by Sean Carroll via his Preposterous Universe Blog

The arxiv, started by Paul Ginsparg in 1991, was a pioneer for the Open Access movement in scientific publishing. Most (many?) working physicists, and an increasing number of scientists in other fields, take it for granted that they will share their research articles freely with everyone in the world by submitting to arxiv. The current submission rate is about 8,000 papers per month, and still growing linearly or possibly a bit faster.

In addition to providing fast and easy communication of new papers, the arxiv is a resource ripe for data-mining. Say hello to Paperscape, a project by Damien George of Cambridge and Rob Knegjens at Nikhef in the Netherlands. This fun (and possibly useful) new tool creates a categorized/zoomable/clickable/searchable map of every paper on the arxiv. Apparently it’s been around since March, but I only heard about it yesterday, possibly because of this post on physicsworld.com. So here’s the birds-eye view of what the arxiv looks like:

There is a lot of data displayed here in quite a dense way. The different colors represent different arxiv categories: condensed matter, astrophysics, and so on. High-energy physics dominates the map, in part because that was the first field to participate in arxiv in the first place. Each circle is an individual paper, with the size representing the number of times that paper has been cited (within arxiv). You can pick out some of the big hits in the field — the accelerating universe, cosmic microwave background observations, AdS/CFT, extra dimensions, and so on. The locations aren’t random, either; circles are placed in proximity depending on how often they cite each other. So the fact that contiguous regions all have the same color isn’t built into the mapping algorithm, it’s a consequence of the (perfectly predictable) fact that papers in the same field cite each other more than papers in other fields.

As you zoom in, the papers become more legible — when a circle becomes big enough, a word or phrase from the title appears, and eventually the author’s name. Here’s one of my papers, a bit standoffish from its surroundings:

Continue Reading: http://www.preposterousuniverse.com/blog/2013/08/17/a-map-of-the-research-literature/