Paper

Formalizing Numerical Analysis: An Agent Pipeline and Quality Audit Beyond Kernel Acceptance

Unreadunread

AI summary

arXiv:2606. 14000v1 Announce Type: new Abstract: Recent work has demonstrated that coding agents can formalize entire advanced mathematics textbooks in Lean 4, yet existing efforts concentrate on branches of mathematics already well-represented in mathlib and measure success solely through kernel acceptance.

Reading status

Priority

About this paper

Authors: Theodore Meek, Siyuan Ge, Di Qiu Xiang, Simon Chess, Vasily Ilin
Released: 2026-06-15 (24d ago)
Topic: Related to current project
Relation to my work: Read next because Formalizing Numerical Analysis: An Agent Pipeline and Quality Audit Beyond Kernel Acceptance overlaps with clean result "LoRA persona trained on <A> alone emits <B> at 23.5% when a co-trained partner learns <A>...<B>, vs 0% control on Qwen2.5-7B-Instruct (MODERATE confidence)", clean result "Leakage rate is a usable signal for recovering trigger-shaped phrases on Gaperon-1125-1B without knowing the hidden trigger itself (MODERATE confidence)", clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion language into bystander directives the model was never trained on, absent under same-language SFT (LOW confidence)". Matching terms: text, rect, correct, eval, line, rate, absent. Source: arxiv cs.AI (Artificial Intelligence).
arXiv: 2606.14000

Ask Claude about this paper

Posts a comment with @claude so the runner spins up a Claude Code session scoped to Formalizing Numerical Analysis: An Agent Pipeline and Quality Audit Beyond Kernel Acceptance. Replies appear in the conversation below.

Comments

No comments yet.

Related records

No links yet.