{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001735176,0.00005851503,0.00004135121,0.00002161965,0.0001346606,0.00007993176,0.001150653,0.00003098905,0.00001435584],"category_scores_gemma":[0.00002338913,0.00003102257,0.0000253844,0.0001368056,0.0000410698,0.0002779919,0.000245847,0.00009017476,0.00004521696],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007147638,"about_ca_system_score_gemma":0.00001354135,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002250542,"about_ca_topic_score_gemma":0.00001052976,"domain_scores_codex":[0.999498,0.00001523091,0.00007433612,0.000142386,0.0001137737,0.0001562542],"domain_scores_gemma":[0.999422,0.00002780818,0.00002763616,0.0004500402,0.00004104484,0.00003152341],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[7.174822e-7,0.00001098416,0.00001888168,0.000001584449,0.000002331297,0.000004603509,0.0004081299,1.159747e-9,0.00008633846,0.8029541,0.0008938831,0.1956184],"study_design_scores_gemma":[0.0001128127,0.0001210236,0.0002010722,0.00001916342,0.000002733674,0.00003076485,0.00006520528,0.00211558,0.1224453,0.8469547,0.02764857,0.0002830388],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0003116237,0.005663131,0.8934596,0.002515612,0.0001726401,0.00009853968,7.483219e-8,0.001653556,0.09612528],"genre_scores_gemma":[0.4313639,0.00003956208,0.5676408,0.0002085496,0.00002034034,0.000008100546,5.246926e-8,0.000003279812,0.0007154919],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4310522,"threshold_uncertainty_score":0.2138218,"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."}}