{
  "document_id": "lb_qasper_8fa5af6a36dd0b6b73900b2ec6f6e43a652a3e7d2b827a58",
  "family": "public_qasper",
  "split": "test",
  "document_hash": "8bd512af0c4c3757e43fbef60070ed3c2d2bba018fa9c9b2313bc12c15f526ed",
  "questions": [
    {
      "question_id": "q00",
      "qtype": "qasper",
      "question": "What are the datasets used for evaluation?",
      "answer": "CNN/DailyMail news highlights, New York Times Annotated Corpus, XSum",
      "aliases": [
        "the CNN/DailyMail news highlights dataset BIBREF24, the New York Times Annotated Corpus (NYT; BIBREF25), XSum BIBREF22"
      ],
      "answer_type": "qa_f1",
      "tolerance": 0.0,
      "supporting_fact_ids": [],
      "answer_position_frac": -1.0
    }
  ],
  "facts": []
}