{"id":"W4306316908","doi":"10.1145/3511808.3557117","title":"BLUTune: Query-informed Multi-stage IBM Db2 Tuning via ML","year":2022,"lang":"en","type":"article","venue":"Proceedings of the 31st ACM International Conference on Information & Knowledge Management","topic":"Parallel Computing and Optimization Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"IBM (Canada); Ontario Tech University; York University","funders":"","keywords":"Computer science; IBM; Reinforcement learning; Embedding; Process (computing); Artificial intelligence; Resource (disambiguation); Machine learning; 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":[0.0007663085,0.0002463619,0.0001986247,0.0006313839,0.000505707,0.0004358979,0.004385871,0.00004984965,0.000220034],"category_scores_gemma":[0.0002335772,0.0002197863,0.0001363206,0.0006681159,0.00006623215,0.001573996,0.00392041,0.0003383475,0.0001440255],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003795811,"about_ca_system_score_gemma":0.00008276253,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000162686,"about_ca_topic_score_gemma":0.000006588726,"domain_scores_codex":[0.9978054,0.00002533265,0.0007369706,0.0002794612,0.0008705893,0.0002822284],"domain_scores_gemma":[0.9977493,0.00004978391,0.0007955469,0.0004792196,0.0008557986,0.0000703853],"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":[0.00005748575,0.0002446452,0.0005788713,0.0002006573,0.0001317971,2.59709e-7,0.006570144,0.005313573,0.0001724833,0.9430408,0.02194396,0.0217453],"study_design_scores_gemma":[0.001345006,0.0001083004,0.001242948,0.000198813,0.00002230026,0.00001270025,0.001426155,0.5547041,0.0009205343,0.007553974,0.4318624,0.0006028053],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002930081,0.00001687668,0.5626501,0.002634041,0.001319422,0.0008168053,0.00002301871,0.0005860815,0.4290236],"genre_scores_gemma":[0.8427862,0.00007016472,0.1357165,0.0008649883,0.00005955412,0.0003202331,0.00007496159,0.00001774994,0.02008959],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9354869,"threshold_uncertainty_score":0.8962625,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07434386009228877,"score_gpt":0.3228954959479354,"score_spread":0.2485516358556466,"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."}}