{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.008101168,0.00006221168,0.0001040402,0.00002956744,0.002262431,0.00009270453,0.0003719599,0.00002648063,0.00004813897],"category_scores_gemma":[0.01326176,0.00003855748,0.00003221828,0.0001178285,0.0001095383,0.0002123395,0.0001249437,0.0005644977,0.00002436008],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002291322,"about_ca_system_score_gemma":0.00006640679,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005277779,"about_ca_topic_score_gemma":0.000266614,"domain_scores_codex":[0.9964644,0.002664108,0.0001180444,0.000140744,0.0004899436,0.0001227701],"domain_scores_gemma":[0.9957094,0.003917937,0.0001554517,0.00009745374,0.00005656626,0.00006316712],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000109291,0.00004972574,0.446135,0.00001481348,0.00005128491,5.042883e-7,0.4960416,0.01975415,0.0001143696,0.02077746,0.001915583,0.01503625],"study_design_scores_gemma":[0.0009652865,0.0002498254,0.1659268,0.0000439832,0.0001466563,9.167804e-7,0.09721538,0.02849611,0.00001133589,0.00003115868,0.7067617,0.0001508353],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8559404,0.00007111504,0.0001648036,0.1227978,0.00004910951,0.000244076,8.770734e-7,0.00005712813,0.02067468],"genre_scores_gemma":[0.9972861,0.00005486326,0.0004926032,0.0004758594,0.0001562066,0.000002284763,8.731971e-7,0.000005036261,0.0015262],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7048461,"threshold_uncertainty_score":0.9990365,"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."}}