发表机构
Niels Bohr Institute, University of Copenhagen（尼尔斯·玻尔研究所，哥本哈根大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究利用黎曼流匹配的基于变压器生成模型，从大型强子对撞机数据中学习标准模型结构，涵盖五个数量级不变质量范围，单次训练能重现粒子内运动学等多种内容，可直接从碰撞数据学习标准模型很大一部分。
AI 中文摘要
在这项工作中，我们证明了一个基于单个变压器的生成模型可以捕捉标准模型结构，涵盖从亚GeV区域到TeV连续体的五个数量级的不变质量范围，这是任何单个蒙特卡罗样本都无法覆盖的范围。为实现这一点，我们设计了ShellFlow，一种黎曼条件流匹配模型，它根据记录的事件组成，在其壳层流形上生成每个粒子。其唯一的物理先验是壳层条件和不变质量公式。该模型在来自ATLAS开放数据13 TeV版本的约10^9个真实pp碰撞事件上进行训练，且未被告知其他信息。从单次训练运行中，该模型学会了重现以下所有内容：粒子内运动学、在其PDG位置的双轻子共振（J/ψ、Υ、Z）、轻子温伯格角、W和顶夸克质量以及未纳入训练目标的粒子间相关性。因此，标准模型的很大一部分可以直接从记录的碰撞数据中学习。
英文摘要
In this work we demonstrate that a single transformer-based generative model can capture Standard Model structure spanning five decades of invariant mass, from the sub-GeV regime to the TeV continuum, a range that no single Monte Carlo sample covers. To achieve this we design \textsc{ShellFlow}, a Riemannian conditional flow matching model that, given the recorded event composition, generates each particle on its on-shell manifold. Its only physics priors are the on-shell condition and the invariant-mass formula. The model is trained on $\sim 10^{9}$ real $pp$ collision events from the ATLAS Open Data 13~TeV release and told nothing else. From a single training run, the model learns to reproduce all of the following: intra-particle kinematics, the dilepton resonances ($J/ψ$, $Υ$, $Z$) at their PDG positions, the leptonic Weinberg angle, the $W$ and top-quark masses, and inter-particle correlations that enter no training objective. A substantial fraction of the Standard Model is thus learnable directly from recorded collision data.
Comments35 pages, 25 figures
