{"id":"W3204466917","doi":"10.31224/osf.io/d4e6a","title":"Log Message Anomaly Detection with Oversampling","year":2020,"lang":"en","type":"article","venue":"","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria","funders":"","keywords":"Oversampling; Autoencoder; Anomaly detection; Computer science; Data mining; Anomaly (physics); Feature (linguistics); Artificial intelligence; Feature extraction; Pattern recognition (psychology); Deep learning; Computer network","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":[0.00003793282,0.0000688291,0.00006353998,0.0000272359,0.0001116707,0.00008157652,0.0002601165,0.00002981137,0.00003410332],"category_scores_gemma":[0.000004551394,0.00005532397,0.00002709271,0.0004060669,0.00001610076,0.0002600705,0.00007343054,0.000075861,0.00005213443],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001454683,"about_ca_system_score_gemma":0.00001427042,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003987489,"about_ca_topic_score_gemma":0.00001346182,"domain_scores_codex":[0.9994479,0.000008269313,0.00008804514,0.0002519035,0.00009683482,0.0001070047],"domain_scores_gemma":[0.9996237,0.00001466258,0.00003963552,0.000210394,0.00003326335,0.00007841368],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00007016525,0.0001652049,0.004760604,0.00005382732,0.00008920697,0.00003072879,0.001337038,0.001094443,0.1890074,0.3812973,0.00272462,0.4193695],"study_design_scores_gemma":[0.0006027386,0.001004587,0.005627772,0.00001154049,0.00001842567,0.00006698912,0.0001424366,0.3352071,0.5592067,0.003430924,0.09399571,0.0006850619],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008292563,0.000006874568,0.9811888,0.001411771,0.00001348295,0.0001092532,3.837728e-7,0.0008473427,0.008129532],"genre_scores_gemma":[0.8983911,0.000002732457,0.1003698,0.001033569,0.00003382672,0.0000237261,3.023275e-7,0.000005001103,0.0001400391],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8900985,"threshold_uncertainty_score":0.2256046,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0176578058795135,"score_gpt":0.2231296155373557,"score_spread":0.2054718096578422,"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."}}