{
  "schema_version": 1,
  "benchmark": {
    "id": "tool_workflow_reliability-development",
    "version": "0.1.0-dev",
    "status": "development",
    "count": 3,
    "path": "data.jsonl",
    "sha256": "e47196fe3b3ec3d3de48e916035640fa111a990074e242351df42a78f8978749"
  },
  "model": {
    "id": "synthetic-baseline-fixture",
    "revision": "fixture-v1",
    "tokenizer_id": "no-tokenizer-fixture",
    "tokenizer_revision": "fixture-v1",
    "chat_template": "{{ prompt }}"
  },
  "sampling": {
    "temperature": 0,
    "max_new_tokens": 256,
    "seed": 42
  },
  "trials": 2,
  "adapter": {
    "type": "fixture",
    "path": "predictions.jsonl",
    "sha256": "d7fb91c114cf2932f6e95ac858b3453afbb72dd0fd0047c91f276fbe970a2acd"
  },
  "scorer_version": "1",
  "harness_version": "1"
}