agentleFS
Sign inStart free
acprkacprk/crypto-research-agents/skills/bib-verify/SKILL.md

bib-verify

Skill15 starsChanged 8 days agoMITView on GitHub

Verify every BibTeX entry against IACR ePrint, Crossref/DataCite and DBLP and flag fabricated, garbled or placeholder references. Use before any draft leaves the machine, after any agent adds citations, and as the P1 and P8 gate item.

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Run the checker (network needed.

    line 16
  2. Very specific:

    Prefer the published version (DOI) for the final paper.

    line 40
  3. Distinctive:

    Never "fill in" missing authors from memory.

    line 41

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

bib-verify

A fabricated reference is a research-integrity failure, not a typo. Typical LLM-era failure modes seen in practice: invented co-author lists on a real paper; a placeholder like {Chen and others} + a journal name propping up a row of a comparison table and a "nobody has done X" claim; a key that points at a different paper by the same group; an ePrint number written from memory that belongs to another paper. When this repo's own reading lists were drafted from memory, the verifier caught three such errors out of ~110 entries.

Procedure

  1. Run the checker (network needed; polite 1 req/s):
    python3 skills/bib-verify/scripts/verify_bib.py refs.bib --json bib-verify.json > bib-verify-report.md
    Resolution order: ePrint id (from eprint=, url=, howpublished=...) → OAI record; doi= → Crossref, then DataCite (Zenodo/LIPIcs/arXiv DOIs); otherwise a title search (DBLP if it answers, else Crossref).
  2. Triage every non-VERIFIED row by hand:
    statusmeaningaction
    MISMATCHthe id/DOI resolves to a different title or author setfix the id or the metadata; if the cited claim was about the other paper, re-read and re-check the sentence that cites it
    NOT_FOUNDnothing plausible existstreat as fabricated: delete, or find the real source and re-cite; re-check every sentence that relied on it
    WEAKsimilar title onlyopen the landing page, compare authors/year/venue manually
    UNCHECKEDoffline / service errorre-run later; never ship with UNCHECKED rows
  3. Lint flags (placeholder authors, and others only, missing year, % UNVERIFIED marker, duplicate titles) must be cleared too.
  4. For every changed entry, grep the paper for its key and re-read the citing sentence: a wrong reference often props up a wrong claim (a comparison row, a novelty statement, a parameter).
  5. Record the run in LITERATURE.md (date, counts) and keep bib-verify-report.md next to refs.bib; the phase-gate script checks that the report is fresh for the bib (the report's bib-sha256: line must equal the hash of the current refs.bib; a --only run writes no hash and therefore never vouches for the whole file) and clean.

Rules

  • Prefer the published version (DOI) for the final paper; keep the ePrint id in eprint= so it can be re-checked.
  • Never "fill in" missing authors from memory. Copy from the ePrint/DOI landing page.
  • Anything added without checking gets a % UNVERIFIED line directly above the entry until verified.
  • Venue strings are not machine-verified; check them on the DOI landing page.
  • Offline: --offline still runs the static lint; the gate stays closed until an online run passes.

Files

  • scripts/verify_bib.py — dependency-free checker (--selftest, --selftest-online, --only k1,k2, --offline).

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free