{"id":"W2740418058","doi":"10.24963/ijcai.2017/326","title":"Cause-Effect Knowledge Acquisition and Neural Association Model for Solving A Set of Winograd Schema Problems","year":2017,"lang":"en","type":"article","venue":"","topic":"AI-based Problem Solving and Planning","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Computer science; Schema (genetic algorithms); Commonsense knowledge; Association (psychology); Artificial neural network; Knowledge acquisition; Artificial intelligence; Commonsense reasoning; Set (abstract data type); Scratch; Machine learning; ENCODE; Knowledge extraction","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":[0.0009154361,0.000119837,0.00018595,0.00006150134,0.0004646557,0.0002825408,0.0003653519,0.00009352009,0.000001396478],"category_scores_gemma":[0.0001274505,0.0001057115,0.00005851747,0.0000490036,0.00002274528,0.0007195835,0.0001652306,0.00008590575,0.000001746578],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003306692,"about_ca_system_score_gemma":0.00004106485,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003635906,"about_ca_topic_score_gemma":0.00002590455,"domain_scores_codex":[0.999136,0.00003633847,0.0001835381,0.000265587,0.0001325457,0.0002460172],"domain_scores_gemma":[0.9988694,0.0002898114,0.0002915834,0.0003636492,0.0001288699,0.00005669059],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001686402,0.0002803718,0.6232947,0.002874537,0.0005430322,0.000008890845,0.02996321,0.04416637,0.04185327,0.04456177,0.03163997,0.1806452],"study_design_scores_gemma":[0.000522133,0.0001497524,0.00243688,0.00009603889,0.0000179467,0.000002322414,0.000005398429,0.9930884,0.002339294,0.001180657,0.00003379943,0.000127396],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1998746,0.0002046202,0.7975518,0.0008350052,0.0001605305,0.0004223087,0.00001194821,0.0001338297,0.0008053695],"genre_scores_gemma":[0.9806715,0.000004006527,0.01872559,0.00003676952,0.00004996751,0.00003350623,0.000007650632,0.000008008607,0.0004630113],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.948922,"threshold_uncertainty_score":0.4310792,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04501237166592456,"score_gpt":0.3065625690844021,"score_spread":0.2615501974184775,"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."}}