[2603.25293] DAGverse: Building Document-Grounded Semantic DAGs from Scientific Papers

Computer Science > Artificial Intelligence arXiv:2603.25293 (cs) [Submitted on 26 Mar 2026] Title:DAGverse: Building Document-Grounded Semantic DAGs from Scientific Papers Authors:Shu Wan, Saketh Vishnubhatla, Iskander Kushbay, Tom Heffernan, Aaron Belikoff, Raha Moraffah, Huan Liu View a PDF of the paper titled DAGverse: Building Document-Grounded Semantic DAGs from Scientific Papers, by Shu Wan and Saketh Vishnubhatla and Iskander Kushbay and Tom Heffernan and Aaron Belikoff and Raha Moraffah and Huan Liu View PDF HTML (experimental) Abstract: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. This problem is challenging because a document may admit multiple plausible abstractions, the intended structure is often implicit, and the supporting evidence is scattered across prose, equations, captions, and figures. To address these challenges, we leverage scientific papers containing explicit DAG figures as a natural source of supervision. In this setting, the DAG figure provides the DAG structure, while the accompanying text provides context and explanation. We introduce DAGverse, a framework for constructing document-grounded ...