{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.07020876,0.0003150681,0.0007937514,0.001285405,0.002926374,0.006194114,0.001315396,0.001713937,0.005205004],"category_scores_gemma":[0.1832877,0.0001973005,0.0008206727,0.001420842,0.003788615,0.003342003,0.005063005,0.003587545,0.0007983183],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.006482604,"about_ca_system_score_gemma":0.009646704,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004300411,"about_ca_topic_score_gemma":0.01256169,"domain_scores_codex":[0.9107653,0.06715521,0.002715404,0.0008402545,0.01691462,0.001609214],"domain_scores_gemma":[0.8529375,0.06315067,0.01262219,0.005563309,0.0501742,0.0155522],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0009629589,0.001552504,0.08825053,0.00162041,0.0002747076,0.000163358,0.0495846,0.0002627238,0.0007557926,0.02443206,0.07656054,0.7555798],"study_design_scores_gemma":[0.0005360778,0.005903967,0.4175634,0.0109498,0.0006379793,0.001247401,0.166183,0.005130575,0.00861886,0.0557228,0.3270311,0.0004750188],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.648581,0.01365042,0.02059797,0.144167,0.004627553,0.0009397903,0.0003448898,0.0004800716,0.1666113],"genre_scores_gemma":[0.9762174,0.001387602,0.007128351,0.004079144,0.0003320308,0.0003266971,0.0001180023,0.00008610454,0.01032458],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9297912,"threshold_uncertainty_score":0.3713039,"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."}}