DAGverse: Building Document-Grounded Semantic DAGs from Scientific Papers

2026-03-26

AI Summary

This work addresses the challenges of automatically constructing evidence-supported semantic directed acyclic graphs (DAGs) from scientific papers, where graph structures are often implicit, evidential support is scattered across text, and concepts exhibit polysemous abstractions. To tackle these issues, we propose DAGverse, a novel framework that leverages scientific papers containing explicit DAG illustrations as supervision signals. Through integrated graph classification, structure reconstruction, semantic anchoring, and expert validation, DAGverse constructs document-anchored semantic DAGs. We introduce DAGverse-1, a dataset comprising 108 expert-validated causal DAGs with multi-granular evidence traces in text, equations, and figure captions, alongside a scalable semi-automatic construction paradigm. Experiments demonstrate that our approach outperforms existing vision-language models on DAG classification and annotation tasks.

Technology Category

• Reasoning under Uncertainty: Graphical Models
• Knowledge Representation and Reasoning: Computational Complexity of Reasoning
• Computer Vision: Visual Reasoning & Symbolic Representations

Application Category

• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Web Mining and Content Analysis: Bridging structured and unstructured data

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 semantic DAGs from online scientific papers. Its core component, DAGverse-Pipeline, is a semi-automatic system designed to produce high-precision semantic DAG examples through figure classification, graph reconstruction, semantic grounding, and validation. As a case study, we test the framework for causal DAGs and release DAGverse-1, a dataset of 108 expert-validated semantic DAGs with graph-level, node-level, and edge-level evidence. Experiments show that DAGverse-Pipeline outperforms existing Vision-Language Models on DAG classification and annotation. DAGverse provides a foundation for document-grounded DAG benchmarks and opens new directions for studying structured reasoning grounded in real-world evidence.

Problem

• semantic DAG
• document grounding
• scientific papers
• structured knowledge
• evidence extraction

Innovation

• semantic DAG
• document-grounded reasoning
• graph reconstruction
• scientific knowledge extraction
• vision-language modeling