{"id":"W2884437142","doi":"10.1097/acm.0000000000002366","title":"Examining Demographics, Prior Academic Performance, and United States Medical Licensing Examination Scores","year":2018,"lang":"en","type":"article","venue":"Academic Medicine","topic":"Medical Education and Admissions","field":"Medicine","cited_by":217,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"United States Medical Licensing Examination; Covariate; Demographics; Medicine; Licensure; Test (biology); Educational measurement; Family medicine; Medical education; Medical school; Psychology; Demography; Curriculum; Statistics; Pedagogy","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","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002426267,0.0002728862,0.0004810755,0.0008068283,0.0003024873,0.000006272662,0.0002101778,0.000661109,0.002937496],"category_scores_gemma":[0.01481727,0.0001946715,0.0000241439,0.001140501,0.001628328,0.0001560563,0.0001056768,0.002051117,0.00004185084],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005197655,"about_ca_system_score_gemma":0.0004962485,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003357189,"about_ca_topic_score_gemma":0.000002222925,"domain_scores_codex":[0.9968427,0.0001563878,0.0008074155,0.0004833753,0.0012088,0.0005012546],"domain_scores_gemma":[0.9961868,0.0007175265,0.0002256813,0.0002766102,0.0003060221,0.00228739],"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":[0.0003705264,0.00009470453,0.3475231,0.001019646,0.0002202168,0.00008521678,0.03637205,9.318568e-7,0.008182214,0.001891233,0.1490718,0.4551683],"study_design_scores_gemma":[0.008602236,0.002649894,0.6176108,0.01420642,0.0006312576,0.00163199,0.01742164,0.03532595,0.001706714,0.0004478915,0.2989904,0.0007748088],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9672617,0.001293843,0.0004069299,0.02790511,0.0006234876,0.0003510961,0.000001334952,0.0001745022,0.001982006],"genre_scores_gemma":[0.9545827,0.01418541,0.0002401451,0.0258214,0.002574932,0.00001415305,0.0001715043,0.00003785678,0.002371884],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4543935,"threshold_uncertainty_score":0.997974,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06430175501914472,"score_gpt":0.365705723401871,"score_spread":0.3014039683827263,"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."}}