I'm not trying to be negative but this site literally does not do what it claims: "automatically and continuously track technical metrics". It doesn't.
I think you are correct: this site doesn't really do what it claims. I'm not sure how it's different from just searching arXiv.
I am pleased to see paperswithcode.com as a collection point of research. But the fact that it casts all of AI as one big set of contests on datasets where "progress" is equated with small increments of classification accuracy is, well, a disappointing view of the field.
I tried to do something similar as one of my final year project with something similar ( keyword and category monitoring ) with a future H-index prediction ranking model, which I think is a more unique approach. The issue with arxiv monitoring is that the only way to obtain the latest submission is through their RSS feed ( correct me if i am wrong ) which luckily I have a running scraper service handling for myself. However the abstract and author from RSS feed isn’t enough, you need to parse PDF for meta info and conference submission as well. As a researcher I think we usually are more interested in new approach or ideas which definitely bring quite a lot of attention until it just pops up around social media ( twitter usually). If you simply want keyword notification service google scholar and semantic scholar already did it quite well. Semantic scholar also have their own API which is slightly better than Arxiv source
It appears that in searches one cannot use double quotes to search for a phrase. I tried searching for "Lenstra Lenstra Lovasz" and got lotsa papers which cite only a Lenstra.
For anyone who's interested I wrote a BASH script that scans selected arXiv groups daily for new content. It parses the deduplicated content returned into two files (filtered; others) -- the former matched on key words/phrases.
7 comments
[ 3.1 ms ] story [ 25.9 ms ] threadPapers with code, does however: https://paperswithcode.com/sota/image-classification-on-imag...
Papers with code literally tracks the progress on common ML tasks programmatically. Please correct me if there's something I missed!
I am pleased to see paperswithcode.com as a collection point of research. But the fact that it casts all of AI as one big set of contests on datasets where "progress" is equated with small increments of classification accuracy is, well, a disappointing view of the field.
https://github.com/victoriastuart/arxiv-rss