We introduce a Monte Carlo (MC) dataset of single- and two-track drift chamber events to advance Machine Learning (ML)-based track reconstruction. To enable standardized and comparable evaluation, we define track reconstruction specific metrics and report results for traditional track reconstruction algorithms and a Graph Neural Networks (GNNs) method, facilitating rigorous, reproducible validation for future research.
Cite
@article{arxiv.2602.14571,
title = {DCTracks: An Open Dataset for Machine Learning-Based Drift Chamber Track Reconstruction},
author = {Qian Liyan and Zhang Yao and Yuan Ye and Zhang Zhaoke and Fang Jin and Jiang Shimiao and Zhang Jin and Li Ke and Liu Beijiang and Xu Chenglin and Zhang Yifan and Jia Xiaoqian and Qin Xiaoshuai and Huang Xingtao},
journal= {arXiv preprint arXiv:2602.14571},
year = {2026}
}