@article{improvingreproducibilityinevaluationthro, title = {Improving Reproducibility in Evaluation through Multi-Level Annotator Modeling}, author = {Deepak Pandita and Flip Korn and Chris Welty and Christopher M. Homan}, year = {2026}, eprint = {2605.13801}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2605.13801}, }