{"id":"W3001759017","doi":"10.1037/cep0000199","title":"Performance monitoring during categorization with and without prior knowledge: A comparison of confidence calibration indices with the certainty criterion.","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Experimental Psychology/Revue canadienne de psychologie expérimentale","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Certainty; Categorization; Psychology; Calibration; Cognitive psychology; Social psychology; Statistics; Artificial intelligence; Computer science; Mathematics","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":[0.000344963,0.0002595049,0.0003750485,0.0002331469,0.0003848169,0.0001378555,0.001026474,0.0001029271,0.00002117317],"category_scores_gemma":[0.00004210213,0.0002027341,0.00004552118,0.0005529985,0.0005085913,0.00083816,0.00005054244,0.0003585638,0.000002774485],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003124147,"about_ca_system_score_gemma":0.0004312427,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001501243,"about_ca_topic_score_gemma":0.008254763,"domain_scores_codex":[0.9981011,0.0001518215,0.0005338443,0.0004682272,0.0001197195,0.0006252866],"domain_scores_gemma":[0.9980614,0.00006226388,0.0005404695,0.0003898622,0.0001812253,0.0007648412],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0006798771,0.0002242405,0.5594379,0.0001174462,0.0001713106,0.0002216473,0.1461412,0.001155358,0.2867988,0.001329292,0.0004074193,0.0033155],"study_design_scores_gemma":[0.002719173,0.006640678,0.1240326,0.0005883204,0.00006852408,0.002028781,0.06794272,0.008910632,0.7856287,0.0001050465,0.0004644467,0.0008703892],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9868727,0.001714624,0.008795313,0.001599017,0.0003781234,0.0003158766,0.000004061184,0.00002122274,0.0002990999],"genre_scores_gemma":[0.9959138,0.00002401562,0.003481378,0.0003777152,0.000137876,0.00002392505,0.000001646482,0.00002390857,0.0000157054],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4988299,"threshold_uncertainty_score":0.8267258,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05784011160937338,"score_gpt":0.3243635665656008,"score_spread":0.2665234549562274,"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."}}