Dataset for RESuM: A Rare Event Surrogate Model for Physics Detector Design

This dataset contains the training data for ICLR 2025 Spotlight Paper: RESuM: A Rare Event Surrogate Model for Physics Detector Design: The experimental discovery of neutrinoless double-beta decay (NLDBD) would answer one of the most important questions in physics: Why is there more matter than antimatter in our universe? To maximize the chances of discovery, NLDBD experiments must optimize their detector designs to minimize the probability of background events contaminating the detector. Given that this probability is inherently low, design optimization either requires extremely costly simulations to generate sufficient background counts or contending with significant variance. In this work, we formalize this dilemma as a Rare Event Design (RED) problem: identifying optimal design parameters when the design metric to be minimized is inherently small. We then designed the Rare Event Surrogate Model (RESuM) for physics detector design optimization under RED conditions. RESuM uses a pre-trained Conditional Neural Process (CNP) model to incorporate additional prior knowledge into a Multi-Fidelity Gaussian Process model. We applied RESuM to optimize neutron shielding designs for the LEGEND NLDBD experiment, identifying an optimal design that reduces the neutron background by % while using only 3.3% of the computational resources compared to traditional methods. Given the prevalence of RED problems in other fields of physical sciences, especially in rare-event searches, the RESuM algorithm has broad potential for accelerating simulation-intensive applications.本数据集为ICLR 2025亮点论文《RESuM：面向物理探测器设计的稀有事件替代模型》的训练数据。 无中微子双β衰变（Neutrinoless Double-Beta Decay, NLDBD）的实验发现，将解答物理学领域最关键的问题之一：为何宇宙中物质总量多于反物质？为最大化发现概率，NLDBD实验需对探测器设计进行优化，以最小化背景事件污染探测器的概率。由于该概率本征极低，设计优化要么需要成本高昂的模拟以生成足够的背景计数，要么需承受显著的方差。 本研究将这一困境形式化为稀有事件设计（Rare Event Design, RED）问题：即当待最小化的设计指标本征极小时，识别最优设计参数。据此，我们针对RED场景下的物理探测器设计优化任务，提出了稀有事件替代模型（RESuM）。 RESuM采用预训练条件神经过程（Conditional Neural Process, CNP）模型，将额外先验知识融入多保真度高斯过程（Multi-Fidelity Gaussian Process）模型中。 我们将RESuM应用于LEGEND NLDBD实验的中子屏蔽设计优化任务，最终得到的最优方案可将中子背景降低%，且相较传统方法仅需3.3%的计算资源。 鉴于RED问题在物理科学其他领域（尤其是稀有事件搜寻方向）的普遍性，RESuM算法有望加速各类依赖大规模模拟的应用场景。