{"id":"W2808863842","doi":"10.1145/3197091.3197116","title":"Gender, confidence, and mark prediction in CS examinations","year":2018,"lang":"en","type":"article","venue":"","topic":"Teaching and Learning Programming","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":true,"ca_institutions":"The Scarborough Hospital; University of Toronto","funders":"","keywords":"Mistake; Work (physics); Computer science; Mathematics education; Artificial intelligence; Psychology; Engineering","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":[0.0003826812,0.00003916996,0.00003818196,0.00008712741,0.0001011772,0.0001020043,0.0001317485,0.00002666187,0.00001671097],"category_scores_gemma":[0.00005711146,0.00003588624,0.000006515069,0.0001708472,0.0000416247,0.000222431,0.0000596228,0.00008968246,0.00002421507],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001069129,"about_ca_system_score_gemma":0.00001575089,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001269791,"about_ca_topic_score_gemma":0.00005208729,"domain_scores_codex":[0.9995129,0.00005622167,0.00007741165,0.000164331,0.00008205462,0.0001071347],"domain_scores_gemma":[0.9997407,0.00005130974,0.00001816618,0.0001356536,0.00002357766,0.0000306303],"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":[0.000001461122,0.00004586345,0.07234168,0.000008588296,0.000005077223,0.000003927127,0.008100879,0.0000109966,0.0001265089,0.2051526,0.001368903,0.7128336],"study_design_scores_gemma":[0.0003409316,0.0001760294,0.8212933,0.00002552567,0.000002821597,0.00003646493,0.0003853308,0.09080765,0.0001405075,0.002279784,0.08435973,0.0001519649],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07630451,0.0000453377,0.908992,0.0002461708,0.0001788375,0.00005605292,1.519574e-7,0.0002266879,0.01395028],"genre_scores_gemma":[0.9371668,0.000002668572,0.06152139,0.00006660426,0.00004093285,0.00000393243,4.41041e-7,0.000001920836,0.001195384],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8608622,"threshold_uncertainty_score":0.1463398,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02749782075312115,"score_gpt":0.2666272239754067,"score_spread":0.2391294032222856,"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."}}