#Correctness — новости

arXiv AI

arXiv AI 18.08.2026 04:00

Beyond Correctness: Toward Automated Novelty Verification with Lean 4

arXiv:2608.14669v1 Announce Type: new Abstract: Artificial intelligence systems applied to mathematics verify correctness but not novelty: an automatically generated theorem can compile in Lean withou...

arXiv AI

5

Читать Источник

arXiv AI

arXiv AI 18.08.2026 04:00

Position: Certified Correctness in Neural Constraint Reasoning Requires Symbolic Integration

arXiv:2608.14569v1 Announce Type: new Abstract: Neural solvers for constraint satisfaction problems have achieved remarkable in-distribution accuracy, yet they suffer from a fundamental limitation per...

arXiv AI

3

Читать Источник

arXiv NLP

arXiv NLP 17.08.2026 04:00

Regime-Conditional Verification: Correctness Estimation for Adapting and Monitoring Safety Classifiers

arXiv:2608.14089v1 Announce Type: cross Abstract: Safety classifiers deployed with large language models often fail for two reasons: their decisions reflect the policy learned during training rather t...

arXiv NLP

3

Читать Источник