Reconstructing hadronically decaying tau leptons with a jet foundation model

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Tani, Laurits, Pata, Joosep, Birk, Joschka
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909678135410688
author Tani, Laurits
Pata, Joosep
Birk, Joschka
author_facet Tani, Laurits
Pata, Joosep
Birk, Joschka
contents The limited availability and accuracy of simulated data has motivated the use of foundation models in high energy physics, with the idea to first train a task-agnostic model on large and potentially unlabeled datasets. This enables the subsequent fine-tuning of the learned representation for specific downstream tasks, potentially requiring much smaller dataset sizes to reach the performance of models trained from scratch. We study how OmniJet-$α$, one of the proposed foundation models for particle jets, can be used on a new set of tasks, and in a new dataset, in order to reconstruct hadronically decaying $τ$ leptons. We show that the pretraining can successfully be utilized for this multi-task problem, improving the resolution of momentum reconstruction by about 50\% when the pretrained weights are fine-tuned, compared to training the model from scratch. While much work remains ahead to develop generic foundation models for high-energy physics, this early result of generalizing an existing model to a new dataset and to previously unconsidered tasks highlights the importance of testing the approaches on a diverse set of datasets and tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2503_19165
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Reconstructing hadronically decaying tau leptons with a jet foundation model
Tani, Laurits
Pata, Joosep
Birk, Joschka
High Energy Physics - Experiment
High Energy Physics - Phenomenology
The limited availability and accuracy of simulated data has motivated the use of foundation models in high energy physics, with the idea to first train a task-agnostic model on large and potentially unlabeled datasets. This enables the subsequent fine-tuning of the learned representation for specific downstream tasks, potentially requiring much smaller dataset sizes to reach the performance of models trained from scratch. We study how OmniJet-$α$, one of the proposed foundation models for particle jets, can be used on a new set of tasks, and in a new dataset, in order to reconstruct hadronically decaying $τ$ leptons. We show that the pretraining can successfully be utilized for this multi-task problem, improving the resolution of momentum reconstruction by about 50\% when the pretrained weights are fine-tuned, compared to training the model from scratch. While much work remains ahead to develop generic foundation models for high-energy physics, this early result of generalizing an existing model to a new dataset and to previously unconsidered tasks highlights the importance of testing the approaches on a diverse set of datasets and tasks.
title Reconstructing hadronically decaying tau leptons with a jet foundation model
topic High Energy Physics - Experiment
High Energy Physics - Phenomenology
url https://arxiv.org/abs/2503.19165