{
  "schema_version": 1,
  "repository": "WootzappLab/fara-9b-baseline-eval",
  "publisher": "IshaGarg1103",
  "published_at": "2026-09-25",
  "checkpoint": {
    "source_repository": "microsoft/Fara1.5-9B",
    "source_revision": "1a93677cd89d5601bc2ed759791e981f3a520032",
    "weights_modified": false,
    "license": "MIT"
  },
  "source": {
    "fara_repository": "https://github.com/microsoft/fara",
    "fara_revision": "a675d6d61c41c47ae87bacefeab22caad18e3e84",
    "dataset_repository": "https://huggingface.co/datasets/WootzappLab/cua-bench",
    "dataset_revision": "745eebb8f07abb92fdaae356bb6bee3a1f2975af",
    "recorder_harness_repository": "https://github.com/tokenbender/w8-cua-bench",
    "recorder_harness_branch": "environment-work",
    "recorder_harness_revision": "66037db6bae4b00a2b5860aa08ebb69b559e6871",
    "environment_revision": "66037db6bae4b00a2b5860aa08ebb69b559e6871",
    "verifier_revision": "66037db6bae4b00a2b5860aa08ebb69b559e6871",
    "infrastructure_revision": null,
    "infrastructure_status": "pending branch push and pull request"
  },
  "evaluation": {
    "run_id": "fara15-dom-baseline",
    "date": "2026-09-25",
    "gcp_instance": "w8-fara-9b-8115f370-head-3ibtw2ah-compute",
    "selected_tasks": 90,
    "passed": 6,
    "verified_failed": 60,
    "verified_tasks": 66,
    "execution_errors": 24,
    "infrastructure_errors": 0,
    "pass_at_1": 0.06666666666666667,
    "verified_pass_rate": 0.09090909090909091,
    "artifact_status": "pending upload",
    "results_report_status": "pending"
  }
}