{"id":"W4414993542","doi":"10.1145/3771283","title":"LLM meets ML: Data-efficient Anomaly Detection on Unstable Logs","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software System Performance and Reliability","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Anomaly detection; Inference; Anomaly (physics); Artificial neural network; Key (lock); Software; Cache; Ensemble learning","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":[0.00130527,0.0002168213,0.0003114227,0.0003709777,0.0002420232,0.00004970702,0.0007777464,0.0001995407,0.000006480035],"category_scores_gemma":[0.0008511941,0.0001947749,0.0000642382,0.0005846657,0.00004574699,0.0001770738,0.00006235948,0.0003576534,0.00001484711],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007396824,"about_ca_system_score_gemma":0.0000633108,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007459145,"about_ca_topic_score_gemma":0.0000128153,"domain_scores_codex":[0.9983242,0.0002052068,0.0002968358,0.0006941214,0.0001465505,0.0003330465],"domain_scores_gemma":[0.9962499,0.001909899,0.00004742647,0.001647754,0.00006122164,0.0000837839],"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":[0.00008071496,0.0002681055,0.0002903202,0.0002722333,0.0001596597,0.00000965587,0.0003974254,0.2980331,0.001077382,0.001317066,0.0001016316,0.6979927],"study_design_scores_gemma":[0.004151012,0.002448569,0.0276416,0.0008340016,0.0003632572,0.0003692668,0.0002255541,0.7087365,0.1209974,0.002166173,0.1298012,0.002265554],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03397091,0.0002236058,0.9622433,0.0003683083,0.002280938,0.000190769,0.00001220617,0.0006852269,0.00002471019],"genre_scores_gemma":[0.5689851,0.00007535271,0.4304818,0.0001942042,0.00003485952,0.00004861292,0.000004006772,0.00001365306,0.0001624047],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6957271,"threshold_uncertainty_score":0.7942688,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07009888762071217,"score_gpt":0.3147679512299077,"score_spread":0.2446690636091955,"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."}}