arXiv:2512.07420v2 Announce Type: cross Abstract: The identification and classification of collimated particle sprays, or jets, are essential for interpreting data from high-energy collider experiments. While deep learning has improved jet classification, it often lacks interpretability. We introduce the Explainable Particle Chebyshev Network (E-PCN), a graph neural network extending the Particle Chebyshev Network (PCN). E-PCN integrates kinematic variables into jet classification by constructing four graph representations per jet, each weighted by a distinct variable: angular separation ($\De
The continuous advancements in deep learning and the increasing complexity of high-energy physics data necessitate more sophisticated yet interpretable classification methods.
Improving the interpretability of AI models for complex scientific data, such as jet tagging in particle physics, enhances experimental validation and accelerates scientific discovery.
This research introduces a method for jet classification that combines high performance with explainability, potentially making AI applications in fundamental science more trustworthy and debuggable.
- · High-energy physics researchers
- · AI interpretability researchers
- · Developers of graph neural networks
- · AI models lacking interpretability
More accurate and explainable identification of particle events in collider experiments becomes possible.
The methodology could be adapted to other scientific domains requiring both high classification accuracy and model interpretability.
Increased trust in AI-driven scientific discovery, potentially accelerating the pace of breakthroughs in fundamental physics.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.LG