Reproduce “SeDa: A Unified System for Dataset Discovery and Multi-Entity Augmented Semantic Exploration” on OpenResearch

Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.

Universal app for Apple silicon and Intel. Requires macOS 11 or later.

About this paper

Kan Ling, Zhen Qin, Yichi Zhu, Hengrun Zhang, Huiqun Yu, Guisheng Fan

SeDa builds standardized dataset records from more than 200 platforms, adding topic tags, link checks, and connections to related datasets and organizations. It combines metadata search with navigation, not dataset-content search. From March to August 2025, it identified 3,047 newly found records, versus 622 for ChatPD and 1,639 for Google Dataset Search: a platform comparison, not an exhaustive coverage test.

Summary by alphaXiv.

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.