{"id":"W2735418241","doi":"10.1109/icdcs.2017.317","title":"Learning from Failure Across Multiple Clusters: A Trace-Driven Approach to Understanding, Predicting, and Mitigating Job Terminations","year":2017,"lang":"en","type":"article","venue":"","topic":"Cloud Computing and Resource Management","field":"Computer Science","cited_by":67,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; University of Toronto","keywords":"Computer science; Limiting; Usability; Task (project management); Cluster (spacecraft); Predictive power; Power consumption; Scale (ratio); Resource (disambiguation); TRACE (psycholinguistics); Machine learning; Power (physics); Engineering; Human–computer interaction","routes":{"ca_aff":true,"ca_fund":true,"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":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0003270885,0.0001722255,0.0001737603,0.00006362557,0.002237825,0.001699734,0.001006785,0.00006980336,0.000002113683],"category_scores_gemma":[0.0002223135,0.0001558054,0.00005679062,0.00009401076,0.00009146614,0.0001255456,0.001621565,0.0002476561,0.000007763172],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007608985,"about_ca_system_score_gemma":0.00001232647,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005083371,"about_ca_topic_score_gemma":0.0003005219,"domain_scores_codex":[0.9984569,0.00006423688,0.0002129561,0.0006116448,0.0002688169,0.0003854434],"domain_scores_gemma":[0.9988086,0.0001714148,0.0001777056,0.0006471915,0.00002759304,0.0001674834],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001651839,0.00030778,0.5158265,0.0001543638,0.0003082453,0.00004837773,0.1695828,0.1922593,0.0005096141,0.01767305,0.003367933,0.09994549],"study_design_scores_gemma":[0.0005453958,0.00005727648,0.02827569,0.00008746512,0.000008451346,0.000006418184,0.006553392,0.9630797,0.00003223477,0.0002930567,0.0008475087,0.0002134088],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5249182,0.000008651495,0.466467,0.001685343,0.00009326514,0.0001903613,0.000001645432,0.0002300663,0.006405465],"genre_scores_gemma":[0.9142331,5.825289e-7,0.08417539,0.00009744619,0.0001201749,0.0000146169,0.000001612319,0.00001264484,0.001344363],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7708204,"threshold_uncertainty_score":0.9993366,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0399174546020463,"score_gpt":0.2682651498599565,"score_spread":0.2283476952579102,"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."}}