{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004802962,0.0003661074,0.0004956432,0.00126404,0.001077056,0.001620556,0.0007977236,0.0007010574,0.0005590805],"category_scores_gemma":[0.03998001,0.0002551448,0.0003472314,0.001778834,0.001383519,0.002371522,0.0008301202,0.001429396,0.0002261321],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001008525,"about_ca_system_score_gemma":0.001089775,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005152005,"about_ca_topic_score_gemma":0.005206841,"domain_scores_codex":[0.995246,0.00199752,0.0002810687,0.0004884809,0.001662053,0.0003248666],"domain_scores_gemma":[0.9307848,0.04976688,0.005371983,0.004858081,0.007345648,0.001872628],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.005436939,0.01022376,0.6914393,0.001331543,0.0005205942,0.002575132,0.04658063,0.04833191,0.02636976,0.01417982,0.01705357,0.1359569],"study_design_scores_gemma":[0.000308045,0.004630313,0.7106209,0.0002436866,0.0002027771,0.001553076,0.057688,0.170876,0.01930849,0.01519251,0.01912452,0.0002516987],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9963469,0.0001062495,0.001733837,0.0002335444,0.00001037466,0.00006615285,0.0003510339,0.000136764,0.001015264],"genre_scores_gemma":[0.9972789,0.00006606914,0.001458064,0.0000565134,0.00001327725,0.00004642547,0.0007092432,0.00006014403,0.0003113414],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005152005,"threshold_uncertainty_score":0.02540076,"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."}}