Secondary Vertex Finding in Jets with Neural Networks

TL;DR

This paper introduces a neural network-based method for secondary vertex finding within jets, significantly enhancing bottom vs. charm flavor tagging and overall jet classification at particle colliders.

Contribution

A novel set-to-graph neural network model that utilizes all track information for improved secondary vertex reconstruction in jets.

Findings

Outperforms traditional vertex finding methods

Leads to better jet classification accuracy

Demonstrates the effectiveness of graph neural networks in particle physics

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.