Effective self-supervised learning (SSL) techniques have been key to unlocking large datasets for representation learning. While many promising methods have been developed using online corpora and captioned photographs, their application to scientific domains, where data encodes highly specialized knowledge, remains in its early stages. We present a self-supervised masked modeling framework for 3D particle trajectory analysis in Time Projection Chambers (TPCs). These detectors produce globally sparse (<1% occupancy) but locally dense point clouds, capturing meter-scale particle trajectories at millimeter resolution. Starting with PointMAE, this work proposes volumetric tokenization to group sparse ionization points into resolution-agnostic patches, as well as an auxiliary energy infilling task to improve trajectory semantics. This approach – which we call Point-based Liquid Argon Masked Autoencoder (PoLAr-MAE) – achieves 99.4% track and 97.7% shower classification F-scores, matching that of supervised baselines without any labeled data. While the model learns rich particle trajectory representations, it struggles with sub-token phenomena like overlapping or short-lived particle trajectories. To support further research, we release PILArNet-M – the largest open LArTPC dataset (1M+ events, 5.2B labeled points) – to advance SSL in high energy physics (HEP). Project site: this https URL
@misc{young2025particletrajectoryrepresentationlearning,title={Particle Trajectory Representation Learning with Masked Point Modeling},author={Young, Sam and Jwa, Yeon-jae and Terao, Kazuhiro},year={2025},eprint={2502.02558},archiveprefix={arXiv},primaryclass={hep-ex},}
The Optical Two- and Three-dimensional Fundamental Plane Correlations for Nearly 180 Gamma-Ray Burst Afterglows with Swift/UVOT, RATIR, and the Subaru Telescope
M. G. Dainotti, S. Young, L. Li, and
21 more authors
The Astrophysical Journal Supplement Series, Jul 2022
@article{ApJS.Dainotti2022,title={The Optical Two- and Three-dimensional Fundamental Plane Correlations for Nearly 180 Gamma-Ray Burst Afterglows with Swift/{UVOT}, {RATIR}, and the Subaru Telescope},author={Dainotti, M. G. and Young, S. and Li, L. and Levine, D. and Kalinowski, K. K. and Kann, D. A. and Tran, B. and Zambrano-Tapia, L. and Zambrano-Tapia, A. and Cenko, S. B. and Fuentes, M. and Sánchez-Vázquez, E. G. and Oates, S. R. and Fraija, N. and Becerra, R. L. and Watson, A. M. and Butler, N. R. and Gonzalez, J. J. and Kutyrev, A. S. and Lee, W. H. and Prochaska, J. X. and Ramirez-Ruiz, E. and Richer, M. G. and Zola, S.},doi={10.3847/1538-4365/ac7c64},url={https://dx.doi.org/10.3847/1538-4365/ac7c64},year={2022},month=jul,publisher={American Astronomical Society},volume={261},number={2},pages={25},journal={The Astrophysical Journal Supplement Series},}
Particle Trajectory Representation Learning with Masked Point Modeling2025