🧠 AI⚪ Neutral

SorryDB: Can AI Provers Complete Real-World Lean Theorems?

arXiv – CS AI|Austin Letson, Leopoldo Sarra, Auguste Poiroux, Oliver Dressler, Paul Lezeau, Dhyan Aranha, Frederick Pu, Aaron Hill, Miguel Corredera Hidalgo, Julian Berman, George Tsoukalas, Lenny Taelman|March 4, 2026 at 05:00 AM|1 views

🤖AI Summary

Researchers have introduced SorryDB, a dynamic benchmark for evaluating AI systems' ability to prove mathematical theorems using the Lean proof assistant. The benchmark draws from 78 real-world formalization projects and addresses limitations of static benchmarks by providing continuously updated tasks that better reflect community needs.

Key Takeaways

→SorryDB is a new dynamic benchmark for testing AI theorem provers on real-world Lean mathematical formalization tasks.
→The benchmark includes tasks from 78 GitHub projects, offering more practical challenges than traditional competition problems.
→Current AI approaches including LLMs and symbolic provers show complementary strengths rather than one dominant solution.
→Agentic approaches using Gemini Flash performed best overall but weren't universally superior to other methods.
→The dynamic nature helps prevent test-set contamination and provides ongoing evaluation metrics for formal mathematics AI.

#ai #machine-learning #theorem-proving #lean #benchmark #mathematical-formalization #llm #symbolic-ai #research

Read Original →via arXiv – CS AI

Act on this with AI

Stay ahead of the market.

Connect your wallet to an AI agent. It reads balances, proposes swaps and bridges across 15 chains — you keep full control of your keys.

Connect Wallet to AI →How it works

AI56m ago

Warren Buffett complained for decades that boosting profits by excluding exec stock comp was ‘cynical’—Nvidia just surprised Wall Street and agreed

Nvidia surprised Wall Street by agreeing to include executive stock compensation in its profit calculations, addressing a decades-old complaint by Warren Buffett about excluding such costs. This accounting change will likely boost Nvidia's credibility with investors while potentially pressuring competitors to follow suit.

AI3h ago

A Neuropsychologically Grounded Evaluation of LLM Cognitive Abilities

Researchers introduced NeuroCognition, a new benchmark for evaluating LLMs based on neuropsychological tests, revealing that while models show unified capability across tasks, they struggle with foundational cognitive abilities. The study found LLMs perform well on text but degrade with images and complexity, suggesting current models lack core adaptive cognition compared to human intelligence.

AI3h ago

Estimating Visual Attribute Effects in Advertising from Observational Data: A Deepfake-Informed Double Machine Learning Approach

Researchers developed DICE-DML, a new framework that uses deepfake technology and machine learning to measure causal effects of visual attributes in digital advertising. The method addresses bias issues in standard approaches when analyzing how image elements like skin tone affect consumer engagement on social media platforms.