Semantic Scholar Academic Graph API
Providing a reliable source of scholarly data for developers
Build projects that accelerate scientific progress with the Semantic Scholar Academic Graph API
Driven by State-of-the-Art AI Research
We provide the RESTful Semantic Scholar Academic Graph (S2AG) API as a service to the global research community. The API is a reliable on-demand source of data about authors, papers, citations, venues, and more that allows you to link directly to the corresponding page on semanticscholar.org
for more information.
Currently the S2AG API supports Paper and Author Lookup, Conflict of Interest detection, Conference Reviewer Match, SPECTER embeddings, and SUPP.AI annotations. We are actively developing new features based on user demand.
Paper and author lookup are available from our Academic Graph service, whose reference documentation is available here. Documentation for our Conference Peer Review service is available here. You can also download detailed information in JSON format about all the research papers in our corpus as described here.
Semantic Scholar providing infrastructure for the research ecosystem is exciting as it enables partners like Litmaps to focus on creating great experiences for end users. We found the Semantic Scholar API and bulk data, clear and straightforward to use. The documentation, examples, and easy access to the raw data allowed us to move quickly on data integration, and get back to solving problems for our users.
Co-founder and CTO, Litmaps
Since day 1 Connected Papers has been built on top of the Semantic Scholar Open Corpus and APIs, and heavily relies on them to provide paper discovery and search capabilities to our users. The APIs are well maintained, frequently updated, fast, and easy to use. The team is extremely responsive and has supported our growth every step of the way from open beta to a million users. This massive resource given to the public for free is a great driver for innovation in science and we are proud to be a part of the next layer of tools being built on top of it.
We are a startup that tracks the evolution and progress of AI research. Thanks to the Semantic Scholar API pulling in the latest references to papers from top AI conferences has been a really simple task. Otherwise, it would have taken much more time and effort.
Access Our Continually Updating Corpus
Core Use Cases
The Semantic Scholar Academic Graph is a way of representing the world’s scientific publications.
Scientific papers and their authors are connected by citations of one paper by another. Our new service allows you to find and explore these relations.
Request an API Key
You can use the API endpoint up to 100 requests per 5 minutes to test your application idea. To access a higher rate limit, complete the form to request authentication for your project. Authenticated partners have access to higher rate limits, personalized support, and co-marketing opportunities.
Searching For Papers By Keyword
This will return the top 10 matching papers, with their titles. We can request more results, and additional information with:
Which will return the following 50 matching papers, with both titles and authors.
Bulk Dataset Download
You can find a summary of the datasets we make available for bulk download with:
See the README
for instructions on how to download sample files. To download the full dataset files, complete the form
to request an API key. Bulk dataset download is only available for authenticated users.
Available datasets include:
- Paper attributes (title, authors, etc.)
- Author attributes (name, paper count, h-index, etc.)
- Citation links (citing/cited paper ids, context, intent)
- S2ORC - full text of open-access PDFs
- TLDRs - Short summaries of papers (from SciTLDR)
- Paper embeddings (from Specter)
We can fetch detailed and targeted information about an individual paper with the /paper endpoint.
Will return the paper’s title and its SPECTER embedding.
Will return the names of all authors who have cited this paper
Accessible Paper Identifiers and Examples
Note: The graph/v1/paper endpoint replaces the existing /v1/paper endpoint, which remains in service but will be deprecated during 2022
We can fetch detailed and targeted information about an individual paper with the /author endpoint.
Will return the authors of all papers written by this author.
Note: The graph/v1/author endpoint replaces the existing /v1/author endpoint, which remains in service but will be deprecated during 2022
Traversing the Literature Graph
Using the above endpoints, it would take many API calls to find, for example, all papers cited by an author. But the new service can return this information in a single call, with:
which will paginate through an author’s papers, returning the list of references for each one. The above link will show the title of each reference, while:
will give the title and author list of each reference. Similarly,
Will paginate through the authors of a paper, returning each author’s list of published papers
You can also paginate through a paper’s citations and references, returning detailed information about the citing/cited papers.
These calls will return the title and author list of all papers that cite (or are cited by) the paper with the given ID.
We offer a service to aid conference chairs with matching conference submissions with potential reviewers.
Linking to Semantic Scholar Papers
You can easily link to Semantic Scholar pages without calling the API. Simply create a link with the ID you have and we will redirect the user's browser to the appropriate page.
Accessible Paper Identifiers and Examples
We also provide the following datasets as free and open resources.
Semantic Scholar Academic Graph Dataset (S2AG)
Download records for research papers published in all fields as an easy-to-use JSON archive
An AI-curated corpus of supplements, drugs, and interactions
A corpus of academic papers about COVID-19 and related coronavirus research
A general purpose corpus for NLP and text mining research over scientific papers
Featured API News
Zombie research haunts academic literature long after its supposed demise
Dubious papers taint specialist journals long after they have been retracted
A New and Improved Semantic Scholar API
Developers can now use our API to programmatically search our corpus of nearly 200 million papers
By Semantic Scholar
Conference Peer Review with the Semantic Scholar API
We are excited to release the first version of our new service specifically for peer review as part of the Semantic Scholar API.
By Rodney Kinney, Principal Engineer
Experience a smarter way to search and discover scholarly research.
Stay Connected With Semantic Scholar
What Is Semantic Scholar?
Semantic Scholar is a free, AI-powered research tool for scientific literature, based at the Allen Institute for AI.