新闻
Target leakage, not model class, explains reported accuracy in survey-based cardiovascular screening: a leakage-tiered audit of glass-box and tabular foundation models
arXiv cs.AI · 发布于 · 阅读约3分钟
30秒读懂
- 发生了什么
- Researchers audited cardiovascular screening models and found that reported high accuracy comes from data leakage in features, not model sophistication.
- 为何重要
- Healthcare engineers building screening systems should care when evaluating model performance claims from survey-based health datasets.
- 注意
- The study used specific datasets and thresholds; results may not generalize to other screening tasks or populations with different demographic distributions.
- foundation model
- eval
- benchmark
这条新闻背后的模式
每个模式都讲清楚技术如何运作、何时值得投入,以及在哪里会失效。
The Agent Architect
每周一个模式、一个权衡、一个生产事故案例。为构建智能体系统的人准备的每周简报。
每周一封邮件,一键退订。您的地址仅用于发送简报。