{"id":"W3195083062","doi":"10.1109/srds53918.2021.00030","title":"What Distributed Systems Say: A Study of Seven Spark Application Logs","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Software System Performance and Reliability","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"SPARK (programming language); Computer science; Benchmark (surveying); Overhead (engineering); Set (abstract data type); Logging; Distributed computing; Software; 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":[],"consensus_categories":[],"category_scores_codex":[0.0008063626,0.0002704794,0.000665925,0.00008857936,0.00007007983,0.0005605041,0.001413659,0.0002885431,0.000004866733],"category_scores_gemma":[0.00003426896,0.0002168426,0.000132008,0.0004458675,0.00003064961,0.0005228909,0.001929932,0.0003285111,0.0000189244],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001441716,"about_ca_system_score_gemma":0.0002490324,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001546346,"about_ca_topic_score_gemma":0.000101109,"domain_scores_codex":[0.9972172,0.0002471018,0.000784653,0.0009446397,0.0005741906,0.0002321915],"domain_scores_gemma":[0.9961935,0.000104712,0.0004718213,0.002661703,0.0004854103,0.00008289896],"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":[0.0001267256,0.01808619,0.3788434,0.02417242,0.003276457,0.0001497523,0.08423308,0.3546986,0.0005605799,0.006722472,0.009016793,0.1201136],"study_design_scores_gemma":[0.002624972,0.000896379,0.1364791,0.003272069,0.000260439,0.00009461327,0.04232185,0.8061547,0.0009292764,0.001519374,0.002933293,0.002513955],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3837566,0.0006487893,0.610628,0.0001525934,0.002759918,0.001710031,0.000008779723,0.0002531819,0.00008203326],"genre_scores_gemma":[0.9980964,0.00008844987,0.001036484,0.00002203552,0.00009758513,0.0004373175,0.00009593986,0.00001041319,0.000115396],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6143397,"threshold_uncertainty_score":0.8842583,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01703558660746616,"score_gpt":0.2643535419507478,"score_spread":0.2473179553432817,"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."}}