We present CorPipe 25, the winning entry to the CRAC 2025 Shared Task on Multilingual Coreference Resolution. This fourth iteration of the shared task introduces a new LLM track alongside the original unconstrained track, features reduced development and test sets to lower computational requirements, and includes additional datasets. CorPipe 25 represents a complete reimplementation of our previous systems, migrating from TensorFlow to PyTorch. Our system significantly outperforms all other submissions in both the LLM and unconstrained tracks by a substantial margin of 8 percentage points. The source code and trained models are publicly available at https://github.com/ufal/crac2025-corpipe.

翻译：我们介绍了CorPipe 25，这是CRAC 2025多语言共指消解共享任务的获胜方案。该共享任务的第四次迭代在原有的无约束赛道基础上新增了LLM赛道，通过缩减开发和测试集规模以降低计算需求，并包含了额外的数据集。CorPipe 25是我们先前系统的完全重构版本，实现了从TensorFlow到PyTorch的迁移。我们的系统在LLM和无约束赛道中均以8个百分点的显著优势超越所有其他参赛方案。源代码及训练模型已公开于https://github.com/ufal/crac2025-corpipe。