{"id":"W4389650432","doi":"10.48550/arxiv.2312.05645","title":"Sample-Optimal Locally Private Hypothesis Selection and the Provable Benefits of Interactivity","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Omega; Combinatorics; Matching (statistics); Distribution (mathematics); Upper and lower bounds; Mathematics; Differential privacy; Selection (genetic algorithm); Binary logarithm; Discrete mathematics; Algorithm; Physics; Computer science; Statistics; Mathematical analysis","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01448668,0.001972975,0.00348904,0.0009745093,0.002127693,0.003595768,0.006196457,0.003624929,0.005051917],"category_scores_gemma":[0.07260215,0.001661652,0.002415621,0.001842242,0.006110867,0.01074806,0.009648481,0.007774141,0.001279224],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00406305,"about_ca_system_score_gemma":0.003761279,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00174315,"about_ca_topic_score_gemma":0.001716343,"domain_scores_codex":[0.9835989,0.009238791,0.0004866562,0.003126194,0.002390569,0.001158886],"domain_scores_gemma":[0.872587,0.1037185,0.003791309,0.01621539,0.001821361,0.001866385],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.005719978,0.0007052931,0.007640156,0.0007866122,0.0006420267,0.001208786,0.001283532,0.5241602,0.0119738,0.3276561,0.009470761,0.1087529],"study_design_scores_gemma":[0.0003470556,0.0002640885,0.0007403254,0.0000447344,0.0000764358,0.0002708094,0.0000936403,0.6868287,0.005401424,0.3041098,0.001767919,0.00005505806],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06868188,0.001049296,0.9166428,0.004677134,0.00006941891,0.0002630631,0.000687863,0.001772806,0.006155718],"genre_scores_gemma":[0.8600069,0.0004559201,0.1324661,0.001465915,0.0002545966,0.0005001531,0.0007797398,0.0003579802,0.003712775],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01448668,"threshold_uncertainty_score":0.07661384,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09834300338755517,"score_gpt":0.2051528974056058,"score_spread":0.1068098940180507,"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."}}