{"id":"W3206996280","doi":"10.18653/v1/2022.findings-naacl.184","title":"CCQA: A New Web-Scale Question Answering Dataset for Model Pre-Training","year":2022,"lang":"en","type":"article","venue":"Findings of the Association for Computational Linguistics: NAACL 2022","topic":"Topic Modeling","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Question answering; Computer science; Open domain; Task (project management); Language model; Domain (mathematical analysis); Artificial intelligence; Natural language processing; Scale (ratio); Training set; Information retrieval; Resource (disambiguation); Natural language; Natural language understanding","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":[0.001414679,0.0001430735,0.0002235931,0.0001387455,0.0006715293,0.00009700989,0.00100116,0.00005781396,0.000007126633],"category_scores_gemma":[0.003026138,0.000155894,0.0001669454,0.0003154786,0.00001291988,0.0001092214,0.0005358108,0.0002058529,0.000001255467],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005716553,"about_ca_system_score_gemma":0.00054141,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003186139,"about_ca_topic_score_gemma":0.000007763039,"domain_scores_codex":[0.9979905,0.00006810661,0.0005016943,0.0003964701,0.0007500421,0.0002931939],"domain_scores_gemma":[0.9977671,0.0008271476,0.0006082441,0.000288816,0.000449072,0.00005960403],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002167915,0.0000386705,0.0008994658,0.00002668462,0.00004219482,1.005578e-7,0.0009337213,0.864004,0.0001357318,0.1165924,0.01695187,0.0003534856],"study_design_scores_gemma":[0.0006917893,0.00005669329,0.000509569,0.00001619257,0.00003206285,0.000001213935,0.00003401504,0.8796859,0.00007783811,0.09314414,0.02560032,0.0001502648],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00683581,0.00003412822,0.9847167,0.001106848,0.001926217,0.0007326242,0.004396274,0.00008655866,0.0001648165],"genre_scores_gemma":[0.6542889,0.000001173943,0.3410559,0.0004136291,0.0005079788,0.000144506,0.001802088,0.00002928549,0.001756554],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6474531,"threshold_uncertainty_score":0.6357175,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02494648340920045,"score_gpt":0.2847366473702726,"score_spread":0.2597901639610721,"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."}}