{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001311658,0.0001773814,0.0002611584,0.0001956657,0.0001519195,0.00003668791,0.0008872825,0.0002149951,0.000002233282],"category_scores_gemma":[0.0002896239,0.0001449709,0.0002617416,0.0005966058,0.00009326532,0.000136754,0.0003403057,0.0002303956,0.00002559232],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001747777,"about_ca_system_score_gemma":0.000134653,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002531572,"about_ca_topic_score_gemma":0.00003817473,"domain_scores_codex":[0.9983115,0.0004802387,0.0001848882,0.0007459428,0.00009687368,0.0001805496],"domain_scores_gemma":[0.9958338,0.002425355,0.000261041,0.001197328,0.0002444676,0.00003798625],"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":[0.0006006722,0.0001342229,0.02442696,0.001191689,0.0001220571,0.00001547773,0.0001012097,0.9334447,0.0004296083,0.03865723,0.00007118797,0.0008049213],"study_design_scores_gemma":[0.0008079864,0.0003178675,0.06891464,0.0003745817,0.00006070569,7.773991e-7,0.00003597746,0.8142816,0.02131754,0.093578,0.00001819716,0.000292137],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4665627,0.000003335776,0.5319489,0.00002856954,0.0006296204,0.0006242552,0.00000768874,0.0001288957,0.00006607863],"genre_scores_gemma":[0.9996511,0.000006280976,0.00016279,0.00001846662,0.00003307156,0.00001634658,0.00001064381,0.00001202412,0.00008925939],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5330884,"threshold_uncertainty_score":0.5911739,"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."}}