{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004543151,0.0001795406,0.0006424797,0.0003184629,0.00003993688,0.00001589922,0.0001230186,0.000105682,0.0008693552],"category_scores_gemma":[0.0008011669,0.0001624423,0.0002283139,0.0005731149,0.00008225669,0.000146191,0.0001380079,0.0000941699,0.00003785238],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006801124,"about_ca_system_score_gemma":0.000188895,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001958486,"about_ca_topic_score_gemma":6.884383e-7,"domain_scores_codex":[0.9967355,0.0005775298,0.0007284338,0.0003433591,0.001358924,0.0002562638],"domain_scores_gemma":[0.9966901,0.001566631,0.0002253884,0.0003625781,0.0009499369,0.0002053796],"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":[0.006430751,0.002696714,0.1196716,0.0003379746,0.0006361434,0.0006861565,0.00101881,0.0001610113,0.02689785,0.00003064631,0.0002101858,0.8412221],"study_design_scores_gemma":[0.008015433,0.008921245,0.9058252,0.001421685,0.0005399095,0.001060383,0.0003292889,0.003489797,0.00725119,0.0001410003,0.06234812,0.0006567436],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9902614,0.00003718906,0.0006123467,0.00005930027,0.0003633584,0.0004057292,0.00001429489,0.00004863451,0.008197792],"genre_scores_gemma":[0.9966999,0.000006189483,0.002810342,0.0001286277,0.0001677209,0.00002748657,0.00003135976,0.00002727056,0.000101097],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8405654,"threshold_uncertainty_score":0.951883,"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."}}