967285, "selected_obs": 1.9218453168869019, "n_selected": 122 }, { "seed": 3, "lr": 0.01, "mse": 2.6477458477020264, "selected_pred": 1.7123332023620605, "selected_obs": 1.9120752811431885, "n_selected": 150 }, { "seed": 4, "lr": 0.01, "mse": 2.5227646827697754, "selected_pred": 1.793519377708435, "selected_obs": 1.784800410270691, "n_selected": 126 }, { "seed": 5, "lr": 0.01, "mse": 2.7045862674713135, "selected_pred": 1.6540354490280151, "selected_obs": 1.926216721534729, "n_selected": 132 }, { "seed": 6, "lr": 0.01, "mse": 2.809804677963257, "selected_pred": 1.7043554782867432, "selected_obs": 1.8070753812789917, "n_selected": 138 }, { "seed": 7, "lr": 0.01, "mse": 2.8784561157226562, "selected_pred": 1.50861656665802, "selected_obs": 1.8454731702804565, "n_selected": 132 } ], "idea_per_seed": [ { "seed": 0, "lr": 0.003, "mse": 1.385545253753662, "selected_pred": 1.8287450075149536, "selected_obs": 1.8415178060531616, "n_selected": 145 }, { "seed": 1, "lr": 0.003, "mse": 1.5307773351669312, "selected_pred": 1.9122552871704102, "selected_obs": 2.0218238830566406, "n_selected": 117 }, { "seed": 2, "lr": 0.003, "mse": 1.6703295707702637, "selected_pred": 1.9163973331451416, "selected_obs": 1.9218453168869019, "n_selected": 122 }, { "seed": 3, "lr": 0.003, "mse": 1.5728068351745605, "selected_pred": 1.8979436159133911, "selected_obs": 1.9120752811431885, "n_selected": 150 }, { "seed": 4, "lr": 0.003, "mse": 1.3386306762695312, "selected_pred": 1.7606240510940552, "selected_obs": 1.784800410270691, "n_selected": 126 }, { "seed": 5, "lr": 0.003, "mse": 1.760671854019165, "selected_pred": 1.8243013620376587, "selected_obs": 1.926216721534729, "n_selected": 132 }, { "seed": 6, "lr": 0.003, "mse": 1.8169323205947876, "selected_pred": 1.844454288482666, "selected_obs": 1.8070753812789917, "n_selected": 138 }, { "seed": 7, "lr": 0.003, "mse": 1.4915093183517456, "selected_pred": 1.7713148593902588, "selected_obs": 1.8454731702804565, "n_selected": 132 } ], "paired_delta_mean": -1.1404218524694443, "paired_deltas": [ -1.175377607345581, -1.2514351606369019, -1.113755464553833, -1.0749390125274658, -1.1841340065002441, -0.9439144134521484, -0.9928723573684692, -1.3869467973709106 ], "permutation_p": 0.007782101167315175, "mechanism_signature": { "selected_m": 1.0, "baseline_predicted_mean": 1.616585150361061, "idea_predicted_mean": 1.844504475593567, "observed_mean": 1.882603496313095, "baseline_abs_error": 0.266018345952034, "idea_abs_error": 0.0380990207195282, "confirmed": true }, "bench_report": { "custom_track": { "name": "stochastic_intervention_scm", "file": "custom_stochastic_intervention_track.py", "domain": "causal-world-model" }, "verdict": "idea better (significant)", "permutation_p": 0.007782101167315175, "paired_delta_mean": -1.1404218524694443 }, "permutation_p_raw": 0.00390625 }