agrag.eval.verifier.verdict_case

verdict_case(item:VerdictItem, predicted:str) -> LLMTestCase

Build a test case with the predicted and the gold verdict.

Parameters:

• item (VerdictItem) – The fixed input.
• predicted (str) – The label from run_verifier.

Returns:

• LLMTestCase – An LLMTestCase with the question, predicted verdict and gold verdict.