{"id":"W4388798538","doi":"10.1007/s42087-023-00377-z","title":"Making Sense of Today’s Use of Student Evaluations of Teaching (SET)","year":2023,"lang":"en","type":"article","venue":"Human Arenas","topic":"Evaluation of Teaching Practices","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Operationalization; Set (abstract data type); Workload; Mathematics education; Test (biology); Psychology; Student engagement; Computer science","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.05778921,0.0003652808,0.0003607818,0.004900941,0.002783646,0.01210423,0.001305528,0.001807954,0.001715302],"category_scores_gemma":[0.143825,0.0002501326,0.0003212384,0.00224359,0.01032765,0.008864839,0.007178166,0.003692829,0.0002968099],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004040844,"about_ca_system_score_gemma":0.003990483,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004169561,"about_ca_topic_score_gemma":0.009298392,"domain_scores_codex":[0.9312381,0.04955192,0.002612502,0.001787452,0.01346536,0.001344695],"domain_scores_gemma":[0.7818919,0.1450083,0.01865112,0.01558048,0.03263548,0.006232721],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001937515,0.0002081939,0.08943918,0.0004714928,0.0001423402,0.0001822955,0.1020898,0.0005936852,0.001871261,0.1531104,0.02177674,0.6299207],"study_design_scores_gemma":[0.00003705473,0.0005139247,0.1529735,0.003373901,0.0001585591,0.0009615837,0.1977056,0.005106163,0.006798719,0.2563597,0.3757619,0.0002493824],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5215233,0.01146325,0.06298812,0.1262122,0.002932791,0.00008788346,0.0002754977,0.0003299802,0.2741869],"genre_scores_gemma":[0.9909763,0.0006694781,0.005122236,0.001452799,0.0002226692,0.00003433964,0.00003389829,0.00003555127,0.001452696],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9422108,"threshold_uncertainty_score":0.3056222,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5861145869692092,"score_gpt":0.5875478068753649,"score_spread":0.001433219906155747,"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."}}