{"id":"W4292841507","doi":"10.3102/1430052","title":"Fairness of Teachers' Grading Practices and Decisions in Canadian and Chinese Secondary Schools","year":2019,"lang":"en","type":"article","venue":"Proceedings of the 2019 AERA Annual Meeting","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Queen's University","funders":"","keywords":"Grading (engineering); Computer science; Mathematics education; Psychology; Engineering","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001789425,0.0001004535,0.0002132523,0.000146195,0.0002204697,0.00009585666,0.0003114295,0.00008189047,0.00001673956],"category_scores_gemma":[0.002170929,0.00007595835,0.00003295916,0.0003562674,0.0001193063,0.0008459153,0.0001495182,0.000260432,0.000002211165],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005625453,"about_ca_system_score_gemma":0.0001942276,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.1645389,"about_ca_topic_score_gemma":0.05528561,"domain_scores_codex":[0.9989595,0.00002723097,0.0002389112,0.0001974326,0.0002909253,0.0002859746],"domain_scores_gemma":[0.9989656,0.0002895499,0.0004062664,0.0000521046,0.0001700184,0.0001164841],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000009089468,0.00001170466,0.9622657,0.00002004344,0.00001133778,1.101902e-7,0.03243881,3.73562e-7,0.002675018,0.001464761,0.0002701027,0.0008328871],"study_design_scores_gemma":[0.0003763842,0.00003114582,0.9082271,0.0003154603,0.00001666008,0.000001302127,0.0877865,0.00002404699,0.0001779159,0.001129929,0.001781695,0.0001318984],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9641874,0.0003131304,4.863448e-8,0.001781989,0.0001435244,0.0003179194,0.000008122614,0.0000079847,0.03323989],"genre_scores_gemma":[0.9988137,0.0001438604,0.0003398824,0.00003615557,0.0000613794,0.000003569151,3.665013e-7,0.000008215435,0.0005928337],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1092532,"threshold_uncertainty_score":0.961953,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01161106929120129,"score_gpt":0.3134544626097813,"score_spread":0.30184339331858,"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."}}