English

Decoding the proton's gluonic density with lattice QCD-informed machine learning

High Energy Physics - Phenomenology 2025-07-25 v1 High Energy Physics - Lattice Nuclear Theory

Abstract

We present a first machine learning-based decoding of the gluonic structure of the proton from lattice QCD using a variational autoencoder inverse mapper (VAIM). Harnessing the power of generative AI, we predict the parton distribution function (PDF) of the gluon given information on the reduced pseudo-Ioffe-time distributions (RpITDs) as calculated from an ensemble with lattice spacing a ⁣ ⁣0.09a\! \approx\! 0.09 fm and a pion mass of Mπ ⁣ ⁣310M_\pi\! \approx\! 310 MeV. The resulting gluon PDF is consistent with phenomenological global fits within uncertainties, particularly in the intermediate-to-high-xx region where lattice data are most constraining. A subsequent correlation analysis confirms that the VAIM learns a meaningful latent representation, highlighting the potential of generative AI to bridge lattice QCD and phenomenological extractions within a unified analysis framework.

Keywords

Cite

@article{arxiv.2507.17810,
  title  = {Decoding the proton's gluonic density with lattice QCD-informed machine learning},
  author = {Brandon Kriesten and Alex NieMiera and William Good and T. J. Hobbs and Huey-Wen Lin},
  journal= {arXiv preprint arXiv:2507.17810},
  year   = {2025}
}

Comments

7 pages, 3 figures

R2 v1 2026-07-01T04:15:51.872Z