Metraipolis › archive › dc_065befadad2f
CodeGraph: Open-Taxonomy Knowledge Graph for Source Code with Wikidata Grounding — arXiv:2609.29474
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.29474
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T04:50:12.434Z
- SHA-256 of the archived text
a83a3ce49403f9a1dcc6dbedf4c965040acf4b70553c6344a2593cf4b2591e88- Stable URL of this page
https://metraipolis.com/documento/dc_065befadad2f
How to cite
CodeGraph: Open-Taxonomy Knowledge Graph for Source Code with Wikidata Grounding — arXiv:2609.29474 — arXiv (en), https://arxiv.org/abs/2609.29474 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_065befadad2f (Metraipolis archive dc_065befadad2f, sha256 a83a3ce49403f9a1dcc6dbedf4c965040acf4b70553c6344a2593cf4b2591e88)
BibTeX
@misc{dc065befadad2f,
title = {CodeGraph: Open-Taxonomy Knowledge Graph for Source Code with Wikidata Grounding — arXiv:2609.29474},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.29474},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_065befadad2f; sha256 a83a3ce49403f9a1dcc6dbedf4c965040acf4b70553c6344a2593cf4b2591e88},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.29474. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Public software repositories, like GitHub and Software Heritage Archive, store billions of files, yet extracting their implicit engineering knowledge ---i.e., the algorithms they implement, the paradigms they follow, the patterns they instantiate, and the application domains they serve--- remains challenging, as current tools are constrained to syntactic and token-level analysis. We present a pipeline for building an open-taxonomy semantic annotation of source code using a code-specialised Large Language Model. The extracted entities are grounded in Wikidata through a three-stage linking procedure: a deterministic SPARQL stage handles unambiguous entities, a Deep Research Agent resolves the residual long tail, and a hierarchy-rollup stage imports the parent-of closure of each resolved Wikidata identifier. The resulting annotations are materialised as a source-code-specific open-taxonomy knowledge graph. We further introduce a calibrated quality-assurance protocol that quantifies annotation precision by combining a small human gold set with an LLM-as-a-judge filter. We applied our pipeline to the 167 million files of the Stack-Edu corpus, creating the first known large-scale open-taxonomy knowledge graph for source code. Our graph, named CodeGraph, contains approximately 158 million nodes, which include around 145 million files, about 63,000 extracted concept entities (such as algorithms, paradigms, design patterns, and application domains), and roughly 19,800 grounded Wikidata entities. Furthermore, CodeGraph features approximately 1 billion typed edges that connect files to their respective concepts, link these concepts to their grounded Wikidata identifiers, and relate them to their parent categories, covering 14 programming languages. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-25 in cs.CL). Categorie arXiv: Software Engineering (cs.SE) ; Computation and Language (cs.CL); Information Retrieval (cs.IR). Pagina del lavoro: https://arxiv.org/abs/2609.29474 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-08T04:27:20.159Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).