{"id":"W2912817604","doi":"10.18653/v1/n19-4013","title":"End-to-End Open-Domain Question Answering with","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":368,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Question answering; Computer science; Open domain; Benchmark (surveying); Information retrieval; Reading (process); End-to-end principle; Natural language processing; Artificial intelligence; Domain (mathematical analysis); Reading comprehension; Language model; Open source; Programming language; Linguistics; Software","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":[0.0005878677,0.0002407351,0.0002939245,0.0001317499,0.0000568859,0.0008088303,0.00289382,0.0001389261,0.00007113889],"category_scores_gemma":[0.00001306423,0.0002001027,0.00003961256,0.0001346406,0.00001301749,0.0003816594,0.005750156,0.0003873536,0.0001583227],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001225139,"about_ca_system_score_gemma":0.0002640866,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001364158,"about_ca_topic_score_gemma":0.0002404539,"domain_scores_codex":[0.9980291,0.00007294461,0.0002489576,0.0009935332,0.0003601258,0.0002953261],"domain_scores_gemma":[0.9979312,0.00003736923,0.0001048948,0.001723854,0.00007844139,0.0001242801],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002959418,0.00009034377,0.002341917,0.000228998,0.00009287298,0.00007386658,0.002939997,0.2782723,0.0007221336,0.598628,0.001145051,0.1154349],"study_design_scores_gemma":[0.00110281,0.0003080624,0.003574132,0.001473822,0.00002509908,0.0000795427,0.0001302724,0.9128873,0.002369229,0.04917598,0.02679308,0.002080631],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01670925,0.00002687064,0.9396752,0.001589937,0.0008335861,0.0006833953,0.000001869302,0.0002213311,0.04025861],"genre_scores_gemma":[0.4007255,0.000003471584,0.5958071,0.0004665676,0.00008781083,0.00004307078,0.000004219763,0.0000149125,0.002847277],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.634615,"threshold_uncertainty_score":0.815995,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02837405652156753,"score_gpt":0.2801999427192826,"score_spread":0.2518258861977151,"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."}}