The rapid expansion of scientific literature presents significant challenges in efficiently verifying claims and synthesizing evidence. Valsci addresses this issue by providing an open-source, self-hostable utility that automates scientific claim verification through retrieval-augmented generation (RAG). By integrating actual excerpts from academic literature and bibliometric scoring (H-index, citation counts, journal impact), Valsci significantly reduces citation errors and improves verification accuracy.
Valsci efficiently handles hundreds of claims per hour, making it ideal for large-scale systematic reviews, meta-analyses, and hypothesis validation in bioinformatics, computational biology, and related disciplines.
Details described in the following publication:
Edelman, B, Skolnick J. In Press. Valsci: An Open-Source, Self-Hostable Literature Review Utility for Automated Large-Batch Scientific Claim Verification Using Large Language Models. BMC Bioinformatics: 26: 140. https://doi.org/10.1186/s12859-025-06159-4. PDF
Source Code
The source code of Valsci is freely available on GitHub under the GNU General Public License (GPL) v3.
Data Set
Valsci uses datasets accessible via the Semantic Scholar Open Research Corpus (S2ORC) and the Semantic Scholar API. Setup scripts and detailed instructions for data access are provided on the project’s GitHub repository.
Questions and Comments
Please direct questions and comments to: Brice Edelman and Jeffrey Skolnick.