How Stable Are LLM-Generated Proofs Under Program Refactoring? A Stress Test for Verifiable Code Generation
arXiv:2610.36328v1 Announce Type: new Abstract: Benchmarks for verifiable code generation usually test a proof against one fixed implementation. We ask whether the same proof remains valid after a program refactoring that preserves behavior. We introduce RefactorProof, which…
AI Summary & Key Takeaways
- arXiv:2610.36328v1 Announce Type: new Abstract: Benchmarks for verifiable code generation usually test a proof against one fixed implementation
- We ask whether the same proof remains valid after a program refactoring that preserves behavior
- We introduce RefactorProof, which…
How Stable Are LLM-Generated Proofs Under Program Refactoring? A Stress Test for Verifiable Code Generation
Related stories
Claude for Legal now verifies sources automatically, then hands the file to a lawyer
Anthropic is adding pre-built templates to Claude for Legal. These interactive overviews and tables simplify setup for legal teams and speed up routine work like contract reviews, while more than 60 integrations let firms connect their own databases directly. The article Claude…
RUNvidia представила новую открытую модель транскрипции аудио
Nvidia выпустила модель Nemotron 3.5 для транскрипции аудио на 40 языках.
Nvidia's open Nemotron 3.5 Transcribe combines transcription, translation, and speaker recognition
Nvidia has released Nemotron 3.5 Transcribe, an open speech recognition model that handles transcription, speaker recognition, and translation and takes its instructions as text prompts. It leads several benchmarks and uses only a sixth of the active parameters of its strongest…
Voice AI in vogue: Nvidia releases new open transcription model
Nvidia just released a free speech-to-text model that can transcribe up to 40 languages, but it only works on recordings, not live audio, so it’s a big step for meeting and medical transcription tools while still leaving real-time use to rivals like ElevenLabs.