{"id":"W4409084641","doi":"10.1038/s44159-025-00444-y","title":"It is time to abandon student evaluations of teaching","year":2025,"lang":"en","type":"article","venue":"Nature Reviews Psychology","topic":"Evaluation of Teaching Practices","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"Brock University","funders":"","keywords":"Mathematics education; Psychology","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":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.01168024,0.0001124108,0.0003698375,0.0002289192,0.0003334065,0.00003097492,0.0005790716,0.0002863554,0.002513103],"category_scores_gemma":[0.006865256,0.00009973669,0.0001294837,0.0004728243,0.00007674082,0.0001530319,0.00005906728,0.000789635,0.00114052],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008635094,"about_ca_system_score_gemma":0.0001533812,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004012095,"about_ca_topic_score_gemma":0.0001283894,"domain_scores_codex":[0.9956124,0.002828549,0.0005248915,0.0003419874,0.0004866396,0.0002055496],"domain_scores_gemma":[0.9983841,0.0006108781,0.0003173852,0.0004352768,0.0001877445,0.00006458741],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001271678,0.0001659882,0.001106927,0.00002481527,0.0000445939,2.775553e-7,0.009004846,0.000002271184,0.0004214653,0.01019111,0.8143339,0.1646911],"study_design_scores_gemma":[0.0002094524,0.0000402945,0.004959658,0.0001708201,0.00008367143,4.545293e-7,0.0001443104,0.000003162865,0.00001009182,0.0008363761,0.9934613,0.00008047992],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"commentary","genre_scores_codex":[0.002355162,0.01895682,0.0005768464,0.3383616,0.0009503395,0.001256966,0.000004056486,0.00004677316,0.6374915],"genre_scores_gemma":[0.2463447,0.02490294,0.04286938,0.503154,0.001420866,0.0006320725,0.0000372169,0.00006671642,0.1805721],"genre_candidate":"commentary","genre_consensus":null,"teacher_disagreement_score":0.4569194,"threshold_uncertainty_score":0.9996372,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1221220600918079,"score_gpt":0.617947088584435,"score_spread":0.4958250284926272,"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."}}