{"id":"W4407979374","doi":"10.1186/s12909-025-06896-3","title":"Student evaluations of teaching do not reflect student learning: an observational study","year":2025,"lang":"en","type":"article","venue":"BMC Medical Education","topic":"Evaluation of Teaching Practices","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Observational study; Medical education; Psychology; Mathematics education; Medicine; Internal medicine","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","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01886842,0.0001127497,0.0001956448,0.0002329152,0.0009708747,0.0001445178,0.0006413986,0.0001129184,0.001023601],"category_scores_gemma":[0.04459296,0.0001123781,0.00005747306,0.0003939932,0.0001368034,0.0005429339,0.00009300609,0.0005345918,0.00002380435],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003631354,"about_ca_system_score_gemma":0.01046558,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001699938,"about_ca_topic_score_gemma":0.003842419,"domain_scores_codex":[0.9898155,0.005772225,0.0006301255,0.0003613094,0.003227512,0.0001933052],"domain_scores_gemma":[0.9962614,0.002282986,0.0003848072,0.0003059074,0.0005688662,0.0001960518],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00002263038,0.00517502,0.7885431,0.00002043,0.00005355211,1.413974e-7,0.07049811,0.0003412191,0.00003612647,0.1080384,0.001292931,0.02597836],"study_design_scores_gemma":[0.0005068058,0.0001899097,0.8564486,0.000108878,0.0001239592,1.994365e-7,0.1276841,0.0004108205,0.000006172468,0.00121086,0.01319691,0.0001127529],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9610466,0.0001018937,0.001278668,0.01069385,0.001355418,0.0008599195,5.628071e-7,0.00008608686,0.02457702],"genre_scores_gemma":[0.9916694,0.00002156983,0.002700122,0.0006441919,0.000385387,0.0001784235,0.00002789798,0.000008746743,0.004364219],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1068275,"threshold_uncertainty_score":0.9998896,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3952213544656644,"score_gpt":0.640712764802941,"score_spread":0.2454914103372766,"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."}}