发表机构
Michigan State University; Grand Valley State University; Davidson College; University of Kentucky（密歇根州立大学; 大峡谷州立大学; 戴维森学院; 肯塔基大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究以TPC数据为测试平台，通过冻结编码器的探针方法，发现架构是TPC嵌入中任务相关结构的主要来源，其诱导的表示可跨实验和探测器系统复用。
AI 中文摘要
深度学习的研究正日益转向基础模型方法。在实验物理学领域，这使得模型和学习到的表示能够在其开发实验之外被复用。本研究通过对冻结编码器上的探针进行评估，探究了跨实验和探测器系统的表示可复用性，这些探针在下游适配前即可揭示与任务相关的结构，对微调起到补充作用。结合随机权重对照，它们能够区分架构和编码器训练的贡献，而仅靠下游性能无法解析这些贡献。时间投影室（TPC）数据是理想的测试平台，因为TPC系统的事件可表示为可变长度的稀疏张量，而探测器几何结构、事件拓扑和科学任务可能存在显著差异。我们研究了固定维度的TPC事件表示是否可在分类任务、实验和探测器系统间复用。Sparse ResNet和PointNet风格的编码器为来自GADGET II TPC和AT-TPC的四个数据集生成512维嵌入。随机初始化的编码器在监督训练前分离出架构的贡献。随后，我们在一个分类任务上训练每个编码器，冻结其参数，并为每个下游任务训练线性或非线性探针。研究发现，这种由架构诱导的结构在跨实验和探测器系统时仍然有用；随机初始化的PointNet风格表示在多个任务上具有高信息量；两种架构对其嵌入空间的组织方式不同，但在跨探测器时均未出现大规模、系统性的效用损失。这些结果表明，架构是TPC嵌入中与任务相关结构的主要来源，在评估表示学习和开发可复用探测器模型时应明确考虑这一点。
英文摘要
Deep-learning efforts have increasingly shifted toward foundation model approaches. In experimental physics, this allows models and learned representations to be reused beyond the experiments in which they were developed. This work evaluates the reusability of representations across experiments and detector systems using probes on frozen encoders. These probes reveal task-relevant structure before downstream adaptation, complementing fine-tuning. Together with random-weight controls, they distinguish contributions from architecture and encoder training that downstream performance alone cannot resolve. Time projection chamber (TPC) data provide a useful testbed because events from TPC systems can be represented as variable-length sparse tensors, while detector geometries, event topologies, and scientific tasks can differ substantially. We investigate whether fixed-dimensional TPC event representations can be reused across classification tasks, experiments, and detector systems. Sparse ResNet and PointNet-style encoders produce 512-dimensional embeddings for four datasets from the GADGET II TPC and AT-TPC. Randomly initialized encoders isolate the contribution from architecture before supervised training. We then train each encoder on a classification task, freeze its parameters, and train a linear or nonlinear probe for each downstream task. We find that this architecture-induced structure remains useful across experiments and detector systems. The randomly initialized PointNet-style representation is highly informative on several tasks. The two architectures organize their embedding spaces differently, but neither exhibits a large, systematic loss of utility cross-detector. These results show that architecture is a major source of task-relevant structure in TPC embeddings and should be treated explicitly when assessing representation learning and developing reusable detector models.
