{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001681239,0.0001029265,0.00009511032,0.000163099,0.00001909991,0.0001823551,0.000318945,0.00005565623,0.00000823651],"category_scores_gemma":[0.000001723853,0.00009372446,0.00002674736,0.000442552,0.00001048233,0.0004371579,0.0001057899,0.0001200768,0.000009680194],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001843776,"about_ca_system_score_gemma":0.00002719485,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000740882,"about_ca_topic_score_gemma":0.00002478195,"domain_scores_codex":[0.9992599,0.00002244441,0.0001131736,0.0002775892,0.0001321096,0.0001947808],"domain_scores_gemma":[0.9996575,0.00004160449,0.000007542959,0.0002424571,0.000008514128,0.00004244984],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[3.642441e-7,0.000008652376,0.0000173954,0.00002028681,0.000005660458,0.0000561239,0.0006747355,0.01363427,0.006485288,0.9701777,0.006739501,0.002180059],"study_design_scores_gemma":[0.00004138701,0.00001262509,0.000002056988,0.0000493556,0.000001079861,0.000005444583,0.000006077514,0.9768205,0.01139019,0.0104467,0.001097688,0.0001269247],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00478798,0.0006581855,0.9902502,0.0001055105,0.0001019999,0.00008760468,0.000002800856,0.002453617,0.001552074],"genre_scores_gemma":[0.7502386,0.0000201749,0.2493539,0.00006002771,0.000009320395,0.00001244816,0.000003355483,0.00001158602,0.0002905503],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9631862,"threshold_uncertainty_score":0.3821973,"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."}}