{"id":"W4214643715","doi":"10.1109/tse.2022.3154672","title":"An Empirical Study on Log Level Prediction for Multi-Component Systems","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software System Performance and Reliability","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Component (thermodynamics); Interpretability; Computer science; Logging; Component-based software engineering; Data mining; Leverage (statistics); Software; Software system; Machine learning; Operating system","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":[0.0005837306,0.0002473186,0.0002655838,0.0002939732,0.0005926306,0.0000904778,0.0005649877,0.00007215411,0.000006358082],"category_scores_gemma":[0.0000144743,0.0002418632,0.0001400767,0.0004164047,0.000011142,0.000337261,0.000006383631,0.0004201887,0.0000121061],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003861742,"about_ca_system_score_gemma":0.00005834125,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003433027,"about_ca_topic_score_gemma":0.000002279586,"domain_scores_codex":[0.998041,0.0001044902,0.0004000824,0.0006094429,0.0005043505,0.0003406882],"domain_scores_gemma":[0.9987379,0.0002117612,0.00006164834,0.0007787824,0.00007511705,0.0001347337],"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":[0.00003496469,0.001359991,0.001868298,0.00005552435,0.00005129996,0.000005136291,0.001267952,0.9926628,0.0001272528,0.00001008431,0.00007053505,0.002486177],"study_design_scores_gemma":[0.001381076,0.002166465,0.01603032,0.00003338047,0.00002514155,0.00003199449,0.0003569928,0.9781827,0.0006107562,0.000001642098,0.000843748,0.0003357478],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1886212,0.00001694581,0.8048009,0.0000169092,0.004283687,0.00103412,0.0001281558,0.001097359,7.199588e-7],"genre_scores_gemma":[0.9804928,0.000001179553,0.01777377,0.0000388105,0.00008863476,0.001506081,0.000006675341,0.00003582767,0.00005621101],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7918716,"threshold_uncertainty_score":0.9862894,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05913968027635651,"score_gpt":0.2978523987647699,"score_spread":0.2387127184884134,"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."}}