{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010626,0.0001131723,0.0001650299,0.0001158298,0.00008917017,0.00002711899,0.0002962945,0.00007801515,0.000001830896],"category_scores_gemma":[0.002138769,0.00007872772,0.0001207057,0.0008527592,0.00002010216,0.0001196681,0.00005289384,0.0001030855,0.00002000299],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006777616,"about_ca_system_score_gemma":0.00003017155,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001128831,"about_ca_topic_score_gemma":8.144629e-7,"domain_scores_codex":[0.9990077,0.00009934689,0.0002006989,0.0002768219,0.0002096391,0.0002058187],"domain_scores_gemma":[0.993955,0.005454477,0.00005146196,0.0004162821,0.00008462039,0.00003821032],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","study_design_scores_codex":[0.0002138996,0.0001188424,0.1682466,0.001292497,0.00007175375,0.000006194713,0.000304404,0.810657,0.005210523,0.001165671,0.0005874189,0.0121252],"study_design_scores_gemma":[0.0005079249,0.0003132099,0.4990327,0.0001535134,0.000008280121,0.000002175968,0.00000566659,0.4225384,0.07566311,0.001246524,0.0003285159,0.0001999963],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4313115,0.000007610418,0.5676087,0.00007224674,0.0003494958,0.0002716269,0.000001777597,0.0003735286,0.000003460906],"genre_scores_gemma":[0.9972361,6.653049e-7,0.002468758,0.00003569984,0.00004665714,0.0001886798,0.000004688917,0.00001205072,0.000006638035],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5659246,"threshold_uncertainty_score":0.3210423,"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."}}