团队

在 AI 时代，每个人都应逐渐变成定义标准的人。在把任务交给 AI 之前，有几个问题值得提前想清楚：AI 的角色是什么？它应该从哪几个角度考虑这个问题？这个任务的成功标准是什么？有没有 AI 可以学习的案例？有哪些是必须避免的错误？ 这几个问题看似简单，但能回答好，本身就是一种稀缺的管理能力。

投行分析师让AI同时跑数据清洗、行业对标和报告初稿，自己只负责审核与决策。律所合伙人用AI几分钟完成过去实习生一整天的尽职调查检索。这些已不是想像。

科幻作品常以《终结者》式的暴力对抗描绘人工智慧（AI）的威胁，但现实中AI的侵蚀远比银幕叙事更安静、更隐蔽——它无关肉体毁灭，而关乎存在根本： 一场针对人类“思考权”的系统性让渡，正在我们与效率的合谋中悄然发生。

This article develops a conformal prediction method for classification tasks that can adapt to random label contamination in the calibration sample, often leading to more informative prediction sets with stronger coverage guarantees compared to existing approaches. This is obtained through a precise characterization of the coverage inflation (or deflation) suffered by standard conformal inferences in the presence of label contamination, which is then made actionable through a new calibration algorithm. Our solution can leverage different modelling assumptions about the contamination process, while requiring no knowledge of the underlying data distribution or of the inner workings of the classification model. The empirical performance of the proposed method is demonstrated through simulations and an application to object classification with the CIFAR-10H image data set.