{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001293169,0.00005688211,0.00006698701,0.00008093293,0.00006608815,0.00008242051,0.000190276,0.00002168137,0.000009293109],"category_scores_gemma":[0.0003091447,0.0000361717,0.00001144295,0.0001267587,0.00001936434,0.0002386747,0.0001239776,0.00009171171,0.00001511208],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002132103,"about_ca_system_score_gemma":0.00001674593,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001021178,"about_ca_topic_score_gemma":0.00001334656,"domain_scores_codex":[0.9991981,0.0001150637,0.0001037867,0.0002818198,0.0001127789,0.0001884915],"domain_scores_gemma":[0.9995369,0.0001769245,0.00002633333,0.0002100008,0.00001168311,0.00003820592],"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":[7.296867e-7,0.00000516449,0.01242631,0.000002121686,0.000001296848,0.000001328632,0.001373038,0.00003070066,0.001373885,0.003877304,0.0000294755,0.9808787],"study_design_scores_gemma":[0.00941946,0.002033917,0.4953963,0.001705404,0.00002636453,0.000265401,0.003295554,0.3241783,0.007139957,0.006806948,0.1467044,0.003027881],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4900351,0.00008067229,0.5058473,0.002990402,0.0001137975,0.00004917268,2.004237e-8,0.0001974989,0.000686006],"genre_scores_gemma":[0.8064201,0.000002426221,0.1929694,0.00007399774,0.00003234835,0.000002994925,3.389362e-8,0.000003162343,0.0004954559],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9778508,"threshold_uncertainty_score":0.1475039,"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."}}