{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","sts","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.02487362,0.0002786237,0.0007284323,0.0004016783,0.001401091,0.00004986006,0.0002034029,0.000258564,0.00001454912],"category_scores_gemma":[0.02181491,0.0001863186,0.00004535965,0.0004863164,0.001561997,0.000160985,0.0001255612,0.00428994,0.000006892917],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001425635,"about_ca_system_score_gemma":0.0003133912,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004590649,"about_ca_topic_score_gemma":8.4051e-7,"domain_scores_codex":[0.9957099,0.001405395,0.001160689,0.0007305351,0.0005396692,0.0004537907],"domain_scores_gemma":[0.9862931,0.01245454,0.0002993142,0.0004336036,0.0002725502,0.0002469106],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00006754766,0.000142702,0.8501908,0.0002034515,0.00002769684,8.431787e-7,0.005915225,0.00007682387,0.000005163246,0.005372066,0.001476685,0.136521],"study_design_scores_gemma":[0.003080403,0.001866827,0.7849898,0.0008617661,0.0001533168,0.00002748841,0.004548008,0.1842145,9.431487e-7,0.0002122813,0.01987194,0.0001727625],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.983911,0.0002077972,0.002055526,0.0111089,0.0002201154,0.0007139439,7.968842e-7,0.00009978211,0.00168217],"genre_scores_gemma":[0.9853942,0.0001125062,0.01058115,0.001834279,0.001648333,0.00005301635,0.00003546135,0.00003295575,0.0003081161],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1841376,"threshold_uncertainty_score":0.999899,"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."}}