{"kind":"task","effective_mode":"full","benchmark":{"kind":"benchmark","effective_mode":"full","slug":"mmlu","formal_name":"MMLU","introduction":"MMLU asks four-way multiple-choice questions across 57 subjects, from elementary material to professional-level examinations. Since 2020 it has been the most widely cited single reference point for general capability.","introduction_ja":"","introduction_en":"","category":"Category not supplied","task_count":null,"acquisition_status":"Acquisition status not supplied","official_url":"https://github.com/hendrycks/test","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":"36808d3e-fd2b-5f32-819e-edff7ff11260","task_key":"all--test--36808d3e-fd2b-5f32-819e-edff7ff11260","task_revision_id":"1","upstream_id":"","short_description":"Consider the paper Native Client: A Sandbox for Portable, Untrusted x86 Native…","config":"all","split":"test","body":"{\"choices\":\"['all instructions that modify segment state', 'all loads or stores to addresses that are not 0 mod 32', 'all indirect loads or stores (via an address in a register or variable)', 'all indirect jumps (via an address in a register or variable)']\",\"question\":\"Consider the paper Native Client: A Sandbox for Portable, Untrusted x86 Native Code by Yee et al. Ben Bitdiddle notes that NaCl uses Intel x86 segmentation to ensure that the sandboxed module does not read or write memory outside its own data area, and does not execute instructions outside its own code. Ben thinks that with these restrictions alone, executing the sandboxed module must be safe; that is, he thinks validation is not needed. Ben is wrong. Circle the types of x86 machine instructions that the validator always forbids in sandboxed code. Please ignore trampoline and springboard code.\",\"subject\":\"computer_security\"}","display_format":"text","language":"","answer_status":"published","assets":[],"source_url":"https://github.com/hendrycks/test","history":"initial import","indexing_mode":"index","subproblems":[],"grids":[]}