{"id":"W4403250823","doi":"10.5334/pme.1128","title":"The Next Era of Assessment Within Medical Education: Exploring Intersections of Context and Implementation","year":2024,"lang":"en","type":"article","venue":"Perspectives on Medical Education","topic":"Innovations in Medical Education","field":"Medicine","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; Royal College of Physicians and Surgeons of Canada; Queen's University; University of Calgary","funders":"National Board of Medical Examiners","keywords":"Competence (human resources); Viewpoints; Medical education; Psychology; Engineering ethics; Medicine; Social psychology; Engineering","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001487785,0.0001541635,0.0002425302,0.0002913514,0.000182039,0.00004678859,0.0001575459,0.0001313195,0.001340476],"category_scores_gemma":[0.004799054,0.0001132634,0.00007743551,0.0007581933,0.0005713767,0.0002452695,0.00004110847,0.0008389257,0.000007789578],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004315408,"about_ca_system_score_gemma":0.00956314,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003397971,"about_ca_topic_score_gemma":0.00007783923,"domain_scores_codex":[0.9972987,0.0001250603,0.0007527175,0.0003551693,0.001297682,0.0001706662],"domain_scores_gemma":[0.9983175,0.0003450559,0.0001878449,0.0003157919,0.0006387662,0.0001950521],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"qualitative","study_design_scores_codex":[0.00004821382,0.001041088,0.001829444,0.0002867982,0.0001207974,8.64968e-7,0.02873801,4.455001e-7,0.0001154354,0.1853507,0.009361332,0.7731069],"study_design_scores_gemma":[0.0009635972,0.0008720773,0.04353684,0.004358381,0.0002193746,0.0001839327,0.9232723,0.004461539,0.0008484814,0.002408793,0.01863146,0.0002432433],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9013116,0.004974535,0.001316518,0.08431792,0.004792906,0.000707023,0.000002918367,0.00006567406,0.002510912],"genre_scores_gemma":[0.9938943,0.001914617,0.001345445,0.001444776,0.0007297361,0.0004185379,0.00005172517,0.00002296647,0.0001778735],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8945343,"threshold_uncertainty_score":0.9995725,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03546718440298215,"score_gpt":0.4356169161670036,"score_spread":0.4001497317640215,"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."}}