{"id":"W4406499796","doi":"10.1109/cascon62161.2024.10837857","title":"Understanding Defects in Generated Codes by Language Models","year":2024,"lang":"en","type":"article","venue":"","topic":"Model-Driven Software Engineering Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Programming language","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":[0.003260665,0.0009164001,0.0004418765,0.002027801,0.0002366195,0.001711515,0.0008935708,0.0008085411,0.001311386],"category_scores_gemma":[0.03801805,0.000436752,0.0008286542,0.0007046114,0.0008180134,0.002734465,0.001051408,0.0009141336,0.0004780222],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008517303,"about_ca_system_score_gemma":0.001227725,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002354246,"about_ca_topic_score_gemma":0.002776685,"domain_scores_codex":[0.9971786,0.001093895,0.0001552414,0.0005647646,0.0008915734,0.0001160172],"domain_scores_gemma":[0.9675483,0.02418922,0.003000445,0.002634282,0.0024715,0.0001561495],"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":[0.000886484,0.000617097,0.0717117,0.001035183,0.0001717045,0.001109386,0.008439652,0.2889111,0.06584243,0.01515285,0.003404092,0.5427185],"study_design_scores_gemma":[0.00003879724,0.0003947733,0.008354164,0.0001462335,0.00006926918,0.0005612653,0.001030475,0.9406022,0.03222008,0.01240499,0.004108773,0.00006906509],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2230123,0.0001643318,0.7678082,0.0003260647,0.00002772108,0.0002417505,0.0003525264,0.006796628,0.001270413],"genre_scores_gemma":[0.6580974,0.0001566372,0.3393227,0.0001044047,0.00001001417,0.0001738548,0.0006981316,0.0005134986,0.0009232747],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003260665,"threshold_uncertainty_score":0.01724428,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05313711111305671,"score_gpt":0.2603973967104646,"score_spread":0.2072602855974079,"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."}}