{"id":"W4386528681","doi":"10.14778/3611540.3611548","title":"Towards General and Efficient Online Tuning for Spark","year":2023,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Cloud Computing and Resource Management","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute","funders":"Tencent","keywords":"Computer science; Overhead (engineering); SPARK (programming language); Generality; Bayesian optimization; Process (computing); Distributed computing; Cloud computing; Computer engineering; Machine learning","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":[0.0004398147,0.000113589,0.0001386336,0.0000990913,0.0001718568,0.00008133455,0.0007000015,0.00002310584,5.575802e-7],"category_scores_gemma":[0.00005286207,0.00007607516,0.00008221273,0.0004248465,0.00004041691,0.00001240339,0.001205357,0.00006382108,0.000001665278],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003345575,"about_ca_system_score_gemma":0.00001236771,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002092796,"about_ca_topic_score_gemma":4.911565e-7,"domain_scores_codex":[0.9989516,0.000004035129,0.0001951092,0.0002899489,0.0002869576,0.0002723989],"domain_scores_gemma":[0.9995751,0.0000323742,0.0001215568,0.0001384575,0.00008079995,0.00005176168],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007233104,0.000733769,0.004053382,0.001294553,0.0003633546,0.000004192872,0.0119807,0.05791363,0.07871843,0.4108082,0.03305833,0.4009991],"study_design_scores_gemma":[0.000606695,0.000113979,0.007071364,0.000110796,0.00002103528,0.000006094816,0.0002697366,0.9698384,0.009464739,0.003160428,0.009174173,0.0001625903],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9890393,0.00007936332,0.003516775,0.005140468,0.0003531809,0.0004467242,0.000003268216,0.0001820298,0.00123887],"genre_scores_gemma":[0.9828041,0.000009974616,0.01574537,0.0002004514,0.0001360712,0.00003271986,6.393378e-7,0.00001035329,0.001060292],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9119247,"threshold_uncertainty_score":0.3102255,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02087801870139926,"score_gpt":0.2481364875198195,"score_spread":0.2272584688184202,"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."}}