MatSKRAFT: A framework for large-scale materials knowledge extraction from scientific tables
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918140022095872 |
|---|---|
| author | Hira, Kausik Zaki, Mohd Mausam Krishnan, N. M. Anoop |
| author_facet | Hira, Kausik Zaki, Mohd Mausam Krishnan, N. M. Anoop |
| contents | Scientific progress increasingly depends on synthesizing knowledge across vast literature, yet most experimental data remains trapped in semi-structured formats that resist systematic extraction and analysis. Here, we present MatSKRAFT, a computational framework that automatically extracts and integrates materials science knowledge from tabular data at unprecedented scale. Our approach transforms tables into graph-based representations processed by constraint-driven GNNs that encode scientific principles directly into model architecture. MatSKRAFT significantly outperforms state-of-the-art large language models, achieving F1 scores of 88.68 for property extraction and 71.35 for composition extraction, while processing data $19$-$496\times$ faster than them (compared to the slowest and the fastest models, respectively) with modest hardware requirements. Applied to nearly 69,000 tables from more than 47,000 research publications, we construct a comprehensive database containing over 535,000 entries, including 104,000 compositions that expand coverage beyond major existing databases, pending manual validation. This systematic approach reveals previously overlooked materials with distinct property combinations and enables data-driven discovery of composition-property relationships forming the cornerstone of materials and scientific discovery. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_10448 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MatSKRAFT: A framework for large-scale materials knowledge extraction from scientific tables Hira, Kausik Zaki, Mohd Mausam Krishnan, N. M. Anoop Information Retrieval Materials Science Scientific progress increasingly depends on synthesizing knowledge across vast literature, yet most experimental data remains trapped in semi-structured formats that resist systematic extraction and analysis. Here, we present MatSKRAFT, a computational framework that automatically extracts and integrates materials science knowledge from tabular data at unprecedented scale. Our approach transforms tables into graph-based representations processed by constraint-driven GNNs that encode scientific principles directly into model architecture. MatSKRAFT significantly outperforms state-of-the-art large language models, achieving F1 scores of 88.68 for property extraction and 71.35 for composition extraction, while processing data $19$-$496\times$ faster than them (compared to the slowest and the fastest models, respectively) with modest hardware requirements. Applied to nearly 69,000 tables from more than 47,000 research publications, we construct a comprehensive database containing over 535,000 entries, including 104,000 compositions that expand coverage beyond major existing databases, pending manual validation. This systematic approach reveals previously overlooked materials with distinct property combinations and enables data-driven discovery of composition-property relationships forming the cornerstone of materials and scientific discovery. |
| title | MatSKRAFT: A framework for large-scale materials knowledge extraction from scientific tables |
| topic | Information Retrieval Materials Science |
| url | https://arxiv.org/abs/2509.10448 |