EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Pretrained event classification model for high energy physics analysis

Joshua Ho, Ryan Roberts, Shuo Han, Haichen Wang

Journal of Instrumentation · 01.08.2026 · 21 (08) · P08006

DOI: 10.1088/1748-0221/21/08/p08006 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Instrumentation, online erschienen am 06.08.2026. Verfasst von Joshua Ho und 3 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We introduce a foundation model for event classification in high-energy physics, built on a Graph Neural Network architecture and trained on 120 million simulated proton-proton collision events spanning 12 distinct physics processes. The model is pretrained to learn a general and robust representation of collision data using challenging multiclass and multilabel classification tasks. Its performance is evaluated across seven event classification tasks, which include new physics processes not encountered during pretraining as well as ATLAS Open Data to demonstrate generalizability across different simulation frameworks, from Delphes fast simulation to full ATLAS detector simulation. Fine-tuning the pretrained model significantly improves classification performance, particularly in scenarios with limited training data, demonstrating gains in both accuracy and computational efficiency. To investigate the underlying mechanisms behind these performance improvements, we employ a representational similarity evaluation framework based on Centered Kernel Alignment. This analysis reveals that encoder-stage representations of the fine-tuned model remain similar to those of the baseline, while intermediate graph processing layers diverge substantially, indicating that fine-tuning preserves general-purpose encoders while developing fundamentally different message-passing pathways to arrive at superior task performance.

Zitieren

APA

Ho, J., Roberts, R., Han, S., & Wang, H. (2026). Pretrained event classification model for high energy physics analysis. Journal of Instrumentation, 21(08), P08006. https://doi.org/10.1088/1748-0221/21/08/p08006

Vancouver

Ho J, Roberts R, Han S, Wang H. Pretrained event classification model for high energy physics analysis. Journal of Instrumentation. 2026;21(08):P08006. doi:10.1088/1748-0221/21/08/p08006

BibTeX
@article{Ho2026,
  author = {Ho, Joshua and Roberts, Ryan and Han, Shuo and Wang, Haichen},
  title = {Pretrained event classification model for high energy physics analysis},
  journal = {Journal of Instrumentation},
  year = {2026},
  volume = {21},
  number = {08},
  pages = {P08006},
  doi = {10.1088/1748-0221/21/08/p08006}
}
Kostenlos starten →