How it works

  1. Describe your project in a few paragraphs (question, method, data, expected results), or upload the PDF of your draft: an AI writes the description from it.
  2. At once, the papers of the last 3 years are searched on arXiv, in the journals and on OpenReview, with those that already cite your key references: you see what is already published close to your project.
  3. Every day, the new papers are compared with each facet of your project apart (question, method, data, results), and with the names that identify it. An AI reads the closest abstracts.
  4. When one overlaps your project, you get an email: a strong overlap (same question, same or very close approach) or a partial one, with how close it is on each facet.
  5. For each paper, the AI says what it shares with your project, what stays yours and what to do: cite it, set your project apart, contact the authors or publish soon. A strong overlap is compared with the full text of the paper when its license allows it.

Useful during a thesis or a long project, to know early that a competing team is close, cite it, and adjust how you present your work.