docsor1212/pubmed-verifier

Batch-verify PMID citations against PubMed API. Built for researchers, medical writers, and evidence-based medicine teams.
简介（中文）
**PubMed 文献引用批量验证工具**——把引用列表交给它，逐条核验 PMID/DOI/arXiv ID 是否真实存在、是否指向你声称的那篇论文（AI 幻觉引用最常见的形态就是「真 PMID 指向别的论文」）。五态判定（正确/不匹配/部分匹配/无效/待确认），撤稿检测全覆盖，网络故障如实标注「未判定」、绝不误报「不存在」。零依赖、纯本地运行。
- **中文文献**：GB/T 7714 格式参考文献可解析（……标题[J]. 刊名, 年… PMID: xxx）；--parse-text 粘贴即核验整张文献表——行内 PMID/DOI 精确路由，中文条目经 OpenAlex 标题检索判定（无编号 ID 也能核）
- **参考文献格式化**：--format-references --citation-style gbt（另支持 Vancouver/APA/AMA），先验证后排版，只排已验真的条目
- **四数据源**：NCBI PubMed、Europe PMC 自动兜底、Crossref、OpenAlex（DataCite/Zenodo 等非 Crossref 注册的 DOI 也可判定）
- **投稿就绪判定 + 审计底稿**：每份报告自带证据链，--export-audit 输出可复放的 JSON 工作底稿
Why?
**为什么要核验引用（中文）**：学术项目的参考文献动辄数百条，人工核对既繁琐又易漏。在我们自己一次 225 条参考文献的审计中，发现了 3 个无效 PMID 和 6 条跨领域错配——任何一条混进稿件都足以动摇整项工作。AI 生成内容的高频问题是「真 PMID 指向别的论文」，存在性检查根本查不出来。
Academic projects routinely contain hundreds of PMID citations. Manual verification is tedious and error-prone. During our own 225-reference audit, we found 3 invalid PMIDs and 6 cross-domain mismatches — errors that would have undermined the entire project.
Features
> **核心能力（中文速览）**：五态判定（正确/不匹配/部分匹配/无效/待确认）· 撤稿检测全覆盖+撤稿替代推荐 · DOI/arXiv/PMID 三类一站审计 · OpenAlex 兜底（DataCite/Zenodo DOI 可判定）· 中文文献 OpenAlex 标题检索 · 参考文献格式化导出（GB/T 7714/Vancouver/APA/AMA）· 差分审计（PRISMA 复跑只看变化）· 审计底稿可复放 · 网络故障诚实标注绝不误报不存在
- **Batch verification** — Scan entire project directories, extract all PMIDs, verify against PubMed in one run
- **Mismatch detection** — Five-state verdicts catch a REAL PMID pointing to a DIFFERENT paper (the most common AI hallucination)
- **Metadata validation** — Title, authors, journal and date fuzzy-compared against your claims (DOI cross-checked via Crossref with --verify-doi)
- **Dual sources** — NCBI E-utilities primary, Europe PMC automatic fallback when NCBI is unreachable
- **Network hardening** — Optional NCBI API key (3x faster batches), Crossref polite pool, 429 Retry-After backoff, UA rotation, per-host circuit breaker
- **Content matching** — Keyword overlap scoring flags potentially irrelevant citations
- **Three citation types in one audit** — PMIDs, DOIs and arXiv IDs (preprints) verified in a single scan; arXiv IDs checked against the official API (nonexistent = fabrication signal); claims rows keyed by DOI get full verdicts, and preprints surface their published version of record
- **Claims lint** — --lint-claims file.csv validates a claims file offline (ID shapes, missing titles, unknown columns, duplicates) before any verification run
- **Bibliography audit** — --bibliography refs.bib / refs.ris verifies BibTeX and RIS files directly (Zotero/EndNote/Mendeley exports; entries route by PMID > DOI > arXiv with full cross-checks); round-trips with --export-bibtex / --export-ris
- **Plain-text reference list parsing** — --parse-text refs.txt verifies a reference list copied straight out of a manuscript draft: numbered entries ([1], 1.) split cleanly, inline PMID/DOI/arXiv IDs route exactly, and a title-only entry resolves via PubMed title search (honestly labeled resolved_by: title_search, never a mismatch source)
- **Formatted reference list export** — --format-references out.txt --citation-style gbt|vancouver|apa|ama renders verified entries as a ready-to-paste numbered list (GB/T 7714-2015, Vancouver, APA 7th, AMA 11th); partial entries go to a manual-review section, retracted ones are excluded with a warning — formatting that stands on registry-verified records