citation-audit
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseCitation Audit
引用审核
Run a pre-submission audit of citations, BibTeX entries, and LaTeX cross-references. This skill is for checking correctness before submission, not for broad literature discovery.
Use this skill when a paper already has draft citations and the user wants confidence that:
- every key in TeX exists in BibTeX
\cite{...} - every BibTeX entry is syntactically valid and not duplicated
- every ,
\ref{...},\cref{...},\eqref{...}target exists\autoref{...} - every is unique and follows the local naming convention
\label{...} - DOI, arXiv, OpenReview, URL, title, author, year, and venue metadata match the real paper
- citation claims in nearby prose are actually supported by the cited work
- bibliography style is submission-ready
Pair this with for the broader submission checklist. Pair it with when citation correctness issues should become blocking paper risks or actions.
submit-paperresearch-project-memory为LaTeX学术论文的引用、BibTeX条目以及交叉引用执行提交前审核。此技能用于提交前检查正确性,而非广泛的文献发现。
当论文已有 draft 引用,且用户希望确认以下内容时使用此技能:
- TeX中的每个键在BibTeX中都存在
\cite{...} - 每个BibTeX条目语法有效且无重复
- 每个、
\ref{...}、\cref{...}、\eqref{...}的目标都存在\autoref{...} - 每个唯一且遵循本地命名规范
\label{...} - DOI、arXiv、OpenReview、URL、标题、作者、年份和会议/期刊元数据与实际论文匹配
- 附近文本中的引用声明确实得到被引用作品的支持
- 参考文献格式符合提交要求
可与技能配合使用,完成更全面的提交检查清单。当引用正确性问题应被列为论文的阻塞性风险或待办事项时,可与技能配合使用。
submit-paperresearch-project-memorySkill Directory Layout
技能目录结构
text
<installed-skill-dir>/
├── SKILL.md
├── scripts/
│ └── audit_latex_refs.py
└── references/
├── citation-claim-audit.md
├── metadata-verification.md
└── report-template.mdtext
<installed-skill-dir>/
├── SKILL.md
├── scripts/
│ └── audit_latex_refs.py
└── references/
├── citation-claim-audit.md
├── metadata-verification.md
└── report-template.mdProgressive Loading
渐进式加载
- Always run for deterministic TeX/BibTeX/reference checks.
scripts/audit_latex_refs.py - Read when checking DOI, arXiv, OpenReview, proceedings, or publisher metadata.
references/metadata-verification.md - Read when the user asks whether citations support the claims made in the paper, or when doing a full pre-submission audit.
references/citation-claim-audit.md - Use for the final audit report.
references/report-template.md
- 始终运行以执行确定性的TeX/BibTeX/引用检查。
scripts/audit_latex_refs.py - 检查DOI、arXiv、OpenReview、会议集或出版商元数据时,阅读。
references/metadata-verification.md - 当用户询问引用是否支持论文中的声明,或进行全面的提交前审核时,阅读。
references/citation-claim-audit.md - 使用生成最终审核报告。
references/report-template.md
Step 1 - Locate Paper Sources
步骤1 - 定位论文源文件
Determine:
- paper root
- main TeX file
- all included TeX files
- BibTeX files referenced by or
\bibliography{...}\addbibresource{...} - target venue and submission mode if obvious
Useful local checks:
bash
find . -maxdepth 4 -name "*.tex" -o -name "*.bib"
find . -maxdepth 3 -name "main.tex" -o -name "paper.tex"If the user provides a paper directory, use it. If no main file is provided, prefer , then , then the TeX file containing .
main.texpaper.tex\begin{document}确定:
- 论文根目录
- 主TeX文件
- 所有被包含的TeX文件
- 通过或
\bibliography{...}引用的BibTeX文件\addbibresource{...} - 若明确,目标会议/期刊及提交模式
有用的本地检查命令:
bash
find . -maxdepth 4 -name "*.tex" -o -name "*.bib"
find . -maxdepth 3 -name "main.tex" -o -name "paper.tex"如果用户提供了论文目录,则使用该目录。若未提供主文件,优先选择,其次是,最后是包含的TeX文件。
main.texpaper.tex\begin{document}Step 2 - Run Deterministic Local Audit
步骤2 - 运行确定性本地审核
Run:
bash
python3 <citation-audit-skill-dir>/scripts/audit_latex_refs.py --paper-dir "$PAPER_DIR" --main "$MAIN_TEX"Use an absolute path to the installed skill script. Do not assume a Claude-specific install path.
The script checks:
- included TeX file discovery
- citation keys in ,
\cite,\citet,\citep,\citealp,\citeauthor,\citeyear,\textcite\parencite - BibTeX keys and basic syntax
- missing citation keys
- unused BibTeX entries
- duplicate BibTeX keys
- missing bibliography files
- duplicate labels
- undefined references
- labels that are never referenced
- unresolved LaTeX placeholders such as and citation placeholders such as
??[?]
