{"id":"W4414076920","doi":"10.5430/ijhe.v14n5p1","title":"Towards an Inclusive Approach to Evaluation of Teaching","year":2025,"lang":"en","type":"article","venue":"International Journal of Higher Education","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Curriculum; Perception; Likert scale; Higher education; Course evaluation; Teaching method; Faculty development","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"},{"model":"gpt","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"other","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"}],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.1351772,0.001648124,0.002784785,0.01515527,0.005322041,0.03013477,0.005159939,0.002736475,0.002798118],"category_scores_gemma":[0.1038002,0.0009498987,0.001884943,0.006912157,0.01582518,0.02150781,0.02144995,0.008046649,0.001228467],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.009003425,"about_ca_system_score_gemma":0.01927729,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006051487,"about_ca_topic_score_gemma":0.007989733,"domain_scores_codex":[0.8479692,0.08674335,0.00970688,0.005442543,0.04771528,0.002422661],"domain_scores_gemma":[0.8427993,0.06079561,0.009921012,0.02020466,0.05765293,0.008626507],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001629663,0.0006358104,0.02039221,0.001977525,0.0002525467,0.0002458142,0.05621634,0.002399655,0.003393587,0.2272772,0.008776422,0.67827],"study_design_scores_gemma":[0.0001292951,0.00110111,0.04191901,0.008847523,0.0004214087,0.001551027,0.08897055,0.01331495,0.005492609,0.6068327,0.2309646,0.0004552679],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04421064,0.008268923,0.7734991,0.02980917,0.00123897,0.001517785,0.0001161526,0.001023907,0.1403153],"genre_scores_gemma":[0.3891637,0.003768948,0.588969,0.002888537,0.0006263771,0.001830716,0.0001812627,0.0003509652,0.01222046],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8648227,"threshold_uncertainty_score":0.7148941,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1747654185085843,"score_gpt":0.582711521443415,"score_spread":0.4079461029348307,"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."}}