{"id":"W4392270931","doi":"10.48550/arxiv.2402.17235","title":"Stochastic Gradient Succeeds for Bandits","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Mathematical economics; Computer science; Economics; Econometrics; Mathematics","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001690142,0.0004501885,0.0006509728,0.001285158,0.0002803426,0.0004309792,0.002491319,0.0003935953,0.0003429545],"category_scores_gemma":[0.001619104,0.0004104224,0.0006068554,0.001613307,0.0003413768,0.0002158019,0.00342877,0.001104805,0.001392925],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000502352,"about_ca_system_score_gemma":0.000455291,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005006358,"about_ca_topic_score_gemma":0.00009044237,"domain_scores_codex":[0.9956967,0.0001632582,0.0005091618,0.002217998,0.0006575713,0.0007552857],"domain_scores_gemma":[0.9949191,0.001995339,0.0002842153,0.001556651,0.0008505707,0.0003941523],"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":[0.0002208531,0.0001072287,0.0001162303,0.0001132898,0.0001833569,0.0003695086,0.0002836067,0.943674,0.00001465913,0.03868845,0.01165882,0.004569949],"study_design_scores_gemma":[0.0004046115,0.00009108979,0.0001269684,0.00007639341,0.00007836318,0.00000478641,0.0002475828,0.4306867,0.00004078453,0.5639943,0.003885226,0.0003631312],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09335161,0.0003557427,0.899599,0.0003172711,0.002981715,0.001294032,0.0004849453,0.0002239474,0.001391762],"genre_scores_gemma":[0.9689417,0.00004068928,0.000459383,0.00003077883,0.0003828408,0.00001085951,0.0000392738,0.00005620845,0.03003824],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8991396,"threshold_uncertainty_score":0.9998348,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2906479033614339,"score_gpt":0.3273040213724201,"score_spread":0.03665611801098623,"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."}}