{"id":"W4403210636","doi":"10.1109/tse.2024.3475375","title":"Exploring the Effectiveness of LLMs in Automated Logging Statement Generation: An Empirical Study","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Semantic Web and Ontologies","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"Basic and Applied Basic Research Foundation of Guangdong Province; Science Foundation Ireland","keywords":"Computer science; Logging; Statement (logic); Empirical research; Data science; Software engineering; Computer security; Risk analysis (engineering); Business; Forestry; Statistics; Political science","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":[0.0007140248,0.0001285154,0.000151627,0.0002339894,0.00006458874,0.0001003695,0.0002700495,0.00002388231,0.000002043638],"category_scores_gemma":[0.00001608437,0.00009865395,0.00004603925,0.0005244485,0.00001206119,0.0005705753,0.000003978053,0.0001846694,0.00000363955],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008764043,"about_ca_system_score_gemma":0.00003640596,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004724019,"about_ca_topic_score_gemma":0.00002483313,"domain_scores_codex":[0.9989716,0.0001406024,0.0002374273,0.0002788001,0.000197137,0.0001744427],"domain_scores_gemma":[0.9990889,0.0005307681,0.00001371725,0.0003126108,0.00002299859,0.00003093681],"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":[0.000007518367,0.0001698194,0.0005884747,0.0001076541,0.00004884585,0.00004562816,0.002843809,0.9849925,0.001380643,0.00008205773,0.00000384367,0.009729191],"study_design_scores_gemma":[0.0002117975,0.0002098397,0.02665513,0.0001459227,0.00001316169,0.000008392686,0.0002039056,0.951965,0.02041298,0.000009697886,0.00002257267,0.0001415793],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4618124,0.00003647739,0.5364859,0.00001309696,0.0008087074,0.0001497075,8.918411e-7,0.0006919313,9.11737e-7],"genre_scores_gemma":[0.992021,0.000008750509,0.007757726,0.000006116665,0.00002339699,0.0001675821,4.734003e-7,0.00001272955,0.000002258787],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5302085,"threshold_uncertainty_score":0.4022991,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07912131087874133,"score_gpt":0.3136969886310401,"score_spread":0.2345756777522988,"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."}}