Metraipolis › archive › dc_4c48aff290ce
Agentic schema-guided extraction of materials process knowledge from scientific literature — arXiv:2610.06322
- Source
- arXiv
- Original
- https://arxiv.org/abs/2610.06322
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T05:27:35.971Z
- SHA-256 of the archived text
45011a6a3554c15fda96f72b0d41f9265384c949fac28e0ccdb7db7bfb5313d2- Stable URL of this page
https://metraipolis.com/documento/dc_4c48aff290ce
How to cite
Agentic schema-guided extraction of materials process knowledge from scientific literature — arXiv:2610.06322 — arXiv, https://arxiv.org/abs/2610.06322 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4c48aff290ce (Metraipolis archive dc_4c48aff290ce, sha256 45011a6a3554c15fda96f72b0d41f9265384c949fac28e0ccdb7db7bfb5313d2)
BibTeX
@misc{dc4c48aff290ce,
title = {Agentic schema-guided extraction of materials process knowledge from scientific literature — arXiv:2610.06322},
howpublished = {arXiv},
url = {https://arxiv.org/abs/2610.06322},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4c48aff290ce; sha256 45011a6a3554c15fda96f72b0d41f9265384c949fac28e0ccdb7db7bfb5313d2},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.06322. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Materials literature contains detailed experimental knowledge, but procedures, chemical entities and measurements remain difficult to aggregate because they are reported in heterogeneous forms and depend on process-specific context. We present SciKGExtract, a schema-guided framework that combines large-language-model extraction with chemical normalization and agent-based evaluation and refinement before knowledge-graph integration. We evaluate the framework on 176 atomic-layer-deposition papers describing zinc oxide (ZnO) and indium--gallium--zinc oxide (IGZO), together with an expert-annotated full-schema subset. PubChem normalization improves exact-match extraction F1 for every tested model. For ZnO, the best F1 increases from 0.591 for direct normalized extraction to 0.805 with agentic refinement, whereas the best IGZO result is 0.344, revealing the greater difficulty of multicomponent supercycle processes. Evaluation against a deeply nested schema containing 65 experimental properties and 155 quantitative measurement nodes further exposes errors in process segmentation and numerical assignment. These results show that chemical canonicalization and targeted agentic verification provide complementary controls for converting complex materials literature into reusable, machine-actionable experimental knowledge. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Computation and Language (cs.CL) ; Materials Science (cond-mat.mtrl-sci); Artificial Intelligence (cs.AI); Digital Libraries (cs.DL); Emerging Technologies (cs.ET). Pagina del lavoro: https://arxiv.org/abs/2610.06322 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-06T05:24:06.144Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).