A New and Improved Semantic Scholar API

Developers can now use our API to programmatically search our corpus of nearly 200 million papers

Semantic Scholar
Aug 10 · 3 min read
Illustrated graphic shows two web browser windows with pixel overlay and Semantic Scholar logo in the lower left corner.
The Semantic Scholar API provides access to a corpus of nearly 200 million academic papers.

Providing a reliable source of scholarly data for developers is key to Semantic Scholar’s mission. Today, we’re excited to release new API features inspired by feedback from our global research community.

In addition to the existing endpoints for fetching paper and author data from our corpus of nearly 200 million papers, we have added two new major capabilities to the Semantic Scholar API:

  • Keyword Search: Search for papers whose title or abstract matches your query.
  • Bulk Fetching of Related Entities: Use a single API call to fetch related papers and authors. For example, find all of an author’s co-authors, or all papers that cite any paper by that author.

As part of this release, we’ve also made infrastructure improvements to increase the stability and reliability of the API services. Better documentation is now available, and is automatically updated at the time of release.

And in case you missed it, we recently introduced a new Academic Conference Partnerships Service (blog post, documentation) available through the API for organizers looking to improve reviewer selection and conflict-of-interest detection.

The Semantic Scholar API has been used in hundreds of projects and applications to date. In June The Economist used the API to analyze the impact of retracted publications. It also powers live applications that serve millions of scholars. We spoke to a few of our partners to learn about their experience building projects that advance science with the Semantic Scholar API.

Started as a weekend side project between friends, Connected Papers is a visualization tool for researchers to explore papers relevant to their work.

“Since day one 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,” Connected Papers Co-founder Eddie Smolyansky says. “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.”

API partner State of the Art AI recently launched a new platform and community for collaborative development of AI.

“We are a startup that tracks the evolution and progress of AI research,’’ says Founder Eduardo Antonio Espinosa Grimaldo. “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.”

Litmaps is a tool for visual discovery of research, providing scholars with an at-a-glance picture of a research topic as a way to make sense of the vast corpus of literature available.

“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,” says Litmaps Co-founder and CTO Axton Pitt. “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.”

Ready to get started? Visit our API page for more information and to contact our team. We’re here to help you make your big idea come to life!

Learn more about the Semantic Scholar API and let us know about your project.

Follow @allen_ai and @semanticscholar on Twitter, and subscribe to the AI2 Newsletter to stay current on news and research coming out of AI2.

AI2 Blog

AI for the Common Good.