{"id":"W4391566127","doi":"10.5334/pme.956","title":"Design and Implementation of a National Program of Assessment Model – Integrating Entrustable Professional Activity Assessments in Canadian Specialist Postgraduate Medical Education","year":2024,"lang":"en","type":"article","venue":"Perspectives on Medical Education","topic":"Innovations in Medical Education","field":"Medicine","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University Health Centre; Queen's University; Royal College of Physicians and Surgeons of Canada; University of Ottawa","funders":"","keywords":"Summative assessment; Competence (human resources); Formative assessment; Coaching; Medical education; Transformative learning; Educational assessment; Computer science; Psychology; Medicine; Pedagogy","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002507664,0.0001979448,0.0003178219,0.001072256,0.00009206705,0.00003732257,0.0001410167,0.0002407601,0.0009078337],"category_scores_gemma":[0.00304238,0.0001782777,0.00005385243,0.001036214,0.0002517308,0.0002847104,0.00003149763,0.0007394387,0.000002484859],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002256242,"about_ca_system_score_gemma":0.06844488,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01745327,"about_ca_topic_score_gemma":0.004312133,"domain_scores_codex":[0.9962783,0.0002214666,0.000671581,0.0004781006,0.00203928,0.0003112176],"domain_scores_gemma":[0.9982011,0.0001716126,0.0001991207,0.0001714218,0.0009131448,0.0003436381],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001335326,0.007022064,0.0126024,0.0008050099,0.0001138298,0.000004036458,0.01196062,0.00003265925,0.0005251865,0.1155171,0.008912337,0.8423712],"study_design_scores_gemma":[0.002510856,0.001495627,0.1984467,0.00732287,0.0001654595,0.0001128848,0.07790553,0.6949041,0.001031163,0.0137351,0.001765544,0.0006040856],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9516681,0.0003503753,0.00705002,0.03278002,0.001378608,0.002329571,0.00001596905,0.00005617441,0.004371129],"genre_scores_gemma":[0.9731946,0.0001498465,0.02463483,0.0007741595,0.0002760772,0.0005645901,0.0002236285,0.00002500089,0.000157287],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8417671,"threshold_uncertainty_score":0.9940143,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02561477575250796,"score_gpt":0.4870729356762655,"score_spread":0.4614581599237575,"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."}}