{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002248075,0.0003903597,0.0005108544,0.0003298371,0.001247983,0.0005579691,0.0004662182,0.0003280343,0.00001286735],"category_scores_gemma":[0.0004542822,0.0003522165,0.0003240852,0.0007835084,0.0001573072,0.0007211237,0.0004713163,0.0003100645,0.000008781634],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002237155,"about_ca_system_score_gemma":0.0002369171,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002041707,"about_ca_topic_score_gemma":0.0002335887,"domain_scores_codex":[0.9969276,0.000181722,0.000672215,0.001210046,0.0002426457,0.0007657601],"domain_scores_gemma":[0.9976642,0.0009928154,0.0002203078,0.0007583657,0.000227387,0.0001369252],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001126923,0.00008647252,0.0754621,0.002408713,0.0002227939,0.000003674166,0.001171502,0.000865718,0.001146515,0.006209358,0.0003214774,0.911989],"study_design_scores_gemma":[0.001343661,0.0004960955,0.02236371,0.001226576,0.0001698668,0.0000473584,0.0001962555,0.9578071,0.006853539,0.002446014,0.006447053,0.000602828],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1713743,0.002630522,0.8187414,0.0001998203,0.003423392,0.001036111,0.000002994058,0.0002794046,0.002312016],"genre_scores_gemma":[0.9777259,0.0002084695,0.02090573,0.0003201274,0.0002313694,0.000124904,0.000001659366,0.00001596231,0.0004658544],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9569413,"threshold_uncertainty_score":0.999893,"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."}}