Pith. sign in

REVIEW 10 cited by

Proof Artifact Co-training for Theorem Proving with Language Models

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2102.06203 v2 pith:B4JK4NGZ submitted 2021-02-11 cs.AI cs.LGcs.LO

Proof Artifact Co-training for Theorem Proving with Language Models

classification cs.AI cs.LGcs.LO
keywords theoremlanguageproofprovingco-trainingdataformalizedlarge
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Labeled data for imitation learning of theorem proving in large libraries of formalized mathematics is scarce as such libraries require years of concentrated effort by human specialists to be built. This is particularly challenging when applying large Transformer language models to tactic prediction, because the scaling of performance with respect to model size is quickly disrupted in the data-scarce, easily-overfitted regime. We propose PACT ({\bf P}roof {\bf A}rtifact {\bf C}o-{\bf T}raining), a general methodology for extracting abundant self-supervised data from kernel-level proof terms for co-training alongside the usual tactic prediction objective. We apply this methodology to Lean, an interactive proof assistant which hosts some of the most sophisticated formalized mathematics to date. We instrument Lean with a neural theorem prover driven by a Transformer language model and show that PACT improves theorem proving success rate on a held-out suite of test theorems from 32\% to 48\%.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 10 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. MiniF2F: a cross-system benchmark for formal Olympiad-level mathematics

    cs.AI 2021-08 accept novelty 8.0

    MiniF2F is a new cross-system benchmark containing 488 Olympiad-level mathematics problems formalized in Metamath, Lean, Isabelle, and HOL Light, together with baseline results from a GPT-3-based prover.

  2. Geometric Measurements of the Axiom of Choice in Neural Proof Embeddings

    cs.LG 2026-06 unverdicted novelty 7.0

    Proofs depending on the axiom of choice show a geometric signature in neural embeddings of tactic sequences that weakens with dependency-graph distance and correlates with prover failure rates.

  3. LeanMarathon: Toward Reliable AI Co-Mathematicians through Long-Horizon Lean Autoformalization

    cs.AI 2026-06 unverdicted novelty 7.0

    LeanMarathon uses four contract-scoped agents on an evolving blueprint coordinated by a two-stage orchestrator to formalize seven theorems from Erdős problems in Lean, proving 258 lemmas with no sorry across three runs.

  4. From Solvers to Research: Large Language Model-Driven Formal Mathematics at the Research Frontier

    cs.CL 2026-07 accept novelty 6.0

    LLM formal provers must shift from competition solvers to research agents that handle open-ended, under-specified frontier mathematics under machine-checked rigor.

  5. Automating Formal Verification with Agent-Guided Tree Search

    cs.LO 2026-05 unverdicted novelty 6.0

    Agent-directed tree search improves LLM performance on Lean formal verification tasks, with context-based orchestration solving more intermediate specs at lower token cost than baseline agents.

  6. OProver: A Unified Framework for Agentic Formal Theorem Proving

    cs.CL 2026-05 unverdicted novelty 6.0

    OProver-32B achieves top Pass@32 scores on MiniF2F, ProverBench, and PutnamBench by combining continued pretraining with iterative agentic proving, retrieval, SFT on repairs, and RL on unresolved cases using a 6.86M-p...

  7. Rethinking Supervision Granularity: Segment-Level Learning for LLM-Based Theorem Proving

    cs.AI 2026-05 unverdicted novelty 6.0

    Segment-level supervision extracts coherent proof segments to train policy models that achieve 61-66% success on miniF2F, outperforming step-level and whole-proof methods while also improving existing provers.

  8. Aristotle: IMO-level Automated Theorem Proving

    cs.AI 2025-10 unverdicted novelty 6.0

    Aristotle reaches gold-medal-equivalent performance on 2025 IMO problems via integrated Lean proof search, informal lemma formalization, and a dedicated geometry solver.

  9. Automating Formal Verification with Reinforcement Learning and Recursive Inference

    cs.LG 2026-05 unverdicted novelty 5.0

    RLVR training raises verified Dafny pass rates from 9.7% to 31.1% on a filtered benchmark while a Lean proof scaffold lifts success from 46.2% to 69.2% on a pilot set and solves 7 of 42 prior unsolved tasks.

  10. NeuroNL2LTL: A Neurosymbolic Framework for Natural Language Translation of Linear Temporal Logic

    cs.AI 2026-05 unverdicted novelty 5.0

    NeuroNL2LTL presents a neurosymbolic system with verifier-in-the-loop RL training for NL-to-LTL translation, reporting 28% semantic equivalence and 86% satisfiability on 200k+ requirements across domains.