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

Korean

모델은 반복적으로 업데이트되는 데이터이며, 업데이트는 검증 데이터에 더 잘 보이지만 새로운 데이터에 더 잘 보이는 것은 임상 결정에 오해 할 수있는 잘못된 개선입니다. 순진한 규칙은 모든 긍정적 인 검증 이득을 받아들이고 동일한 데이터를 선택하고 업데이트를 판단 할 때 낙관적입니다. BRIDGE는 예측 데이터 세트와 사용할 수있는 데이터 세트에서 각 업데이트를 결정하는 4 가지 설정입니다. (B) 합성 작업, (C) 12 개의 retrospective 임상 작업, (D) 39 개의 새로운 데이터 세트를 지원하는 가짜 업데이트를 판단하여 동일한 데이터를 선택하고 업데이트를 판단합니다. 수락은 이득의 낮은 부트 스트랩이 한계를 초과해야합니다. (A) 4 개의 설정

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