Hacker News Reader

cjlooion Show HN: LaTeX → structured ArXiv data for scientific RAG

PDF-based pipelines are fundamentally lossy and compute-heavy—whether they rely on OCR, GROBID, or LLM-based parsing. They're simply not good enough for accurate, scientific agents at scale.

To fix this, I'm launching ScienceStack API: a lossless, node-based API for scientific papers with LaTeX source, starting with arXiv.

It currently covers 150k+ arXiv papers, mainly in CS, Math, and Physics.

Every paper also ships with a WYSIWYG interactive reader at sciencestack.ai/paper/{arxivId}. Example: https://www.sciencestack.ai/paper/2512.24601v1

I’m giving away 5× 3-month Pro keys to early commenters who are building in this space (scientific tooling, agents, copilots, RAG etc). I’d love to hear what you’re working on

cjlooion Show HN: Interactive research papers (a big step up from ArXiv HTML)

It works! After the initial data load (big paper), the scrolling and performance works nicely.

Can visit at sciencestack.ai/arxiv/2105.10386

Note: no support for nomenclature/index yet. I'm also working on refactoring the data/json to a streaming model (right now it's one big json dump on load)

cjlooion Show HN: Interactive research papers (a big step up from ArXiv HTML)

Currently the dependency graph only works on newtheorems e.g. theorems/lemmas/definitions etc

https://www.sciencestack.ai/docs/dep-graph

cjlooion Show HN: Interactive research papers (a big step up from ArXiv HTML)

Works with any latex source

https://www.sciencestack.ai/docs/faq

cjlooion Show HN: Interactive research papers (a big step up from ArXiv HTML)

Yea there were several attempts (including ar5iv), and distill.pub is no longer active + Semantic Scholar is PDF-based. None quite made the full use of HTML or have a robust conversion system. Jeff Dean's post is awesome - though using Gemini 3 is compute intensive and may still hallucinate in the end (I'm using a source-based latex to json parser). And the output is still...not very interactive.