AtomBench: a benchmarking framework for generative crystal reconstruction models in conventional superconductors

Digital Discovery 2026 Open access

Read full text
Authors: C.S. Campbell, Aldo Humberto Romero, Kamal Kumar Choudhary
DOI: 10.1039/d5dd00468c
Cited by: 0

Abstract

A key question in benchmarking generative crystal reconstruction models is how the amount and type of crystallographic information provided to a generative model affects its ability to reconstruct atomic structures.

Fields of Study & Subjects

Machine Learning in Materials Science Advanced Electron Microscopy Techniques and Applications X-ray Diffraction in Crystallography

Publication details

Journal / source
Digital Discovery
Volume
5
Issue
9
Pages
3916–3933
Publication date
1 January 2026
Language
EN