router_metadata_only/model_metadata.json

{
  "artifact": "metadata-only protocol router (multinomial logistic regression)",
  "task": "predict the fixed-order-oracle action for a problem, before any protocol runs",
  "actions": [
    "baseline_llm",
    "single_agent",
    "per",
    "broadcast",
    "none"
  ],
  "n_features_in": 220,
  "feature_blocks": [
    {
      "block": "source",
      "type": "OneHotEncoder",
      "note": "competition/source identifier"
    },
    {
      "block": "domain",
      "type": "MultiLabelBinarizer",
      "note": "topic tags; unseen tags dropped"
    },
    {
      "block": "numeric",
      "type": "StandardScaler(with_mean=False)",
      "columns": [
        "difficulty",
        "difficulty_tier"
      ]
    }
  ],
  "feature_order": "source one-hot, then domain multi-hot, then the two scaled numeric columns",
  "split": {
    "scheme": "stratified 80/10/10",
    "seed": 42,
    "train": 3342,
    "dev": 416,
    "test": 423
  },
  "selected_hyperparameters": {
    "name": "plain_l2_c0.25",
    "class_weight": null,
    "C": 0.25
  },
  "selection": "macro-F1 then excess-token-cost on DEV only, with validation-based early stopping",
  "leakage": "features are problem metadata only: no gold answers, no correctness, no protocol outcomes, no oracle label",
  "pickled_with": {
    "note": "recorded so a loader can explain a version warning",
    "sklearn_at_fit": "1.8.0 (from the InconsistentVersionWarning emitted on load)"
  },
  "verified_in_this_environment": {
    "sklearn": "1.6.1",
    "numpy": "2.0.2",
    "scipy": "1.13.1",
    "predict": "works",
    "predict_proba": "raises AttributeError under this version; predict_example.py falls back to the decision function"
  },
  "files": {
    "class_recalls.csv": {
      "bytes": 525,
      "sha256": "a4cbb87ec4a07cb3e56543aef9dd54aaa929ab95933adfc106cf52845da7540b"
    },
    "feature_builders.joblib": {
      "bytes": 23857,
      "sha256": "3252c274c6ae5a90afe3655823e2a16977c21796f7d76fbe3e6141454ca61e62"
    },
    "label_mapping.json": {
      "bytes": 906,
      "sha256": "ac5c5cfef8e8d8a556351d078e3b2fd4a6415c19c3ff8d439f53c543cf6c590e"
    },
    "metrics.csv": {
      "bytes": 376,
      "sha256": "7e043f4946fc3219cb1c8ba5a7b259b3b991084c452b8ef388fd07d4f3356833"
    },
    "model.joblib": {
      "bytes": 9711,
      "sha256": "63b5358423b430b39f2a586913d48bf84f2b6774cda78bf1bc383c76de7f0c3b"
    },
    "predict_example.py": {
      "bytes": 4724,
      "sha256": "a61bdbf294349bc2c21a3543d4e197b2bb83ba0b4be824cbfd981496ad40a813"
    },
    "selected_config.json": {
      "bytes": 1283,
      "sha256": "44542b6696893bbd23e630b208a2061f67085c5dc56fbc04cb8b61c1464770ed"
    },
    "test_predictions.csv": {
      "bytes": 17241,
      "sha256": "5bcb554174f5cc34588d201938835473170c1c57154718dfede792341fcf3ee1"
    }
  },
  "root_widget_copy": {
    "path": "sklearn_model.joblib",
    "purpose": "byte-identical duplicate so Hugging Face's auto-generated sklearn snippet resolves",
    "canonical": "router_metadata_only/model.joblib",
    "sha256": "63b5358423b430b39f2a586913d48bf84f2b6774cda78bf1bc383c76de7f0c3b"
  }
}