0101111101
Joined 8 years ago
Karma
134
Submissions
29
Member since
Aug 13
Recent submissions
Comment · 1 year ago
Amazing!
Comment · 1 year ago
True, but similarly if your embeddings are any good they'll capture interesting associations between authors, topics and your search query. If you find any interesting author overlap results I'd be very interested!
Comment · 1 year ago
One chunk embedded together
Comment · 1 year ago
Exactly! A near property of the matryoshka embeddings is that you can compute a low dimension embedding similarity really fast and then refine afterwards.
Comment · 1 year ago
That's a nice idea! Might take a look this weekend!
Comment · 1 year ago
Thanks!
Comment · 1 year ago
Looks cool!
You can input either a search query or a paper URL on arxiv xplorer. You can even combine paper URLs to search for combinations of ideas by putting + or - before the URL, like `+ 2501.12948 + 1712.01815`
Comment · 1 year ago
Sadly I couldn't find a public API for chemrxiv, but would be happy to be proven wrong!
Comment · 1 year ago
Do they have a public API/dataset?
Comment · 1 year ago
Sure! I first used openai embeddings on all the paper titles, abstracts and authors. When a user submits a search query, I embed the query, find the closest matching papers and return those results. Nothing too fancy involved!
I'm also maintaining a dataset of all the embeddings on kaggle if you want to use them yourself: https://www.kaggle.com/datasets/tomtum/openai-arxiv-embeddin...