{"id":"W2947847669","doi":"10.1503/cjs.009516","title":"Development of a cumulative teaching score for tracking surgeon performance in undergraduate medical education","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Surgery","topic":"Innovations in Medical Education","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Medicine; Medical education; Tracking (education); Quality (philosophy); Delphi method; Teaching method; Curriculum; Mathematics education; Psychology; Computer science; Pedagogy","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"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":[0.01659922,0.000660293,0.0006435694,0.00611565,0.0006422477,0.001552865,0.001240904,0.0006160068,0.002703238],"category_scores_gemma":[0.03162817,0.0002920467,0.001259147,0.002241335,0.0007523012,0.001631983,0.001724013,0.0008582183,0.0006698929],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002129851,"about_ca_system_score_gemma":0.003028534,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003216631,"about_ca_topic_score_gemma":0.006723954,"domain_scores_codex":[0.9915508,0.00259989,0.001644304,0.0003861242,0.003344651,0.0004742796],"domain_scores_gemma":[0.971032,0.007991875,0.006085528,0.0008670789,0.01188931,0.002134201],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0004577738,0.0005497585,0.8345129,0.000389076,0.0002215254,0.0001098622,0.00228304,0.002213839,0.00168457,0.0009761938,0.004179043,0.1524224],"study_design_scores_gemma":[0.0001058593,0.002261099,0.9692471,0.0002665985,0.0001476632,0.000251493,0.003688511,0.01387464,0.0034475,0.0008298544,0.005794812,0.00008489114],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9477591,0.0002832828,0.03077728,0.0005973175,0.0001762257,0.002193527,0.001595279,0.000401103,0.01621697],"genre_scores_gemma":[0.9349525,0.000201964,0.06041978,0.00006617853,0.00003684932,0.001952679,0.00126007,0.00003073417,0.001079221],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9834008,"threshold_uncertainty_score":0.08778614,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04986510045778844,"score_gpt":0.3253385653979958,"score_spread":0.2754734649402073,"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."}}