Oct 2026· ACM/IEEE Joint Conference on Digital Libraries· pp. 1-5· 0 citations· 14 references
Computer Science
TL;DR
This work presents SciClaim2Explore, a system that turns statement-data links into entry points for natural-language exploration of research data supporting the claims conveyed by these statements, and evaluates the system on 84 claim-guided tasks from five scientific papers.
Abstract
Digital libraries provide access to research articles and related datasets and code, if available. However, even if a scientific statement is linked to supporting data, turning such relations into executable analyses requires separate workflows. This gap is increasingly urgent as computational reproducibility remains an imperative. Building on the TIB Knowledge Loom, which links scientific statements to supporting evidence, we present SciClaim2Explore, a system that turns statement-data links into entry points for natural-language exploration of research data supporting the claims conveyed by these statements. Starting from a selected scientific statement, in the proposed system a user asks a query about underlying linked, tabular data. The system uses the statement and schema context to generate and execute SQL, returns the resulting data table and, when appropriate, a data visualization. We evaluate the system on 84 claim-guided tasks from five scientific papers: 37 reproduce reported analytical results and 47 pose new analytical questions on the underlying data. In the grounding ablation, linked-dataset scoping reduces wrong-dataset queries from 14.3–28.6% to 0% and improves Answer Accuracy across three cloud models. These results suggest how scientific evidence links can provide executable context for exploring research data beyond artifact discovery. The source code is publicly available in the project’s repository1. A video demonstrating the system is also publicly available 2.
Scientific discovery from the literature requires assessing connections among findings obtained under different study conditions. Source attribution makes individual findings traceable, but does not determine what they jointly support. We introduce GI-TraceBench, a benchmark of 10,282 questions in gastrointestinal onco...
Jing-Xuan Wei, Song Tan, Xiao-Han Liu et al.· 0 citations
Scientific data selection is typically driven by relevance or utility scores, providing limited insight into why a document is retained. We introduce SciGraphSelect, a reference-grounded framework for auditable scientific data selection. SciGraphSelect organizes domain-specific knowledge, reusable reasoning operations,...
Mihyeon Kim, Ji-Eun Han, Eunkyeong Lee et al.· 0 citations
Understanding and reusing software repositories is a fundamental challenge in modern scientific research. While existing tools such as RepoSim4Py and RepoSnipy can identify semantically related repositories, they lack the interpretability required for researchers to assess architectural choices or execution requirement...
Hong-Lin Zhang, Lei Fang, Juan Ye et al.· eScience· 0 citations
Extracting structured information from scientific literature (e.g., in life sciences) is a considerably valuable and knowledge-intensive task. Relevant target information is often highly context-sensitive and scattered across unstructured, heterogeneous documents spanning text, tables, figures, and supplementary materi...
Diana Martínez-Minguet, Carlo Alberto Bono, A. García S. et al.· Proceedings of the 35th ACM...· 0 citations
This work builds four modules (for drug-discovery chemistry, materials science, machine learning, and mineral geochemistry) in the ArticleMiner framework, and evaluates them on 163 papers, including a new geochemistry benchmark with expert-curated ground truth.
Md Abrar Jahin, Craig A. Knoblock, Jay Pujara· arXiv.org· 2 citations
The experiments showed that participants perceived correct data claims to be more accurate with citations when compared with no explanations, and that they perceived incorrect data claims to be less accurate with citations when compared with code and no explanations.
Po-Ming Law, Jian-Heng Ouyang, Nguyen-Truong Thinh et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.