πŸ“„ Paper

This repository hosts the paper:

Certified Self-Consistency: Statistical Guarantees and Test-Time Training for Reliable Reasoning in LLMs
Paula Cordero-Encinar and Andrew B. Duncan arXiv:2510.17472 [stat.ML]
πŸ”— Read on arXiv

You can find the implementation here: GitHub Repository

Wandb Log of AIME Wandb Log of AMC Wandb Log of MATH-500

If you use this work, please cite:

@article{PCEAD_certified,
  title={Certified Self-Consistency: Statistical Guarantees and Test-Time Training for Reliable Reasoning in LLMs},
  author={Paula Cordero-Encinar and Andrew B. Duncan},
  journal={arXiv:2510.17472},
  year={2025}
}
Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support