{"id":"W4407551092","doi":"10.1007/s10664-025-10614-4","title":"Bugs in large language models generated code: an empirical study","year":2025,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Advanced Malware Detection Techniques","field":"Computer Science","cited_by":44,"is_retracted":false,"has_abstract":false,"ca_institutions":"Polytechnique Montréal","funders":"Fonds de recherche du Québec; Natural Sciences and Engineering Research Council of Canada; Consortium de Recherche et d’innovation en Aérospatiale au Québec; Canadian Institute for Advanced Research","keywords":"Computer science; Programming language; Empirical research; Code (set theory); Statistics; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003753022,0.0002590842,0.0003153931,0.0004232114,0.00008237187,0.0001057153,0.0007464796,0.0001435877,0.00000901813],"category_scores_gemma":[0.0003246877,0.0002644567,0.00005968433,0.00163212,0.00001194722,0.0007223745,0.000408114,0.000470113,0.000007799837],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002216932,"about_ca_system_score_gemma":0.00006635619,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002685574,"about_ca_topic_score_gemma":0.00005874937,"domain_scores_codex":[0.9980975,0.00009039001,0.0003902606,0.0006570683,0.0002709975,0.0004937447],"domain_scores_gemma":[0.9988729,0.0001745203,0.00003904894,0.0007041023,0.00007333372,0.0001360851],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007567163,0.004073576,0.3857477,0.0001670917,0.0001468966,0.001144822,0.01545858,0.5474647,0.003199092,0.002336327,0.003587571,0.036598],"study_design_scores_gemma":[0.001118368,0.0002672182,0.06742168,0.0000584455,0.000009697252,0.00001232312,0.0001750484,0.9209314,0.005044395,0.001368767,0.002918412,0.0006742419],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3167437,0.000104716,0.6805146,0.0001027119,0.000171398,0.0002629806,0.000004037655,0.002071207,0.00002468309],"genre_scores_gemma":[0.8850526,0.000002938668,0.1141426,0.0004938691,0.00004353499,0.0001180972,0.000005318435,0.00002602805,0.0001149804],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5683089,"threshold_uncertainty_score":0.9999807,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01986234801095843,"score_gpt":0.3267766397706522,"score_spread":0.3069142917596938,"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."}}