{"id":"W2557764419","doi":"10.18653/v1/w17-2623","title":"NewsQA: A Machine Comprehension Dataset","year":2017,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":742,"is_retracted":false,"has_abstract":true,"ca_institutions":"Microsoft (Canada)","funders":"","keywords":"Textual entailment; Computer science; Comprehension; Natural language processing; Artificial intelligence; Matching (statistics); Set (abstract data type); Word (group theory); Process (computing); Exploratory analysis; Information retrieval; Machine learning; Logical consequence; Data science; Linguistics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008816955,0.00005403512,0.00006646345,0.00001828972,0.0002461974,0.0002628193,0.001319198,0.00001860932,0.00004017734],"category_scores_gemma":[0.00001923999,0.00004236995,0.00001518855,0.00001404128,0.00001686241,0.0004687571,0.0008312701,0.00005373596,0.000159751],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005861908,"about_ca_system_score_gemma":0.00001114465,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004917207,"about_ca_topic_score_gemma":0.00007834107,"domain_scores_codex":[0.9994643,0.00001065036,0.00008077696,0.0002159422,0.0001122197,0.0001160659],"domain_scores_gemma":[0.9982005,0.00001384705,0.00004423927,0.001677472,0.00001302975,0.00005087146],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000006191231,0.0000914506,0.004994242,0.00001879569,0.00001926218,0.00009480955,0.0002121711,0.0003528376,0.00240844,0.3509961,0.1368288,0.5039768],"study_design_scores_gemma":[0.0002558783,0.00001355173,0.004238506,0.000006139664,0.000001461999,0.00001344819,0.000001737012,0.870136,0.0003671494,0.002993393,0.1218651,0.0001076397],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00401394,0.0000300604,0.9840404,0.003687455,0.0003046205,0.00005090975,0.00001817085,0.00009306747,0.007761398],"genre_scores_gemma":[0.7826574,0.000005585123,0.2153838,0.00111857,0.00006825837,0.000001685306,0.00003516429,0.000003475196,0.0007260134],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8697832,"threshold_uncertainty_score":0.2534372,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05848331174708454,"score_gpt":0.3064087311719761,"score_spread":0.2479254194248916,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}