Newest papers

BRIDGE: An Acceptance Gate to Block False Improvements in Model Updates, with a Retrospective Clinical Evaluation

Dwi Sunaryono · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.29515 · cited by 0 works (OpenAlex) · open-access PDF

Portuguese

A regra ingênua aceita cada ganho de validação positiva e é otimista quando os mesmos dados escolhem e julgam a atualização. BRIDGE é uma porta de aceitação modelo-agnostic que decide cada atualização de predições e rótulos disponíveis, com configurações fixas. Cada fold dos dados julga a atualização escolhida sobre as outras tarefas (intervalo cruzado) para reduzir os preconceitos de seleção; a aceitação exige que a taxa de inicialização inferior do ganho exceda uma margem. As quatro configurações são (A) 11 novas atualizações em conjuntos de dados disponíveis, (B) tarefas sintéticas caídas, (C) 12 tarefas clínicas retrospectivas, e (D) 39 tarefas de suporte a novos conjuntos de dados falsos. A taxa de confidência falsa

Machine translation (Meta M2M100); the English original follows.

Abstract

Models are updated repeatedly, and an update that looks better on validation data but not on new data is a false improvement that can misguide clinical decisions. The naive rule accepts every positive validation gain and is optimistic when the same data choose and judge the update. BRIDGE is a model-agnostic acceptance gate that decides each update from predictions and the available labels, with fixed settings. Each fold of the data judges the update chosen on the other folds (cross-fitting) to reduce selection bias; acceptance requires the gain's lower bootstrap bound to exceed a margin. The four settings are (A) 11 new datasets, (B) synthetic tasks, (C) 12 retrospective clinical tasks, and (D) 39 supporting datasets. The false-improvement rate falls from 19.1% (naive) to 1.1% (BRIDGE) in (A), 20.7% to 1.7% (B), 20.0% to 0% (C), and 12.5% to 0.5% (D); every 95% confidence interval of the reduction over datasets or tasks excludes zero (not over the clinical sources). An equal-size random draw from the naive acceptances contains more false improvements in (A)-(E) (post hoc, p<0.001). On the OpenML collection (E) of 14 new datasets, the false-improvement rate falls from 25.6% to 1.0%. BRIDGE removes 97% to 100% of the false improvements that the naive rule accepts, and its mean gain per deployed update is 1.8 to 3.1 times the naive rule's. The 95% upper bound on the false-improvement rate is below 5.5%: formal in (B) for independent tasks (3.56%), and conditional on the real data tested (0.33% to 5.40%).

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Computer science, Block (permutation group theory), Data mining, Bridge (graph theory), Upper and lower bounds, Interval (graph theory)

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange