Literature Search: Google Scholar Alternative with Retraction Screening, BibTeX, RIS & Excel

Search 250M+ scholarly papers by topic or from papers you already trust. Get a ranked reading list with every result screened for retractions, legal open-access PDF links, and exports for Zotero, EndNote, LaTeX and Excel.

Google Scholar has no API, and scraping it breaks Google's terms and fails without warning. Literature Search uses the open scholarly infrastructure instead: OpenAlex (250M+ works, CC0) for search, Crossref for publisher metadata and retraction/correction notices (including the Retraction Watch database), and Unpaywall for legal open-access copies. You get structured data you can trust and re-run, with no CAPTCHAs and no blocked IPs.

• 🔎 Scholar-style search, with real filters: Boolean queries, title/abstract or full-text search, year range, minimum citations, document type, language, open access only
• 🌱 Explore from seed papers: papers that cite your seeds, papers your seeds cite, or related work
• 🚦 Every paper screened: OK, CHECK (preprint, expression of concern, editorial notice) or FIX (retracted). You can exclude retracted papers entirely
• 🔓 Legal open-access PDFs from Unpaywall, with licence and version (published vs. accepted manuscript)
• 📚 Ranked reading list that blends search relevance with field-normalised citation impact, so a strong 2024 paper isn't buried under a 2015 classic
• 🧾 Ready-to-use exports: BibTeX, RIS, CSV, a colour-coded Excel workbook, and formatted citations in APA 7, MLA 9, Chicago, Harvard, IEEE or Vancouver (citeproc-js and the official CSL styles)
• 🧪 Reproducible: every run saves the exact query, filters, date and match count, ready to paste into a methods section
• 💸 $0.003 per paper returned. 100 papers cost $0.30. Searches with no results cost nothing

Who it's for

• Researchers, postdocs and R&D teams: scope a new topic, track recent work, or build a background reading list in minutes
• Medical writers, consultants and analysts: build a verified source list with no retracted papers and links to free full text
• Librarians and research support staff: run reproducible searches and hand over RIS files for Zotero, EndNote or Rayyan
• Developers and AI agents: a clean JSON literature API with abstracts, for RAG pipelines and research agents, over the Apify API or MCP

Not for coursework or ghostwriting. This is a search and source-checking tool. It doesn't write anything, and it isn't meant for completing assignments or academic work on someone else's behalf. Read what you cite.

How to use it

1. Click Try for free and enter a search query. Use quotes for phrases and capitalised AND / OR / NOT, e.g. "retrieval augmented generation" AND (clinical OR medicine).
2. Optional: add filters (years, open access, minimum citations, types) or seed DOIs to search around papers you trust.
3. Set Maximum papers. You pay per returned paper, so this also caps the cost.
4. Click Start. 100 papers usually take 15–30 seconds.
5. Open READING_LIST for the ranked list, or download RESULTS_XLSX, REFERENCES_RIS or REFERENCES_BIBTEX from the Storage → Key-value store tab.

Input example

{
  "query": "\"retrieval augmented generation\" AND (clinical OR medicine)",
  "searchIn": "titleAbstract",
  "yearFrom": 2023,
  "yearTo": 2025,
  "minCitations": 0,
  "openAccessOnly": false,
  "types": [],
  "retractedPapers": "flag",
  "sortBy": "relevance",
  "maxResults": 100,
  "citationStyle": "apa"
}

Seed-paper example: papers that cite LeCun, Bengio & Hinton (2015), Deep learning and mention medical image segmentation, open access only, most cited first:

{
  "query": "medical image segmentation",
  "seedDois": ["10.1038/nature14539"],
  "seedMode": "citing",
  "openAccessOnly": true,
  "sortBy": "citations",
  "citationStyle": "ieee"
}

Output example

Real output from a platform run (query above, 2023–2025):

Reading list (READING_LIST, Markdown)

1. Benchmarking Retrieval-Augmented Generation for Medicine OK · 2024 · Findings of the Association for Computational Linguistics: ACL · 310 citations · score 100 · PDF

Xiong, G., Jin, Q., Lu, Z., & Zhang, A. (2024). Benchmarking retrieval-augmented generation for medicine. Findings of the Association for Computational Linguistics ACL 2024, 6233–6251. https://doi.org/10.18653/v1/2024.findings-acl.372

One dataset row (shortened):

{
  "rank": 1,
  "readingRank": 1,
  "readingScore": 100,
  "status": "OK",
  "title": "Benchmarking Retrieval-Augmented Generation for Medicine",
  "authors": "Guangzhi Xiong, Qiao Jin, Zhiyong Lu, Aidong Zhang",
  "year": 2024,
  "venue": "Findings of the Association for Computational Linguistics: ACL (Findings of ACL)",
  "type": "conference-paper",
  "doi": "10.18653/v1/2024.findings-acl.372",
  "citations": 310,
  "citationPercentile": 100.0,
  "isOpenAccess": true,
  "oaStatus": "hybrid",
  "pdfUrl": "https://aclanthology.org/2024.findings-acl.372.pdf",
  "license": "cc-by",
  "retracted": false,
  "notices": [],
  "citation": "Xiong, G., Jin, Q., Lu, Z., & Zhang, A. (2024). Benchmarking retrieval-augmented generation for medicine. ...",
  "bibtex": "@inproceedings{Xiong2024Benchmarking, ...}",
  "ris": "TY  - CONF ...",
  "abstract": "While large language models (LLMs) have achieved state-of-the-art performance on ...",
  "notes": []
}

