Measurement of the singly Cabibbo-suppressed decay $\Lambda_c^+\to p\eta'$ with Deep Learning

TL;DR

This paper reports the first observation of the decay $Lambda_c^+ o p eta'$ using deep learning techniques to distinguish signal from background in electron-positron collision data, measuring its branching ratio relative to $Lambda_c^+ o p omega$.

Contribution

It introduces a Transformer-based deep learning classifier to improve signal-background separation in measuring the $Lambda_c^+ o p eta'$ decay, achieving a statistical significance of 3.4 sigma.

Findings

First observation of $Lambda_c^+ o p eta'$ decay.

Measured branching ratio relative to $Lambda_c^+ o p omega$ as 0.55 ± 0.22 (stat) ± 0.05 (syst).

Demonstrated effectiveness of deep learning in particle decay analysis.

Abstract

Using $4.5$ fb$^{-1}$ of $e^+e^-$ collision data collected with the BESIII detector at center-of-mass energies from 4.600 to 4.699 GeV, we report a measurement of the singly Cabibbo-suppressed decay $\Lambda_c^+ \to p\eta'$ with the single-tag method. To effectively distinguish the signal from the large backgrounds, we exploit a deep-learning classifier built on a Transformer-based neural network. Extensive validation and uncertainty quantification are carried out. The $\Lambda^+_c\to p\eta'$ signal is observed with a statistical significance of $3.4 \sigma$. The ratio of branching fractions of $\mathcal{B}{\Lambda^+_c\to p\eta'}/\mathcal{B}{\Lambda^+_c\to p\omega}$= $0.55\pm 0.22_{\rm{stat.}} \pm 0.05_{\rm{syst.}}$ is obtained, where the first uncertainty is statistical and the second systematic.