{"kind":"task","effective_mode":"full","benchmark":{"kind":"benchmark","effective_mode":"full","slug":"bbh","formal_name":"BIG-Bench Hard","introduction":"BIG-Bench Hard is the set of 23 BIG-Bench tasks on which models of the time scored below the average human rater. It is best known for showing how much chain-of-thought prompting changes the result.","introduction_ja":"","introduction_en":"","category":"Category not supplied","task_count":null,"acquisition_status":"Acquisition status not supplied","official_url":"https://github.com/suzgunmirac/BIG-Bench-Hard","indexing_mode":"index","profile":{"resources":[],"task_format":"","scoring":"","metric":"","size":"","answer_access":"","license":"","citation":"","maintainer":"","released":"","why_hard":"","related":[],"history":"","construction":"","limitations":"","saturation":"","scores":[]}},"task_id":"052f4f0b-b830-5fa4-ae1c-f172135a6b62","task_key":"formal~5ffallacies--main--052f4f0b-b830-5fa4-ae1c-f172135a6b62","task_revision_id":"1","upstream_id":"","short_description":"\"Is Siri a stepsister of Mary? Is Susan related to Kate? In large families, it…","config":"formal_fallacies","split":"main","body":"{\"input\":\"\\\"Is Siri a stepsister of Mary? Is Susan related to Kate? In large families, it is sometimes difficult to keep track of all one's relatives. The following argument seeks to clarify some such relations: Every aunt of Amanda is a stepsister of Nicole. Every stepsister of Nicole is either a stepsister of Kerstin or a classmate of Tanisha, or both. We may conclude that to be a stepsister of Kerstin or a classmate of Tanisha is necessary for being an aunt of Amanda.\\\"\\nIs the argument, given the explicitly stated premises, deductively valid or invalid?\\nOptions:\\n- valid \\n- invalid\"}","display_format":"text","language":"","answer_status":"published","assets":[],"source_url":"https://github.com/suzgunmirac/BIG-Bench-Hard","history":"initial import","indexing_mode":"index","subproblems":[],"grids":[]}