Posted by jerpint 1 day ago
Show HN: ArXiv-txt, LLM-friendly ArXiv papers
arxiv-txt.org

Just change arxiv.org to arxiv-txt.org in the URL to get the paper info in markdown

Example:

Original URL: https://arxiv.org/abs/1706.03762

Change to: https://arxiv-txt.org/abs/1706.03762

To fetch the raw text directly, use https://arxiv-txt.org/raw/abs/1706.03762, this will be particularly useful for APIs and agents

20
9
lgas • 1 day ago

It just extracts the abstracts?

1 reply
jerpint • 1 day ago

For now , yes - abstracts and other metadata

1 reply
rrekaf • 21 hours ago

do you plan on adding descriptions of figures and tables?

1 reply
jerpint • 16 hours ago

will probably focus on getting the text out of the papers first, figures might be a good next step after that

sbpost • 1 day ago

The example you give doesn't seem to work - the raw txt does not have authors.

1 reply
jerpint • 16 hours ago

you're right - I hadn't noticed! I fixed it now, thanks for pointing it out

jmartin2683 • 1 day ago

This would be awesome wrapped in an MCP server/tool call :)

1 reply
jerpint • 1 day ago

whoa - i haven't yet played with MCP - might be a good first project!

westurner • 1 day ago

If you train an LLM on only formally verified code, it should not be expected to generate formally verified code.

Similarly, if you train an LLM on only published ScholarlyArticles ['s abstracts], it should not be expected to generate publishable or true text.

Traceability for Retraction would be necessary to prevent lossy feedback.