{"id":"W4386545263","doi":"10.1007/s42087-023-00361-7","title":"Student Evaluation of Teaching (SET): Why the Emperor Has No Clothes and What We Should Do About It","year":2023,"lang":"en","type":"article","venue":"Human Arenas","topic":"Evaluation of Teaching Practices","field":"Social Sciences","cited_by":23,"is_retracted":false,"has_abstract":false,"ca_institutions":"Mount Royal University","funders":"","keywords":"Set (abstract data type); Promotion (chess); Grade inflation; Mathematics education; Population; Quality (philosophy); Psychology; Higher education; Medical education; Computer science; Sociology; Medicine; Political science; Law","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":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.01742119,0.0001203372,0.0001579023,0.0001234058,0.001990925,0.001124596,0.0004251715,0.00007493496,0.0006778876],"category_scores_gemma":[0.002267075,0.00009117921,0.00006068312,0.0001623363,0.0003725195,0.001260297,0.0001286429,0.0002972153,0.0001520396],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009979083,"about_ca_system_score_gemma":0.0001414028,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001079535,"about_ca_topic_score_gemma":0.003730638,"domain_scores_codex":[0.9949951,0.002310313,0.0003113503,0.0002712873,0.001879913,0.0002320958],"domain_scores_gemma":[0.9981194,0.0009582933,0.0003036253,0.0003028348,0.0002541963,0.00006168925],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002177644,0.0001745856,0.01119512,0.00005671465,0.0001676234,0.000001918047,0.7877803,0.0004488351,0.00118562,0.04713816,0.06495086,0.08687848],"study_design_scores_gemma":[0.001011962,0.0001733955,0.09163001,0.0006342783,0.0003571181,0.000001015073,0.3198234,0.0009605089,0.0001217288,0.01339292,0.5715026,0.0003910037],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9319116,0.001659771,0.000007841306,0.04594557,0.0005345395,0.0006510851,0.000002428649,0.0001334043,0.01915372],"genre_scores_gemma":[0.9964418,0.0008282891,0.00005840665,0.000527142,0.000312385,0.00005263791,0.000007252842,0.0000168186,0.001755254],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5065517,"threshold_uncertainty_score":0.9999123,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4572463530790007,"score_gpt":0.5312590074083061,"score_spread":0.07401265432930537,"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."}}