研究人员开发了一种用于新物理搜索中机器学习异常检测的新校准层。该层基于共形预测，旨在提供异常得分的统计上合理的解释，解决“elsewhere效应”和背景模型错误等问题。所提出的方法在不重新训练探测器的情况下生成有效的局部p值并校正失校准，通过消除人为的超额信号并确保可靠的误报率，证明了其在LHC Olympics数据上的有效性。 AI
影响 这项研究为科学发现中基于机器学习的异常检测的解释提供了一个更鲁棒的统计框架，有可能提高新物理发现的可靠性。
排序理由 该集群包含一篇详细介绍物理搜索中异常检测新方法的论文。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
完整方法见我们的编辑标准。
arXiv:2606.13780v1 Announce Type: cross Abstract: Machine-learned anomaly detection is reshaping searches for new physics, but it has outrun the statistics used to interpret it. A raw anomaly score has no calibrated meaning, a model that scans many regions inflates the look-elsew…
Machine-learned anomaly detection is reshaping searches for new physics, but it has outrun the statistics used to interpret it. A raw anomaly score has no calibrated meaning, a model that scans many regions inflates the look-elsewhere effect, and the asymptotic significances the …