ICJ decision documents linked to cases and laws in layered citation graph
ICJ-Graph: A Citation Graph and a Layered Document Corpus of the International Court of Justice
Computation and Language
Summary
Legal documents from the International Court of Justice and related bodies are connected in a big digital map that keeps court decisions separate from lawyer submissions. The creators collected over 6,000 ICJ documents plus related court rulings and legal rules, linking them all so computers can read and compare the information. They also made tools that help predict which legal cases or rules a given court decision will cite using only data available before that decision. They found that using special citation research tools helps computers better guess citations in court decisions.
What this means in practice
- •For legal tech developers: Build retrieval systems that navigate ICJ documents and related legal references for faster, context-aware legal research.
- •For court archive managers: Organize, link, and enrich court document collections with citation graphs to improve accessibility and legal reasoning traceability.
Authors
Jirameth Wannasiwaporn, Pawitsapak Akarajaradwong, Chompakorn Chaksangchaichot
Abstract
We present ICJ-Graph, a machine-readable resource connecting documents of the International Court of Justice (ICJ) to cited cases, legal provisions and United Nations resolutions. Court decisions, written pleadings and oral records form distinct document layers, preserving the distinction between the Court's reasoning and the parties' submissions. The collection contains 6,396 ICJ documents and 505 documents from other courts and legal bodies, together with 12,375 provisions and 20,291 UN resolutions. The data files contain text, metadata and embeddings. The accompanying pipeline lets users load the graph and generate embeddings for use in their own retrieval systems. To illustrate the resource's use, we evaluate five models on citation prediction for 199 decisions using documents available before each decision. Tools designed for citation research improve citation-prediction F1 over answering without tools for all five models across case, provision and resolution citations.