A literature-guided descriptor-based framework for filtering composition search spaces
Abstract
Scientific literature contains latent knowledge about materials behavior, but much of this knowledge is expressed through words, contexts, and recurring associations rather than explicit design principles. This raises a central question: how can large-scale scientific corpora be used for practical problems in materials discovery? Here, we present a literature-guided descriptor-based filtering framework for reducing composition search spaces. For a given performance metric, the framework selects two descriptors from a filtered vocabulary in a literature-trained word embedding model and uses the selected descriptors to construct a Pareto-based filter for candidate compositions. Across the evaluated performance metrics and composition search spaces, the framework filters out an average of 74.27\% of the candidate compositions, with an average best-value error of 1.93\% relative to experimental measurements. Compared with expert-chosen and random descriptors, our performance metric-dependent descriptors provide a more controlled balance between retained fraction and best-value error. These results show that literature-derived embeddings can support intuitive and reproducible filters for narrowing candidate composition spaces while preserving high-performing compositions.
Related
- An Open-Source Data Infrastructure for Alloy Synthesis Research: Stage 1 --- Composition Screening and Literature Cross-Referencing
- Agentic schema-guided extraction of materials process knowledge from scientific literature
- Information limits of photonic lantern wavefront sensing: a Fisher- and quantum-Fisher-information framework and its relation to Fourier-filtering sensitivity limits
- SVD-guided hybrid optimization framework for ab initio aspheric optical design
- ERAF4XRD: A multimodal agentic framework for constructing validated experimental X-ray diffraction databases from scientific literature
BibTeX
@misc{zhang2026literatureguided,
title = {{A literature-guided descriptor-based framework for filtering composition search spaces}},
author = {Lei Zhang and Markus Stricker},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.31650},
eprint = {2609.31650},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.31650},
note = {CC BY-SA 4.0},
}
RIS
TY - UNPB
TI - A literature-guided descriptor-based framework for filtering composition search spaces
AU - Lei Zhang
AU - Markus Stricker
PY - 2026
DA - 2026/09/14
PB - arXiv
DO - 10.48550/arxiv.2609.31650
UR - https://arxiv.org/abs/2609.31650
AB - Scientific literature contains latent knowledge about materials behavior, but much of this knowledge is expressed through words, contexts, and recurring associations rather than explicit design principles. This raises a central question: how can large-scale scientific corpora be used for practical problems in materials discovery? Here, we present a literature-guided descriptor-based filtering framework for reducing composition search spaces. For a given performance metric, the framework selects two descriptors from a filtered vocabulary in a literature-trained word embedding model and uses the selected descriptors to construct a Pareto-based filter for candidate compositions. Across the evaluated performance metrics and composition search spaces, the framework filters out an average of 74.27\% of the candidate compositions, with an average best-value error of 1.93\% relative to experimental measurements. Compared with expert-chosen and random descriptors, our performance metric-dependent descriptors provide a more controlled balance between retained fraction and best-value error. These results show that literature-derived embeddings can support intuitive and reproducible filters for narrowing candidate composition spaces while preserving high-performing compositions.
ER -