BibTeX Verification Skill

SkillFiles & storage

Lets your agent check a BibTeX file for fake citations by matching every entry against CrossRef, arXiv, and DBLP.

Use BibTeX Verification Skill in Claude, ChatGPT or Ahel Desktop

Free. Sign in, add BibTeX Verification Skill and connect your AI. About a minute.

Also: Claude Code · Cursor · Codex

Then ask your AI: use the BibTeX Verification Skill skill

Details

Instructions available. Your AI can read the instructions. Execution depends on the setup they require.

Add ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.

BibTeX Verification SkillStart free
About this skill

Verify a BibTeX file for hallucinated or fabricated references by cross-checking every entry against CrossRef, arXiv, and DBLP. Reports each reference as verified, suspect, or not found, with field-level mismatch details (title, authors, year, DOI). Use when the user wants to check a .bib file for f

What this skill tells your AI

The instructions your AI receives, as published by agentscope-ai/openjudge in skills/academic-eval/02-bib-verify/SKILL.md and read by ahel’s review.

Check every entry in a .bib file against real academic databases using the OpenJudge PaperReviewPipeline in BibTeX-only mode:

  1. Parse — extract all entries from the .bib file
  2. Lookup — query CrossRef, arXiv, and DBLP for each reference
  3. Match — compare title, authors, year, and DOI
  4. Report — flag each entry as verified, suspect, or not_found

Prerequisites

pip install py-openjudge litellm

Gather from user before running

InfoRequired?Notes
BibTeX file pathYes.bib file to verify
CrossRef emailNoImproves CrossRef API rate limits

Quick start

# Verify a standalone .bib file
python -m cookbooks.paper_review --bib_only references.bib

# With CrossRef email for better rate limits
python -m cookbooks.paper_review --bib_only references.bib --email your@email.com

# Save report to a custom path
python -m cookbooks.paper_review --bib_only references.bib \
  --email your@email.com --output bib_report.md

Relevant options

FlagDefaultDescription
--bib_only—Path to .bib file (required for standalone verification)
--email—CrossRef mailto — improves rate limits, recommended
--outputautoOutput .md report path
--languageenReport language: en or zh

Interpreting results

Each reference entry is assigned one of three statuses:

StatusMeaning
verifiedFound in CrossRef / arXiv / DBLP with matching fields
suspectTitle or authors do not match any real paper — likely hallucinated or mis-cited
not_foundNo match in any database — treat as fabricated

Field-level details are shown for suspect entries:

  • title_match — whether the title matches a real paper
  • author_match — whether the author list matches
  • year_match — whether the publication year is correct
  • doi_match — whether the DOI resolves to the right paper

Additional resources

Signals

GitHub stars
859
Forks
74
Last commit
Sep 2026

ahel review

  • K1binfo
    installs-packages

Automated review, not a security audit. Ruleset v1+k2.

Advanced
Item type
skill
Key
x-02-bib-verify
Source
github.com/agentscope-ai/openjudge