{"id":"W1486190448","doi":"10.1111/medu.12091","title":"Rethinking programme evaluation in health professions education: beyond ‘did it work?’","year":2013,"lang":"en","type":"article","venue":"Medical Education","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":217,"is_retracted":false,"has_abstract":true,"ca_institutions":"Holland Bloorview Kids Rehabilitation Hospital; The Wilson Centre; London Health Sciences Centre; Centre Hospitalier Universitaire Sainte-Justine; SickKids Foundation; University of Toronto","funders":"","keywords":"Parallels; Context (archaeology); Engineering ethics; Curriculum; Field (mathematics); Process (computing); Work (physics); Health professions; Sociology; Program evaluation; Medical education; Management science; Health care; Psychology; Pedagogy; Political science; Medicine; Computer science; 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":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0197132,0.0001492923,0.0002461922,0.0004800796,0.0002740421,0.0002666949,0.000561383,0.000173115,0.02777538],"category_scores_gemma":[0.01327927,0.0001115862,0.00005725619,0.001874581,0.00009005772,0.0007750383,0.00007520419,0.0004627018,0.001484708],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005610498,"about_ca_system_score_gemma":0.02447969,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005847532,"about_ca_topic_score_gemma":0.0006480052,"domain_scores_codex":[0.9917692,0.001235487,0.001319934,0.0005079057,0.004767813,0.0003996373],"domain_scores_gemma":[0.9966258,0.0005502746,0.0004994622,0.0005935089,0.001342724,0.0003882717],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.000003358183,0.000600027,0.02735099,0.00001246583,0.000002066635,3.81092e-8,0.006203607,0.00001397351,0.000001740782,0.001750415,0.1787212,0.7853401],"study_design_scores_gemma":[0.000949665,0.0001507055,0.406803,0.001011632,0.0000126931,0.000009404574,0.02274506,0.02668127,0.00001304838,0.2428915,0.2983561,0.0003759445],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.3264521,0.0008345829,0.0008498525,0.6307736,0.00554372,0.003072134,6.404841e-7,0.00006353504,0.03240988],"genre_scores_gemma":[0.9565141,0.00006178032,0.003574868,0.0306138,0.0004396267,0.001866368,0.0001139846,0.00001279787,0.006802675],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7849641,"threshold_uncertainty_score":0.9992927,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2344919811446988,"score_gpt":0.5649593503657884,"score_spread":0.3304673692210895,"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."}}