cs.AIOct 30, 2026

SciGraphSelect: Auditable Scientific Data Selection through Knowledge--Reasoning Graphs

Authors: MiHyeon Kim, Ji-Eun Han, Eunkyeong Lee, Jeehyun Lim, Hwijung Ryu

Organizations: KT Corporation

Abstract

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, and reference-attested relations into a typed knowledge--reasoning graph, then scores candidate documents using concept coverage, relation and path co-support, and directional alignment. To avoid over-interpreting document embeddings, rich relational structure is preserved on the reference side while candidate-side evidence is treated conservatively without assuming relation entailment. By exposing the reference-grounded evidence behind each selection, SciGraphSelect brings traceability to the upstream construction of scientific training corpora and complements downstream scientific verification.

Figures & tables

Appendix figures & tables10 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. GRAFT: Graph-Distilled Generative Retrieval for Facet-Aware Scientific Literature Exploration

    Aug 23, 2026Italo Luis da Silva, Hanqi Yan, Yujing Wang +3Scientific Document RetrievalInformation Retrieval

  2. SciDocBench: A Workflow-Centered Benchmark and Data Pipeline for Scientific Document Understanding

    Sep 4, 2026Shenxi Wu, Yuhong Liu, Haosong Zhang +8Document UnderstandingLLM Evaluation