{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006627773,0.0004132893,0.000395853,0.001086401,0.0002338313,0.00173032,0.0005871925,0.001066893,0.00124723],"category_scores_gemma":[0.106701,0.0002781503,0.0003155353,0.0008529092,0.0005224429,0.001820047,0.001174022,0.000925366,0.0004070208],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003519711,"about_ca_system_score_gemma":0.0003786668,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001187869,"about_ca_topic_score_gemma":0.00138047,"domain_scores_codex":[0.9960209,0.001243368,0.0003010207,0.000763673,0.001499413,0.0001717393],"domain_scores_gemma":[0.9261472,0.04598918,0.01635102,0.005794758,0.004226859,0.001490927],"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":[0.01069184,0.001569461,0.5553271,0.0008044399,0.000703765,0.0001781473,0.007913322,0.009259149,0.09292325,0.003232109,0.001551148,0.3158464],"study_design_scores_gemma":[0.00007725802,0.002619853,0.9472083,0.00009805198,0.0001374512,0.0003558218,0.0005868228,0.02492866,0.01977824,0.00283351,0.001237351,0.0001387036],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9624467,0.0005077576,0.03011912,0.00006991532,0.00003708736,0.0001382019,0.000308774,0.0002060367,0.006166414],"genre_scores_gemma":[0.9936787,0.0000856299,0.00537788,0.00002207992,0.0000141064,0.00007812023,0.0002837318,0.00004771911,0.0004120023],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006627773,"threshold_uncertainty_score":0.03505141,"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."}}