{"id":"W3034579453","doi":"10.36510/learnland.v13i1.1012","title":"Student Evaluations and the Performance of University Teaching: Teaching to the Test","year":2020,"lang":"en","type":"article","venue":"LEARNing Landscapes","topic":"Evaluation of Teaching Practices","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Autoethnography; Excellence; Test (biology); Mathematics education; Psychology; Pedagogy; Reflection (computer programming); Identity (music); Perception; Sociology; Medical education; Computer science; Political science; Medicine","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0148529,0.0002272942,0.0003679656,0.001202605,0.001555989,0.005571304,0.0008289571,0.0006929883,0.002404826],"category_scores_gemma":[0.1229474,0.0001205338,0.0003066074,0.00121087,0.002169466,0.001452164,0.002917962,0.001589158,0.0005796539],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003998992,"about_ca_system_score_gemma":0.002784179,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007856279,"about_ca_topic_score_gemma":0.01032333,"domain_scores_codex":[0.9799187,0.01172207,0.0006874113,0.0004781919,0.005855347,0.001338176],"domain_scores_gemma":[0.9037731,0.038816,0.01581694,0.003682663,0.02497803,0.01293322],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0006407409,0.001949677,0.6861097,0.0001112216,0.0001147,0.0003670687,0.1152565,0.0006935388,0.001739342,0.003291054,0.004814663,0.1849117],"study_design_scores_gemma":[0.00003252578,0.001852264,0.8704933,0.0001598558,0.00003458892,0.0002257287,0.1086331,0.001692579,0.002768029,0.001908124,0.01208763,0.0001122676],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9869394,0.0001504696,0.0004741367,0.0005813997,0.00004120949,0.00003443946,0.00003713949,0.00002115636,0.01172066],"genre_scores_gemma":[0.9982883,0.00004461905,0.000172284,0.00005158761,0.00001105038,0.00002461308,0.00002596825,0.00001031317,0.001371171],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0148529,"threshold_uncertainty_score":0.07855058,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04932384494756675,"score_gpt":0.3740967221089505,"score_spread":0.3247728771613838,"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."}}