{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.4108022,0.0004964818,0.00116439,0.0009488058,0.0007395563,0.001052446,0.001542855,0.0009855203,0.0003923628],"category_scores_gemma":[0.8869654,0.0003550275,0.0007630885,0.002471785,0.0004411191,0.004944779,0.0002156017,0.002867152,0.0004566732],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001017179,"about_ca_system_score_gemma":0.01142328,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006747536,"about_ca_topic_score_gemma":0.0004378099,"domain_scores_codex":[0.937115,0.02436636,0.01293419,0.001213894,0.02268472,0.001685905],"domain_scores_gemma":[0.38842,0.5618237,0.01787298,0.002507521,0.02745347,0.001922409],"domain_codex":null,"domain_gemma":"methods","domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001839187,0.007685776,0.1923999,0.00005042469,0.0002877818,0.000003534151,0.009363551,0.002382867,0.00001291452,0.02462642,0.1182069,0.644796],"study_design_scores_gemma":[0.004475671,0.001008771,0.3262503,0.0002901095,0.0005316515,0.00008705239,0.03765704,0.0455089,0.00002424998,0.1564829,0.4275824,0.0001009174],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8124878,0.008637863,0.09894874,0.03803823,0.01778125,0.007528023,0.00003719807,0.00008083959,0.01645999],"genre_scores_gemma":[0.9066002,0.002955195,0.07412715,0.007162616,0.005494236,0.001610711,0.0001042925,0.000100311,0.001845286],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6446951,"threshold_uncertainty_score":0.9999846,"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."}}