{"id":"W2967149707","doi":"10.1097/acm.0000000000002942","title":"The Validity of Scores From the New MCAT Exam in Predicting Student Performance: Results From a Multisite Study","year":2019,"lang":"en","type":"article","venue":"Academic Medicine","topic":"Medical Education and Admissions","field":"Medicine","cited_by":65,"is_retracted":false,"has_abstract":true,"ca_institutions":"Memorial University of Newfoundland; University of Calgary","funders":"","keywords":"Summative assessment; United States Medical Licensing Examination; Entrance exam; Psychology; Medicine; Predictive validity; Medical school; Medical education; Clinical psychology; Mathematics education; Formative assessment","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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00231189,0.0001917544,0.0004919884,0.00006772271,0.0001234821,0.000005748262,0.0005319948,0.000161618,0.0009795267],"category_scores_gemma":[0.01147281,0.00008756388,0.00004337396,0.0003598527,0.0001905184,0.00006462399,0.0001541854,0.001409896,0.00005227038],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006642187,"about_ca_system_score_gemma":0.0004521776,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0034917,"about_ca_topic_score_gemma":0.0001165404,"domain_scores_codex":[0.9968433,0.0002681162,0.001076517,0.0004027625,0.001111832,0.0002974109],"domain_scores_gemma":[0.9940894,0.00413856,0.000350234,0.0007772859,0.00007859842,0.0005659796],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0003170533,0.00009227981,0.9257029,0.00001290227,0.00006265219,0.000003665093,0.04174772,0.000004795049,0.001320442,0.000009897481,0.02552663,0.005199033],"study_design_scores_gemma":[0.008033487,0.0005215588,0.9426302,0.001642527,0.0001578788,0.000002978173,0.03487969,0.0006948907,0.0003119438,0.00007362414,0.01096751,0.00008373861],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9680882,0.001299472,0.000009371869,0.02743989,0.001112782,0.00132871,0.00001424237,0.00003245621,0.000674846],"genre_scores_gemma":[0.9907604,0.001573304,0.00002928954,0.002571563,0.00155137,0.00002185916,0.0000697597,0.00001677136,0.00340567],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02486832,"threshold_uncertainty_score":0.9999337,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0736437354464028,"score_gpt":0.392143416943867,"score_spread":0.3184996814974642,"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."}}