Home – Iris.ai - Your Science Assistant

The future of Science

We’ve built AI tools to take you from a problem to a precise reading list in less than two days. Read more.

We are also launching Project Aiur to open up and validate science in a tokenized model. You can join in these efforts today!

Buy tokens

Free Premium

Exploration of interdisciplinary research

Consistently outperforming old school search tools, Iris.ai starts from a paper of your choice, "fingerprints" it based on machine extracted keywords and contextual synonyms and hypernyms, and matches the fingerprint against more than 83M Open Access papers

Bypass keyword search
Bypass citations
Navigate papers visually

Bookmark papers
Download full text directly
Access full history

Use the free tool

Free Premium

Full research landscape mapping

Use the Exploration tool starting from your free text description of the problem and a result editor, to build a large corpus of documents related to the problem statement. Use the iterative Focus tool to narrow down to a precise reading list.

Incorporate other databases
Exploration from free text
Edit exploration results

Focus to a reading list
Corpus analysis
Machine topic filtering

Get access to the premium services

Natural Language Understanding

Iris.ai uses a combination of keyword extraction, word embeddings, neural topic modeling, word importance based similarity of document metrics and hierarchical topic modeling. The approach is mainly unsupervised but we utilize an evaluated annotation set from our community of AI Trainers for benchmarking and improving our tools.

Key information extraction
Key terms identification. Marking of possible contextually disambiguating information. Forming basis for a document fingerprint.

Neural Topic Modelling
Clustering of semantically similar documents. Cluster labeling. Document fingerprint update.

WISDM
Fingerprints are matched using the WISDM document similarity metric.
Basis for document fingerprint indexing.

HOURS SAVED

PER YEAR

WITH A TEAM OF

RESEARCHERS

Saved time and increased radical discovery

Industrial researchers use on average 3 weeks to build a reading list, with a self-reported 70% confidence. Using the systematic academic approach, we save you time and resources – while increasing the chances of groundbreaking interdisciplinary discovery.

Up to 90% time reduction
85% precision
Increase interdisciplinary inspiration
Organize your internal R&D documents

LATEST NEWS

Sowing the seeds of science. Read more: https://t.co/ShWZAE9jFr #amnc18
V/@wef
C/@antgrasso @evankirstel @ipfconline1 @helene_wpli @TamaraMcCleary @debashis_dutta @Ronald_vanLoon @Andi_staub @JacBurns_Comext @MikeQuindazzi @SpirosMargaris
@andy_lucerne

What do you believe makes "good science?"

After much reflection and assessment of the current crypto market, we've postponed the ICO for @ProjectAiur. We remain committed to blockchain as the right technology to further our mission of validation, accessibility, and transparency in science. ANN: https://t.co/EbySbx8TPr

Haven't seen #PaywallTheMovie? Join us to watch the full-length film tomorrow in our Facebook group (https://t.co/ER5G4wSw51) at 9AM PST/6PM CEST. On the heels of the #planS announcement, learn more about the world of #openaccess. Trailer: https://t.co/WuNCeEtNwr

A group of European scientists publish a response to the recently announced #planS claiming "unethical" and "too risky" to enact with the current system as it is. But they did not neglect to suggest alternatives that still support #OA. Thoughts? https://t.co/9pPW6M7O2I

Not a Library as You Know it – welcome to AI workshop: how to speed up your literature searches with https://t.co/vhHFmSEYLM! https://t.co/n9W4tpiEWS

One step closer to #openscience - next steps to make science more efficient: (1) Incentivize publication of "negative results" (2) Develop tools such @OK_Maps and @TheIrisAI to cope with all the data available https://t.co/oncqS4gooN

New article in @NatureNews today answers questions about how AI tools like @TheIrisAI, Semantic Scholar and more can help tame the constantly growing pool of the world's scientific knowledge and how each serves a different function in the research process. https://t.co/HtWoMuXB6m

Scientific knowledge is arguably the ultimate decentralised system: Victor Botev from @TheIrisAI https://t.co/sx2dsc4DxW

https://t.co/MFbEj3hsW0's Maria Ritola rounds off the day with a look into the future of AI. What's the Next Big Thing? #bilotgoai

“…tools such as Iris.ai…can accelerate researchers’ entry into new fields.”

Andy Extance

“[Iris.ai] might just revolutionize scientific research”

Phil Barker

“Computers can’t yet replace humans, but they can do a great job handling the mundane clutter of our lives.”

Fast Company’s Most Innovative Companies 2017

“One wonders just what she’ll be capable of when she’s all grown up.”

Andrew Wade

“Iris.ai drastically expedites research.”

Haje Jan Kamps

“Access to reliable knowledge – the academic literature – is becoming a fundamental bottleneck for humanity.”

Owen Gaffney and Denise Young

“humans need increasingly smarter, machine-assisted ways to navigate the ever-growing mountain of scientific knowledge”

Natasha Lomas

“…especially useful when you don’t know the exact keywords for the type of research you are looking for”

Bahar Golipur

“As AIs take on more responsibility in managing the discovery process, the science community may free up significant portions of the time they currently devote to scanning for trends.”

Aaron Frank

“This type of assistant is a huge asset to academics and scientists.”

Sam Cohen

“artificial intelligence (AI) that enhance or even replace the role of humans each step of the way”

John Bohannonur

“…built with smart, savvy tech leaders”

Ed Sappin

“found to have the most potential to positively impact one billion people”

Vanessa Bates Ramirez

“Iris.ai is on its way to transform from Science Assistant to fully-fledged, curious Scientist – and we can’t wait to see the impact Iris.ai will have on the scientific community”

Elsa Snellman