RS3L: A jet tagging dataset for self-supervised learning based on re-simulation
收藏资源简介：
Jet tagging dataset used for "Re-Simulation-based Self-Supervised Learning" (RS3L, arXiv:2403.07066). Simulated partons are re-showered with various parton shower configurations and reconstructed with the Delphes3 detector software. The singletons array contains information about the jet and has dimensions N_examples x N_augmentations x N_singletons. The augmenations are ordered by: 1. nominal scenario: jet showered with Pythia82. changing the numerical seed in Pythia83. changing the scale controlling the probability for final state radiation by 1/sqrt(2)4. changing the scale controlling the probability for final state radiation by sqrt(2)5. using Herwig7 as parton shower The variables stored in the singletons array are: singletons = ['jettype','parton1_pt','parton1_eta','parton1_phi','parton1_e','parton2_pt','parton2_eta','parton2_phi','parton2_e', 'jet_pt','jet_eta','jet_phi','jet_e','jet_msd','jet_n2'] For gluon-initiated jets, parton1 and parton2 are the two gluon daughters (see below). For any other jet type, parton1 is the main particle (W, H, Z, or single quark), and parton2 is filled with 0s. The jet_pflow_cands contains the particles clustered into the jet. The array has a shape N_examples x N_augmentations x N_features x N_particles.The features per particle are: features = ['pt','relpt','eta','phi','dr','e','rele','charge','pdgid','d0','dz']The jettype gives the parton at the origin of the jet: jettype: 1: q2: c3: b4: H->bb5: g->qq6: g->cc7: g->bb8: g->gg9: W->two quarks10: Z->qq11: Z->bb
本数据集用于论文《基于重模拟的自监督学习》（Re-Simulation-based Self-Supervised Learning，缩写RS3L，arXiv:2403.07066）。模拟得到的部分子将使用多种部分子喷注（parton shower）配置进行重新喷注模拟，并通过Delphes3探测器软件完成探测器响应重建。 singletons数组存储了喷注相关信息，其维度为N_examples × N_augmentations × N_singletons。数据增强顺序依次为： 1. 标称场景：使用Pythia8进行喷注模拟； 2. 更改Pythia的数值种子； 3. 将控制末态辐射概率的尺度调整为1/√2； 4. 将控制末态辐射概率的尺度调整为√2； 5. 使用Herwig7作为部分子喷注模拟器。 singletons数组包含的变量依次为：["喷注类型标识（jettype）","粒子1横向动量（parton1_pt）","粒子1快度（parton1_eta）","粒子1方位角（parton1_phi）","粒子1能量（parton1_e）","粒子2横向动量（parton2_pt）","粒子2快度（parton2_eta）","粒子2方位角（parton2_phi）","粒子2能量（parton2_e）","喷注横向动量（jet_pt）","喷注快度（jet_eta）","喷注方位角（jet_phi）","喷注能量（jet_e）","喷注软滴质量（jet_msd）","喷注二阶子喷注度（jet_n2）"]。其中：喷注类型标识（jettype）用于指示喷注起源的部分子；粒子1横向动量（parton1_pt）为粒子1的横向动量，粒子1快度（parton1_eta）为粒子1的快度，粒子1方位角（parton1_phi）为粒子1的方位角，粒子1能量（parton1_e）为粒子1的能量；粒子2横向动量（parton2_pt）、粒子2快度（parton2_eta）、粒子2方位角（parton2_phi）、粒子2能量（parton2_e）分别为粒子2的对应物理量；喷注横向动量（jet_pt）为喷注横向动量，喷注快度（jet_eta）为喷注快度，喷注方位角（jet_phi）为喷注方位角，喷注能量（jet_e）为喷注能量，喷注软滴质量（jet_msd）为喷注的软滴质量，喷注二阶子喷注度（jet_n2）为喷注的二阶子喷注度。 对于胶子引发的喷注，粒子1与粒子2为其两个胶子子体（详见下文）；对于其他类型的喷注，粒子1为主粒子（W玻色子、希格斯玻色子、Z玻色子或单夸克），粒子2将填充0值。 jet_pflow_cands数组存储了聚类至喷注内的粒子，其维度为N_examples × N_augmentations × N_features × N_particles。每个粒子对应的特征依次为：["横向动量（pt）","相对横向动量（relpt）","快度（eta）","方位角（phi）","粒子间距离（dr）","能量（e）","相对能量（rele）","电荷（charge）","粒子数据组标识（pdgid）","横向冲击参数（d0）","纵向冲击参数（dz）"]。 喷注类型标识（jettype）的取值及对应物理意义如下： 1: 夸克（q） 2: 粲夸克（c） 3: 底夸克（b） 4: H→bb（希格斯玻色子衰变至底夸克对） 5: g→qq（胶子衰变至夸克对） 6: g→cc（胶子衰变至粲夸克对） 7: g→bb（胶子衰变至底夸克对） 8: g→gg（胶子衰变至胶子对） 9: W→两夸克 10: Z→qq（Z玻色子衰变至夸克对） 11: Z→bb（Z玻色子衰变至底夸克对）
