{"id":"W7125974758","doi":"10.1109/ase63991.2025.00035","title":"LogMoE: Lightweight Expert Mixture for Cross-System Log Anomaly Detection","year":2025,"lang":"","type":"article","venue":"","topic":"Software System Performance and Reliability","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"National Natural Science Foundation of China","keywords":"Anomaly detection; Scalability; Set (abstract data type); Event (particle physics); Software; Generalization; Anomaly (physics)","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":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001380232,0.0006576286,0.000827826,0.0003774481,0.001304505,0.001040235,0.001664602,0.0009664518,0.00006076043],"category_scores_gemma":[0.0001516359,0.0005150241,0.0006426757,0.001505568,0.0002519512,0.001223017,0.0004994678,0.0003764812,0.0002127783],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007215104,"about_ca_system_score_gemma":0.000538262,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002018979,"about_ca_topic_score_gemma":0.00007787516,"domain_scores_codex":[0.99507,0.0001999495,0.001417644,0.001767891,0.000493823,0.001050689],"domain_scores_gemma":[0.99597,0.0003999374,0.0003483869,0.002067293,0.0009868888,0.0002274687],"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":[0.001377312,0.001427891,0.08723444,0.01360229,0.001028593,0.00005421554,0.007050116,0.0006079555,0.008639155,0.04530185,0.0465087,0.7871675],"study_design_scores_gemma":[0.004859507,0.001278197,0.02723788,0.001781417,0.0001353405,0.000135107,0.0005695455,0.4646955,0.2278035,0.001120448,0.2683952,0.001988392],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04378968,0.003682789,0.9220378,0.001142896,0.01876687,0.00216513,0.00001725388,0.000852439,0.007545129],"genre_scores_gemma":[0.9751309,0.00008049409,0.007846883,0.000686478,0.0009352308,0.0004211167,0.000004917488,0.00002799956,0.01486599],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9313412,"threshold_uncertainty_score":0.9999968,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009875331043543482,"score_gpt":0.2779389944802919,"score_spread":0.2680636634367484,"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."}}