HyperTSRAG: Temporal-Spatial Reasoning over Hypergraph Knowledge Structures for Multimodal Retrieval-Augmented Generation

Zenodo (CERN European Organization for Nuclear Research) 2026 Dataset Open access

Read full text
Authors: Timothy Dillan
DOI: 10.5281/zenodo.18181183
Cited by: 0

Abstract

This dataset supports the evaluation of HyperTSRAG and baseline retrieval-augmented generation systems, comprising processed corpus data, annotated queries across five complexity categories (simple lookup, relationship discovery, temporal filtering, spatial reasoning, and complex multi-hop reasoning), hypergraph knowledge structures with entity and hyperedge nodes.

Publication details

Journal / source
Zenodo (CERN European Organization for Nuclear Research)
Publication date
25 April 2026
Document type
Dataset