@inproceedings{sun-etal-2023-validity,
    title = "The Validity of Evaluation Results: Assessing Concurrence Across Compositionality Benchmarks",
    author = "Sun, Kaiser  and
      Williams, Adina  and
      Hupkes, Dieuwke",
    editor = "Jiang, Jing  and
      Reitter, David  and
      Deng, Shumin",
    booktitle = "Proceedings of the 27th Conference on Computational Natural Language Learning (CoNLL)",
    month = dec,
    year = "2023",
    address = "Singapore",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2023.conll-1.19/",
    doi = "10.18653/v1/2023.conll-1.19",
    pages = "274--293"
}