{"id":"W3161148246","doi":"10.1145/3440757","title":"Predicting Performance Anomalies in Software Systems at Run-time","year":2021,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software System Performance and Reliability","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":true,"ca_institutions":"IBM (Canada); Thompson Rivers University; Queen's University","funders":"","keywords":"Computer science; Baseline (sea); Precision and recall; Anomaly detection; Software; Recall; Anomaly (physics); Data mining; Software system; Machine learning; Real-time computing; Artificial intelligence; Operating system","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"],"consensus_categories":[],"category_scores_codex":[0.001076957,0.000261471,0.0004713304,0.000248182,0.0002249368,0.00005932185,0.0004195187,0.0002446628,0.00001698092],"category_scores_gemma":[0.001058634,0.0002535907,0.00008642936,0.0005500342,0.00004849654,0.0003574271,0.00007185155,0.000387542,0.0000291799],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001384105,"about_ca_system_score_gemma":0.00008498351,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003834041,"about_ca_topic_score_gemma":0.0000106229,"domain_scores_codex":[0.9979862,0.0002855329,0.0004486842,0.0006203381,0.00019872,0.0004605332],"domain_scores_gemma":[0.9966828,0.002139213,0.00007071988,0.0008866529,0.00009876235,0.0001218696],"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":[0.00010273,0.0002670818,0.2220644,0.002120038,0.0002504009,0.0001852854,0.004668059,0.5495487,0.002700509,0.0002297419,0.00007341726,0.2177896],"study_design_scores_gemma":[0.005343483,0.001449552,0.3316766,0.002507172,0.0001969948,0.005991844,0.0006017347,0.588644,0.04378666,0.0003800837,0.01580919,0.003612723],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.4009191,0.0007067738,0.5968238,0.00006139614,0.0009017437,0.0001085596,0.000006484437,0.0004664991,0.000005707578],"genre_scores_gemma":[0.3449613,0.000316957,0.6538268,0.00007215821,0.00007186301,0.0001101727,0.000006459156,0.00003148236,0.0006027178],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2141769,"threshold_uncertainty_score":0.9999917,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03758739881469653,"score_gpt":0.261884824459496,"score_spread":0.2242974256447994,"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."}}