Among many things, I really want to see Nostr used to create an open, decentralized library of research papers from around the world.
Discussion
will happen for sure
100% this... a successor to arxiv.org?
> A data set based on all arXiv publications, pre-processed for NLP, including structured full-text and citation network
Well we should just publish all that work as nostr wiki events asap right?
I shady have a script to publish NIPS like this
~350gbs partitioned into paragraphs.
make those partioned paragraphs into individual notes (replacing the citations/latex unique identifiers with their actual text)
this is one use case for the modular article nip
In addition to the actual citation network built by the authors, im taking the word embeddings of a subset to create a more organic semantic network -> higher resolution knowledge navigation at the paragraph level
Have a script to mass publish modular articles (kind 30040 + 30041) rate limiting do be a bitch though
thought about this too. BUIDL pls!