AI学会读实验笔记：分清“确定”和“不确定”
科学家在实验笔记里写的东西，和论文完全不同——里面有“这个结果可能不对”“下次试试另一种条件”这类不确定的表述。以前的AI只读论文和数据库，错过了这些信号。这篇研究做了一个叫Notes2Skills的框架，它能把实验笔记转成AI能执行的技能，同时保留作者对每句话的“确定程度”。比如，笔记里写“X可能抑制Y”，AI不会把它当成确定结论去执行，而是标记为待验证。在7种条件和3次湿实验测试中，只有这个框架既没把不确定的笔记当成指令，也没丢掉确定的指令。它不是你明天就能用的工具，但它是让AI成为靠谱科研助手的关键一步——学会区分“我确定”和“我猜”。
📄 原文摘要(英文)
Scientific discovery workflows usually contain and rely heavily on lab notes, where researchers record observations, interpret uncertain results, and plan follow-up experiments. Such informative lab notes preserve evolving scientific reasoning and author uncertainty, rather than polished final results exhibited in publications, providing a valuable opportunity for AI to engage in scientific exploration at a more comprehensive and deeper level. However, most prior work on scientific text focuses on papers, protocols, or structured databases, leaving informal laboratory notes underexplored as inputs to AI agents for science. This gap matters because lab notes often intermingle validated observations, tentative judgments, and possible experimental next steps within the same passage. If these signals are conflated, an AI agent may mistake uncertain scientific judgments for confirmed conclusions or executable actions. To this end, we present Notes2Skills, a two-stage framework for turning lab notebooks into verifiable skills for scientific AI agents while preserving the author's certainty. Across seven conditions and three wet-lab sessions, Notes2Skills is the only configuration that neither mistakes uncertain notes for firm instructions nor discards firm ones. We show that certainty preservation is the missing piece between lab notebooks and reliable agent skills, opening a path toward safer AI co-scientist systems.