@inproceedings{palermo-etal-2025-operational,
    title = "Operational Alignment of Confidence-Based Flagging Methods in Automated Scoring",
    author = "Palermo, Corey  and
      Chen, Troy  and
      Wibowo, Arianto",
    editor = "Wilson, Joshua  and
      Ormerod, Christopher  and
      Beiting Parrish, Magdalen",
    booktitle = "Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Coordinated Session Papers",
    month = oct,
    year = "2025",
    address = "Wyndham Grand Pittsburgh, Downtown, Pittsburgh, Pennsylvania, United States",
    publisher = "National Council on Measurement in Education (NCME)",
    url = "https://preview.aclanthology.org/name-variant-enfa-fane/2025.aimecon-sessions.6/",
    pages = "56--60",
    ISBN = "979-8-218-84230-7",
    abstract = "In hybrid scoring systems, confidence thresholds determine which responses receive human review. This study evaluates a relative (within-batch) thresholding method against an absolute benchmark across ten items. Results show near-perfect agreement and modest distributional differences, supporting the relative method{'}s validity as a scalable, operationally viable approach for flagging low-confidence responses."
}