Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

DAGverse: Building Document-Grounded Semantic DAGs from Scientific Papers

Shu Wan, Saketh Vishnubhatla, Iskander Kushbay, Tom Heffernan, Aaron Belikoff, Raha Moraffah, Huan Liu

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.

DAGverse: Building Document-Grounded Semantic DAGs from Scientific Papers

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.

Paper Structure

This paper contains 22 sections, 1 equation, 5 figures, 4 tables.

Table of Contents

  1. Introduction
  2. Problem Setting
  3. Scientific Papers with DAG Figures
  4. DAGverse-Pipeline
  5. Dataset Validation
  6. Human Expert Validation
  7. LLM-as-a-Judge for Scalable Validation
  8. Experiments
  9. RQ1: Pipeline Effectiveness
  10. RQ2: Pipeline Robustness Across Sources
  11. DAGverse-1: A Dataset of Document-Grounded Causal DAGs
  12. Intended Use and Applications
  13. Related Work
  14. Graph–Text Paired Datasets
  15. Causal DAG Datasets
  16. ...and 7 more sections

Figures (5)

  • Figure 1: Constructing a semantic DAG (Appendix \ref{['app:semantic-dag']}) from a scientific paper STROBL2024104585.
  • Figure 2: Overview of DAGverse-Pipeline. Paper collection can be updated routinely.
  • Figure 3: Validation interface artifacts used by experts. Left: reconstructed DAG view for structure checking. Right: evidence panel for node and edge grounding checks.
  • Figure 4: DAGverse-1 data card. The left panel summarizes key statistics, including node and edge summaries and the most frequent domain tags. The right panel visualizes the node and edge distribution by source, a domain word cloud, and a top domain count plot. We omit two general tags "Causal Inference" and "Machine Learning" in domain visualizations.
  • Figure 5: A single semantic DAG in DAGverse can be used in different ways. Using the cirrhosis example STROBL2024104585, we demonstrate 3 tasks: text-to-graph recovery from grounded evidence, graph-to-text generation of a coherent causal narrative, and causal question answering over graph structure and semantics.

Theorems & Definitions (4)

  • definition 1: Semantic DAG
  • remark 1: Faithful vs. Factual
  • remark 2: Preferred Canonicalization
  • remark 3: DAG Scope