{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002837972,0.0001905034,0.0002206923,0.0002222912,0.00006714499,0.00009113236,0.0002624728,0.0001231878,0.00001356657],"category_scores_gemma":[0.0003964827,0.0001495795,0.0002478445,0.000760615,0.00001997786,0.000254921,0.00005283736,0.000356052,0.00005016213],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002568241,"about_ca_system_score_gemma":0.00007373441,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002826084,"about_ca_topic_score_gemma":0.000001119131,"domain_scores_codex":[0.9987398,0.00003894989,0.0002770937,0.0003706301,0.0002694046,0.0003041251],"domain_scores_gemma":[0.9989504,0.0005293405,0.00003928715,0.0003220818,0.00005353698,0.0001053638],"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":[0.00001380749,0.00005775369,0.1462144,0.0002831472,0.00004973699,0.00002281037,0.0002855031,0.7976631,0.0004620971,0.00001250734,0.00005120241,0.05488403],"study_design_scores_gemma":[0.0001354305,0.0005248333,0.2118931,0.0002059172,0.000007790163,0.0000155182,0.000001486878,0.783646,0.002472756,0.00002496556,0.0008548245,0.000217359],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4345242,0.0002142053,0.5639368,0.00002233587,0.0004431952,0.0000628017,6.100278e-7,0.0007876225,0.000008214613],"genre_scores_gemma":[0.9946241,0.000002810601,0.005200387,0.00001522611,0.0001123173,0.00001168465,0.000001860361,0.0000210363,0.00001062572],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5600998,"threshold_uncertainty_score":0.6099674,"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."}}