{"id":"W2499016561","doi":"10.3138/jvme.1215-201r","title":"A Guide for Making Valid Interpretations of Student Evaluation of Teaching (SET) Results","year":2016,"lang":"en","type":"article","venue":"Journal of Veterinary Medical Education","topic":"Innovations in Medical Education","field":"Medicine","cited_by":26,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Set (abstract data type); Promotion (chess); Medical education; Curriculum; Sample (material); Psychology; Mathematics education; Medicine; Pedagogy; Computer science; Political science","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.1253438,0.002968739,0.002698193,0.01375234,0.003884434,0.006161615,0.00492797,0.005197471,0.01626808],"category_scores_gemma":[0.2295182,0.003569206,0.002725182,0.007317435,0.00461432,0.00585692,0.004770024,0.009327229,0.02431759],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005720822,"about_ca_system_score_gemma":0.02033044,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005578798,"about_ca_topic_score_gemma":0.01715897,"domain_scores_codex":[0.8494843,0.09892111,0.02413404,0.001845712,0.02403377,0.001581133],"domain_scores_gemma":[0.5716872,0.2444827,0.01566616,0.01869068,0.1452234,0.004249802],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002810622,0.001221711,0.003536237,0.002285236,0.00009905485,0.001136151,0.01681938,0.001921339,0.005400578,0.01605862,0.5291256,0.4221149],"study_design_scores_gemma":[0.0002884963,0.0008771166,0.01173538,0.007474574,0.00009365032,0.002178036,0.01776654,0.008748468,0.006209319,0.02668946,0.9174094,0.0005295915],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01534409,0.002978307,0.7765886,0.0322735,0.004219817,0.05285892,0.01089198,0.02115813,0.08368662],"genre_scores_gemma":[0.006472246,0.001226763,0.9588244,0.00210433,0.0001819005,0.01911204,0.001438314,0.001095055,0.009544953],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8746562,"threshold_uncertainty_score":0.6628895,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1681039235270954,"score_gpt":0.5506300885867667,"score_spread":0.3825261650596712,"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."}}