1{2 "document_id": "lb_qasper_8fa5af6a36dd0b6b73900b2ec6f6e43a652a3e7d2b827a58",3 "family": "public_qasper",4 "split": "test",5 "document_hash": "8bd512af0c4c3757e43fbef60070ed3c2d2bba018fa9c9b2313bc12c15f526ed",6 "questions": [7 {8 "question_id": "q00",9 "qtype": "qasper",10 "question": "What are the datasets used for evaluation?",11 "answer": "CNN/DailyMail news highlights, New York Times Annotated Corpus, XSum",12 "aliases": [13 "the CNN/DailyMail news highlights dataset BIBREF24, the New York Times Annotated Corpus (NYT; BIBREF25), XSum BIBREF22"14 ],15 "answer_type": "qa_f1",16 "tolerance": 0.0,17 "supporting_fact_ids": [],18 "answer_position_frac": -1.019 }20 ],21 "facts": []22}