<img width="1108" alt="Image" src="https://github.com/user-attachments/assets/5d0dba75-b28a-4e74-8b76-2ea04379a036" /> Is there a code to calculate Cohen’s Kappa? And, has the consistency rate between the two gold annotators (GPT-4o and Claude Sonnet-3.5) been observed? If so, what is it?