{"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":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.000768778,0.0001484621,0.0001790712,0.0001340234,0.00010226,0.0001496097,0.007705489,0.00002595594,0.0005592139],"category_scores_gemma":[0.0001583028,0.0001046598,0.00004239507,0.0002940072,0.0001962127,0.0005565677,0.00489004,0.0002588078,0.000001445333],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005962787,"about_ca_system_score_gemma":0.00003374383,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001352591,"about_ca_topic_score_gemma":9.564192e-7,"domain_scores_codex":[0.9975532,0.00002485331,0.0003074454,0.0005197566,0.001437603,0.0001571608],"domain_scores_gemma":[0.9983569,0.0001862691,0.0004070224,0.0007896041,0.0002341041,0.00002607907],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001569912,0.0003730424,0.0003944496,0.00005872671,0.0001547328,0.000001014358,0.0000862914,0.000007219305,0.0005299217,0.9930882,0.001874222,0.003275193],"study_design_scores_gemma":[0.002375108,0.001742318,0.009483857,0.001598517,0.0002455522,0.000007330477,0.00121525,0.1547249,0.03208428,0.7883603,0.007359374,0.0008032326],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2372356,0.00004475602,0.4216555,0.2197318,0.002648212,0.00564062,0.01076424,0.001386132,0.1008931],"genre_scores_gemma":[0.8915988,0.00001829693,0.107574,0.0004818452,0.00001258437,0.00007478274,0.00009209997,0.0000101042,0.000137504],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6543632,"threshold_uncertainty_score":0.9976633,"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."}}