If the script reports blocking issues, fix or report those before doing web metadata checks. Metadata validation is much less useful if the TeX/BibTeX graph is broken.
运行:
bash
python3 <citation-audit-skill-dir>/scripts/audit_latex_refs.py --paper-dir "$PAPER_DIR" --main "$MAIN_TEX"使用已安装技能脚本的绝对路径。不要假设特定于Claude的安装路径。
该脚本检查:
- 被包含TeX文件的识别情况
- 、
\cite、\citet、\citep、\citealp、\citeauthor、\citeyear、\textcite中的引用键\parencite - BibTeX键及基本语法
- 缺失的引用键
- 未使用的BibTeX条目
- 重复的BibTeX键
- 缺失的参考文献文件
- 重复的标签
- 未定义的引用
- 从未被引用的标签
- 未解析的LaTeX占位符(如)和引用占位符(如
??)[?]
如果脚本报告阻塞性问题,在进行网络元数据检查之前先修复或报告这些问题。如果TeX/BibTeX关系图已损坏,元数据验证的用处会大打折扣。
Step 3 - Classify Findings
步骤3 - 分类检查结果
Use this severity model:
- : missing cited key, duplicate BibTeX key, undefined ref, duplicate label, invalid BibTeX structure, broken DOI for a cited work
blocking - : metadata mismatch, wrong venue/year, likely duplicate entry, citation claim not supported, arXiv cited when peer-reviewed version should be cited
important - : unused BibTeX entry, unreferenced label, inconsistent key naming, missing optional DOI/URL
warning - : style cleanup, capitalization, field normalization, BibTeX key rename suggestion
note
Do not treat unused BibTeX entries as blocking unless the target venue or user requires a minimal bibliography.
使用以下严重程度模型:
- (阻塞性):缺失引用键、重复BibTeX键、未定义引用、重复标签、无效BibTeX结构、被引用作品的DOI损坏
blocking - (重要):元数据不匹配、会议/年份错误、疑似重复条目、引用声明未被支持、应引用同行评审版本却引用了arXiv版本
important - (警告):未使用的BibTeX条目、未被引用的标签、键命名不一致、缺失可选DOI/URL
warning - (备注):格式清理、大小写规范、字段标准化、BibTeX键重命名建议
note
除非目标会议/期刊或用户要求最小化参考文献,否则不要将未使用的BibTeX条目视为阻塞性问题。
Step 4 - Verify Metadata
步骤4 - 验证元数据
Read .
references/metadata-verification.mdFor every cited key, verify the best available identifier:
- DOI through publisher/CrossRef/doi.org
- arXiv ID through arXiv
- OpenReview URL or forum ID through OpenReview
- proceedings URL for NeurIPS, ICML, ICLR, ACL Anthology, CVF, ACM, IEEE, Springer, or PMLR
Check:
- title
- author list or first author + author count
- year
- venue or publication status
- DOI/arXiv/OpenReview/proceedings URL
- whether a peer-reviewed version exists
When metadata cannot be verified, mark it explicitly instead of guessing.
阅读。
references/metadata-verification.md对每个引用键,验证最可靠的标识符:
- 通过出版商/CrossRef/doi.org验证DOI
- 通过arXiv验证arXiv ID
- 通过OpenReview验证OpenReview URL或论坛ID
- NeurIPS、ICML、ICLR、ACL Anthology、CVF、ACM、IEEE、Springer或PMLR的会议集URL
检查:
- 标题
- 作者列表或第一作者+作者数量
- 年份
- 会议/期刊或出版状态
- DOI/arXiv/OpenReview/会议集URL
- 是否存在同行评审版本
当元数据无法验证时,明确标记而非猜测。
Step 5 - Audit Citation Claims
步骤5 - 审核引用声明
Read for full guidance.
references/citation-claim-audit.mdFor each citation context, classify what the prose asks the citation to support:
- background fact
- prior method existence
- closest related work
- empirical result
- theoretical result
- dataset or benchmark
- negative claim or limitation
- comparison or state-of-the-art claim
Then check whether the cited paper actually supports that role. For high-risk claims, inspect the abstract, introduction, method/result section, and if needed the PDF.
