{"id":"W4282597468","doi":"10.1145/3514221.3517900","title":"One Size Does Not Fit All: A Bandit-Based Sampler Combination Framework with Theoretical Guarantees","year":2022,"lang":"en","type":"article","venue":"Proceedings of the 2022 International Conference on Management of Data","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Sample (material); Population; Set (abstract data type); Sampling (signal processing); Measure (data warehouse); Data mining; Mathematical optimization; Mathematics","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":[0.01639899,0.00295624,0.003960376,0.001942932,0.001374428,0.003304729,0.004273809,0.003369833,0.003732263],"category_scores_gemma":[0.04114315,0.002110922,0.002097255,0.002199828,0.002455785,0.005256801,0.004000609,0.004442994,0.0009994131],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002329723,"about_ca_system_score_gemma":0.003171776,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00395804,"about_ca_topic_score_gemma":0.003713477,"domain_scores_codex":[0.9921537,0.004424977,0.0002990814,0.00110879,0.001366505,0.0006468167],"domain_scores_gemma":[0.9706308,0.02337806,0.001802775,0.001590229,0.001711696,0.0008864984],"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":[0.0004628683,0.0002324815,0.003325942,0.0002507836,0.0003031818,0.0003033754,0.0003123691,0.8238928,0.001468436,0.08436814,0.003819024,0.08126056],"study_design_scores_gemma":[0.00003617988,0.00005714237,0.0001243551,0.00002068735,0.00003389528,0.00004085047,0.00001231414,0.9770452,0.0002496162,0.02178573,0.0005818206,0.00001213558],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007911635,0.0007087525,0.9884152,0.0006367197,0.00003829854,0.0001231781,0.00009394367,0.0004793401,0.001592943],"genre_scores_gemma":[0.5237663,0.001124757,0.4660354,0.001291687,0.0004785531,0.001199134,0.0005470797,0.0003823297,0.005174892],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01639899,"threshold_uncertainty_score":0.0867272,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07058486992079954,"score_gpt":0.3138620069286691,"score_spread":0.2432771370078695,"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."}}