{"id":"W7125924447","doi":"10.1109/ase63991.2025.00161","title":"Defects4Log: Benchmarking LLMs for Logging Code Defect Detection and Reasoning","year":2025,"lang":"","type":"article","venue":"","topic":"Software System Performance and Reliability","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Logging; Code (set theory); Commit; Construct (python library); Source code; Benchmark (surveying); Variety (cybernetics)","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":[0.004604639,0.002263408,0.0006298489,0.004701834,0.0005710525,0.001345511,0.003950905,0.00198158,0.00154381],"category_scores_gemma":[0.0241232,0.0006280764,0.00117279,0.002334084,0.0009674159,0.002978185,0.002155126,0.001814542,0.001432537],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00166387,"about_ca_system_score_gemma":0.002734927,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0133555,"about_ca_topic_score_gemma":0.02186188,"domain_scores_codex":[0.9934041,0.00169081,0.0008651209,0.0015706,0.002021921,0.0004474333],"domain_scores_gemma":[0.9837885,0.007645522,0.001335674,0.003589561,0.002920946,0.0007198239],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.002724068,0.003943807,0.1656277,0.004683279,0.0007855811,0.001043822,0.001627088,0.1645171,0.02881232,0.006649752,0.1844782,0.4351073],"study_design_scores_gemma":[0.0003924607,0.001125305,0.02581281,0.0002006689,0.0001368617,0.0005520162,0.0007281448,0.9036211,0.03209195,0.004430647,0.03078357,0.0001245681],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6787583,0.004066919,0.1095682,0.001384518,0.0006136053,0.001059243,0.03566951,0.1594803,0.00939952],"genre_scores_gemma":[0.6968637,0.0008868058,0.2010952,0.0005284914,0.00007227503,0.0006182427,0.0949092,0.00237753,0.002648494],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0133555,"threshold_uncertainty_score":0.02655554,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01022014907929805,"score_gpt":0.2627221758080929,"score_spread":0.2525020267287948,"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."}}