@misc{arxiv_2610_32572v1,
  title = {Pseudo-Labels as Rewards, Not Targets: Group-Relative Policy Optimization for Semi-Supervised ASR},
  author = {{Shashi Kumar} and {Yanis Labrak} and {Sergio Burdisso} and {Esaú Villatoro-Tello} and {Petr Motlicek} and {Kadri Hacioglu} and {Andreas Stolcke}},
  eprint = {2610.32572v1},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.32572v1}
}