{"id":"W4387435361","doi":"10.1007/s10664-023-10364-1","title":"On the effectiveness of log representation for log-based anomaly detection","year":2023,"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":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Representation (politics); Computer science; Workflow; Web log analysis software; Context (archaeology); Data mining; Anomaly detection; Feature (linguistics); External Data Representation; Heuristic; Log-log plot; Software; Binary logarithm; Artificial intelligence; Database; Mathematics; World Wide Web; Programming language; Web service","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":[0.008194394,0.0009080081,0.001137059,0.002495349,0.0005356799,0.002401454,0.001424166,0.001705568,0.001560082],"category_scores_gemma":[0.07160185,0.0003431066,0.0005469165,0.001442832,0.001043366,0.004887678,0.001376233,0.001692513,0.0004805645],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006222599,"about_ca_system_score_gemma":0.0008378564,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003819114,"about_ca_topic_score_gemma":0.00165278,"domain_scores_codex":[0.9946807,0.002989281,0.0002789177,0.0005562091,0.001195265,0.0002996634],"domain_scores_gemma":[0.892787,0.0972812,0.001942702,0.005023359,0.002555506,0.000410224],"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":[0.00308621,0.0008834676,0.03161988,0.0002882004,0.0001884767,0.0002476115,0.0002879013,0.2304624,0.01375178,0.03050075,0.003991057,0.6846923],"study_design_scores_gemma":[0.00002600115,0.0001570069,0.002649372,0.00002087212,0.00003294706,0.0001619087,0.00005960419,0.9852342,0.002954634,0.008305151,0.0003789755,0.0000194307],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2186513,0.002030128,0.7701521,0.001280686,0.0001601506,0.00009433895,0.00038874,0.002618271,0.004624315],"genre_scores_gemma":[0.9164084,0.0005272982,0.08118993,0.0001478996,0.0001796726,0.0000379121,0.0003546276,0.0001093778,0.001044797],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008194394,"threshold_uncertainty_score":0.04333663,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02589351023582413,"score_gpt":0.2845307926426779,"score_spread":0.2586372824068537,"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."}}