{"id":"W4412870717","doi":"10.24908/pceea.2025.19674","title":"Preliminary Review of Instructor and Teaching Assistant Perceptions of Grading","year":2025,"lang":"en","type":"article","venue":"Proceedings of the Canadian Engineering Education Association (CEEA)","topic":"Evaluation of Teaching Practices","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"University of Waterloo","keywords":"Grading (engineering); Mathematics education; Psychology; Teaching assistant; Medical education; Computer science; Engineering; Medicine; Civil engineering","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":true,"about_ca":false,"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":[0.02822229,0.0001493033,0.0005330347,0.004865863,0.0007517375,0.001824129,0.000584265,0.0003591827,0.002099809],"category_scores_gemma":[0.09768526,0.0001952533,0.000618533,0.004484419,0.0004285388,0.001387694,0.0006463318,0.0005473663,0.0004404284],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002943532,"about_ca_system_score_gemma":0.005616192,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009665482,"about_ca_topic_score_gemma":0.02736504,"domain_scores_codex":[0.9854959,0.005461006,0.00241787,0.0006188304,0.00562042,0.0003860385],"domain_scores_gemma":[0.7506787,0.1479901,0.01906296,0.002404551,0.0758829,0.003980785],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000528942,0.0002791152,0.2950083,0.01331099,0.0003135434,0.0003205023,0.02491778,0.0001929522,0.003006471,0.0005914753,0.007392864,0.6541372],"study_design_scores_gemma":[0.00004018355,0.001202634,0.8689662,0.01104476,0.0004431137,0.0005308969,0.02993433,0.0003914039,0.002113004,0.0002268669,0.08502532,0.00008115884],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"review","genre_scores_codex":[0.8832431,0.07062008,0.005692626,0.00510297,0.0004880139,0.0006668381,0.001558913,0.000126375,0.03250097],"genre_scores_gemma":[0.9457481,0.04459408,0.004224621,0.001151341,0.0002038977,0.000303472,0.0009672524,0.00004570369,0.00276148],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.02822229,"threshold_uncertainty_score":0.1492555,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01576878012726357,"score_gpt":0.3299732794528919,"score_spread":0.3142044993256283,"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."}}