Reference Audit – Check All References in a PDF/DOCX
Pricing
from $10.00 / 1,000 reference checkeds
Reference Audit – Check All References in a PDF/DOCX
Upload a manuscript, grant proposal or thesis (PDF, DOCX, TXT): finds the reference list, checks every reference against Crossref and flags invented, mismatched or retracted citations. Markdown audit report included.
Pricing
from $10.00 / 1,000 reference checkeds
Rating
0.0
(0)
Developer
Research Analyst
Maintained by CommunityActor stats
0
Bookmarked
2
Total users
1
Monthly active users
a minute ago
Last modified
Categories
Share
Reference Audit – Check All Citations in a PDF or DOCX
Upload-link a manuscript, grant proposal or thesis (PDF, DOCX, TXT) or paste text: finds the reference list, checks every reference against Crossref (exists, correct metadata, retracted?) and writes a one-page audit report. Catches AI-invented and mistyped citations before submission.
Why use it
- Check grant proposals and manuscripts before submission
- Editors and reviewers: screen reference lists for invented or retracted citations
- Supervisors: quick check of theses and AI-assisted texts
No API keys, no scraping of HTML – the actor talks to the official public API, handles paging, rate limits and retries, and returns flat JSON you can export as CSV/Excel or call from code, Make, Zapier, n8n or AI agents (Apify MCP server).
Input
| Field | Title | Description |
|---|---|---|
documentUrl | Document URL | Public link to a PDF, DOCX or TXT (Google Drive / Dropbox share links work). |
text | …or paste text | Paste a reference list or the whole manuscript instead of a URL. |
maxReferences | Max references | Upper limit of references to check (cost control). |
email | Contact e-mail | Optional; routes requests to Crossref's faster 'polite' pool. |
Example input:
{"documentUrl": "https://arxiv.org/pdf/1706.03762","maxReferences": 150}
Output (one dataset item per result)
{"position": 7,"input": "Jumper J et al. Highly accurate protein structure prediction with AlphaFold. Nature 2021","status": "probable_match","auditFlag": "OK_MATCHED","doi": "10.1038/s41586-021-03819-2","title": "Highly accurate protein structure prediction with AlphaFold","year": 2021,"matchConfidence": 1.0,"retractedOrConcern": false}
Status values
auditFlag: OK (DOI verified) · OK_MATCHED (citation matched) · NOT_FOUND_CHECK_MANUALLY · DOI_NOT_FOUND · RETRACTED_OR_CONCERN · ERROR. The Markdown report is stored in the key-value store under REPORT. Scanned (image-only) PDFs are not supported.
Pricing
Pay per event: $0.01 per reference-checked (reference checked). You only pay for results you get;
set a max cost per run to cap spending.
Data source & terms
Crossref REST API (metadata CC0; Retraction Watch data via Crossref). Your document is processed only during the run and not stored beyond the run's own storage. Please respect the data provider's terms and cite the original resource in publications. This actor is an independent tool and is not affiliated with or endorsed by the data provider.