Keeping on top of the latest most interesting scientific publications can be hard. With so many papers and preprints coming out every week, how much time do you want to spend picking the most relevant ones?
Hopefully not a lot, so you'd rather automate this boring task. Well... that's what refy is for
Refy downloads the latest preprints from biorxiv and arxiv and checks them against a library of papers you've previously read to select the most relevant preprints for you.
There's other literature recommendation systems out there that aim to facilitate keeping up with the literature (e.g., meta.org, inciteful, scite.ai), but these generally work using keywords to select papers of interest. This usually is not specific enough and you end up sifting through lots of unrelated papers to find an interesting one. Other softwares use one single reference paper instead and look for other papers similar to that. That's better, but it's not great...
Your library likely has hundreds of papers that you've read and, hopefully, found interesting. That's a lot of information about what kind of papers you'd want to read next. So why not use this information to select recently published papers that you'd actually want to readd? That's exactly what refy aims to do. Refy uses a .bib file with metadata about lots of papers you've read as input. It then uses natural language processing algorithms to find preprints whose abstract is semantically similar to those of papers you've read before, at it works
Refy's very easy to install and use (see User guide) and you can even automate your literature updates even more. Have fun and get in touch with questions, bugs or suggestions on GitHub.