Saved in:
Bibliographic Details
Main Authors: Wildridge, Andrew J., Rodgers, Jack P., Colbert, Ethan M., yao, Yao, Jung, Andreas W., Liu, Miaoyuan
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2412.07867
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915058208997376
author Wildridge, Andrew J.
Rodgers, Jack P.
Colbert, Ethan M.
yao, Yao
Jung, Andreas W.
Liu, Miaoyuan
author_facet Wildridge, Andrew J.
Rodgers, Jack P.
Colbert, Ethan M.
yao, Yao
Jung, Andreas W.
Liu, Miaoyuan
contents Bumblebee is a foundation model for particle physics discovery, inspired by BERT. By removing positional encodings and embedding particle 4-vectors, Bumblebee captures both generator- and reconstruction-level information while ensuring sequence-order invariance. Pre-trained on a masked task, it improves dileptonic top quark reconstruction resolution by 10-20% and excels in downstream tasks, including toponium discrimination (AUROC 0.877) and initial state classification (AUROC 0.625). The flexibility of Bumblebee makes it suitable for a wide range of particle physics applications, especially the discovery of new particles.
format Preprint
id arxiv_https___arxiv_org_abs_2412_07867
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Bumblebee: Foundation Model for Particle Physics Discovery
Wildridge, Andrew J.
Rodgers, Jack P.
Colbert, Ethan M.
yao, Yao
Jung, Andreas W.
Liu, Miaoyuan
High Energy Physics - Experiment
Machine Learning
High Energy Physics - Phenomenology
Bumblebee is a foundation model for particle physics discovery, inspired by BERT. By removing positional encodings and embedding particle 4-vectors, Bumblebee captures both generator- and reconstruction-level information while ensuring sequence-order invariance. Pre-trained on a masked task, it improves dileptonic top quark reconstruction resolution by 10-20% and excels in downstream tasks, including toponium discrimination (AUROC 0.877) and initial state classification (AUROC 0.625). The flexibility of Bumblebee makes it suitable for a wide range of particle physics applications, especially the discovery of new particles.
title Bumblebee: Foundation Model for Particle Physics Discovery
topic High Energy Physics - Experiment
Machine Learning
High Energy Physics - Phenomenology
url https://arxiv.org/abs/2412.07867