{
  "artifact": "AI_EVALUATION_V1",
  "task": "INVALID_NCM candidate selection",
  "pipeline": "candidate_generation -> provider_selection -> validator",
  "provider": "baseline",
  "model": "baseline-deterministic-v1",
  "prompt_version": "ai-semantic-v1",
  "dataset_versions": {
    "ncm": "3abc0d2eb2501bbd0cc3f5e0ee3774d33f091ea305e8127ee020e4009878987e"
  },
  "k": 50,
  "eval_total": 200,
  "metrics": {
    "EXACT_MATCH": 2,
    "WRONG_SELECTION": 164,
    "NONE_WHEN_KNOWN": 34,
    "INVALID_OUTPUT": 0,
    "RECALL_AT_K": 15
  },
  "accuracy_exact_match": 0.01,
  "recall_at_k": 0.075,
  "by_segment": {
    "base_testes": {
      "EXACT_MATCH": 0,
      "WRONG_SELECTION": 27,
      "NONE_WHEN_KNOWN": 13,
      "INVALID_OUTPUT": 0,
      "RECALL_AT_K": 2,
      "TOTAL": 40
    },
    "construcao": {
      "EXACT_MATCH": 1,
      "WRONG_SELECTION": 39,
      "NONE_WHEN_KNOWN": 0,
      "INVALID_OUTPUT": 0,
      "RECALL_AT_K": 5,
      "TOTAL": 40
    },
    "mercado": {
      "EXACT_MATCH": 1,
      "WRONG_SELECTION": 35,
      "NONE_WHEN_KNOWN": 4,
      "INVALID_OUTPUT": 0,
      "RECALL_AT_K": 4,
      "TOTAL": 40
    },
    "moda": {
      "EXACT_MATCH": 0,
      "WRONG_SELECTION": 35,
      "NONE_WHEN_KNOWN": 5,
      "INVALID_OUTPUT": 0,
      "RECALL_AT_K": 1,
      "TOTAL": 40
    },
    "restaurante": {
      "EXACT_MATCH": 0,
      "WRONG_SELECTION": 28,
      "NONE_WHEN_KNOWN": 12,
      "INVALID_OUTPUT": 0,
      "RECALL_AT_K": 3,
      "TOTAL": 40
    }
  },
  "cost_usd": 0.0,
  "note": "baseline provider (deterministic, zero-cost): measures the pipeline floor; rerun with a real provider once credentials exist"
}