The arxivist uses your preferences to sort arXiv articles --- making it easier to find new arXiv submissions that are pertinent to you.
If you're a new user, start by following instructions in the alerts: find some articles you like and tell use you like them; and sign up for the daily email!
Join us on Facebook to see the arXiv Catch of the Day.
Suggestions and positive feedback are very welcome. Contact us at firstname.lastname@example.org.
The system becomes effective after about 5 upvotes, but improves as you keep rating articles.
Loosley speaking, the arxivist skims the title, authors and categories of each article to see whether it matches up with your interests
as indicated through upvotes/downvotes of previous articles.
More specifically, the arxivist keeps track of keywords for each article: the authors and categories, as well as words and phrases in the title. When you upvote/downvote an article, the arxivist interprets that as a upvote/downvote of each keyword for that article. When the arxivist needs to rate a new article for you, it looks at your preference for each of the article's keywords and sums them up to get the total score.
For example, if you click thumbs-up for 10 articles in the category "math.MG", then any article in the category "math.MG" will gain 10 points towards its computed score. Likewise, if you upvote 10 articles with the word "hyperbolic" in the title, any other article with the word "hyperbolic" will gain 10 points. Because word pairs are keywords as well, phrases like "Heisenberg group" count more strongly: liking 10 articles with the phrase "Heisenberg group" will give add a score of 30 towards any article with that phrase in the title.
Most likely. Search for "au:last_first", for example "au:lukyanenko_anton", and then click the "upvote all" at the bottom of the table. Note that searching for more complicated names (starting with d', de, le, etc) is tricky. If you figure out the arxiv's general pattern for this, please let us know.
Yes, but it will take some work. We'll set this functionality up once we reach 1000 users. Articles with only minor modifications (e.g. journal citation added) will also be filtered out at this time.
At the moment, the arxivist sends daily emails, showing the top 3 (relative to you) articles announced on the arXiv that day.
Eventually, it will be possible to change the frequency of the emails and the number of articles shown. We'll set this functionality up once we reach 1000 users.
Designing layouts is a pain, but we do need a mobile version at some point. We'll set this functionality up once we reach 1000 users.
The arxivist was created by Anton Lukyanenko,
then postdoc at the University of Michigan Department of Mathematics, in the fall of 2016,
and entered beta testing at the end of January 2017. Anton is now a faculty member at the George Mason University Department of Mathematics.
By way of Anton's salary, the arxivist has been supported by the UM Math and the NSF RTG grant, and is now in the same way supported by the GMU Math.
The arxivist is not associated with the arXiv.