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

Chinese

模型是重复更新的数据,而更新看起来在验证数据上更好,但不是在新数据上是一个错误的改进,可以误导临床决策。天真的规则接受每一个正面验证收益,当相同的数据选择和评判更新时是乐观的。BRIDGE是一个模型-agnostic接受门户,决定每一个更新从预测和可用数据集,有固定的设置。数据的每一个折叠评估了在其他折叠(交叉配对)上选择的更新,以减少选择偏见的95%;接受要求收益的较低的bootstrap约束超过一个边界。 四个设置是(A)11个新的预测和可用数据集,(B)合成任务,(C)12个回顾临床任务,(D)39个支持

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