{"id":"W2071699777","doi":"10.1080/10401334.2014.945033","title":"Relationship Between Performance on the NBME®Comprehensive Clinical Science Self-Assessment and USMLE®Step 2 Clinical Knowledge for USMGs and IMGs","year":2014,"lang":"en","type":"article","venue":"Teaching and Learning in Medicine","topic":"Innovations in Medical Education","field":"Medicine","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Logistic regression; Medical education; United States Medical Licensing Examination; Medicine; Psychology; Family medicine; Medical school; Internal medicine","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00205207,0.0003278693,0.0002325245,0.00116213,0.000417699,0.0009138524,0.0005526366,0.000578697,0.003547791],"category_scores_gemma":[0.01793015,0.0001962843,0.0004321861,0.0006780632,0.0004825083,0.0006611273,0.001093422,0.001220299,0.0006349277],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009961064,"about_ca_system_score_gemma":0.001247039,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02410169,"about_ca_topic_score_gemma":0.02692995,"domain_scores_codex":[0.9985978,0.0002632312,0.0001480379,0.000234149,0.0004855319,0.000271128],"domain_scores_gemma":[0.9870026,0.004059935,0.004261259,0.0003918943,0.002077199,0.002207096],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00002476126,0.00004112337,0.9988919,0.000002075887,0.00001091764,0.000008264608,0.0001068095,0.00003230231,0.00002603273,0.00001078973,0.00009805088,0.0007471025],"study_design_scores_gemma":[0.000001807568,0.00007544858,0.9993637,0.000003546083,0.000005894538,0.00002776983,0.0002102342,0.0001711585,0.00003980136,0.000008871497,0.00008972601,0.000001988072],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9989201,0.00005442979,0.00003880947,0.00008235185,0.000006459258,0.000007905208,0.0001438767,0.000005018926,0.0007412088],"genre_scores_gemma":[0.9990016,0.00002502458,0.00005379288,0.00001535335,0.000004440025,0.000009329063,0.0002835122,0.000002291765,0.000604777],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02410169,"threshold_uncertainty_score":0.04792279,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09360601244113748,"score_gpt":0.4549729039612216,"score_spread":0.3613668915200841,"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."}}