Academic Paper Resolver — DOI, arXiv & PubMed to Metadata & Citations

Turn any DOI, arXiv ID, PubMed ID, or paper title into a rich, structured record: authors, abstract, venue, year, citation count, references, open-access PDF, topics and cross-IDs — merged from several scholarly databases into one clean answer, plus a RAG-ready Markdown card.

Built for AI agents, research assistants, literature reviews and RAG pipelines. No API key, no setup.

---

Why this Actor?

An LLM can't reliably recall a paper's exact citation count, its DOI, or who it cites — that data lives across OpenAlex, Crossref, arXiv and PubMed, each with a different format and different gaps. This Actor is the scholarly grounding an agent needs: give it an identifier (or a title) and get back verified metadata it can cite, with a PDF link when the paper is open access.

• RAG & literature review — resolve a batch of DOIs, embed the abstracts and reference lists, and ground your assistant in real papers.
• AI research agents — a tool an agent calls to answer "what is this paper, how many times is it cited, and what does it reference?"
• Citation graphs — walk references (and, optionally, citing papers) to map a research area.
• Reference management & enrichment — clean up a messy bibliography into structured, deduplicated records.

Because it merges multiple sources, a gap in one is filled by another: OpenAlex provides the backbone and topics, Crossref adds a titled reference list, arXiv supplies the abstract and PDF for preprints.

---

What you get

For every query, one structured record:

Field	Description
query	What you asked for
resolved	Whether a paper was found
title	Paper title
authors	Author list
year	Publication year
venue	Journal / conference / source
publisher	Publisher
doi, arxivId, pmid, openAlexId	Cross-identifiers
citationCount	Times cited
referenceCount	Number of references
influentialCitationCount	Influential citations (when available)
isOpenAccess, oaStatus	Open-access status
pdfUrl	Open-access PDF link (when available)
abstract	Abstract
concepts	Topics / fields
tldr	One-line summary (when available)
references	Full reference list (titles, years, DOIs)
citations	Papers that cite this one (optional)
markdown	A RAG-ready paper card
url	Landing page
sources	Which databases contributed
scrapedAt	Timestamp

---

Example output

{
  "query": "10.1038/nature14539",
  "resolved": "true",
  "title": "Deep learning",
  "authors": "Yann LeCun, Yoshua Bengio, Geoffrey E. Hinton",
  "year": "2015",
  "venue": "Nature",
  "doi": "10.1038/nature14539",
  "pmid": "26017442",
  "citationCount": "81929",
  "referenceCount": "50",
  "isOpenAccess": "true",
  "pdfUrl": "https://hal.science/hal-04206682",
  "concepts": "Computer science, Deep learning, Artificial intelligence",
  "sources": "OpenAlex, Crossref",
  "markdown": "# Deep learning\n\n**Yann LeCun, Yoshua Bengio, Geoffrey E. Hinton · 2015 · Nature**\n\nCited by 81929 · ...",
  "scrapedAt": "2026-07-06T15:00:00.000Z"
}

The markdown field renders as a self-contained card:

Attention Is All You Need

Ashish Vaswani, Noam Shazeer, … · 2017 · arXiv Cited by 100000+ · Open access PDF

Abstract

The dominant sequence transduction models are based on complex recurrent or convolutional neural networks …

---

Input

Field	Type	Default	Description
queries	array	—	Required. DOIs, arXiv IDs, PubMed IDs, or titles — mixed is fine.
includeReferences	boolean	true	Include the paper's reference list.
includeCitations	boolean	false	Also fetch papers that cite this one (extra lookup).
maxReferences	integer	50	Cap references / citations per paper.

The Actor auto-detects each identifier

• DOI — 10.1038/nature14539 or a https://doi.org/… URL
• arXiv — 1706.03762, arXiv:1706.03762, or old-style hep-th/9901001
• PubMed — a bare PMID like 26017442
• Title — any free text, resolved by best match

Example input

{
  "queries": [
    "10.1038/nature14539",
    "1706.03762",
    "26017442",
    "attention is all you need"
  ],
  "includeReferences": true
}

---

Use cases in detail

1. RAG & literature review

Feed a list of DOIs, take the abstract and markdown fields, embed them, and your assistant now answers from real papers — with citation counts and DOIs for provenance. The references array gives you the next hop for expanding a review.

2. AI research agents

Expose this as a tool so an agent can resolve a paper mid-task: "summarize this DOI and tell me how influential it is." The agent gets structured, sourced data instead of guessing.

3. Citation-graph exploration

Turn on includeCitations to fetch papers that cite a work, and use references for papers it cites — build a two-way citation graph around a seed paper.

4. Bibliography cleanup & enrichment

Have a messy list of titles or half-formed references? Resolve them into clean records with DOIs, years and venues, deduplicated by identifier.

5. Open-access discovery

isOpenAccess and pdfUrl tell you instantly whether a paper is freely readable and where to get the PDF.

---

How to use it

1. Click Try for free.
2. Paste identifiers or titles into queries.
3. Click Start.
4. Read the results as JSON, CSV, Excel, or via the Apify API.

Batches resolve in parallel — a hundred papers finish in well under a minute.

---

Calling from the API

curl -X POST "https://api.apify.com/v2/acts/YOUR_ACTOR_ID/runs?token=YOUR_APIFY_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{ "queries": ["10.1038/nature14539", "1706.03762"] }'

Then fetch the dataset:

$curl "https://api.apify.com/v2/acts/YOUR_ACTOR_ID/runs/last/dataset/items?token=YOUR_APIFY_TOKEN"

Works with webhooks, Zapier, Make and n8n.

---

Frequently asked questions

What can I search by? DOI, arXiv ID, PubMed ID, or a plain title — mixed in one run. Each is auto-detected.

Where does the data come from? Multiple open scholarly databases are merged so gaps in one are covered by another. The sources field lists which contributed to each record.

Why is an abstract sometimes missing? Some publishers (e.g. certain Nature titles) don't release abstracts to any open database. When that happens the field is empty even though the rest of the metadata is complete.

Do I get the full reference list? When the publisher deposits references (most do), yes — titled and dated. referenceCount always reflects the total.

Can I get citing papers too? Yes — set includeCitations: true.

Is it good for RAG? Yes — use the markdown card or the abstract for embeddings, and keep doi/url for citations.

Can an AI agent call this automatically? Yes — it's keyless and returns structured JSON, ideal as an agent/MCP tool.

---

Tips for great results

• Prefer identifiers over titles. A DOI or arXiv ID resolves the exact paper; a title returns the best match, which may differ for very common titles.
• Batch your DOIs. Resolving 100 at once is far faster than one at a time.
• Chunk by reference. The references array is a natural boundary for building citation-aware embeddings.
• Keep the DOI. Store it with each embedding so your assistant can cite its source.

---

Notes

This Actor retrieves bibliographic metadata from open scholarly sources for research, indexing and AI-grounding purposes. Metadata may be incomplete or contain source-side errors; verify against the publisher of record for critical use. Abstracts and content remain the rights of their respective publishers and authors.

Metadata aggregated from open scholarly databases including OpenAlex, Crossref and arXiv.

---

Support

Want another identifier type, more citation depth, or an extra field? Open an issue from the Actor's page. Happy researching.