{"id":"W2161422843","doi":"10.1145/2157136.2157215","title":"Stepping up to integrative questions on CS1 exams","year":2012,"lang":"en","type":"article","venue":"","topic":"Teaching and Learning Programming","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Formative assessment; Computer science; Code (set theory); Mathematics education; Programming language; Psychology","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":[0.0004376412,0.00008760727,0.00007544158,0.0000926072,0.0001737278,0.0001384107,0.0003265561,0.00002789712,0.0000159244],"category_scores_gemma":[0.0001691377,0.00006484444,0.00003080419,0.0002320171,0.00001061868,0.000298283,0.0001046671,0.0002295766,0.0005016326],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004209856,"about_ca_system_score_gemma":0.00001455223,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001579394,"about_ca_topic_score_gemma":0.00001197025,"domain_scores_codex":[0.9992076,0.0001136084,0.00008876188,0.0001768581,0.0001320032,0.0002811314],"domain_scores_gemma":[0.9994012,0.0001197282,0.00002421478,0.0002808185,0.00002226573,0.0001517767],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000001230758,0.00003616271,0.0009275869,0.00000137137,0.000005773882,5.135074e-7,0.01801469,0.0001023334,0.00006206735,0.2403533,0.001194612,0.7393004],"study_design_scores_gemma":[0.0002346796,0.0004635884,0.01801514,0.0001973849,0.000006727104,0.00001774032,0.002672874,0.003848187,0.001487802,0.0002655892,0.9722555,0.0005347997],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02364307,0.00003120911,0.9654832,0.001282625,0.0007514041,0.00008265534,1.149085e-7,0.0005119652,0.008213691],"genre_scores_gemma":[0.8760241,3.75017e-7,0.1182207,0.0005772749,0.00009799726,0.00001255975,4.283483e-7,0.000004972345,0.005061556],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9710609,"threshold_uncertainty_score":0.644764,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03266876838149385,"score_gpt":0.3106006042948273,"score_spread":0.2779318359133334,"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."}}