GraphIV: a rich, open source, and updating citation graph of arXiv

GraphIV ("graph" + arXiv) is an open source, reproducible citation graph of all of arXiv, rebuilt every two weeks on a single PC. Each resolved citation between two arXiv papers is labeled with its intent, each paper carries an embedding and a place in a topic tree of 4,096 topics, and the whole graph is served as an MCP server that turns a question into a grounded literature review.

There are tens of thousands of papers released to arXiv each month, and even a single topic easily exceeds several hundred. LLM deep research tools take upwards of 30 minutes per question and often miss niche and recent publications, while the closest tool, consensus, still misses the newest papers and runs on proprietary algorithms. I built GraphIV to catch up with modern AI research using infrastructure anyone can host.

On top of the graph sit two algorithms of my own. BoundedField retrieves and ranks papers by where they sit in the citation graph, with no language model in the ranking, and LeyLine mines the lineages that led a field to where it is and the new papers that have already answered them.

Table of contents

• Using GraphIV

  • Live Demo

  • Reproduction

  • Self-hosting

• Components

  • Data

  • BoundedField

  • LeyLine

  • Pipeline

• Repository layout

• Future directions

• License and citation

Related MCP server: kiro-research-mcp

Using GraphIV

Live Demo

graphiv.kuroma.dev serves the dashboard over the reports my own server has written. Each report opens on six tabs: the report itself, its method table, its papers, the lineages as a citation graph, where its papers sit in the topic tree, and the run's details. The demo serves the dashboard alone, so asking a new question needs a server of your own, below.

Reproduction

Everything in GraphIV is rebuilt from public sources: arXiv's metadata snapshot on Kaggle, arXiv's own HTML and PDF files, and open weight models. The build is ten stages filling four tables, run in this order, and docs/preprocess.md is the runbook with what each stage reads and writes. To skip the build, docs/restore.md restores the published dump and serves from it.

uv run python scripts/papers_preprocess/stage0_fetch_source_json.py --dry-run   # what a new snapshot adds
uv run python scripts/papers_preprocess/stage0_fetch_source_json.py --no-fetch
uv run python scripts/papers_preprocess/stage1_download_pdf.py
uv run python scripts/papers_preprocess/stage2_download_html.py
uv run python scripts/papers_preprocess/stage3_embed_papers.py
uv run python scripts/papers_preprocess/stage4_label_survey.py
uv run python scripts/topic_tree_creation/stage0_umap.py
uv run python scripts/topic_tree_creation/stage1_create_topic_tree.py
uv run python scripts/topic_tree_creation/stage2_topic_labeling.py
uv run python scripts/citation_preprocess/stage0_create_citation.py --workers 16
uv run python scripts/citation_preprocess/stage1_label_citation.py

The two labelers the build loads are trained by scripts/citation_labeler/ and described on their cards, GraphIV-citation-intent and GraphIV-survey. The four retrieval benchmarks, defined in docs/benchmarks.md and published at GraphIV_benchmarks, are fit and rerun by scripts/recipe_tuning/, which writes every case and every ranking under experiments/retrieve/, and every figure on this page and on the cards is redrawn from those files by direnv exec . uv run python assets/run.py.

Self-hosting

GraphIV ships as an MCP server, which any agent that speaks MCP can drive, plus a dashboard over what it wrote. Everything below was measured on the one PC GraphIV runs on: a Ryzen 7 7700X, 64 GB of RAM and an RTX 3090 with 24 GB.

The store holds the citation sentences, which are each paper's own text, so it is not published as a dump, and the server tier needs a build of its own for now.

nix develop                                               # Python 3.13, uv, postgres17 with pgvector
uv sync
uv run python scripts/serve.py --http --role api          # the tools, at http://127.0.0.1:6767/mcp
uv run python scripts/serve.py --http --role frontend     # the dashboard, at http://127.0.0.1:6969
claude mcp add --transport http graphiv http://127.0.0.1:6767/mcp

On NixOS, services.graphiv runs the cluster, the server, the dashboard and the manager as units, and nix/README.md is its page. Every path, port and endpoint is a key of config.toml.

Components

GraphIV's data

The release is gated on kkuroma/GraphIV, with one tag per rebuild, the present one being GraphIV-2026-10-01. Its card covers the columns, how citations are resolved and how the topic tree is built and named.

BoundedField - Citation Aware LLM-free Retriever & Reranker

BoundedField takes the 5,000 papers closest to a question, adds what the top 200 cite and what cites them, and ranks the pool by a product of cosine, recency and citation-graph terms whose exponents are tuned per mode, because embedding search finds the papers that sound like a question rather than the ones its field cites. Read more at docs/retrieval.md.

LeyLine - Magnetic Monte Carlo Trajectory Miner

LeyLine walks the papers a field takes positions on, drawing every step by how much the field argues with the next paper, keeps the paths that recur as lineages, and collects the newest papers extending, critiquing or comparing against the answer, because a ranking built on citations cannot see a paper too new to be cited. Read more at docs/leyline.md, and the Topic Queries behind its evaluation are in docs/supplement.md.

Automated research pipeline

The agent owns the loop, and the server answers one call at a time while holding the corpus, the tuned constants and the rankings. A two-area standard run measured 139 seconds end to end over MCP, where 59 went to the two retrieve calls and 71 to write_report.

Five modes pick the recipe: survey, frontier and consensus are each tuned on their own benchmark, and ancestry and evolution start from one paper, with the score's forward or backward terms set to zero. src/mcp/README.md covers the tools and the three efforts.

Repository Layout

Future Directions

• My vision is to eventually unify the web of science into a singular graph database, where querying becomes a simple graph operation, and arXiv is the first part.

• Anyone should be able to host the server, which needs a loader from the Hugging Face release into Postgres that fetches the citation sentences from arXiv's HTML.

• A paper too new to be cited is still the open problem: the successors reached 136 of 557 such papers that later took off, and BoundedField's top 20 none.

• The reports have no end-to-end evaluation yet, and the ancestry and evolution modes are untuned.

Acknowledgments

Thank you to arXiv for use of its open access interoperability. GraphIV is built on arXiv's metadata snapshot on Kaggle, on arXiv's own HTML renders and its PDF bucket on Google Cloud, and on ar5iv for the papers from before arXiv rendered HTML itself.

License

The code is AGPLv3 from the commit after c484e9a, and every commit up to and including c484e9a was released under GPLv3.

Citation

@misc{graphiv2026,
  title={GraphIV: An Open, Reproducible Citation Knowledge Graph of arXiv},
  author={kkuroma},
  year={2026},
  howpublished={\url{https://huggingface.co/datasets/kkuroma/GraphIV}}
}