Papers › Draft, Sketch, and Prove: Guiding Formal Theorem Provers with Informal Proofs

Draft, Sketch, and Prove: Guiding Formal Theorem Provers with Informal Proofs

21 Oct 2022arXiv:2210.12283archive 2025-07-28

Albert Q. Jiang, Sean Welleck, Jin Peng Zhou, Wenda Li, Jiacheng Liu, Mateja Jamnik, Timothée Lacroix, Yuhuai Wu, Guillaume Lample

The formalization of existing mathematical proofs is a notoriously difficult process. Despite decades of research on automation and proof assistants, writing formal proofs remains arduous and only accessible to a few experts. While previous studies to automate formalization focused on powerful search algorithms, no attempts were made to take advantage of available informal proofs. In this work, we introduce Draft, Sketch, and Prove (DSP), a method that maps informal proofs to formal proof sketches, and uses the sketches to guide an automated prover by directing its search to easier sub-problems. We investigate two relevant setups where informal proofs are either written by humans or generated by a language model. Our experiments and ablation studies show that large language models are able to produce well-structured formal sketches that follow the same reasoning steps as the informal proofs. Guiding an automated prover with these sketches enhances its performance from 20.9% to 39.3% on a collection of mathematical competition problems.

PaperPDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

facebookresearch/minif2f officialmentioned in papermentioned on GitHubSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to MiniF2F: a cross-system benchmark for formal Olympiad-level mathematics (arXiv:2109.00110; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
albertqjiang/draft_sketch_prove officialmentioned in paperNOASSERTIONSyntology: not harvested report
rah4927/lean-dojo-mew mentioned on GitHubMITSyntology: not harvested report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Automated Theorem ProvingLanguage ModelingLanguage ModellingMathematical Proofs

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Automated Theorem Proving miniF2F-test DSP (540B Minerva informal) ITP Isabelle #12 of 29 Archive leaderboard report
Automated Theorem Proving miniF2F-test DSP (540B Minerva informal) Pass@100 38.9 #12 of 29 Archive leaderboard report
Automated Theorem Proving miniF2F-test DSP (540B Minerva informal) cumulative 38.9 #12 of 29 Archive leaderboard report
Automated Theorem Proving miniF2F-test Sledgehammer + heuristics ITP Isabelle #25 of 29 Archive leaderboard report
Automated Theorem Proving miniF2F-test Sledgehammer + heuristics Pass@1 20.9 #25 of 29 Archive leaderboard report
Automated Theorem Proving miniF2F-test Sledgehammer + heuristics cumulative 20.9 #25 of 29 Archive leaderboard report
Automated Theorem Proving miniF2F-valid DSP (62B Minerva informal) Pass@100 43.9 #10 of 10 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections