{"id":"W1904031896","doi":"10.1111/j.1365-2753.2012.01879.x","title":"The 2011 <scp>P</scp>rogram <scp>E</scp>valuation <scp>S</scp>tandards: a framework for quality in medical education programme evaluations","year":2012,"lang":"en","type":"article","venue":"Journal of Evaluation in Clinical Practice","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Centre for Advancing Health Outcomes","funders":"","keywords":"Valuation (finance); Accountability; Quality (philosophy); Computer science; Business; Political science; Accounting","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.4672679,0.0017521,0.0040511,0.020939,0.004038596,0.01625879,0.005164198,0.00676588,0.004008446],"category_scores_gemma":[0.5423355,0.001930553,0.008949853,0.01468412,0.01323112,0.01097248,0.01097301,0.008567588,0.000712934],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.03647808,"about_ca_system_score_gemma":0.07636089,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.016846,"about_ca_topic_score_gemma":0.01891235,"domain_scores_codex":[0.4758489,0.4183332,0.04716334,0.005374173,0.05076118,0.002519124],"domain_scores_gemma":[0.3862372,0.4297329,0.04264954,0.04304217,0.092445,0.005893224],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000999019,0.0004673439,0.01574076,0.04065092,0.003052376,0.0001896939,0.008494598,0.01539981,0.0007025402,0.3991862,0.1322614,0.3828552],"study_design_scores_gemma":[0.001856582,0.002209474,0.04819755,0.1424056,0.004994042,0.0005442832,0.009214073,0.03820793,0.003840535,0.4307646,0.3168562,0.0009091909],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03354306,0.04116293,0.6306914,0.1543851,0.003998639,0.05325441,0.01180299,0.001616042,0.06954541],"genre_scores_gemma":[0.1611494,0.006474716,0.7693691,0.007948956,0.0002849308,0.0488535,0.002876201,0.0002788069,0.002764337],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5327321,"threshold_uncertainty_score":0.6569536,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4121633544668809,"score_gpt":0.6581448782419245,"score_spread":0.2459815237750436,"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."}}