High-risk contexts:
- "first", "only", "state-of-the-art", "significantly", "provably", "guarantees"
- claims about a paper's results or limitations
- citations used to justify a baseline choice
- citations used for theory assumptions
- citations in contribution bullets or problem motivation
Do not silently rewrite scientific claims. If a citation does not support a claim, propose one of:
- replace citation
- weaken claim
- add a more specific citation
- move the claim to related work
- mark as needing author confirmation
阅读获取完整指导。
references/citation-claim-audit.md对每个引用上下文,分类文本要求引用支持的内容类型:
- 背景事实
- 已有方法的存在性
- 最相关的研究工作
- 实证结果
- 理论结果
- 数据集或基准
- 负面声明或局限性
- 比较或最先进水平声明
然后检查被引用论文是否确实支持该角色。对于高风险声明,检查摘要、引言、方法/结果部分,必要时查看PDF。
高风险上下文:
- "首次"、"唯一"、"最先进"、"显著地"、"可证明地"、"保证"
- 关于论文结果或局限性的声明
- 用于证明基线选择合理性的引用
- 用于理论假设的引用
- 贡献要点或问题动机中的引用
不要擅自改写科学声明。如果引用不支持声明,建议采取以下措施之一:
- 替换引用
- 弱化声明
- 添加更具体的引用
- 将声明移至相关工作部分
- 标记为需作者确认
Step 6 - Fix Safe Issues
步骤6 - 修复安全问题
Safe auto-fixes:
- add missing extension resolution in the report
.bib - remove obvious duplicate BibTeX entries only after confirming they are truly identical
- normalize capitalization braces in titles
- add missing DOI/arXiv/URL fields when verified
- fix BibTeX field spelling
- rename labels or citation keys only if all TeX call sites are updated consistently
Never auto-fix:
- citation claims whose support is ambiguous
- substitution of one cited paper for another without explaining the scientific difference
- venue status when multiple versions exist
- author order if sources disagree
For any edit, keep the smallest possible diff.
可自动修复的安全问题:
- 在报告中添加缺失的扩展名解析
.bib - 仅在确认完全相同时删除明显重复的BibTeX条目
- 标准化标题中的大小写括号
- 验证后添加缺失的DOI/arXiv/URL字段
- 修复BibTeX字段拼写错误
- 仅在所有TeX调用位置都一致更新时,重命名标签或引用键
禁止自动修复:
- 支持性不明确的引用声明
- 未经解释科学差异就替换被引用论文
- 存在多个版本时的会议/期刊状态
- 来源不一致时的作者顺序
对于任何编辑,保持最小化的差异。
Step 7 - Write the Audit Report
步骤7 - 撰写审核报告
Use .
references/report-template.mdThe final report should include:
- files checked
- local TeX/BibTeX graph status
- metadata verification status
- citation-claim support status
- blocking fixes required before submission
- recommended non-blocking cleanup
- unresolved items requiring author judgment
If the user asks for a saved report and gives no path, use:
text
docs/reports/citation_audit_YYYY-MM-DD.md使用。
references/report-template.md最终报告应包含:
- 已检查的文件
- 本地TeX/BibTeX关系图状态
- 元数据验证状态
- 引用声明支持状态
- 提交前需修复的阻塞性问题
- 建议的非阻塞性清理工作
- 需作者判断的未解决事项
如果用户要求保存报告但未提供路径,使用:
text
docs/reports/citation_audit_YYYY-MM-DD.mdStep 8 - Final Sanity Check
步骤8 - 最终 Sanity 检查
Before finalizing:
- all cited keys resolve to exactly one BibTeX entry
- all required TeX references resolve to exactly one label
- blocking citation/reference problems are tracked as actions when project memory exists
完成前检查:
- 所有引用键都能解析到恰好一个BibTeX条目
- 所有必需的TeX引用都能解析到恰好一个标签
- 当存在项目记忆时,阻塞性引用/引用问题被列为待办事项
Step 9 - Write Back to Project Memory
步骤9 - 写入项目记忆
If the project uses , update:
research-project-memory- : blocking or important citation, metadata, label, reference, or citation-claim risks
memory/risk-board.md - : concrete fixes for missing keys, metadata corrections, unsupported claims, or broken refs
memory/action-board.md - : claims that must be weakened because citations do not support them
memory/claim-board.md - : citation-audit status and unresolved author decisions
paper/.agent/paper-status.md
Use for deterministic TeX/BibTeX graph findings and for metadata or claim-support issues not fully checked.
observedneeds-verification- every blocking metadata issue is fixed or explicitly listed
- high-risk citation claims have been audited
- unresolved citation correctness questions are not hidden
- the final answer distinguishes deterministic script findings from web/semantic verification findings
如果项目使用,更新:
research-project-memory- :阻塞性或重要的引用、元数据、标签、引用或引用声明风险
memory/risk-board.md - :针对缺失键、元数据修正、未被支持的声明或损坏引用的具体修复措施
memory/action-board.md - :因引用不支持而必须弱化的声明
memory/claim-board.md - :引用审核状态及未解决的作者决策
paper/.agent/paper-status.md
对确定性的TeX/BibTeX关系图检查结果使用(已观测),对未完全检查的元数据或声明支持问题使用(需验证)。
observedneeds-verification- 所有阻塞性元数据问题已修复或明确列出
- 高风险引用声明已审核
- 未解决的引用正确性问题未被隐藏
- 最终答案区分确定性脚本检查结果与网络/语义验证结果