{"id":"W1998221613","doi":"10.1109/dsn.2013.6575356","title":"Reading between the lines of failure logs: Understanding how HPC systems fail","year":2013,"lang":"en","type":"article","venue":"","topic":"Radiation Effects in Electronics","field":"Engineering","cited_by":100,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Los Alamos National Laboratory","keywords":"Reliability (semiconductor); Supercomputer; Computer science; Reliability engineering; Component (thermodynamics); Field (mathematics); Reading (process); Quality (philosophy); Mean time between failures; Power (physics); Failure rate; Operating system; 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":[0.000215357,0.0001222455,0.0001857921,0.00007376841,0.00005761033,0.0001004888,0.0001874987,0.00008912672,0.00002745478],"category_scores_gemma":[0.0000542911,0.00008437807,0.00004426458,0.0002061518,0.00003183345,0.0002257892,0.00001548232,0.0001610093,0.00002878786],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002044035,"about_ca_system_score_gemma":0.00001128463,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005635538,"about_ca_topic_score_gemma":0.00001157632,"domain_scores_codex":[0.9992797,0.00004058523,0.0001732041,0.00009785013,0.0001571434,0.0002514928],"domain_scores_gemma":[0.9992348,0.0004035124,0.00004800951,0.0002410639,0.00003415346,0.00003848078],"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":[0.000001195621,0.00000686778,0.004920858,0.0005523347,0.0004502028,8.768836e-7,0.001140806,0.8483782,0.008904434,0.08356695,0.05048246,0.001594796],"study_design_scores_gemma":[0.0002969411,0.00006256573,0.0008317677,0.0001062077,0.00005836645,0.000006077452,0.004268593,0.9798557,0.006398269,0.001692038,0.006072774,0.00035069],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3292711,0.001145903,0.6402656,0.003498597,0.001117966,0.001566716,0.00001183697,0.001229554,0.02189277],"genre_scores_gemma":[0.9990709,0.00001778324,0.0002754378,0.000009529644,0.0001985389,0.00002424179,0.000004041143,0.00003150932,0.0003680541],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6697998,"threshold_uncertainty_score":0.3440838,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0157304137949093,"score_gpt":0.2009797020531246,"score_spread":0.1852492882582153,"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."}}