{"id":"W2172012155","doi":"10.1109/noms.2010.5488459","title":"Identifying symptoms of recurrent faults in log files of distributed information systems","year":2010,"lang":"en","type":"article","venue":"","topic":"Software System Performance and Reliability","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Downtime; Leverage (statistics); Process (computing); Identification (biology); Task (project management); Data mining; Distributed computing; Machine learning; Engineering","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":[0.0005113007,0.00007404708,0.0001898315,0.0001341239,0.00002135196,0.00002789321,0.0004167158,0.00008018476,0.000005875877],"category_scores_gemma":[0.00009581746,0.00005528731,0.00004327937,0.0003388701,0.00003850575,0.0009765449,0.000112903,0.0001142144,0.00001371897],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002103825,"about_ca_system_score_gemma":0.00004820864,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003163538,"about_ca_topic_score_gemma":0.00003538864,"domain_scores_codex":[0.9988811,0.00002949166,0.0006035988,0.000110173,0.0002463528,0.0001292787],"domain_scores_gemma":[0.9990622,0.00007357936,0.0002460587,0.0004067886,0.0001798126,0.00003157355],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00005793486,0.0005050525,0.7389894,0.004906687,0.00006468006,0.000002345364,0.009068511,0.002951326,0.005405935,0.08641616,0.001169578,0.1504624],"study_design_scores_gemma":[0.001538043,0.0003071693,0.7227484,0.0008783754,0.000009914726,0.0000250014,0.0006146011,0.252189,0.01838459,0.0008467447,0.001999387,0.000458713],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8725377,0.00003096144,0.12552,0.00001790136,0.001263417,0.0002209927,0.00001919227,0.0000561079,0.0003337335],"genre_scores_gemma":[0.9987673,0.000004307179,0.001174094,0.000003469525,0.0000125275,0.00001209507,0.00001819714,0.000001324258,0.00000666716],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2492377,"threshold_uncertainty_score":0.2254551,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009700964547620237,"score_gpt":0.2474721216626639,"score_spread":0.2377711571150437,"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."}}