DCTracks: An Open Dataset for Machine Learning-Based Drift Chamber Track Reconstruction
This work provides a dataset and benchmarks for machine learning-based track reconstruction in particle physics, which is incremental as it builds on existing methods with new data and metrics.
The authors tackled the problem of drift chamber track reconstruction by introducing an open Monte Carlo dataset and defined metrics for standardized evaluation, reporting results for traditional algorithms and a Graph Neural Networks method to enable reproducible validation.
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.