Secondary Vertex Finding in Jets with Neural Networks

Abstract

Jet classification is an important ingredient in measurements and searches for new physics at particle coliders, and secondary vertex reconstruction is a key intermediate step in building powerful jet classifiers. We use a neural network to perform vertex finding inside jets in order to improve the classification performance, with a focus on separation of bottom vs. charm flavor tagging. We implement a novel, universal set-to-graph model, which takes into account information from all tracks in a jet to determine if pairs of tracks originated from a common vertex. We explore different performance metrics and find our method to outperform traditional approaches in accurate secondary vertex reconstruction. We also find that improved vertex finding leads to a significant improvement in jet classification performance.

References in corpus (9)

• An Introduction to PYTHIA 8.2
• Jet Flavor Classification in High-Energy Physics with Deep Neural Networks
• Graph Neural Networks in Particle Physics
• ABCNet: An attention-based method for particle tagging
• MLPF: Efficient machine-learned particle-flow reconstruction using graph neural networks
• Casting a graph net to catch dark showers
• Object condensation: one-stage grid-free multi-object reconstruction in physics detectors, graph and image data
• The Boosted Higgs Jet Reconstruction via Graph Neural Network
• Towards a Computer Vision Particle Flow

Cited by in corpus (11)

• Jet Flavour Tagging for Future Colliders with Fast Simulation
• Machine Learning in High Energy Physics: A review of heavy-flavor jet tagging at the LHC
• Topological Reconstruction of Particle Physics Processes using Graph Neural Networks
• Learning Tree Structures from Leaves For Particle Decay Reconstruction
• Comparing Point Cloud Strategies for Collider Event Classification
• Development of a Vertex Finding Algorithm using Recurrent Neural Network
• Secondary Vertex Reconstruction with MaskFormers
• Top-philic Machine Learning
• PASCL: Supervised Contrastive Learning with Perturbative Augmentation for Particle Decay Reconstruction
• Prospects for Higgs boson and new scalar resonant production searches in ttbb final state at the LHC
• B-jet Tagging Using a Hybrid Edge Convolution and Transformer Architecture