refactor: Update task configurations and grading logic for improved scoring and consistency dccaaac ajaxwin commited on 2 days ago
refactor: Update ActionType to include costs and modified grader for task 1 5235476 ajaxwin commited on 4 days ago
refactor: Rename submit_function to submit and removes asserts from eval.py 277ec6e ajaxwin commited on 6 days ago
refactor: Update grading logic and submission handling across tasks for improved accuracy and consistency cfae7a7 ajaxwin commited on 6 days ago