{"id":"W2287911028","doi":"10.1145/2839509.2844561","title":"Introducing and Evaluating Exam Wrappers in CS2","year":2016,"lang":"en","type":"article","venue":"","topic":"Teaching and Learning Programming","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Summative assessment; Formative assessment; Computer science; Test (biology); Mathematics education; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01433881,0.00137659,0.0006292381,0.002057064,0.001177322,0.0047887,0.001380582,0.001539569,0.005569299],"category_scores_gemma":[0.09356765,0.0004931255,0.0004525401,0.001485241,0.0004998558,0.0024784,0.002355166,0.001342214,0.003610938],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002132505,"about_ca_system_score_gemma":0.002015693,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002002715,"about_ca_topic_score_gemma":0.006945143,"domain_scores_codex":[0.9885305,0.00523058,0.0009355705,0.001334039,0.003036777,0.0009326396],"domain_scores_gemma":[0.8998984,0.05084166,0.00904407,0.008069567,0.02064341,0.01150294],"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":[0.004306388,0.01304716,0.1453682,0.001222644,0.000203331,0.0007888488,0.00993659,0.01110153,0.05422253,0.001939973,0.03112744,0.7267353],"study_design_scores_gemma":[0.0007974602,0.02575882,0.6304383,0.000838007,0.0002553792,0.001368289,0.00891717,0.04412386,0.1651753,0.004896358,0.1168253,0.0006057406],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9775003,0.0003396519,0.008825841,0.0003413288,0.0001797836,0.0004177679,0.0003625745,0.00176932,0.01026345],"genre_scores_gemma":[0.9443967,0.0003017162,0.04143191,0.0003746759,0.0001003676,0.0002619087,0.001988361,0.0004667034,0.01067746],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01433881,"threshold_uncertainty_score":0.07583177,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02474203145349091,"score_gpt":0.2954238833065804,"score_spread":0.2706818518530895,"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."}}