Show HN: Document parsing 5B tokens on a single CPU thread

Hacker News Show2026-11-06 12:510 views

doc2struct is an algorithm that can parse documents fast on one thread. For example it can parse every every 2025 annual report 19GB in 40s.

It preserves nesting, does mild table cleaning, among other things.

Points: 1

# Comments: 0

arXiv:2610.40358v2 Announce Type: replace-cross Abstract: We develop a state discrimination approach to unassisted quant

arXiv:2610.15393v2 Announce Type: replace Abstract: A model of propagation and accumulation of errors caused by round-of

arXiv:2607.10652v2 Announce Type: replace Abstract: This paper presents a symplectic Hamiltonian direct discontinuous Ga

arXiv:2611.07266v1 Announce Type: cross Abstract: A quadratic source is a random variable $X\sim\mathbb{F}_2^n$ generate

Article URL: https://github.com/neoma-pcam/pcam-live Comments URL: https://news.ycombinator.com/item?id=50388401 Points:

You ask your AI agent for an order status page. It returns a polished card grid, a sparkline you never asked for, and a

Related posts