Hacker News Reader

0101111101on Semantic search engine for ArXiv, biorxiv and medrxiv

Amazing!

0101111101on Semantic search engine for ArXiv, biorxiv and medrxiv

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!

0101111101on Semantic search engine for ArXiv, biorxiv and medrxiv

One chunk embedded together

0101111101on Semantic search engine for ArXiv, biorxiv and medrxiv

Exactly! A near property of the matryoshka embeddings is that you can compute a low dimension embedding similarity really fast and then refine afterwards.

0101111101on Semantic search engine for ArXiv, biorxiv and medrxiv

That's a nice idea! Might take a look this weekend!

0101111101on Semantic search engine for ArXiv, biorxiv and medrxiv

Thanks!

0101111101on Semantic search engine for ArXiv, biorxiv and medrxiv

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`

0101111101on Semantic search engine for ArXiv, biorxiv and medrxiv

Sadly I couldn't find a public API for chemrxiv, but would be happy to be proven wrong!

0101111101on Semantic search engine for ArXiv, biorxiv and medrxiv

Do they have a public API/dataset?

0101111101on Semantic search engine for ArXiv, biorxiv and medrxiv

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...

0101111101on Practical Deep Learning for Coders 2019

Tensorflow also created Eager - their dynamic environment

0101111101on Show HN: Mined for Change – In-Browser Crypto Mining for Effective Altruism

Yeah I think it's important to be completely open about it since browser mining has a bad rep. Everyone trying it should know what happens as much as possible before just clicking 'mine'

0101111101on Show HN: Mined for Change – In-Browser Crypto Mining for Effective Altruism

Hey HN!

Would love to hear any feedback on this project! Positive or negative