{"id":"W4403764066","doi":"10.24908/pceea.2023.17153","title":"The Long and Winding Road: standards- and attribute-based grading in vastly different first-year math courses","year":2024,"lang":"en","type":"article","venue":"Proceedings of the Canadian Engineering Education Association (CEEA)","topic":"Educational Technology and Assessment","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Grading (engineering); Mathematics education; Mathematics; Computer science; Psychology; Engineering; Civil engineering","routes":{"ca_aff":true,"ca_fund":false,"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":[0.03772989,0.0004488456,0.0005334795,0.001218483,0.002726049,0.00500496,0.002072814,0.001735856,0.001618198],"category_scores_gemma":[0.07254644,0.000329369,0.000575027,0.001640357,0.002360908,0.004308727,0.004142483,0.00339632,0.0006787025],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003413999,"about_ca_system_score_gemma":0.003137737,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006992009,"about_ca_topic_score_gemma":0.01871907,"domain_scores_codex":[0.9625814,0.02278586,0.001520388,0.002266783,0.009488207,0.001357328],"domain_scores_gemma":[0.9596102,0.02181813,0.002517412,0.004236319,0.007762263,0.004055826],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.002198936,0.002334915,0.08900606,0.0003748838,0.00008617337,0.0007242847,0.06390813,0.002442225,0.01057404,0.008259412,0.008209643,0.8118814],"study_design_scores_gemma":[0.002378623,0.01982426,0.448575,0.001361589,0.0003353194,0.005611358,0.1382371,0.0741755,0.07474826,0.05332091,0.1798005,0.001631577],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.959012,0.0005277156,0.02703724,0.002888219,0.0003004416,0.0002440848,0.00004228048,0.0003360791,0.00961202],"genre_scores_gemma":[0.9471313,0.0002349188,0.04633779,0.0006795492,0.00005752788,0.00008915668,0.0001037684,0.0001089743,0.005256987],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03772989,"threshold_uncertainty_score":0.1995371,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.004946312715142178,"score_gpt":0.2245496839161518,"score_spread":0.2196033712010097,"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."}}