{"id":"W4404293037","doi":"10.36834/cmej.79759","title":"Artificial Intelligence can transform formative assessment in medical education","year":2024,"lang":"en","type":"article","venue":"Canadian Medical Education Journal","topic":"Innovations in Medical Education","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Regent Park Community Health Centre; University of Toronto","funders":"","keywords":"Formative assessment; Computer science; Artificial intelligence; Psychology; Mathematics education","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"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":[0.006864655,0.0006193813,0.000373498,0.00215605,0.0005979913,0.005763172,0.001128457,0.001212454,0.009219818],"category_scores_gemma":[0.04861739,0.0002539856,0.0005201455,0.001641548,0.001618092,0.004907841,0.002447413,0.001647661,0.001550527],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001700036,"about_ca_system_score_gemma":0.002778814,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004884947,"about_ca_topic_score_gemma":0.004320715,"domain_scores_codex":[0.9943235,0.003161098,0.0004041487,0.0004013397,0.001497492,0.0002123322],"domain_scores_gemma":[0.9736394,0.01974353,0.001220012,0.00197266,0.002944683,0.0004796891],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0003342623,0.0007669413,0.01225081,0.0004396984,0.00009513074,0.0001566049,0.002570479,0.02550198,0.002780454,0.1288078,0.008420733,0.8178751],"study_design_scores_gemma":[0.000116428,0.0003865747,0.01025615,0.0007733582,0.0001257902,0.0001957548,0.002957871,0.2255677,0.008085925,0.6942379,0.05716262,0.000133974],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"commentary","genre_scores_codex":[0.1023745,0.001418101,0.7026241,0.01642213,0.0009301321,0.0006372572,0.0006515566,0.003607566,0.1713346],"genre_scores_gemma":[0.7265978,0.0006852172,0.2632953,0.0007973888,0.0001500358,0.0002162167,0.0004597402,0.0001641159,0.007634205],"genre_candidate":"commentary","genre_consensus":null,"teacher_disagreement_score":0.009219818,"threshold_uncertainty_score":0.03630418,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01868005671031109,"score_gpt":0.3924891264834925,"score_spread":0.3738090697731815,"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."}}