SciPost Submission Page
Reconstructing hadronically decaying tau leptons with a jet foundation model
by Laurits Tani, Joosep Pata, Joschka Birk
Submission summary
| Authors (as registered SciPost users): | Laurits Tani |
| Submission information | |
|---|---|
| Preprint Link: | https://arxiv.org/abs/2503.19165v1 (pdf) |
| Code repository: | https://doi.org/10.5281/zenodo.15005034 |
| Data repository: | https://doi.org/10.5281/zenodo.12664634 |
| Date submitted: | 2025-03-26 10:30 |
| Submitted by: | Tani, Laurits |
| Submitted to: | SciPost Physics Core |
| Ontological classification | |
|---|---|
| Academic field: | Physics |
| Specialties: |
|
| Approach: | Experimental |
Abstract
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-$\alpha$, 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 $\tau$ 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.