00-academic-router
Use when the user wants help with academic papers or citations but it's unclear which specific workflow fits — reviewing a paper, checking a BibTeX file for…
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
$ npx -y skills add agentscope-ai/OpenJudge --skill 02-bib-verify --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/02-bib-verifyContext preview
The summary Claude sees to decide when to auto-load 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
name: 02-bib-verify description: > 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 fake citations, validate references in a paper, or audit bibliography entries for accuracy.
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`
pip install py-openjudge litellm
| Info | Required? | Notes | |------|-----------|-------| | BibTeX file path | Yes | `.bib` file to verify | | CrossRef email | No | Improves CrossRef API rate limits |
# 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
| Flag | Default | Description | |------|---------|-------------| | `--bib_only` | — | Path to `.bib` file (required for standalone verification) | | `--email` | — | CrossRef mailto — improves rate limits, recommended | | `--output` | auto | Output `.md` report path | | `--language` | `en` | Report language: `en` or `zh` |
Each reference entry is assigned one of three statuses:
| Status | Meaning | |--------|---------| | `verified` | Found in CrossRef / arXiv / DBLP with matching fields | | `suspect` | Title or authors do not match any real paper — likely hallucinated or mis-cited | | `not_found` | No match in any database — treat as fabricated |
**Field-level details** are shown for `suspect` entries:
OpenJudge: A Unified Framework for Holistic Evaluation and Quality Rewards
Use when the user wants help with academic papers or citations but it's unclear which specific workflow fits — reviewing a paper, checking a BibTeX file for…
Review academic papers for correctness, quality, and novelty using OpenJudge's multi-stage pipeline. Supports PDF files and LaTeX source packages…
Benchmark LLM reference recommendation capabilities by verifying every cited paper against Crossref, PubMed, arXiv, and DBLP. Measures hallucination rate,…
Use when the user wants to compare or benchmark multiple LLMs/agents arena-style but it's unclear which specific workflow fits — a general-purpose win-rate…
Automatically evaluate and compare multiple AI models or agents without pre-existing test data. Generates test queries from a task description, collects…
Benchmark LLM reference recommendation capabilities by verifying every cited paper against Crossref, PubMed, arXiv, and DBLP. Measures hallucination rate,…