{"id":"W1524724430","doi":"10.22329/celt.v2i0.3220","title":"26. The Validity of Student Course Evaluations: An Eternal Debate?","year":2009,"lang":"en","type":"article","venue":"Collected Essays on Learning and Teaching","topic":"Evaluation of Teaching Practices","field":"Social Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Course (navigation); Course evaluation; Psychology; Mathematics education; Higher education; Pedagogy; Political science; Engineering; Law","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.01021034,0.0001194382,0.0001668707,0.00009664311,0.003161683,0.0002572512,0.0002919416,0.00008182404,0.0000880482],"category_scores_gemma":[0.005080753,0.00009473621,0.00004744624,0.0001659928,0.0001352408,0.000346469,0.0000259189,0.0009222096,0.000008570761],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008178062,"about_ca_system_score_gemma":0.0002202289,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005418007,"about_ca_topic_score_gemma":0.0002696672,"domain_scores_codex":[0.9924453,0.005928136,0.0002628351,0.0002446757,0.0008933299,0.0002257575],"domain_scores_gemma":[0.9975106,0.001714067,0.0003390973,0.0001720716,0.0001670868,0.00009704974],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0001863614,0.001976492,0.2692496,0.00002003007,0.0001978088,0.00001048487,0.257269,0.01259701,0.001514344,0.1613286,0.001992721,0.2936576],"study_design_scores_gemma":[0.002008958,0.002585581,0.8839255,0.0003182342,0.0004249528,0.00001203289,0.04842267,0.01646063,0.0001242523,0.00947421,0.03558735,0.0006556491],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.954618,0.0001099676,0.0005262548,0.006065948,0.0001630068,0.0002786106,8.109577e-7,0.0002037453,0.03803362],"genre_scores_gemma":[0.9973435,0.00005998305,0.000573331,0.0001861689,0.0001664109,0.000008888207,0.000003074108,0.00001201339,0.001646622],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6146759,"threshold_uncertainty_score":0.998136,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1216538769873287,"score_gpt":0.4768516063873564,"score_spread":0.3551977294000277,"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."}}