{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007803345,0.002357669,0.001426701,0.003071209,0.0005238923,0.001743959,0.002277654,0.001701093,0.0009222004],"category_scores_gemma":[0.03037773,0.0007583144,0.001408352,0.002526816,0.0009385429,0.003804006,0.001265544,0.003924049,0.0009302447],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001379466,"about_ca_system_score_gemma":0.001298814,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001671814,"about_ca_topic_score_gemma":0.001692901,"domain_scores_codex":[0.9927945,0.002545909,0.0005003057,0.001280839,0.002659885,0.0002185536],"domain_scores_gemma":[0.9744848,0.01740716,0.002493119,0.002694494,0.002691576,0.0002288281],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001701795,0.000321268,0.01300001,0.001068983,0.0004263207,0.00009975416,0.0001429396,0.216382,0.00840158,0.007334358,0.004291807,0.7483608],"study_design_scores_gemma":[0.00001495561,0.0003053456,0.006507696,0.0001936583,0.00006889378,0.0003535941,0.00005682336,0.966107,0.01070637,0.00922205,0.006411513,0.00005215593],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04451874,0.01855051,0.9280307,0.001904206,0.0001929804,0.0001749644,0.0003706176,0.003083628,0.003173674],"genre_scores_gemma":[0.5410702,0.01169005,0.4425638,0.0005131155,0.0004650464,0.0003386842,0.001063647,0.000303827,0.001991574],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007803345,"threshold_uncertainty_score":0.04126853,"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."}}