Proposes framing auditing of deployed AI systems as continuous statistical monitoring of risk-controlled constraints like fairness and safety under uncertainty.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CY 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Towards Auditing AI Systems in the Wild
Proposes framing auditing of deployed AI systems as continuous statistical monitoring of risk-controlled constraints like fairness and safety under uncertainty.