Apps & data pipelines
author.link ranks new arXiv, bioRxiv and medRxiv papers by how closely each matches your written research interests, with Jev estimating the chance of relevance.
Only you can see your notes.
Screenshot unavailable. Open the experiment ↗
A. Sina Booeshaghi built it as a relevance filter, not a quality judge. On his small 66-paper test, he reports Jev separating his own papers from unrelated controls with an ROC AUC of 0.981, against 0.915 for OpenAI's Decisions API. He cautions that a 0.8 score is not an 80% chance you will find a paper useful.
Write a detailed description of what you research, and author.link sorts newly posted preprints so the closest matches appear first. It checks for new papers every four hours and can send an optional daily email. It only judges relevance to your description, so a highly ranked paper still needs your own reading to judge its quality.