{"id":"W4386044434","doi":"10.48550/arxiv.2308.08736","title":"On the Effectiveness of Log Representation for Log-based Anomaly Detection","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Software System Performance and Reliability","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Representation (politics); Workflow; Computer science; Context (archaeology); Data mining; Web log analysis software; Anomaly detection; Log-log plot; Feature (linguistics); Software; Heuristic; External Data Representation; Binary logarithm; Artificial intelligence; Database; Mathematics; 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":[0.0166447,0.001964862,0.001161059,0.005683794,0.00104327,0.003523251,0.001819142,0.001603881,0.001231265],"category_scores_gemma":[0.1000855,0.0004107438,0.001222377,0.003809701,0.00140031,0.007800499,0.00208164,0.00253939,0.0006804441],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001354253,"about_ca_system_score_gemma":0.001761229,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009035953,"about_ca_topic_score_gemma":0.006143488,"domain_scores_codex":[0.9891122,0.005689298,0.0008247471,0.001391266,0.002478813,0.0005035776],"domain_scores_gemma":[0.8813776,0.09771603,0.004632383,0.009526373,0.006075337,0.0006723386],"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":[0.001689453,0.001182372,0.08401272,0.0006866389,0.0004405999,0.0001808381,0.0007559297,0.2085501,0.007254423,0.009728326,0.01223841,0.6732802],"study_design_scores_gemma":[0.00006487052,0.0005190084,0.01489577,0.0001193598,0.0001682812,0.0002136333,0.0004678575,0.9659895,0.005491482,0.009546104,0.00245538,0.00006883273],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4696015,0.005699578,0.4990816,0.004552943,0.0004518806,0.0004109032,0.002059683,0.01000882,0.008133161],"genre_scores_gemma":[0.8637388,0.001147801,0.1313013,0.0003185286,0.0001756539,0.0001209028,0.002167415,0.0003249179,0.0007045721],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0166447,"threshold_uncertainty_score":0.08802664,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08230473629448808,"score_gpt":0.2188244675415315,"score_spread":0.1365197312470434,"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."}}