发表机构
Università degli Studi di Perugia; INFN Sezione di Perugia（佩鲁贾大学; 意大利国家核物理研究所佩鲁贾分部）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出一种新型量子启发式树张量网络喷注标记器，其参数远少于 LundNet，在夸克/胶子区分任务上性能接近 LundNet，可用于分析不同喷注产生器的表示分歧。
AI 中文摘要
喷注标记器以 Lund 聚类树为输入，编码量子色动力学（QCD）辐射结构并通过图网络处理。本文探究该树本身是否可约束计算，以及约束后能获取哪些信息。为此，我们构建了一种新型量子启发式树张量网络（Tree Tensor Network, TTN），该网络在 Cambridge/Aachen 聚类树的内部节点间共享单个张量核，采用 Lund 坐标，且不包含粒子识别或探测器级信息。该构建基于辐射历史的强先验，而非粒子组分，与紧凑等变标记器互补。由于相同的学习映射在每个节点上作用一致，训练后的模型可在截断树中评估，其潜在空间可跨递归比较，还可用于定位 Lund 喷注平面上 Pythia 和 Herwig 喷注表示的分歧，显示出依赖于产生器的集中区域。χ=8 的模型有 4014 个可训练参数，而 LundNet 约有 391000 个。我们在粒子水平上对 Pythia 和 Herwig 样本评估了增强顶夸克标记与夸克/胶子区分，包括原生（Pythia→Pythia）和迁移（Pythia→Herwig）两种配置。尽管容量相差两个数量级，TTN 在夸克/胶子区分上的原生性能接近 LundNet，在顶夸克标记上略逊，且在两项任务中表现出相似的 Pythia→Herwig 迁移行为。最后，我们展示了网络随键维度和微扰标度的变化行为。
英文摘要
Jet taggers built on the Lund declustering tree encode QCD radiation structure in the inputs and process it with graph networks. We ask whether the tree itself can also constrain the computation, and what becomes accessible when it does. For this, we construct a novel quantum-inspired Tree Tensor Network (TTN), where a single tensor core is shared among the internal nodes of the Cambridge/Aachen declustering tree, employing Lund coordinates, and with no particle-identification or detector-level information. The construction is based on a strong prior on the radiation history rather than on the constituents, complementary to compact equivariant taggers. Because the same learned map acts identically at every node, the trained model can be evaluated on truncated trees and its latent space compared across recursions, and used to localise where on the Lund jet plane the Pythia and Herwig jet representations diverge, showing the regions of generator-dependent concentration. The $χ=8$ model has 4014 trainable parameters against approximately 391,000 for LundNet. We evaluate boosted top tagging and quark/gluon discrimination at particle level on Pythia and Herwig samples, in both native (Pythia$\to$Pythia) and transfer (Pythia$\to$Herwig) configurations. Despite differing in capacity by two orders of magnitude, the TTN reaches native performance close to LundNet in quark/gluon discrimination, slightly underperforming in top tagging, with a similar Pythia-to-Herwig transfer behavior in both tasks. Finally, we show the behavior of the network as a function of the bond dimension, and as a function of the perturbative scale.
