Diagnosing and narrowing the simulation-to-real gap in powder X-ray diffraction with a wet-dry agentic loop
Abstract
Powder X-ray diffraction (PXRD) is the routine probe of crystalline matter, yet its analysis is the rate-limiting step as laboratories automate acquisition. Deep-learning analyzers excel on simulated patterns and degrade on measured ones. This simulation-to-real gap is structural, not additive: synthetic denoising gives no measurable lift on real spectra, whereas correcting a small peak-position drift more than doubles median retrieval correlation. Real-spectrum fine-tuning, peak-aligned reranking, and recalibration narrow what remains and restore the coverage synthetic anchors lose. Xtalyst integrates these in an agent-orchestrated system spanning phase identification, refinement, and calibrated property prediction. On a frozen held-out partition (n=534) each module measured on both splits reproduces its development finding -- including the synthetic-anchor under-coverage, whose magnitude differs between the two pools -- while held-out refinement converges and preserves symmetry without reaching profile-quality fits, and on a diffractometer its wet-dry recommend-rescan-reanalyze loop flips a blinded silicon standard to a gated PASS and changes which minor phase is resolved on a multi-metal alloy.
Related
- X2SBench: an open benchmark for evaluating crystal structure determination from powder diffraction
- Machine learning magnetic interactions from neutron powder diffraction data
- Differentiable powder X-ray diffraction enables analysis of evolving structures
- A Hybrid Quantum Neural Network to Analyse Big Experimental Powder X-ray Diffraction Data
- PXtal: Learning to Align Powder X-Ray Diffraction and Crystal Structures under Information Asymmetry across Modalities
BibTeX
@misc{wang2026diagnosing,
title = {{Diagnosing and narrowing the simulation-to-real gap in powder X-ray diffraction with a wet-dry agentic loop}},
author = {Shaoguang Wang and Weiyu Guo and Ben Fei and Xiaohong Shao and Zhihui Wang and Wanli Ouyang},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2608.22400},
eprint = {2608.22400},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2608.22400},
}
RIS
TY - UNPB
TI - Diagnosing and narrowing the simulation-to-real gap in powder X-ray diffraction with a wet-dry agentic loop
AU - Shaoguang Wang
AU - Weiyu Guo
AU - Ben Fei
AU - Xiaohong Shao
AU - Zhihui Wang
AU - Wanli Ouyang
PY - 2026
DA - 2026/09/06
PB - arXiv
DO - 10.48550/arxiv.2608.22400
UR - https://arxiv.org/abs/2608.22400
AB - Powder X-ray diffraction (PXRD) is the routine probe of crystalline matter, yet its analysis is the rate-limiting step as laboratories automate acquisition. Deep-learning analyzers excel on simulated patterns and degrade on measured ones. This simulation-to-real gap is structural, not additive: synthetic denoising gives no measurable lift on real spectra, whereas correcting a small peak-position drift more than doubles median retrieval correlation. Real-spectrum fine-tuning, peak-aligned reranking, and recalibration narrow what remains and restore the coverage synthetic anchors lose. Xtalyst integrates these in an agent-orchestrated system spanning phase identification, refinement, and calibrated property prediction. On a frozen held-out partition (n=534) each module measured on both splits reproduces its development finding -- including the synthetic-anchor under-coverage, whose magnitude differs between the two pools -- while held-out refinement converges and preserves symmetry without reaching profile-quality fits, and on a diffractometer its wet-dry recommend-rescan-reanalyze loop flips a blinded silicon standard to a gated PASS and changes which minor phase is resolved on a multi-metal alloy.
ER -