{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002613463,0.0004718413,0.001206303,0.0004404353,0.0003086283,0.0006102388,0.001653028,0.0003364086,0.00007125341],"category_scores_gemma":[0.01042065,0.0004384471,0.0005935669,0.0007091081,0.0005867577,0.0002754688,0.001831391,0.0009564824,0.0003216735],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002852342,"about_ca_system_score_gemma":0.0003646591,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000529469,"about_ca_topic_score_gemma":0.000006217531,"domain_scores_codex":[0.9958044,0.0002912841,0.0008168261,0.001975062,0.000520074,0.0005923572],"domain_scores_gemma":[0.9880607,0.009302096,0.0005197051,0.001035146,0.0007643845,0.000318023],"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":[0.0126371,0.0000421372,0.0000987502,0.0001856142,0.0001951586,0.0001873048,0.0003597503,0.6419554,0.00003662096,0.3419691,0.0002507797,0.002082275],"study_design_scores_gemma":[0.01005666,0.00002146422,0.000007773837,0.0001983889,0.0002227423,0.000001538863,0.0002475721,0.317822,0.0001202457,0.6708218,0.0001423271,0.0003374543],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04599375,0.0004243948,0.9456897,0.00008559497,0.00568946,0.001006157,0.0001217844,0.0002215494,0.0007675786],"genre_scores_gemma":[0.9913362,0.00003678536,0.002446204,0.00001171274,0.0008205965,0.00002567948,0.000006725326,0.0000490022,0.005267106],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9453424,"threshold_uncertainty_score":0.9998067,"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."}}