Shiwen Xu | Search arXiv

arXiv2026

Detailed investigation on the Geant4 simulation of alpha particles in liquid scintillator detector

Purpose: Alpha particles from $^{214}$Po, $^{212}$Po, and $^{210}$Po are increasingly used to calibrate large liquid scintillator detectors, but Geant4 simulations of their energy deposition require detailed validation. Methods: We simulate alpha particles in a 4 m cube of LAB-based liquid scintillator with Geant4 11.4.2 and apply Birks quenching per step. We study step-size, production-threshold, Birks-constant, and electromagnetic-model dependence, and use Geant4-DNA to examine keV-scale electron track structure. Results: Delta-electron-associated fluctuations dominate the simulated response. Across the tested explicit-delta settings, the variance of the quenched-response contribution from secondary tracks is 1.01--1.12 times the total variance; a negative primary--secondary covariance reduces the total. The simulated quenching-curve shape is compatible with SNO+ data within current uncertainties, with $χ^2/\mathrm{ndf}\simeq0.14$--$0.17$ for $k_B=0.007$--$0.010$ g cm$^{-2}$ MeV$^{-1}$. Geant4-DNA gives strong electron-track curvature, with tortuosity decreasing from about 6 at 200 eV to 1.6 at 10 keV. Conclusion: Delta-electron fluctuations are the dominant contribution to the intrinsic resolution in the tested configurations. The production threshold has a larger effect than the electromagnetic model: Penelope and Livermore agree within about 3% in L/E, whereas Standard gives higher L/E, especially at low thresholds.

hep-ex↗

arXiv2025

Player-Team Heterogeneous Interaction Graph Transformer for Soccer Outcome Prediction

Predicting soccer match outcomes is a challenging task due to the inherently unpredictable nature of the game and the numerous dynamic factors influencing results. While it conventionally relies on meticulous feature engineering, deep learning techniques have recently shown a great promise in learning effective player and team representations directly for soccer outcome prediction. However, existing methods often overlook the heterogeneous nature of interactions among players and teams, which is crucial for accurately modeling match dynamics. To address this gap, we propose HIGFormer (Heterogeneous Interaction Graph Transformer), a novel graph-augmented transformer-based deep learning model for soccer outcome prediction. HIGFormer introduces a multi-level interaction framework that captures both fine-grained player dynamics and high-level team interactions. Specifically, it comprises (1) a Player Interaction Network, which encodes player performance through heterogeneous interaction graphs, combining local graph convolutions with a global graph-augmented transformer; (2) a Team Interaction Network, which constructs interaction graphs from a team-to-team perspective to model historical match relationships; and (3) a Match Comparison Transformer, which jointly analyzes both team and player-level information to predict match outcomes. Extensive experiments on the WyScout Open Access Dataset, a large-scale real-world soccer dataset, demonstrate that HIGFormer significantly outperforms existing methods in prediction accuracy. Furthermore, we provide valuable insights into leveraging our model for player performance evaluation, offering a new perspective on talent scouting and team strategy analysis.

cs.LG↗