Test sets for jet anomaly detection at the LHC
收藏资源简介：
<strong>Data Description</strong> These datasets are generated as a series of test sets for anomalous jet tagging at the LHC. They include boosted W jets, Top jets and Higgs jets. Jet transverse momentum is focused around 600 GeV. Each file includes 100k original events from MadGraph, but might have slightly less events in the final h5 files due to fatjet pre-selection. Production processes include: pp -> W' -> W (jj) Z(\(\nu \nu\)); \(m_{W} = 59, 80, 120, 174 ~GeV\) pp -> Z' -> t t~; \(m_t=80, 174 ~GeV\) pp -> HH -> (hh) (hh), (h -> bb); \(m_H=174~GeV\), \(m_h = 20, 80 ~GeV\) <strong>Data Generation</strong> Jet samples in this dataset are generated with MadGraph, Pythia8 and Delphes (no pile-up effects simulated). Particle flow objects are used to cluster jets. FastJet was used for jet clustering. Jets are clustered using anti-kt algorithm with cone size R=1.0. Leading jet: \(p_T>450 \textrm{GeV}\); sub-leading jet: \(p_T>200 \textrm{GeV}\) <strong>Data Structure</strong> To get jets: f['objects/jets'] For jets, there are two datasets: ['constituents', 'obs']. (jets information is stored with higher-pt jet first) `obs[:, n_j - 1]`: jet four vectors and n-subjettiness for (n_j -1) th jet (pt, eta, phi, m, tau1, tau2, tau3, tau4, tau5) pt-sorted (highest first) jet constituents information are stored in variable length arrays for (n_j -1) th jet `constituents[:, n_j - 1]`: \(\{ E_i, P_{xi}, P_{yi}, P_{zi}, \textrm{PID}_i\}\) (PID: PDG for tracks; [22] for photon; [0] for neutral hadron) <strong>Extra Notes</strong> Since the dataset is structured as events, for W jet samples, only leading jet is available; while for Top and Higgs jets, leading and sub-leading jets are both valid. One might need to restrict jet \(p_T\) range at use. e.g. to get leading jet constituents: `f["objects/jets/constituents"][:,0]` The file names are self-explanatory on the corresponding generation process.
**数据集说明** 本数据集为大型强子对撞机（Large Hadron Collider，LHC）上的异常喷注标记任务构建的一系列测试集，包含增强型W玻色子喷注、顶夸克喷注与希格斯玻色子喷注三类样本。喷注的横向动量集中于600 GeV附近。每个原始文件包含来自MadGraph的100k个事件，但由于大喷注预筛选步骤，最终生成的h5文件中事件数可能略少。其生成过程包括： 1. 质子-质子碰撞（pp）生成W'玻色子，随后W'玻色子衰变至W玻色子（衰变至双喷注jj）与Z玻色子（衰变至中微子对$ u u$）；W玻色子质量设置为59、80、120、174 GeV 2. 质子-质子碰撞生成Z'玻色子，随后Z'玻色子衰变至顶夸克-反顶夸克对$tar{t}$；顶夸克质量设置为80、174 GeV 3. 质子-质子碰撞生成双希格斯玻色子对HH，随后HH衰变至两对轻希格斯玻色子hh，轻希格斯玻色子h衰变至底夸克对$bb$；重希格斯玻色子H质量为174 GeV，轻希格斯玻色子h质量为20、80 GeV **数据生成** 本数据集的喷注样本通过MadGraph、Pythia8与Delphes生成（未模拟堆集效应）。采用粒子流对象进行喷注聚类，聚类过程使用FastJet软件包，以反k_t算法（anti-kt）进行喷注聚类，锥尺寸参数$R=1.0$。样本要求领头喷注的横向动量$p_T>450$ GeV，次领头喷注的横向动量$p_T>200$ GeV。 **数据结构** 访问喷注数据的方式为`f['objects/jets']`。喷注数据包含两个数据集：`['constituents', 'obs']`。喷注信息按照横向动量从高到低的顺序存储。 - `obs[:, n_j - 1]`：对应第$(n_j-1)$个喷注的四动量与n-子喷注性（n-subjettiness）参数，格式为$(p_T, eta, phi, m, au_1, au_2, au_3, au_4, au_5)$，其中$p_T$为横向动量，$eta$为赝快度，$phi$为方位角，$m$为不变质量，$ au_1$至$ au_5$为各阶子喷注性参数。 - 按横向动量从高到低排序的喷注组成粒子信息以变长数组形式存储，第$(n_j-1)$个喷注的组成粒子信息对应`constituents[:, n_j -1]`，格式为${E_i, P_{xi}, P_{yi}, P_{zi}, ext{PID}_i}$。其中$ ext{PID}$为径迹的粒子数据组（Particle Data Group，PDG）编号：光子对应编号[22]，中性强子对应编号[0]。 **附加说明** 由于数据集以事件为基本组织单元，W玻色子喷注样本仅包含领头喷注；而顶夸克与希格斯玻色子喷注样本同时包含领头与次领头喷注。使用时可能需要限制喷注的横向动量范围。例如，获取领头喷注的组成粒子可通过代码：`f["objects/jets/constituents"][:,0]`。文件名可直观反映其对应的生成过程。
