PaperPanorama

arXiv:2503.16070·v2·High Energy Physics — Experiment

Search for the radiative leptonic decay using Deep Learning

BESIII Collaboration: M. Ablikim · M. N. Achasov · P. Adlarson · X. C. Ai · R. Aliberti · A. Amoroso · Q. An · Y. Bai · O. Bakina · Y. Ban · H.-R. Bao · V. Batozskaya

PDFarXivINSPIREDOI

Abstract

Using 20.3 of annihilation data collected at a center-of-mass energy of 3.773 with the BESIII detector, we report an improved search for the radiative leptonic decay . An upper limit on its partial branching fraction for photon energies was determined to be at 90\% confidence level; this excludes most current theoretical predictions. A sophisticated deep learning approach, which includes thorough validation and is based on the Transformer architecture, was implemented to efficiently distinguish the signal from massive backgrounds.

Comments: 16 pages, 6 figures

Citation historyopen in Citation History ↗