Paper

Pythagoras-Prover: Advancing Efficient Formal Proving via Augmented Lean Formalisation

Unreadunread

AI summary

arXiv:2606. 12594v1 Announce Type: new Abstract: Modern Lean theorem provers achieve strong performance only with substantial training and inference compute, driven in part by scarce verified proof data and the long reasoning traces of formal proof search, making both supervised fine-tuning (SFT) and sampling expensive.

Reading status

Priority

About this paper

Authors: Joshua Ong Jun Leang, Zheng Zhao, Mihaela C\u{a}t\u{a}lina Stoian, Qiyuan Xu, Haonan Li, Wenda Li, Shay B. Cohen, Eleonora Giunchiglia
Released: 2026-06-12 (27d ago)
Topic: Related to current project
Relation to my work: Read next because Pythagoras-Prover: Advancing Efficient Formal Proving via Augmented Lean Formalisation 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: strong, text, eval, source, token, without, test, model. Source: arxiv cs.AI (Artificial Intelligence).
arXiv: 2606.12594

Ask Claude about this paper

Posts a comment with @claude so the runner spins up a Claude Code session scoped to Pythagoras-Prover: Advancing Efficient Formal Proving via Augmented Lean Formalisation. Replies appear in the conversation below.

Comments

No comments yet.

Related records

No links yet.