{"id":"W2794264948","doi":"10.1111/vsu.12772","title":"Evaluation of a method to assess digitally recorded surgical skills of novice veterinary students","year":2018,"lang":"en","type":"article","venue":"Veterinary Surgery","topic":"Surgical Simulation and Training","field":"Medicine","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"","keywords":"Intraclass correlation; Medicine; Rubric; Generalizability theory; Inter-rater reliability; Grading (engineering); Cronbach's alpha; Medical physics; Reliability (semiconductor); Statistics; Rating scale; Psychology; Clinical psychology; Psychometrics; Mathematics","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":[0.0161327,0.0007727705,0.0004217489,0.001866396,0.0003510902,0.001001173,0.0009065838,0.000868707,0.002340058],"category_scores_gemma":[0.04814167,0.0002692236,0.0006969121,0.0007490105,0.0004755727,0.0008432697,0.001368762,0.0005218021,0.0007164157],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007193605,"about_ca_system_score_gemma":0.001184649,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009828714,"about_ca_topic_score_gemma":0.002562483,"domain_scores_codex":[0.9839314,0.008024912,0.001444705,0.001095466,0.005056837,0.00044668],"domain_scores_gemma":[0.9307203,0.03012353,0.006019755,0.00343611,0.02750182,0.002198531],"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":[0.005450603,0.00794291,0.413406,0.001404155,0.0002990192,0.0003862998,0.004775168,0.002063869,0.04459393,0.0003849246,0.002594439,0.5166987],"study_design_scores_gemma":[0.001471955,0.05256753,0.8594572,0.0005241935,0.0004118815,0.001588173,0.005515019,0.02170366,0.04227291,0.0003449151,0.01387128,0.0002711517],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9502999,0.0003936922,0.0361561,0.00024207,0.0002466319,0.006472267,0.0004898143,0.0003521997,0.005347425],"genre_scores_gemma":[0.8773134,0.0004259449,0.1111555,0.0002487859,0.0001617119,0.006824285,0.0006221632,0.00006283913,0.003185358],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0161327,"threshold_uncertainty_score":0.08531886,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2278134446514922,"score_gpt":0.4712252885179457,"score_spread":0.2434118438664535,"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."}}