@article{revisitingreliabilityinlargescalemachine,
  title = {Revisiting Reliability in Large-Scale Machine Learning Research Clusters},
  author = {Apostolos Kokolis and Michael Kuchnik and John Hoffman and Adithya Kumar and Parth Malani and Faye Ma and Zachary DeVito and Shubho Sengupta and Kalyan Saladi and Carole-Jean Wu},
  year = {2024},
  eprint = {2410.21680},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2410.21680v2},
}