{"id":"W2106668378","doi":"10.1016/j.surge.2010.11.016","title":"Evaluation matters: Lessons learned on the evaluation of surgical teaching","year":2011,"lang":"en","type":"review","venue":"The Surgeon","topic":"Innovations in Medical Education","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Promotion (chess); Consistency (knowledge bases); Process (computing); Medical education; Anonymity; Psychology; Computer science; Medicine; Political science","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03316362,0.001702109,0.005411508,0.006989974,0.0009664923,0.006077255,0.00309171,0.007497998,0.003366155],"category_scores_gemma":[0.08155119,0.0009377019,0.002099762,0.008614521,0.006014256,0.008823724,0.002684343,0.008151582,0.001164819],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.006900851,"about_ca_system_score_gemma":0.01190089,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01120114,"about_ca_topic_score_gemma":0.02322884,"domain_scores_codex":[0.9843158,0.00672906,0.00271592,0.001235372,0.004638731,0.0003650019],"domain_scores_gemma":[0.8367551,0.1296862,0.006362143,0.00199518,0.02300052,0.002200826],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"qualitative","study_design_scores_codex":[0.00009326549,0.0000598808,0.0007070383,0.03099244,0.0003096091,0.0001114699,0.0002512382,0.0002058184,0.0001383981,0.008577667,0.07487424,0.8836789],"study_design_scores_gemma":[0.0001352695,0.0001515748,0.006228712,0.1439975,0.0008274589,0.001377073,0.0007810768,0.000377335,0.0002366424,0.01975254,0.8259787,0.0001560243],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00001952693,0.9961143,0.0001184823,0.003115931,0.0004537919,0.000003306747,0.00000592186,0.000003039226,0.0001656489],"genre_scores_gemma":[0.001003552,0.9920995,0.0007555884,0.00434026,0.001583674,0.0000132852,0.00001727101,0.000006588633,0.0001804203],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.03316362,"threshold_uncertainty_score":0.1753881,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3871785433775477,"score_gpt":0.5118842981378183,"score_spread":0.1247057547602706,"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."}}