Search for radiative leptonic decay D + → γe + ν e using deep learning * * This work is supported in part by National Key R&D Program of China (2020YFA0406400, 2023YFA1606000, 2020YFA0406300); National Natural Science Foundation of China (NSFC) (11635010, 11735014, 11935015, 11935016, 11935018, 12025502, 12035009, 12035013, 12061131003, 12192260, 12192261, 12192262, 12192263, 12192264, 12192265, 12221005, 12225509, 12235017, 12361141819); the Chinese Academy of Sciences (CAS) Large-Scale Scientific Facility Program; the CAS Center for Excellence in Particle Physics (CCEPP); Joint Large-Scale Scientific Facility Funds of the NSFC and CAS (U1832207); CAS (YSBR-101); 100 Talents Program of CAS; CAS Project for Young Scientists in Basic Research (YSBR-117); The Institute of Nuclear and Particle Physics (INPAC) and Shanghai Key Laboratory for Particle Physics and Cosmology; Agencia Nacional de Investigación y Desarrollo de Chile (ANID), Chile (ANID PIA/APOYO AFB230003); German Research Foundation DFG (FOR5327); Istituto Nazionale di Fisica Nucleare, Italy; Knut and Alice Wallenberg Foundation (2021.0174, 2021.0299); Ministry of Development of Turkey (DPT2006K-120470); National Research Foundation of Korea (NRF-2022R1A2C1092335); National Science and Technology fund of Mongolia; National Science Research and Innovation Fund (NSRF) via the Program Management Unit for Human Resources & Institutional Development, Research and Innovation of Thailand (B50G670107); Polish National Science Centre (2019/35/O/ST2/02907); Swedish Research Council (2019.04595); The Swedish Foundation for International Cooperation in Research and Higher Education (CH2018-7756); U. S. Department of Energy (DE-FG02-05ER41374)

Journal article

Using 20.3 fb–1 of annihilation data collected at a center-of-mass energy of 3.773 GeV with the BESIII detector, we report on an improved search for the radiative leptonic decay . An upper limit on its partial branching fraction for photon energies MeV was determined to be at a 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.

Authors: Ablikim, M; Achasov, MN; Adlarson, P; Ai, XC; Aliberti, R

• Publication status: Published
• Peer review status: Peer reviewed
• Publisher: IOP Publishing
• Journal: Chinese Physics C
• Volume: 49
• Issue: 8
• Article number: 083001
• Publication date: 2025-08-01
• DOI: 10.1088/1674-1137/adcdf3
• ISSN: 1674-1137
• Language: English
• Keywords: deep learning; BESIII experiment; charmed hadron; radiative leptonic decay