{"id":"W4411350866","doi":"10.1038/s44159-025-00464-8","title":"Student evaluations of teaching should not be abandoned","year":2025,"lang":"en","type":"article","venue":"Nature Reviews Psychology","topic":"Evaluation of Teaching Practices","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Regina","funders":"","keywords":"Mathematics education; Psychology; Pedagogy","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01608022,0.0001303753,0.0004322332,0.000225411,0.0004573746,0.00003315129,0.00062423,0.0004180242,0.0004143695],"category_scores_gemma":[0.01053693,0.0001130251,0.0001685587,0.0004069233,0.0001744614,0.0002071129,0.000056367,0.00131165,0.00004602241],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008543082,"about_ca_system_score_gemma":0.0001746614,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001089556,"about_ca_topic_score_gemma":0.0004310695,"domain_scores_codex":[0.9938998,0.004222288,0.0006271996,0.000357146,0.0006635392,0.000229982],"domain_scores_gemma":[0.9976862,0.001104138,0.0004838054,0.0004795292,0.0001933451,0.00005297627],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0000495123,0.0005296806,0.009208493,0.00008982422,0.0001369514,0.000001172379,0.01019267,0.000006582728,0.00135845,0.5354355,0.1368017,0.3061895],"study_design_scores_gemma":[0.0004000629,0.00003228703,0.02086644,0.0001166039,0.0001309762,6.634342e-7,0.0003150415,0.000003692166,0.00002245663,0.001517978,0.9765024,0.00009141296],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.01955598,0.05985222,0.001549575,0.3158617,0.00401236,0.002090316,0.000008039381,0.0001315116,0.5969383],"genre_scores_gemma":[0.937579,0.0164462,0.008099951,0.03061978,0.0003412324,0.0001456123,0.00001414752,0.00001539417,0.006738724],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.918023,"threshold_uncertainty_score":0.9977977,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2812396077840588,"score_gpt":0.6414214610472315,"score_spread":0.3601818532631727,"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."}}