Request for CoT-E Codes for Comparative Evaluation

[AI4Math-ShanZhang]

Thanks for the great benchmark. I am currently conducting research related to the MathVerse benchmark and deeply appreciate your valuable contributions to the field.

While working on my evaluation, I noticed that the accuracy metrics are available for comparison, but I would like to extend my analysis to include the CoT-E (Chain-of-Thought Evaluation) framework mentioned in your work. Having access to the CoT-E codes would enable me to conduct a more comprehensive evaluation and draw meaningful comparisons with your methodology.

If possible, could you kindly share the CoT-E implementation?