{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02151939,0.001182169,0.0008320941,0.002137614,0.0007669495,0.00247406,0.001738239,0.001337345,0.001183297],"category_scores_gemma":[0.1135035,0.0004421207,0.001017411,0.002862363,0.001169702,0.005189698,0.001171151,0.004137189,0.0005781832],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001673531,"about_ca_system_score_gemma":0.001025387,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01268745,"about_ca_topic_score_gemma":0.008486643,"domain_scores_codex":[0.9886864,0.00583705,0.0008574129,0.002202685,0.001954518,0.0004619277],"domain_scores_gemma":[0.7747768,0.1928617,0.008856159,0.01123449,0.01032342,0.001947355],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0008773764,0.001475309,0.7648036,0.000720404,0.0005290651,0.0004278326,0.001647769,0.1228946,0.0009284402,0.001986889,0.008036801,0.09567189],"study_design_scores_gemma":[0.00006548003,0.0007119759,0.1824448,0.0001661172,0.0001458844,0.0003629513,0.001260907,0.8052325,0.001656616,0.003282661,0.004602946,0.00006710539],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9704028,0.001769463,0.02299475,0.0009568747,0.00007049367,0.0001305899,0.001372244,0.0005239247,0.001778935],"genre_scores_gemma":[0.9882625,0.000303503,0.00787029,0.0000960709,0.00004197344,0.00006479872,0.002815915,0.00007342236,0.000471559],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02151939,"threshold_uncertainty_score":0.1138068,"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."}}