{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00816352,0.0001102013,0.0003562486,0.0004811306,0.00005163315,0.000006274491,0.0002223055,0.0001285185,0.0001898429],"category_scores_gemma":[0.03283907,0.00007558409,0.0001522709,0.0002309438,0.0001362255,0.0002191312,0.00003400573,0.0002420918,0.000001497903],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004408657,"about_ca_system_score_gemma":0.003621288,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006615073,"about_ca_topic_score_gemma":9.489354e-7,"domain_scores_codex":[0.9958698,0.0002741828,0.001801377,0.0001503552,0.001764017,0.0001403206],"domain_scores_gemma":[0.9946941,0.0004624301,0.001468069,0.000277663,0.003000456,0.00009724463],"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":[0.001039119,0.001946901,0.001898444,0.0003812085,0.0001915292,0.000002551406,0.005015668,0.000009571987,0.02003826,0.001061421,0.02755758,0.9408578],"study_design_scores_gemma":[0.06157857,0.04192713,0.3971374,0.09368731,0.007021006,0.007469929,0.04737631,0.01418977,0.01402713,0.01201455,0.3021269,0.001443904],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9655069,0.0002233972,0.0187344,0.01153845,0.00208007,0.0005284459,0.000006837639,0.000007408456,0.001374146],"genre_scores_gemma":[0.9767213,0.00004069983,0.02186213,0.0004870053,0.0006506508,0.00004424979,0.00001934792,0.0000157667,0.0001588783],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9394138,"threshold_uncertainty_score":0.9753078,"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."}}