MAP-2 — Map 2: Tasks, Methods, and Scientific Integrity
12 requirements in the Map 2: Tasks, Methods, and Scientific Integrity function
MAP 2.1The specific tasks and methods used to implement the tasks that the AI system will support are
MP-2.1-001Establish known assumptions and practices for determining data origin and content lineage, for
MP-2.1-002Institute test and evaluation for data and content flows within the GAI system, including but not
MAP 2.2Information about the AI system's knowledge limits and how system output may be utilized and
MP-2.2-001Identify and document how the system relies on upstream data sources, including for content
MP-2.2-002Observe and analyze how the GAI system interacts with external networks, and identify any
MAP 2.3Scientific integrity and TEVV considerations are identified and documented, including those
MP-2.3-001Assess the accuracy, quality, reliability, and authenticity of GAI output by comparing it to a set
MP-2.3-002Review and document accuracy, representativeness, relevance, suitability of data used at different
MP-2.3-003Deploy and document fact-checking techniques to verify the accuracy and veracity of information
MP-2.3-004Develop and implement testing techniques to identify GAI produced content (e.g., synthetic media)
MP-2.3-005Implement plans for GAI systems to undergo regular adversarial testing to identify vulnerabilities