{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002601484,0.00007765044,0.0001798992,0.0002853199,0.0003203771,0.00003706564,0.0002482129,0.00008881276,0.0000281429],"category_scores_gemma":[0.01258103,0.00008008348,0.00006619373,0.000334073,0.00005190953,0.0003313606,0.00002698517,0.0002148084,4.429382e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001132647,"about_ca_system_score_gemma":0.001235937,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02007249,"about_ca_topic_score_gemma":0.004178508,"domain_scores_codex":[0.9989488,0.00005267516,0.0003630731,0.0001189204,0.0003721766,0.0001443431],"domain_scores_gemma":[0.998308,0.0002254732,0.0006698868,0.00007460639,0.0006379901,0.00008401087],"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":[0.000006239944,0.0001436396,0.3559034,0.009016867,0.0002267684,2.086838e-8,0.03074143,0.00005780891,0.002991252,0.5510275,0.03627375,0.01361128],"study_design_scores_gemma":[0.0002436849,0.00003953882,0.8867737,0.01301715,0.000412321,0.00000119768,0.01429893,0.0004871557,0.0006336272,0.001762626,0.08202805,0.0003020396],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8655054,0.002836562,0.00003207461,0.0669382,0.001648337,0.0009959135,0.00003213488,0.00006622012,0.06194514],"genre_scores_gemma":[0.9952697,0.0004382372,0.002122717,0.0002035507,0.00005027126,0.00001989951,0.000002447399,0.000008136411,0.001885028],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5492649,"threshold_uncertainty_score":0.9957364,"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."}}