{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008265607,0.0005303847,0.0004586484,0.001821485,0.0005963879,0.001119894,0.001065644,0.0007401772,0.001021849],"category_scores_gemma":[0.0369565,0.0003199714,0.000768014,0.001200171,0.0007556259,0.001042109,0.001824583,0.001110635,0.0005670935],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006470119,"about_ca_system_score_gemma":0.0009311758,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0054183,"about_ca_topic_score_gemma":0.008731601,"domain_scores_codex":[0.9956591,0.001695642,0.0004571521,0.0004581287,0.001442894,0.000287032],"domain_scores_gemma":[0.9744002,0.008400818,0.00852719,0.001949384,0.00409902,0.002623391],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00004206295,0.00009921037,0.9982435,0.000004623297,0.00003424413,0.00001047173,0.0001772375,0.00002560471,0.00004588651,0.000007385775,0.00004790597,0.001261856],"study_design_scores_gemma":[0.000006241046,0.0002121294,0.9989391,0.000009383495,0.00001371294,0.00004645462,0.0002512997,0.0002824127,0.00009287189,0.00001398057,0.0001285305,0.000004070735],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9994177,0.00004312787,0.000108459,0.00003480287,0.000007438094,0.00002044609,0.0001192725,0.000002923653,0.0002459706],"genre_scores_gemma":[0.9994048,0.00003164357,0.0001455286,0.00001694909,0.000008223257,0.00002274879,0.0002605553,0.000003362039,0.0001061802],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.008265607,"threshold_uncertainty_score":0.04371321,"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."}}