ERAF4XRD: A multimodal agentic framework for constructing validated experimental X-ray diffraction databases from scientific literature
Abstract
The scientific literature contains decades of experimental measurements that remain difficult to access as structured data for modern AI and data-driven research. Much of this information is distributed across figures, captions, text, and tables, requiring experimental data and their context to be identified, connected, and verified before they can be reused. Here we introduce ERAF4XRD (Experiment Reader Agentic Framework for X-Ray Diffraction), a fully automated multimodal (i.e., image and text), multi-agent framework that reconstructs validated X-ray diffraction (XRD) records from scientific publications. ERAF4XRD downloads and screens documents, identifies XRD figures, extracts and links metadata to the corresponding experimental data, and validates outputs against source evidence using an independent validation agent. On a manually curated benchmark of 273 scientific publications containing 3,150 candidate figures, ERAF4XRD achieved up to 98.7% accuracy for XRD figure identification and generated 1,400 metadata values across 22 fields. Independent manual assessment of the final validated records yielded 98.5% precision and 90.7% recall, with no unsupported metadata observed among 443 evaluated fields. By moving beyond information extraction to the reconstruction and validation of linked experimental records, ERAF4XRD establishes an automated approach for transforming published scientific information into machine-readable experimental datasets for AI and data-driven science.
Related
- A self-learning scientific agent for X-ray diffraction
- AI's Capability in Assisting Scientific Research in Physics, Astrophysics, and Cosmology I: Literature Review
- Mined from Scientific Literature: Process Schemas for Atomic Layer Deposition and Etching in Materials Science
- A Hybrid Quantum Neural Network to Analyse Big Experimental Powder X-ray Diffraction Data
- Agentic schema-guided extraction of materials process knowledge from scientific literature
BibTeX
@misc{mostafa2026eraf4xrd,
title = {{ERAF4XRD: A multimodal agentic framework for constructing validated experimental X-ray diffraction databases from scientific literature}},
author = {Afnan Mostafa and William Ratcliff and Simon J. L. Billinge and Niaz Abdolrahim},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.18583},
eprint = {2609.18583},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.18583},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - ERAF4XRD: A multimodal agentic framework for constructing validated experimental X-ray diffraction databases from scientific literature
AU - Afnan Mostafa
AU - William Ratcliff
AU - Simon J. L. Billinge
AU - Niaz Abdolrahim
PY - 2026
DA - 2026/09/17
PB - arXiv
DO - 10.48550/arxiv.2609.18583
UR - https://arxiv.org/abs/2609.18583
AB - The scientific literature contains decades of experimental measurements that remain difficult to access as structured data for modern AI and data-driven research. Much of this information is distributed across figures, captions, text, and tables, requiring experimental data and their context to be identified, connected, and verified before they can be reused. Here we introduce ERAF4XRD (Experiment Reader Agentic Framework for X-Ray Diffraction), a fully automated multimodal (i.e., image and text), multi-agent framework that reconstructs validated X-ray diffraction (XRD) records from scientific publications. ERAF4XRD downloads and screens documents, identifies XRD figures, extracts and links metadata to the corresponding experimental data, and validates outputs against source evidence using an independent validation agent. On a manually curated benchmark of 273 scientific publications containing 3,150 candidate figures, ERAF4XRD achieved up to 98.7% accuracy for XRD figure identification and generated 1,400 metadata values across 22 fields. Independent manual assessment of the final validated records yielded 98.5% precision and 90.7% recall, with no unsupported metadata observed among 443 evaluated fields. By moving beyond information extraction to the reconstruction and validation of linked experimental records, ERAF4XRD establishes an automated approach for transforming published scientific information into machine-readable experimental datasets for AI and data-driven science.
ER -