Single-jet datasets for particle reconstruction with deep learning

Training and test datasets used for [1]* . singleQuarkJet_train.root : N=60649 singleQuarkJet_test.root: N=38922 singleGluonJet_test.root: N=38295 The events are formed by a single initial state quark or gluon followed by parton shower generated in Pythia8 and then simulated using GEANT4 in a nearly-hermetic 6-layer calorimeter system as described in [1,2]. The branches in the ROOT files store features associated with cells, tracks, particles, pflow objects, jets, as well as edge lists for creating a graph representation of each event.<br> <br> *Note that subsets of N=50000 and N=30000 were used from the train and test samples, respectively, for the results in [1]. [1] Reconstructing particles in jets using set transformer and hypergraph prediction networks<br> [2] Configurable Calorimeter Simulation for AI (COCOA)用于[1]*的训练与测试数据集如下： singleQuarkJet_train.root：样本量N=60649；singleQuarkJet_test.root：N=38922；singleGluonJet_test.root：N=38295。 每个事件均由单个初始态夸克或胶子生成，经由Pythia8生成部分子簇射（parton shower），随后在[1,2]中描述的近乎全封闭6层量能器系统内，使用GEANT4完成模拟。ROOT文件中的分支存储了与探测器单元（cells）、径迹（tracks）、粒子、粒子流（pflow）对象、喷注（jets）相关的特征，以及用于构建各事件图表示的边列表（edge lists）。 *注：[1]的研究工作分别从训练样本与测试样本中选取了N=50000与N=30000的子集开展实验。 [1] 《利用集合Transformer（Set Transformer）与超图预测网络重建喷注内粒子》（Reconstructing particles in jets using set transformer and hypergraph prediction networks） [2] 《面向人工智能的可配置量能器模拟（COCOA）》（Configurable Calorimeter Simulation for AI (COCOA)）