@article{beyondaggregatescoresbehavioralcorrectne,
  title = {Beyond Aggregate Scores: Behavioral Correctness Assumptions for Assessing Reference-Based Automatic Evaluation Methods},
  author = {Maria Mahbub and Ashley Rice and Michael R. Munroe and Amidu Kamara and Amir Sadovnik},
  year = {2026},
  eprint = {2609.05289},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.05289},
}