NuGraph2 with explainability: post-hoc explanations for geometric neural network predictions

With the growing popularity of artificial intelligence (AI) used for scientific applications, the ability of attribute a result to a reasoning process from the network is in high demand for robust scientific generalizations to hold. In this work we aim to motivate the need for and demonstrate the us...

Fuld beskrivelse

Bibliografiske detaljer

Principais autores:	M Voetberg, Vitor F Grizzi, V Hewes, Giuseppe Cerati, Hadi Meidani
Format:	Artigo
Sprog:	Inglês
Udgivet:	IOP Publishing 2026-01-01
Serier:	Machine Learning: Science and Technology
Fag:	explainable AI high energy physics graph neural networks neutrino physics LArTPC post-hoc explainability
Online adgang:	https://doi.org/10.1088/2632-2153/ae6a5d
Tags:	Tilføj Tag Ingen Tags, Vær først til at tagge denne postø!