Search for the radiative leptonic decay $D^{+}\to {\hat{I}}^3{e}^{+}\hat{I}{½}_e$ using Deep Learning

Abstract

Using 20.3$\mathrm{f}{\mathrm{b}}^{-1}$ of $e^{+}{e}^{-}$ annihilation data collected at a center-of-mass energy of 3.773$\mathrm{GeV}$ with the BESIII detector, we report an improved search for the radiative leptonic decay $D^{+}\to {\hat{I}}^3{e}^{+}\hat{I}{½}_e$. An upper limit on its partial branching fraction for photon energies $E_{\hat{I}}^3>10\mathrm{MeV}$ was determined to be $1.2\times 10^{-5}$ 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.

16 pages, 6 figures