{"id":"W4411538180","doi":"10.1007/s10664-025-10669-3","title":"A comprehensive study of machine learning techniques for log-based anomaly detection","year":2025,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software System Performance and Reliability","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"Alliance de recherche numérique du Canada; Natural Sciences and Engineering Research Council of Canada; Mitacs; Canada Research Chairs","keywords":"Anomaly detection; Anomaly (physics); Computer science; Machine learning; Artificial intelligence; Data mining; Physics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0001972638,0.0001676588,0.0003026686,0.0002273349,0.0001130337,0.00003252938,0.0003444327,0.00009702189,0.000001284606],"category_scores_gemma":[0.0004093198,0.0001489177,0.000103991,0.0006511037,0.00001591783,0.0001378381,0.0001195194,0.0002048066,0.000001195427],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008596588,"about_ca_system_score_gemma":0.00004598691,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005898378,"about_ca_topic_score_gemma":0.000007167594,"domain_scores_codex":[0.9988747,0.00004624543,0.0003511352,0.0003396331,0.0001668349,0.0002214652],"domain_scores_gemma":[0.9987037,0.0006435044,0.00007653207,0.0003496091,0.0001823143,0.00004439701],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000104156,0.0008220663,0.8260722,0.001593942,0.0001646259,0.00000766473,0.00105092,0.09981027,0.003787986,0.00003663397,0.0001057767,0.06644382],"study_design_scores_gemma":[0.001921483,0.002199841,0.2359681,0.0002733415,0.00004890871,0.000005555664,0.00008156116,0.6871225,0.053726,0.00009273681,0.01797976,0.0005801711],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.351666,0.00009999712,0.6469004,0.00003370686,0.0001986092,0.0004342333,0.000001092977,0.0006629009,0.000003020166],"genre_scores_gemma":[0.952826,0.00000123129,0.0469101,0.00005006708,0.00002895182,0.0001517884,0.000002004959,0.00001105693,0.00001879509],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6011599,"threshold_uncertainty_score":0.6072686,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01575046496258971,"score_gpt":0.278540047779716,"score_spread":0.2627895828171263,"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."}}