@inproceedings{trott-parkinson-coombs-2026-graduating,
    title = "Graduating the Benchmark Scale: Lessons from Thermometry",
    author = "Trott, Sean  and
      Parkinson-Coombs, Ois{\'i}n",
    editor = "Akhtar, Mubashara  and
      Batzner, Jan  and
      Choshen, Leshem  and
      Ghosh, Avijit  and
      Gohar, Usman  and
      Mickel, Jennifer  and
      Pant, Ichhya  and
      Talat, Zeerak  and
      Lin, Michelle",
    booktitle = "Proceedings of the Workshop on Evaluating Evaluations ({E}val{E}val)",
    month = jul,
    year = "2026",
    address = "San Diego, CA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/corrections-2026-06/2026.evaleval-1.21/",
    doi = "10.18653/v1/2026.evaleval-1.21",
    pages = "111--115",
    ISBN = "979-8-89176-429-3"
}