cd /news/ai-tools/show-hn-citeparse-parse-reference-li… · home › topics › ai-tools › article
[ARTICLE · art-172973] src=github.com ↗ pub= topic=ai-tools verified=true sentiment=↑ positive

Show HN: Citeparse: parse reference lists and flag invented citations on a CPU

Citeparse, a new open-source tool from HedwigAI, parses reference lists into CSL-JSON or BibTeX using a local 32M-parameter model (hedwigai/citeparse-32m, with a 150M option) and flags invented citations by checking each record against Crossref and DataCite. In an evaluation on 100 real references with DOIs removed and 83 fabricated references built by swapping titles onto other authors' names and years, citeparse matched 89 of the real references, left 11 for manual checking and accused none, while flagging 3 fakes as matched, 80 for hand-checking and 0 as mismatches or bad DOIs. The tool exits with status 1 on a mismatch or unregistered DOI so it can run in CI over a paper's bibliography, and agents can check references through the hosted hedwigai MCP server at https://mcp.hedwigai.com.

key takeaway

Citeparse's 32M local model parses references to CSL-JSON/BibTeX and, in testing, matched 89 of 100 real references with zero false accusations while flagging 80 of 83 fabricated references for hand-checking.

read5 min views7 publishedNov 20, 2026
Show HN: Citeparse: parse reference lists and flag invented citations on a CPU
Image: Michielbdejong (auto-discovered)

citeparse turns reference strings into structured records. It reads one reference per line and writes CSL-JSON or BibTeX. A small local model does the work, so nothing leaves your machine unless you ask it to check a record against Crossref.

Try it in your browser: huggingface.co/spaces/hedwigai/citeparse. The model runs on the page, so nothing you paste is uploaded.

pip install citeparse
citeparse refs.txt            # CSL-JSON, one record per line
citeparse refs.txt --bibtex   # BibTeX
citeparse check refs.txt      # flag references that point to no real work
python
from citeparse import Parser

p = Parser()  # hedwigai/citeparse-32m; pass "hedwigai/citeparse-150m" for the larger model
p.parse('K. He, X. Zhang, S. Ren, and J. Sun, "Deep residual learning for image recognition," '
        'in Proc. CVPR, 2016, pp. 770-778. doi:10.1109/CVPR.2016.90')

citeparse check looks for citations that point to no real work, such as references invented by a language model. Each reference is parsed on your machine. Its DOI is then looked up on Crossref and DataCite; a reference without one is searched on Crossref, and on OpenAlex when there is budget. A match needs the title, a surname and the year to agree.

$ citeparse check refs.txt
  1  ok         K. He, X. Zhang, S. Ren, and J. Sun, "Deep residual learning for image recognition," in Pr
  2  NOT FOUND  Smith, J. A., & Patel, R. (2021). Recursive attention gating for low-resource legal summar
                no published work with a close title; check it by hand
  3  MISMATCH   Hinton, G. (2015). Deep residual learning for image recognition. Nature, 521, 436-444. htt
                the DOI's record has a different author: "Deep Residual Learning for Image Recognition"
  4  BAD DOI    Lee, M., & Gomez, T. (2020). Neural citation graphs for clinical trial retrieval. Bioinfor
                DOI 10.1093/bioinformatics/btz99999 is not registered

How well does it work? We ran it on 100 real references from the benchmark below, with their DOIs removed so that each had to be found by search, and on 83 fakes made by putting one reference's title on another's authors and year. Crossref was the only index (no OpenAlex key).

Matched (ok) Check by hand (not found) Accused (mismatch or bad DOI)
100 real references 89 11 0
83 fakes 3 80 0

No real reference was accused. The 11 left to check by hand are mostly old physics references with no title, an Italian law chapter, a Russian book and one reference whose title is miswritten. The script is train/eval_check.py.

The command exits with status 1 when a reference is a mismatch or has an unregistered DOI, so it can run in CI over a paper's bibliography. "Not found" is a prompt to look by hand, not proof of a fake: theses, reports and old books are often missing from every index. Pass --mailto you@example.org so Crossref can reach you, and set OPENALEX_API_KEY for OpenAlex, whose free budget without a key is small and shared by your network.

citeparse doesn't run an MCP server of its own. Agents check references through the hosted hedwigai MCP, with nothing to install:

claude mcp add --transport http hedwigai https://mcp.hedwigai.com

Any client that takes a remote MCP server works with https://mcp.hedwigai.com. Sign in with your email when it asks, then ask your agent to "check the references in paper.tex". It looks each entry up on Crossref and OpenAlex and flags those that point to no real work. A few checks are free; after that each check is billed to your hedwigai account.

Parsing into CSL-JSON or BibTeX stays local: use the citeparse command or the Python API above.

We scored it on 700 real references taken from Crossref. Each one cites a DOI, so the cited work's own Crossref record is the answer key. None of these DOIs were in our training data. We gave GROBID the same DOI rule that citeparse uses, so the DOI column is equal and the rest of the gap comes from the models.

Parser Fields right References fully right Title Container Volume Issue First page DOI
GROBID 0.8.1 (CRF) 0.911 71.1% 0.882 0.805 0.908 0.803 0.953 0.994
citeparse-32m 0.939 80.3% 0.921 0.858 0.956 0.841 0.968 0.988
citeparse-150m 0.952 83.4% 0.934 0.878 0.966 0.861 0.982 0.994

GROBID still wins on its own held-out citations (0.943 against 0.900 for citeparse-150m and 0.882 for citeparse-32m, all on GROBID's own scorer). Those citations come from the same sources as GROBID's training data. We report both results.

"Fields right" is the share of the 3,138 fields in the set that come out exactly right. A journal also counts as right when it matches its short title.

Speed on CPU (8 threads): citeparse-32m parses about 118 references a second, and citeparse-150m about 20.

AUTHOR, EDITOR, TITLE, CONTAINER, DATE, VOLUME, ISSUE, PAGES, PUBLISHER, LOCATION, EDITION, DOI, URL, ISBN, IDENTIFIER, NOTE. Names are split into family and given parts. DOIs are read with a regular expression, because a DOI has a fixed shape; the model's DOI span is used only when the text has no well-formed DOI.

The models were trained on GROBID's citation corpus (Apache-2.0), with its evaluation files and any reference that also appears in them removed, and on Crossref records (CC0) written out in 11 citation styles. The code to rebuild the data, train and benchmark is in train/.

Apache-2.0 for the code and the models.

── more in #ai-tools 4 stories · sorted by recency
── more on @citeparse 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
→ Live at https://your-agent.zahid.host ✓
Get free account → Pricing
from €0/mo · no card required
LIVE [news/show-hn-citeparse-pa…] indexed:0 read:5min 2026-11-20 · —