training · natural-language-draft-then-formalize-checker-in-the TEC-0072 · proposed

Natural-language draft, then formalize, with checker-in-the-

Have the model write an informal proof sketch first, translate it into Lean, and refine against compiler feedback; train the prover by reinforcement learning on long interactions with Lean so it accumulates experience of what checks.

Proposed. Filed by the drafting stage because a paper introduces or tests it. Nobody has vouched for it. The claim drafted from that paper is its first evidence, and what the paper used to validate it is in that claim’s source note. Say whether it held up for you, below.

Have the model write an informal proof sketch first, translate it into Lean, and refine against compiler feedback; train the prover by reinforcement learning on long interactions with Lean so it accumulates experience of what checks. Filed by the drafting stage from Seed-Prover 1.5: Mastering Undergraduate-Level Theorem Proving via Learning from Experience (2512.17260) with status proposed: the paper introduces or tests it, and the claim drafted from the paper is its first evidence. The paper validated it by: Pass rates on PutnamBench, Fate-H, Fate-X and Putnam 2025 against prior provers at stated compute budgets; RL training accuracy curve from about 50% to near 90%; developer-reported.. Nobody has vouched for it; add support or contest it on this page.

Addresses: Formalizing and machine-checking mathematics

Does it work?

nothing measured0 supporting · 0 contesting sources

Efficacy claims — what this technique actually moves, under which conditions, and whether that has been contested.

No efficacy claim filed yet. The technique is catalogued; whether it moves the capability, and when, is a separate assertion that needs its own sources.

No search recorded either, so this says nothing about the literature — only that nobody has looked here yet.

Code

No repository linked yet. Contribute one.

Sources

Either way, bring evidence: a link, or what you saw.

Whether a technique works is a claim. What you file here becomes a claim about this technique under the capability it addresses, with your evidence as its source, and moves the standing above the same way a paper would.