{
  "generator": "make_realistic_memory_eval.py",
  "purpose": "realistic-shaped memory evaluation corpus (multi-entity, aliases, updates, multi-hop, near-miss, noise, long facts, unknowns)",
  "per_category": 25,
  "seed": 20260913,
  "episodes": 200,
  "sha256": "333a3c02c6b5fede753bea15d597de655287677ad5b08230da36039867238035",
  "categories": {
    "multi_entity": {
      "episodes": 25,
      "answerable": 25,
      "unknown": 0,
      "max_candidates": 3
    },
    "alias_paraphrase": {
      "episodes": 25,
      "answerable": 25,
      "unknown": 0,
      "max_candidates": 5
    },
    "update_conflict": {
      "episodes": 25,
      "answerable": 25,
      "unknown": 0,
      "max_candidates": 5
    },
    "multi_hop": {
      "episodes": 25,
      "answerable": 25,
      "unknown": 0,
      "max_candidates": 5
    },
    "near_miss": {
      "episodes": 25,
      "answerable": 25,
      "unknown": 0,
      "max_candidates": 4
    },
    "noise_context": {
      "episodes": 25,
      "answerable": 25,
      "unknown": 0,
      "max_candidates": 9
    },
    "long_fact": {
      "episodes": 25,
      "answerable": 25,
      "unknown": 0,
      "max_candidates": 4
    },
    "unknown_attribute": {
      "episodes": 25,
      "answerable": 0,
      "unknown": 25,
      "max_candidates": 5
    }
  },
  "note": "episodes use the schema consumed by eval_end_to_end_memory (query / candidates[].text / positive_indices / metadata.acceptable)"
}