{"id":"W2594056401","doi":"10.1145/3017680.3017766","title":"In-Lab Programming Tests in a Data Structures Course in C for Non-Specialists","year":2017,"lang":"en","type":"article","venue":"","topic":"Teaching and Learning Programming","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"British Columbia Institute of Technology; University of British Columbia","funders":"","keywords":"Computer science; Programming language; Test (biology); Compiler; Test suite; Software engineering; Mathematics education; Test case; Psychology; Machine learning; Regression analysis","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":[0.001210493,0.000132486,0.0001964274,0.0001524475,0.000176883,0.0007693949,0.002719655,0.00007637327,0.00000273424],"category_scores_gemma":[0.0005046962,0.0001213103,0.00002189598,0.0001527347,0.00005242305,0.001039623,0.0007548398,0.0003251263,0.000003679625],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004525945,"about_ca_system_score_gemma":0.00009613806,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00213888,"about_ca_topic_score_gemma":0.0150219,"domain_scores_codex":[0.9985214,0.0000558712,0.0002491304,0.0005645392,0.000163026,0.0004459996],"domain_scores_gemma":[0.9981484,0.0001294133,0.0001260675,0.001520433,0.00002086226,0.00005478833],"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":[0.000008770887,0.0001190108,0.09129179,0.00002407008,0.000003043559,0.00006348894,0.002165236,0.00005722699,0.00001497567,0.008642482,0.0004239611,0.8971859],"study_design_scores_gemma":[0.002320495,0.0001001131,0.7611938,0.0001837727,0.000003471794,0.00001734678,0.0002001243,0.0448134,0.00003854737,0.002000806,0.1886625,0.0004656771],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6902105,0.0003501032,0.2875089,0.01433349,0.002615218,0.002834809,0.00001099643,0.0005030153,0.00163299],"genre_scores_gemma":[0.7827976,0.000001617591,0.216798,0.00007037647,0.0001020654,0.00002998404,0.000006004487,0.00000892865,0.0001854784],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8967203,"threshold_uncertainty_score":0.8382573,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06333500086749563,"score_gpt":0.3795348762367063,"score_spread":0.3161998753692107,"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."}}