AI 中文总结
本研究提出通过多几何预训练，引入SimpleBox合成箱式量能器集合，实现可迁移的量能器簇射生成器，经微调后在未见过的量能器上表现优于真实探测器预训练模型，降低模拟成本。
AI 中文摘要
量能器簇射的详细Geant4模拟占据了高能物理实验的计算预算，深度生成代理模型可降低该成本，但仍与训练所用探测器绑定，因此每种新几何都需要大量领域内数据集。本研究探讨是否可在多个探测器上预训练单个点云簇射生成器，并将其迁移至未见过的量能器。预训练几何来自合成几何变化，而非真实探测器数据。我们引入SimpleBox，即10^4个箱式量能器的集合，覆盖采样分数与纵向分段的平面，并将其与在真实探测器上预训练的情况进行基准对比。在预训练中未见过的量能器上，使用10^3个目标簇射进行微调时，两种先验相对于从头训练，将聚合切片Wasserstein距离降低至Geant4的5.2倍（合成先验）和8.0倍（真实先验）。在更大的目标规模下，合成先验的表现优于真实先验。因此，仅几何多样性就是预训练可迁移簇射生成器的实用方法。
英文摘要
Detailed Geant4 simulation of calorimeter showers dominates the computing budget of high-energy physics experiments. Deep generative surrogates reduce this cost, but they have remained tied to the detector they were trained on, so each new geometry needs a large in-domain dataset. We study whether a single point cloud shower generator can be pre-trained on multiple detectors and transferred to unseen calorimeters. The pre-training geometries come from synthetic geometric variation rather than real-detector data. We introduce SimpleBox, a family of $10^4$ box calorimeters spanning the plane of sampling fraction and longitudinal segmentation, and benchmark it against pre-training on realistic detectors. On a calorimeter unseen in pre-training, with $10^3$ target showers for fine-tuning, the two priors reduce the aggregated sliced Wasserstein distance to Geant4 by factors of 5.2 (synthetic) and 8.0 (realistic) relative to training from scratch. At larger target sizes the synthetic prior performs better than the realistic one. Geometric diversity alone is therefore a practical way to pre-train a transferable shower generator.
Comments50 pages, 29 figures, 12 tables
