Consensus (a startup) has partnered with the Allen Institute for Artificial Intelligence (2AI2) in order to provide access to research data.
Consensus is part of a growing ecosystem of applications built on Semantic Scholar, AI2’s research tool that pulls from a library of more than 200 million publications.
Consensus searches the literature for studies that best answer queries it receives. Semantic Scholar was designed for scholars, but Consensus can be used by anyone.
Consensus CEO Eric Olson calls himself a “diehard amateur science consumer” on his company profile. GeekWire spoke to him that he loves science but has trouble finding research that interests him.
He formed Consensus with Christian Salem (his former football coach at Northwestern University), during the pandemic.
“It was this culmination of a bunch of things: of being locked in our rooms and having some time, seeing the societal demand, and realizing the technology was actually ready to solve the problem,” said Olson.
About a year ago, Olson and Salem quit their previous jobs to work on Consensus out of a second bedroom in Olson’s Boston apartment. Olson worked previously as a Data Analyst at DraftKings, while Salem was the Product Manager at National Football League.
To build their first engine, the pair contracted Ali Farid (a Turkish machine learning engineer) as an employee. The startup now has five full-time employees including Farid, and is powered with $1.25 million in funding from Winklevoss Capital and individual investors, including Quotient Technology founder Michael Walsh and The Hustle founder Sam Parr.
Consensus has launched an early version this September of the tool It announced its partnership to Semantic Scholar.
Semantic Scholar’s library has been “semantically” analyzed to draw meaning from paper texts and rank them for the most relevant content for a given search. Semantic Scholar also developed its services in order to be compatible with bolt-on programs over the past 2 years.
“We’ve done the heavy lifting and we make our corpus of semantically analyzed papers available so others can build these innovative experiences quickly and easily,” said Joe Gorney, manager of strategic partnerships at AI2. “But we can’t do it all, so helping build an ecosystem around AI analysis of scientific literature is the best way to use AI for the common good.”
Nearly 600 applications and researchers now benefit from Semantic Scholar’s support. Connected Papers, a tool for mapping and recommending papers, as well as The Collaboratory, Opscidia, Publish or Perish, and Ought, Publish, Perish are other partners.
These applications are part of a growing number of services geared mainly to researchers that go beyond workhorse search engines like Google Scholar or PubMed, the National Institutes of Health’s tool. Semantic Scholar is also continuing to expand its offerings. Semantic Reader offers in-line links for citations and note taking.
Consensus is home to 15,000 people, which includes students in undergraduate sciences and health enthusiasts who are interested in health issues.
Consensus’ engine interprets questions asked in plain English and returns results that best match the question.
Consensus includes publication date and number of citations, which are rough indicators of quality. It mainly measures how pertinent the answer to a question is, by separating out clear sentences and writing them down. It is designed to be easy-to-use and easily accessible.
Olson remembered showing Consensus his grandfather, who is a scholar of Eastern European politics systems and was amazed that Consensus could bring up his research about Polish history. “It was a really cool moment when I could see that he got it,” said Olson.
Consensus will generate revenue as it expands its product through either a usage-based or premium subscription.
Olson advises users searching for answers to medical questions to “do your due diligence.” Consensus pulls from a broad library of papers of varying quality and is intentionally calling the current offering a beta version. “The results are not meant to be taken as the definitive truth on anything,” said Olson.
Consensus future versions will add additional quality indicators like the number of participants in a study or ratings for the quality of statistical analysis. SciScore is a tool that measures the reliability of journals’ methods, while CORE provides open access and free access to thousands of research papers.
In the end, Olson hopes to create a dashboard that combines data from multiple studies related to a particular topic. Olson imagines creating a dashboard to help users weigh each side of polarized questions.
“That’s why we call the company Consensus,” said Olson. “That’s what we want to build.”