{"id":"W4391673415","doi":"10.48550/arxiv.2402.05002","title":"Randomized Confidence Bounds for Stochastic Partial Monitoring","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Statistical Process Monitoring","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Mitacs; Canadian Institute for Advanced Research","keywords":"Confidence interval; Randomized controlled trial; Statistics; Mathematics; Computer science; Medicine; Internal medicine","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":[0.01591334,0.002355335,0.003000996,0.00162878,0.0009097058,0.002955444,0.003807555,0.002716459,0.004853461],"category_scores_gemma":[0.08360922,0.001171742,0.001373465,0.001177107,0.003065946,0.004612978,0.00398482,0.004688168,0.0006721548],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002803927,"about_ca_system_score_gemma":0.00272047,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002493449,"about_ca_topic_score_gemma":0.001799964,"domain_scores_codex":[0.9883095,0.005998757,0.0005215724,0.002179338,0.002098917,0.0008919988],"domain_scores_gemma":[0.9140491,0.07196207,0.005113877,0.004524685,0.002784607,0.001565742],"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":[0.0005182489,0.000182863,0.00228412,0.0002443223,0.0001613848,0.0001252813,0.0001458613,0.7765093,0.001271891,0.1765956,0.003358702,0.03860246],"study_design_scores_gemma":[0.00004466544,0.00008481381,0.0002275322,0.00003217681,0.00001799277,0.00003028207,0.00001032216,0.9432152,0.000505748,0.05537112,0.000441511,0.00001864022],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02683326,0.0009890331,0.9662316,0.001022155,0.00008315322,0.0001626776,0.0003546378,0.0006823499,0.003641135],"genre_scores_gemma":[0.8720691,0.0007364101,0.1221886,0.0006390426,0.0002001578,0.0005151954,0.0005957961,0.000206923,0.002848794],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01591334,"threshold_uncertainty_score":0.08415878,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2955852263075284,"score_gpt":0.3449954180451168,"score_spread":0.04941019173758843,"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."}}