{"id":"W2021130872","doi":"10.1097/acm.0b013e3181ed3f5c","title":"Relationship Between Performance on the NBME Comprehensive Basic Sciences Self-Assessment and USMLE Step 1 for U.S. and Canadian Medical School Students","year":2010,"lang":"en","type":"article","venue":"Academic Medicine","topic":"Innovations in Medical Education","field":"Medicine","cited_by":34,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Logistic regression; United States Medical Licensing Examination; Medical education; Psychology; Medical school; Regression analysis; Medicine; Demography; Statistics; Mathematics; 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":[],"consensus_categories":[],"category_scores_codex":[0.003057814,0.0001605384,0.0002724297,0.0002974939,0.0005975416,0.00001201884,0.0002922468,0.0003401862,0.0003976745],"category_scores_gemma":[0.004343276,0.00009893097,0.00001376032,0.000404826,0.0008528677,0.00009625917,0.00005117655,0.001994243,0.00001588043],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001207012,"about_ca_system_score_gemma":0.001446205,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005885402,"about_ca_topic_score_gemma":0.0002403105,"domain_scores_codex":[0.9976821,0.0000606286,0.0004386345,0.0003320331,0.001148246,0.0003383512],"domain_scores_gemma":[0.9973617,0.001410298,0.0001201586,0.0002402755,0.0002093966,0.0006581864],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000009903574,0.00001006064,0.9606286,0.00007647389,0.00002434329,0.000001196418,0.000601173,7.689197e-8,0.00004609871,0.009511531,0.02507689,0.004013599],"study_design_scores_gemma":[0.001469397,0.0004045067,0.969142,0.0003022247,0.0001065817,0.00004998264,0.001139036,0.0008726231,0.00001373547,0.000548613,0.02585173,0.00009962699],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.906546,0.0001234112,0.00006746905,0.09107729,0.0004946631,0.0009067121,0.000004977775,0.00002994727,0.000749511],"genre_scores_gemma":[0.9795172,0.0001198573,0.001117141,0.01762427,0.001241441,0.0001163512,0.00002877065,0.00001470071,0.0002202854],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.07345302,"threshold_uncertainty_score":0.8664104,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06411790585150015,"score_gpt":0.4183081263111712,"score_spread":0.3541902204596711,"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."}}