@inproceedings{hariri2026dontpassk,
  title        = {Don't Pass@k: A Bayesian Framework for Large Language Model Evaluation},
  author       = {Hariri, Mohsen and Samandar, Amirhossein and Hinczewski, Michael and Chaudhary, Vipin},
  booktitle    = {Proceedings of the 14th International Conference on Learning Representations},
  year         = {2026},
  eprint       = {2510.04265},
  archivePrefix = {arXiv},
  doi          = {10.48550/arXiv.2510.04265},
  url          = {https://openreview.net/forum?id=PTXi3Ef4sT}
}