Pythagoras-Prover 发布 4B 参数定理证明器及扩散模型概念验证版

Rohan Paul · @rohanpaul_ai · X·2026-06-16 06:58·70天前
AI 导读

Pythagoras-Prover 团队发布最小定理证明器 4B 版本及首个扩散模型概念验证版,均仅 4B 参数。在 MiniF2F 测试中,4B 模型以 86.1% Pass@32 超越 DeepSeek-Prover-V2-671B;32B 版本达 89.8% Pass@32 和 92.6% Pass@2024,创当前最佳成绩。核心在于数据效率:构造约 80 万 Lean 验证示例,按易到难训练,并采用 LoRA 微调避免全参数更新。模型上下文窗口为 8192 tokens。模型、数据及训练流水线将陆续开源。

Rohan Paul@rohanpaul_ai
58AI 编辑部评分,满分 100

Pythagoras-Prover 发布 4B 参数定理证明器及扩散模型概念验证版

2026-06-16 06:58· 70天前
AI 导读

Pythagoras-Prover 团队发布最小定理证明器 4B 版本及首个扩散模型概念验证版,均仅 4B 参数。在 MiniF2F 测试中,4B 模型以 86.1% Pass@32 超越 DeepSeek-Prover-V2-671B;32B 版本达 89.8% Pass@32 和 92.6% Pass@2024,创当前最佳成绩。核心在于数据效率:构造约 80 万 Lean 验证示例,按易到难训练,并采用 LoRA 微调避免全参数更新。模型上下文窗口为 8192 tokens。模型、数据及训练流水线将陆续开源。

Pythagoras-Prover just made Lean theorem proving look far less dependent on giant models, with a 4B prover beating DeepSeek-Prover-V2-671B at MiniF2F Pass@32.

Shows in formal reasoning, better data geometry can buy back an astonishing amount of scale.

A theorem prover is not just a language model writing clever math; it is a machine trying to produce text that survives a compiler with no patience for style, confidence, or almost-right reasoning.

The main trick is data efficiency: the team built about 800K Lean-verified examples, trained from easy to hard, then used LoRA so the model learned without updating every parameter.

Joshua Ong @ ICML🚀🚀 Introducing Pythagoras-Prover 🚀🚀 🔹 The smallest theorem prover to date – Pythagoras-Prover-4B 🔹 The first proof-of-concept diffusion theorem proving mo...