{
  "schema_version": 1,
  "benchmark": {
    "id": "reasoning_reliability-development",
    "version": "0.1.0-dev",
    "status": "development",
    "count": 4,
    "path": "data.jsonl",
    "sha256": "fe294af00937e0c757f54c37f8aaf125501d71c98424f58d07f4e77f01e08cf0"
  },
  "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": "cff4fb2f78c64219d58738b19fae80bfd06dc20ac95242f0b9a583c6a2aed6e9"
  },
  "scorer_version": "1",
  "harness_version": "1"
}