{"id":"W291597054","doi":"10.5430/ijhe.v4n2p116","title":"The Tail Wagging the Dog; An Overdue Examination of Student Teaching Evaluations","year":2015,"lang":"en","type":"article","venue":"International Journal of Higher Education","topic":"Evaluation of Teaching Practices","field":"Social Sciences","cited_by":45,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Mathematics education; Class (philosophy); Class size; Psychology; Test (biology); Set (abstract data type); Variance (accounting); Sample size determination; Statistics; Mathematics; Computer science","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01350339,0.00007512418,0.00008889967,0.0001554097,0.0005377871,0.0003385672,0.0009910078,0.00004333631,0.00009822841],"category_scores_gemma":[0.002377611,0.00004892308,0.00006721292,0.0001170947,0.0001534225,0.00144997,0.00004520597,0.0003156401,0.00001072998],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005243559,"about_ca_system_score_gemma":0.001373225,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005264912,"about_ca_topic_score_gemma":0.0001379181,"domain_scores_codex":[0.9949489,0.002072545,0.0005352563,0.00009551091,0.002236719,0.0001111195],"domain_scores_gemma":[0.9949431,0.001004765,0.001253364,0.0001675762,0.002542931,0.00008822648],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.00006833772,0.001212265,0.02594415,0.000003674985,0.0003111808,0.00000123022,0.1686079,0.001809976,0.0009088417,0.4889925,0.01543332,0.2967066],"study_design_scores_gemma":[0.0005159031,0.0001503269,0.6621287,0.00008019916,0.0001170675,0.00001477608,0.05486953,0.0002033025,0.0001011622,0.01497998,0.2667196,0.0001193945],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8993973,0.0007374649,0.000395893,0.06636503,0.009109963,0.0002186552,0.00000155515,0.00001609353,0.0237581],"genre_scores_gemma":[0.9926426,0.00005773516,0.0008842007,0.0002803388,0.001945706,0.00001063117,0.000005103657,0.000008379704,0.004165351],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6361846,"threshold_uncertainty_score":0.4680033,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1634833105387061,"score_gpt":0.5496602999909036,"score_spread":0.3861769894521975,"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."}}