@article{clueweb2210billionwebdocumentswithrich,
  title = {ClueWeb22: 10 Billion Web Documents with Visual and Semantic Information},
  author = {Arnold Overwijk and Chenyan Xiong and Xiao Liu and Cameron VandenBerg and Jamie Callan},
  year = {2022},
  eprint = {2211.15848},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2211.15848v2},
}