{"id":"W4401667316","doi":"10.1007/s10664-024-10533-w","title":"Impact of log parsing on deep learning-based anomaly detection","year":2024,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software System Performance and Reliability","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; Fonds National de la Recherche Luxembourg; Science Foundation Ireland","keywords":"Anomaly detection; Parsing; Anomaly (physics); Computer science; Artificial intelligence; Natural language processing; Deep learning; 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":[0.01030849,0.001858324,0.0009888668,0.002536975,0.0007560004,0.002257163,0.001801603,0.001410468,0.0007650925],"category_scores_gemma":[0.06600802,0.0004914955,0.0009614868,0.002171981,0.001073857,0.005159288,0.001798383,0.003334241,0.0006541381],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001331301,"about_ca_system_score_gemma":0.002021669,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006254668,"about_ca_topic_score_gemma":0.006329909,"domain_scores_codex":[0.9897361,0.003927493,0.0009105687,0.001820583,0.002993099,0.0006121568],"domain_scores_gemma":[0.9155621,0.06316587,0.004956087,0.009945082,0.00551054,0.0008603226],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.001581069,0.00172163,0.2013115,0.0006682039,0.0006002613,0.000399065,0.0004394679,0.2558476,0.008959902,0.003091316,0.01717904,0.5082008],"study_design_scores_gemma":[0.00004570167,0.0003842047,0.02374423,0.00009632674,0.0001390122,0.0003056887,0.0002021613,0.9517565,0.01266308,0.00748542,0.003113428,0.00006424876],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8435624,0.00369735,0.1222744,0.002495019,0.0003532746,0.0001661294,0.002865191,0.02028485,0.004301382],"genre_scores_gemma":[0.9526482,0.0004110883,0.04151486,0.0003279549,0.00006746215,0.00005588709,0.003786746,0.0003352509,0.0008525466],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01030849,"threshold_uncertainty_score":0.05451715,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01206183152058299,"score_gpt":0.2753947141403206,"score_spread":0.2633328826197376,"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."}}