{"id":"W1599016936","doi":"","title":"The Winograd Schema Challenge","year":2011,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":865,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Schema (genetic algorithms); Ambiguity; Natural language processing; Artificial intelligence; Turing test; Sentence; Turing; Information retrieval; Programming language","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005606096,0.0005297365,0.001211139,0.001242146,0.004412415,0.007310462,0.003023573,0.004613525,0.04409001],"category_scores_gemma":[0.02591913,0.000673229,0.001134602,0.00279534,0.006164418,0.027611,0.008611195,0.007086279,0.01043049],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002788191,"about_ca_system_score_gemma":0.002695765,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003823795,"about_ca_topic_score_gemma":0.0028321,"domain_scores_codex":[0.9951805,0.001854249,0.0003113649,0.001116589,0.001095272,0.0004420133],"domain_scores_gemma":[0.990988,0.004383037,0.0003171433,0.002640021,0.001067161,0.0006047302],"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":[0.00004136825,0.00001231424,0.0002304,0.00006706834,0.000007696262,0.00007577547,0.0003174763,0.0003205466,0.0000587406,0.926314,0.04584873,0.02670583],"study_design_scores_gemma":[0.0000222051,0.00000570963,0.00008627852,0.00005741122,0.000005527787,0.0002114279,0.0002757332,0.001231238,0.0002078425,0.8497819,0.1481019,0.00001287442],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.03664895,0.01186783,0.2469405,0.2642632,0.005475698,0.0002006964,0.003974223,0.003103255,0.4275257],"genre_scores_gemma":[0.6646176,0.01095007,0.1204658,0.04116027,0.005468423,0.0006727921,0.006977824,0.003256379,0.1464308],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.04409001,"threshold_uncertainty_score":0.1474957,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03539908514315045,"score_gpt":0.2591166325644209,"score_spread":0.2237175474212704,"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."}}