{"id":"W4383823191","doi":"10.1007/s44186-023-00130-8","title":"Design of a new competency-based entrustment scale for the evaluation of resident performance","year":2023,"lang":"en","type":"article","venue":"Global Surgical Education - Journal of the Association for Surgical Education","topic":"Innovations in Medical Education","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University; University of Toronto","funders":"","keywords":"Summative assessment; Formative assessment; Competence (human resources); Documentation; Scale (ratio); Medical education; Psychology; Medicine; Applied psychology; Computer science; Pedagogy; Social psychology","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":[],"category_scores_codex":[0.009409695,0.0004155274,0.0004389602,0.002833636,0.0006411142,0.001063189,0.000824239,0.0003910118,0.002885399],"category_scores_gemma":[0.02253969,0.0002799805,0.0008839192,0.001105044,0.0007329775,0.001342378,0.0015606,0.0009037576,0.0004927121],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001840695,"about_ca_system_score_gemma":0.002681007,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004036551,"about_ca_topic_score_gemma":0.00933001,"domain_scores_codex":[0.9936935,0.00239086,0.001204027,0.000290731,0.002091946,0.000328984],"domain_scores_gemma":[0.9839175,0.005490731,0.002976387,0.0005827474,0.00546833,0.001564365],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001286098,0.001733077,0.782141,0.0004991665,0.0002181364,0.0002276061,0.004830879,0.002613462,0.004556674,0.001693531,0.00573732,0.1944631],"study_design_scores_gemma":[0.0002945246,0.003029714,0.9714281,0.0001467152,0.00005166098,0.0001907708,0.004676396,0.01098252,0.002014913,0.0009354652,0.006124462,0.0001247909],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.9592285,0.0001574064,0.01744917,0.0004160237,0.0001341493,0.008918968,0.001171023,0.0002363684,0.01228835],"genre_scores_gemma":[0.9240892,0.0001752713,0.06283425,0.0001651806,0.00005033152,0.01013139,0.001128701,0.00002201736,0.001403679],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9905903,"threshold_uncertainty_score":0.0497638,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04045126658654256,"score_gpt":0.3851443111767701,"score_spread":0.3446930445902275,"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."}}