{ "purpose": "Multi-seed evaluation across 10 stratified splits of the 9,200-alert sample. Reports XGBoost performance averaged over the full set of seeds.", "seeds_evaluated": [ 42, 7, 13, 17, 23, 31, 45, 99, 123, 200 ], "per_seed": [ { "seed": 42, "test_n_classes": 5, "accuracy": 0.7659420289855072, "macro_f1": 0.7429876131468711, "macro_roc_auc_ovr": 0.9522005654044479 }, { "seed": 7, "test_n_classes": 5, "accuracy": 0.7768115942028986, "macro_f1": 0.769435481914568, "macro_roc_auc_ovr": 0.9535405274694995 }, { "seed": 13, "test_n_classes": 5, "accuracy": 0.7862318840579711, "macro_f1": 0.7773476010631033, "macro_roc_auc_ovr": 0.9593350309948587 }, { "seed": 17, "test_n_classes": 5, "accuracy": 0.7731884057971015, "macro_f1": 0.7657000386460112, "macro_roc_auc_ovr": 0.9510884009809615 }, { "seed": 23, "test_n_classes": 5, "accuracy": 0.7768115942028986, "macro_f1": 0.7655808630589699, "macro_roc_auc_ovr": 0.9557712595581618 }, { "seed": 31, "test_n_classes": 5, "accuracy": 0.7789855072463768, "macro_f1": 0.7635031878905345, "macro_roc_auc_ovr": 0.9575528903552497 }, { "seed": 45, "test_n_classes": 5, "accuracy": 0.7920289855072464, "macro_f1": 0.7827912746822961, "macro_roc_auc_ovr": 0.9599146202095736 }, { "seed": 99, "test_n_classes": 5, "accuracy": 0.7666666666666667, "macro_f1": 0.7513856936195747, "macro_roc_auc_ovr": 0.9498718419129876 }, { "seed": 123, "test_n_classes": 5, "accuracy": 0.7760869565217391, "macro_f1": 0.7672910648132462, "macro_roc_auc_ovr": 0.9549881182366795 }, { "seed": 200, "test_n_classes": 5, "accuracy": 0.7753623188405797, "macro_f1": 0.7594433532222149, "macro_roc_auc_ovr": 0.9530752276015168 } ], "aggregate": { "accuracy_mean": 0.7768115942028986, "accuracy_std": 0.0074957104585424775, "accuracy_min": 0.7659420289855072, "accuracy_max": 0.7920289855072464, "macro_f1_mean": 0.7645466172057391, "macro_f1_std": 0.01093479933122361, "roc_auc_mean": 0.9547338482723937, "roc_auc_std": 0.003234503129030738 }, "published_artifact_seed": 42 }