{"id":"W4399655979","doi":"10.48550/arxiv.2406.07467","title":"LLM meets ML: Data-efficient Anomaly Detection on Unstable Logs","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Alliance de recherche numérique du Canada; Fonds National de la Recherche Luxembourg; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Anomaly detection; Anomaly (physics); Computer science; Data mining; Physics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003111761,0.0003291483,0.0002588819,0.0004265577,0.0002745175,0.0002583405,0.002628037,0.0003138549,0.00002979215],"category_scores_gemma":[0.00001471787,0.0003662755,0.0001646176,0.001051226,0.00008564023,0.0001774702,0.004880841,0.0007898146,0.0004939963],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003189428,"about_ca_system_score_gemma":0.0001651353,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003357217,"about_ca_topic_score_gemma":0.00007653135,"domain_scores_codex":[0.9973391,0.00007731518,0.0002332853,0.001879531,0.0001318149,0.0003389001],"domain_scores_gemma":[0.9964439,0.00006114361,0.0001988149,0.003032997,0.0001122482,0.0001508619],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003806036,0.0005335998,0.0000479781,0.000172255,0.0001700485,0.0002650495,0.0001250481,0.2740749,0.0006259608,0.7006367,0.003235943,0.02007454],"study_design_scores_gemma":[0.0001259426,0.0001211565,0.0001066075,0.00007990969,0.0000742305,0.00001069025,0.00002195084,0.9441226,0.004387221,0.03151086,0.01898274,0.0004561329],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06235797,0.00006746715,0.9265176,0.0003140529,0.0007036654,0.0004756091,0.0000728973,0.001411955,0.008078769],"genre_scores_gemma":[0.9951218,0.00009387753,0.001946831,0.0001012693,0.000100041,0.000006726769,0.00003094228,0.00002763191,0.002570915],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9327638,"threshold_uncertainty_score":0.9998789,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09849332833791093,"score_gpt":0.2092229584217083,"score_spread":0.1107296300837973,"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."}}