{"id":"W2970946372","doi":"10.18653/v1/d19-1335","title":"How Reasonable are Common-Sense Reasoning Tasks: A Case-Study on the Winograd Schema Challenge and SWAG","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Logic, Reasoning, and Knowledge","field":"Computer Science","cited_by":43,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research; Microsoft Research","keywords":"Computer science; Schema (genetic algorithms); Common sense; Commonsense reasoning; Ask price; Artificial intelligence; Theoretical computer science; Machine learning; Epistemology","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02376161,0.0005757581,0.0009211216,0.002174249,0.002493182,0.004454958,0.002809481,0.004564952,0.005311503],"category_scores_gemma":[0.1199043,0.0004055875,0.0009328928,0.003693995,0.003615965,0.01576729,0.00417635,0.003417052,0.001108632],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001786337,"about_ca_system_score_gemma":0.002742023,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01482466,"about_ca_topic_score_gemma":0.02254377,"domain_scores_codex":[0.9836856,0.01063732,0.001141938,0.001869872,0.00216562,0.0004996691],"domain_scores_gemma":[0.8325851,0.1467356,0.002354374,0.01146206,0.005063417,0.00179949],"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":[0.004226654,0.002579224,0.1053911,0.002695861,0.0004456339,0.004054891,0.04288926,0.01904249,0.002815928,0.3037094,0.1036684,0.4084813],"study_design_scores_gemma":[0.0008899241,0.0006233238,0.01964178,0.001078542,0.0003493127,0.005412309,0.03995689,0.1345403,0.005992127,0.6653739,0.1259491,0.0001924012],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7891065,0.007125862,0.1046052,0.03851866,0.0003054837,0.000863549,0.005405067,0.002022775,0.05204701],"genre_scores_gemma":[0.9037442,0.0009700017,0.08335727,0.001767628,0.00007986565,0.0001906172,0.005564682,0.0006011438,0.003724596],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02376161,"threshold_uncertainty_score":0.1256649,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05092409937177934,"score_gpt":0.2665618099533431,"score_spread":0.2156377105815637,"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."}}