{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004675203,0.001608454,0.001607573,0.0008292738,0.0008638761,0.001851661,0.002913316,0.001331123,0.001894152],"category_scores_gemma":[0.01112714,0.0009744602,0.001303924,0.0009689032,0.001508459,0.002291403,0.003190638,0.002871064,0.001016408],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001194088,"about_ca_system_score_gemma":0.003878468,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00493657,"about_ca_topic_score_gemma":0.004661902,"domain_scores_codex":[0.9959483,0.001126499,0.0001878488,0.0007677485,0.001468262,0.0005014348],"domain_scores_gemma":[0.9977259,0.0008787144,0.0002102336,0.0006022303,0.0004128513,0.0001700797],"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":[0.0002825118,0.0002015733,0.00143168,0.0003215405,0.0001104229,0.0001353268,0.0002721864,0.7647256,0.01551106,0.0439857,0.00925799,0.1637644],"study_design_scores_gemma":[0.00003614592,0.00002905797,0.00009662528,0.00001232995,0.000006330344,0.00002609023,0.0000197569,0.979984,0.001584138,0.01570642,0.002487338,0.00001180432],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003962625,0.0002692103,0.990844,0.000153802,0.00003042288,0.00007351678,0.00004102347,0.003416879,0.001208593],"genre_scores_gemma":[0.2285643,0.0003890388,0.7667282,0.0003920595,0.00009676225,0.0003806777,0.000344456,0.001709403,0.001395027],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00493657,"threshold_uncertainty_score":0.02472514,"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."}}