2024/09/17 by Andrés Corrada-Emmanuel, Corrada-Emmanuel, Andrés, Ilya Parker +3 · 1 voice
Computer Science · Engineering · #14Q99 (Secondary) #62G99 (Primary) #Artificial Intelligence (cs.AI) #Data Stream Mining Techniques #FOS: Computer and information sciences #Fault Detection and Control Systems #I.2.3 #Machine Learning (cs.LG) #Neural Networks and Applications #cs.AI #cs.LG
paper · pdf · doi:10.48550/arxiv.2409.11052
openalex publication_date 2024/09/17 · arxiv published 2024/09/17 · arxiv updated 2024/09/17 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
If two agents disagree in their decisions, we may suspect they are not both correct. This intuition is formalized for evaluating agents that have carried out a binary classification task. Their agreements and disagreements on a joint test allow us to establish the only group evaluations logically consistent with their responses. This is done by establishing a set of axioms (algebraic relations) that must be universally obeyed by all evaluations of binary responders. A complete set of such axioms are possible for each ensemble of size N. The axioms for N = 1, 2 are used to construct a fully logical alarm - one that can prove that at least one ensemble member is malfunctioning using only unlabeled data. The similarities of this approach to formal software verification and its utility for recent agendas of safe guaranteed AI are discussed.