{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006419846,0.00009949123,0.00009438374,0.0002387276,0.0002642412,0.0003718324,0.0002706092,0.00007759341,0.000001270534],"category_scores_gemma":[0.0004090628,0.00007791118,0.00002702382,0.0003982956,0.00002522078,0.0002318167,0.00004044461,0.0002048984,4.740953e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001494658,"about_ca_system_score_gemma":0.0006372895,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006098949,"about_ca_topic_score_gemma":0.003123122,"domain_scores_codex":[0.9991875,0.000005759171,0.0001622994,0.0001841036,0.0002495682,0.0002107465],"domain_scores_gemma":[0.999423,0.0001609827,0.00009626096,0.00007527414,0.0001631555,0.00008136744],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[9.21484e-7,0.00003034852,0.6268613,0.0002211449,0.00005239601,2.489683e-7,0.001077013,0.0001366822,0.0001368797,0.364028,0.004222245,0.003232843],"study_design_scores_gemma":[0.0001337528,0.00001731633,0.9605882,0.0005114242,0.00002047789,0.000004819649,0.0004298545,0.02828207,0.0007147944,0.002521295,0.006595434,0.0001805738],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9546698,0.0008180786,0.0006456802,0.04212809,0.001236827,0.000258637,0.00001558443,0.00008972249,0.0001376221],"genre_scores_gemma":[0.9989618,0.00004604931,0.000644311,0.00005168348,0.00004865306,0.00004044589,0.00000155866,0.000009194415,0.0001962723],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3615067,"threshold_uncertainty_score":0.390848,"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."}}