AI RESEARCH
DAGverse: Building Document-Grounded Semantic DAGs from Scientific Papers
arXiv CS.AI
•
ArXi:2603.25293v1 Announce Type: new Directed Acyclic Graphs (DAGs) are widely used to represent structured knowledge in scientific and technical domains. However, datasets for real-world DAGs remain scarce because constructing them typically requires expert interpretation of domain documents. We study Doc2SemDAG construction: recovering a preferred semantic DAG from a document together with the cited evidence and context that explain it.