{"id":"W1841123149","doi":"10.1080/02602938.2015.1044421","title":"Whose feedback? A multilevel analysis of student completion of end-of-term teaching evaluations","year":2015,"lang":"en","type":"article","venue":"Assessment & Evaluation in Higher Education","topic":"Evaluation of Teaching Practices","field":"Social Sciences","cited_by":41,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Respondent; Set (abstract data type); Psychology; Quality (philosophy); Quality assurance; Term (time); Higher education; Medical education; Multilevel model; Course evaluation; Mathematics education; Computer science; Medicine; Political science","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.02040448,0.0001502903,0.0004451743,0.001184331,0.0001663858,0.00004851677,0.0003628785,0.0001130151,0.00147546],"category_scores_gemma":[0.001344601,0.000166411,0.0001396891,0.001246652,0.0001835577,0.0008571519,0.00005361857,0.0002162413,0.000005868434],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001163612,"about_ca_system_score_gemma":0.003532922,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004774563,"about_ca_topic_score_gemma":0.001090211,"domain_scores_codex":[0.9906278,0.004363454,0.001189572,0.0003380206,0.003290223,0.0001909309],"domain_scores_gemma":[0.994328,0.001011391,0.001739525,0.0004280951,0.002392778,0.0001002392],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00002966994,0.002833675,0.8001143,0.00004083569,0.0004636079,4.526565e-8,0.05081913,0.0188165,0.001647892,0.08905154,0.0003765268,0.03580624],"study_design_scores_gemma":[0.0008343612,0.00009101739,0.9699257,0.00009525783,0.001579385,6.684686e-8,0.01089885,0.0133635,0.00006608642,0.002276757,0.0007276679,0.0001413169],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9758937,0.0001935192,0.001496157,0.00298803,0.001151217,0.001193507,0.00001484374,0.00002433407,0.01704464],"genre_scores_gemma":[0.9876195,0.00001916975,0.01126488,0.00004333248,0.0001080378,0.0002343318,0.0002797709,0.00001242274,0.0004185548],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1698114,"threshold_uncertainty_score":0.9994373,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4085236037266901,"score_gpt":0.6050658361994158,"score_spread":0.1965422324727257,"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."}}