{"id":"W4401312109","doi":"10.18260/1-2--48493","title":"Work in Progress: Grading through a Capability Lens","year":2024,"lang":"en","type":"article","venue":"","topic":"Engineering Education and Pedagogy","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Grading (engineering); Feeling; Higher education; Mathematics education; Psychology; Curriculum; Computer science; Pedagogy; Engineering; Social psychology; Political science","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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":[0.00007076219,0.00007275216,0.00006534754,0.00005654361,0.000007277259,0.00003373707,0.00004765235,0.00003954407,0.0002329443],"category_scores_gemma":[0.000008443517,0.00006802217,0.00002423964,0.0003050873,0.00001202935,0.0001188651,0.000005529046,0.0001329465,0.0001018041],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006604972,"about_ca_system_score_gemma":0.00001333255,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001410898,"about_ca_topic_score_gemma":0.00002493655,"domain_scores_codex":[0.9995971,0.000005421522,0.0001049368,0.0001021284,0.00004551257,0.0001449386],"domain_scores_gemma":[0.9998268,0.0000382955,0.000001636654,0.0001082563,0.000004704812,0.0000202938],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002020754,0.0003225057,0.1161093,0.005808029,0.0002937953,0.000135592,0.07977137,0.1712848,0.001613981,0.2901483,0.2076443,0.1268479],"study_design_scores_gemma":[0.0002094851,0.00002158385,0.04200136,0.0004677028,0.0000133288,0.00001771778,0.0005614691,0.07432615,0.001651551,0.00233747,0.8777426,0.0006495024],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8616653,0.0128293,0.01436738,0.002677758,0.004902286,0.000378577,0.000004269313,0.004815223,0.09835991],"genre_scores_gemma":[0.9963937,0.00005231266,0.002968087,0.00002249012,0.00008570181,0.00003078205,0.000002487953,0.00002002928,0.0004244352],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6700984,"threshold_uncertainty_score":0.2773864,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0294360399142276,"score_gpt":0.2914837774805486,"score_spread":0.262047737566321,"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."}}