{"id":"W7133405170","doi":"","title":"Lexicographic Lipschitz Bandits:New Algorithms and a Lower Bound","year":2025,"lang":"en","type":"article","venue":"CityU Scholars","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"National Natural Science Foundation of China; City University of Hong Kong","keywords":"Lexicographical order; Regret; Upper and lower bounds; Lipschitz continuity; Dimension (graph theory); Matching (statistics)","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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00305919,0.0002765644,0.0004378596,0.001268229,0.0005820416,0.002314221,0.001479621,0.0002277174,0.0006652948],"category_scores_gemma":[0.00611011,0.0002267854,0.0001737394,0.003198293,0.0004415543,0.001508115,0.0006893243,0.0009090925,0.0003749952],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007229195,"about_ca_system_score_gemma":0.000340445,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004510885,"about_ca_topic_score_gemma":0.00004322022,"domain_scores_codex":[0.9954969,0.0002453045,0.0006369249,0.001098948,0.001861062,0.0006608059],"domain_scores_gemma":[0.9968605,0.0009640648,0.0001339983,0.001132121,0.0004539516,0.0004553531],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002001232,0.0002147408,0.04059453,0.00001378355,0.0001633972,0.0002017723,0.0002514772,0.0001241968,0.001227345,0.001728469,0.0502983,0.9049819],"study_design_scores_gemma":[0.00226323,0.0001543871,0.07761455,0.00008080443,0.00002946402,0.00004685664,0.000360465,0.002017468,0.001123323,0.1826801,0.7331041,0.0005252858],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6659198,0.00957529,0.2563366,0.01313296,0.008444889,0.001626962,0.0001109133,0.0005218145,0.04433079],"genre_scores_gemma":[0.8919334,0.0008965395,0.02025168,0.002162496,0.0007955397,0.00006269003,0.00001426514,0.00007141921,0.08381194],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9044566,"threshold_uncertainty_score":0.9987215,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07882936778791948,"score_gpt":0.4231396116865803,"score_spread":0.3443102438986608,"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."}}