{"id":"W2047540418","doi":"10.1007/s10459-006-9057-8","title":"The effect of question format and task difficulty on reasoning strategies and diagnostic performance in Internal Medicine residents","year":2007,"lang":"en","type":"article","venue":"Advances in Health Sciences Education","topic":"Clinical Reasoning and Diagnostic Skills","field":"Medicine","cited_by":30,"is_retracted":false,"has_abstract":false,"ca_institutions":"McMaster University; Calgary General Hospital; Foothills Medical Centre; University of Calgary","funders":"","keywords":"Task (project management); Odds; Association (psychology); Verbal reasoning; Think aloud protocol; Deductive reasoning; Logical reasoning; Matching (statistics); Inductive reasoning; Analytic reasoning; MEDLINE; Cognitive psychology; Psychology; Logistic regression; Computer science; Mathematics education; Cognition; Artificial intelligence; Medicine; Machine learning; Pathology","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":[0.006823754,0.0007776876,0.0006968118,0.000795714,0.0003859054,0.001784807,0.001009827,0.001430107,0.003810427],"category_scores_gemma":[0.09513076,0.000580664,0.000680867,0.0005882992,0.0007084166,0.001635803,0.001152637,0.001372123,0.0006248516],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006060177,"about_ca_system_score_gemma":0.001054318,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001695045,"about_ca_topic_score_gemma":0.002142869,"domain_scores_codex":[0.9967453,0.001455317,0.0004751273,0.0004598736,0.00052844,0.0003359363],"domain_scores_gemma":[0.8401228,0.1343012,0.01450528,0.002222964,0.002820848,0.006026973],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.02399479,0.01023242,0.9164875,0.0002123024,0.000681224,0.0004076736,0.003845887,0.001373832,0.009429836,0.0001097704,0.0007374285,0.0324874],"study_design_scores_gemma":[0.0005448336,0.007449585,0.9863646,0.00004685179,0.0001535543,0.0003102468,0.001028527,0.002024406,0.001456331,0.000361438,0.0002045715,0.00005497646],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9996256,0.00006862146,0.00004695599,0.00004515377,0.000008415886,0.000006982553,0.00002173965,0.000004063607,0.0001725538],"genre_scores_gemma":[0.9989555,0.00006052259,0.0003367063,0.00008577828,0.00002104266,0.00002958803,0.00008524739,0.00001115673,0.0004143833],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006823754,"threshold_uncertainty_score":0.03608787,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01050650716699165,"score_gpt":0.4108181503220709,"score_spread":0.4003116431550793,"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."}}