{"id":"W2033127427","doi":"10.1007/s11251-013-9275-4","title":"Metacognitive scaffolds improve self-judgments of accuracy in a medical intelligent tutoring system","year":2013,"lang":"en","type":"article","venue":"Instructional Science","topic":"Clinical Reasoning and Diagnostic Skills","field":"Medicine","cited_by":57,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"U.S. National Library of Medicine; Drexel University","keywords":"Metacognition; Dermatopathology; Test (biology); Correctness; Self-confidence; Computer science; Educational psychology; Cognitive psychology; Psychology; Artificial intelligence; Cognition; Developmental psychology; Medicine; Pathology; Social psychology; Psychiatry; Algorithm","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0008143719,0.00009674495,0.0002470573,0.0001801141,0.00006111526,0.00002384131,0.0001956823,0.00007675117,0.0002513486],"category_scores_gemma":[0.02028262,0.00007449447,0.0000658963,0.0006806952,0.0004286248,0.0002341474,0.0001147219,0.000134739,0.00007774308],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002552644,"about_ca_system_score_gemma":0.0006297086,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006094638,"about_ca_topic_score_gemma":0.000005555462,"domain_scores_codex":[0.9976956,0.00002494149,0.0004673072,0.0003247021,0.001222531,0.000264924],"domain_scores_gemma":[0.9968151,0.002151379,0.0001335459,0.0001635153,0.000383429,0.0003529643],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0001301995,0.001335865,0.2158683,0.0002216268,0.0001402135,0.0001210412,0.0008616361,0.00003392934,0.02548525,0.02126786,0.0001017472,0.7344323],"study_design_scores_gemma":[0.001874077,0.0003278754,0.9550079,0.003480977,0.00005858826,0.0004122308,0.001033505,0.007601214,0.02915063,0.0007116374,0.0001374431,0.0002039043],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9944572,0.00003941201,0.00009439301,0.0003137865,0.0007964297,0.0002981775,0.00000346737,0.00004002606,0.003957045],"genre_scores_gemma":[0.9964763,0.00002371378,0.003151329,0.0001170833,0.0001485921,0.00004275472,0.000001913414,0.000005016444,0.00003330096],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7391396,"threshold_uncertainty_score":0.9879699,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01730056856659524,"score_gpt":0.3305150644929815,"score_spread":0.3132144959263863,"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."}}