{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01538748,0.0008260766,0.0005586838,0.002337085,0.0008868919,0.002383976,0.002127346,0.00153831,0.001520216],"category_scores_gemma":[0.1177222,0.0005278798,0.0007531465,0.001876335,0.001103898,0.004699909,0.001434365,0.002431153,0.001309702],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001094079,"about_ca_system_score_gemma":0.001611235,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005033328,"about_ca_topic_score_gemma":0.006781656,"domain_scores_codex":[0.9882182,0.006539221,0.0009905623,0.001861081,0.002093466,0.000297324],"domain_scores_gemma":[0.7797922,0.1856039,0.01013573,0.01327481,0.008808848,0.002384569],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00509445,0.01020645,0.4711172,0.004957317,0.0005873431,0.0007651672,0.009014988,0.02380477,0.01151273,0.002333894,0.05117606,0.4094296],"study_design_scores_gemma":[0.001941832,0.007566536,0.4029824,0.001457839,0.001057856,0.001781831,0.01164053,0.4447099,0.03216099,0.006859682,0.0874034,0.0004372305],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9803604,0.001270037,0.00503933,0.0007787839,0.00004183895,0.0004294802,0.00554946,0.003495866,0.003034711],"genre_scores_gemma":[0.9391948,0.000539251,0.03411618,0.0003834346,0.00003754473,0.0004742968,0.02358102,0.0005031043,0.001170485],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01538748,"threshold_uncertainty_score":0.08137774,"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."}}