A retracted paper, as the screen reports it:

{
  "status": "FIX",
  "title": "RETRACTED: Hydroxychloroquine or chloroquine with or without a macrolide for treatment of COVID-19: a multinational registry analysis",
  "year": 2020,
  "citations": 1201,
  "retracted": true,
  "notes": ["RETRACTED or withdrawn. Do not cite it as valid evidence. Notice: retraction doi:10.1016/s0140-6736(20)31324-6, ..."]
}

What OK, CHECK and FIX mean

Status	Meaning
🟢 OK	No retraction, withdrawal or expression of concern on record. Corrections are noted but don't change the status
🟡 CHECK	Preprint (not peer-reviewed), expression of concern, or a record that is an editorial notice rather than a paper
🔴 FIX	Retracted or withdrawn (Crossref / Retraction Watch notice, or OpenAlex flag). Never ranked in the reading list

"OK" means no notice was found. It doesn't mean a paper is correct, so read it critically. Before you submit, run the bibliography through our Reference Checker.

Files you get

Key-value store key	What it is
READING_LIST	Ranked Markdown reading list: citation, status, OA link and abstract per paper, plus a "Retracted: do not cite" section. Paste it into an LLM or a doc
CITATIONS	Bibliography in your chosen style (retracted papers left out)
REFERENCES_BIBTEX	.bib file for LaTeX / Overleaf
REFERENCES_RIS	.ris file for Zotero, Mendeley, EndNote, Rayyan, Covidence
RESULTS_XLSX	Excel workbook: colour-coded status, clickable links, filters, and a Search log sheet
RESULTS_CSV	Same columns as CSV (UTF-8, opens cleanly in Excel)
SUMMARY	Search log: exact query, filters, OpenAlex request, match count, date, counts by status

Need the citations in other styles or more formats? Send the DOIs to our Citation Formatter.

How the reading score works

readingScore (0–100) = 60% search relevance (OpenAlex's relevance rank within your results) + 40% citation impact (OpenAlex's field- and year-normalised citation percentile, or citations per year if that's missing). Without a text query, or when you sort by citations or date, the score uses citation impact only. Retracted papers score 0 and are never ranked. The dataset keeps your chosen sort order in rank.

Pricing

$0.003 per paper returned (pay-per-event). The retraction screen, Unpaywall lookup, abstract, citation, BibTeX, RIS and Excel/CSV exports are all included.

Papers	Cost
25 (a quick scope)	$0.075
100 (a reading list)	$0.30
500 (a broad search)	$1.50
2,000 (the per-run maximum)	$6.00

A search with no matches costs nothing. Choose Exclude for retracted papers and they are dropped before you're charged. The Actor also respects the maximum charge per run you set in Apify.

FAQ

How is this different from scraping Google Scholar? Scholar scrapers break when Google changes its pages or blocks the scraper's IPs, and scraping goes against Google's terms. This Actor only uses open APIs built for this purpose. OpenAlex covers more than 250M works (journals, conferences, preprints, books, theses, datasets) with abstracts and citation counts. Coverage differs from Scholar's: OpenAlex is strongest on content with DOIs and weaker on some grey literature.

Are citation counts the same as Google Scholar's? No. They're OpenAlex counts, which are usually lower than Scholar's because Scholar also counts non-scholarly pages. They're consistent and reproducible, which matters if you report them.

How reliable is the retraction screen? Every paper with a DOI is checked against Crossref's update notices. These include the Retraction Watch database, which Crossref has published openly since 2023, and OpenAlex's retraction flag. Papers without a DOI only get the OpenAlex check. A paper retracted yesterday may not be in either source yet.

Why are some abstracts missing? Some publishers don't share abstracts with open indexes. OpenAlex rebuilds abstracts from an index of words, so the odd spacing glitch can appear.

Can I use my own OpenAlex key? Yes, though you don't need one. A free key from openalex.org gives your runs their own daily OpenAlex budget, which is useful for very large or frequent searches. It's stored as a secret input and never logged.

Can AI agents call it? Yes, through the Apify API, the Python or JavaScript clients, or Apify's MCP server. Each run returns clean JSON with abstracts and OA links, which suits RAG and research agents.

Data sources and credits

• OpenAlex (CC0) for search, abstracts, topics and citation metrics
• Crossref for publisher metadata and retraction / correction notices, including Retraction Watch data
• Unpaywall for legal open-access locations
• citeproc-js, citation.js and the CSL project styles (CC BY-SA 3.0) for citations, BibTeX and RIS

---

Built by Panda Federation

Self-healing, local-first AI systems and data tools that run themselves.

The Panda Federation research toolkit:

• Literature Search: find papers and screen them for retractions
• Citation Formatter: DOIs, ISBNs and messy references to APA, MLA, Chicago, Harvard, IEEE, Vancouver, BibTeX and RIS
• Reference Checker: fake citations and retracted papers, found

More from Panda Federation on Apify · GitHub