{
  "dataset_version": "cc81ed8f7624261a2fa43a335eb46159b7665074b82ddfb4e2c0783fbf2caa46",
  "schema_version": 2,
  "instances_with_rubric": 700,
  "total_nuggets": 2415,
  "instance_count": 700,
  "chat_size": "1M",
  "built_at": "2026-07-06T13:34:37.017Z",
  "source": "mohammadtavakoli78/BEAM (GitHub)",
  "source_reference": "Tavakoli, Salemi, Ye, Abdalla, Zamani, Mitchell 2024, \"Beyond a Million Tokens: Benchmarking and Enhancing Long-Term Memory in LLMs\" (arXiv:2510.27246, ICLR 2026)",
  "beam_chats_path": "D:\\Projects\\BEAM\\chats",
  "conversations_processed": 35,
  "chat_size_dir_alias": "1M",
  "canonicalisation": {
    "sort_order": "instance_id ascending",
    "field_order": [
      "instance_id",
      "conversation_id",
      "question",
      "expected",
      "context",
      "memory_ability",
      "chat_size",
      "conversation_index",
      "rubric"
    ],
    "line_terminator": "\\n",
    "trailing_newline": true,
    "encoding": "utf-8",
    "no_bom": true
  },
  "distribution_by_memory_ability": {
    "abstention": 70,
    "contradiction_resolution": 70,
    "event_ordering": 70,
    "information_extraction": 70,
    "instruction_following": 70,
    "knowledge_update": 70,
    "multi_session_reasoning": 70,
    "preference_following": 70,
    "summarization": 70,
    "temporal_reasoning": 70
  },
  "skip_stats": {
    "missingChat": 0,
    "missingProbing": 0,
    "missingQuestion": 0,
    "missingAnswer": 0,
    "noTurns": 0
  }
}