The maximum achievable performance of strange-jet tagging at hadron colliders and the loss in performance in different detector designs is estimated based on simulated truth jets from strange-quark and down-quark hadronisation. Both jet types are classified with a recurrent neural network using long short-term memory units, at first using all available truth particles and then applying selections to study the impacts of ideal tracking detectors, Cherenkov detectors, and calorimeters. Additionally, a manual reconstruction of strange hadron decays such as K_S →π⁺π^- from charged tracks is considered.

中文翻译：

---

强子对撞机上奇异喷射标记的最大性能

强子对撞机奇特喷流标记的最大可实现性能和不同探测器设计中的性能损失是基于奇夸克和下夸克强子化的模拟真实喷流估计的。两种喷射类型都使用循环神经网络使用长短期记忆单元进行分类，首先使用所有可用的真实粒子，然后应用选择来研究理想跟踪探测器、切伦科夫探测器和热量计的影响。此外，还考虑了从带电轨道手动重建奇怪的强子衰变，例如K _S →π ⁺ π ^-。