{
  "source": "V2_dpskw\\data\\net_locomo\\locomo10.json",
  "dataset": "LoCoMo (snap-research/locomo) locomo10.json",
  "provenance": "real published benchmark; dialogue, questions and answers are the dataset's own",
  "conversations": 10,
  "written": 195,
  "pool_cap": 16,
  "per_category_cap": 40,
  "seed": 20260915,
  "by_category": {
    "multi_hop": 40,
    "temporal": 39,
    "open_domain": 36,
    "single_hop": 40,
    "adversarial": 40
  },
  "skipped": {
    "no_evidence_in_index": 5
  },
  "caveats": [
    "candidate pool is bounded per question, so this is not a full 5,882-turn haystack run",
    "category adversarial is scored as 'must refuse': the dataset provides a plausible wrong answer",
    "answers phrased differently from the benchmark string fail exact-anchor matching; metadata.answer_tokens supports a paraphrase-tolerant secondary metric"
  ]
}