Resolving Distributed Knowledge
This work addresses a foundational issue in epistemic logic for researchers in formal methods and multi-agent systems, offering a novel formalization but is incremental in extending existing logical frameworks.
The paper tackles the problem of formalizing what happens when a group shares all their information, introducing a new operator R_G to represent resolved distributed knowledge, and provides sound and complete axiomatizations for logics combining this with common and distributed knowledge operators.
Distributed knowledge is the sum of the knowledge in a group; what someone who is able to discern between two possible worlds whenever any member of the group can discern between them, would know. Sometimes distributed knowledge is referred to as the potential knowledge of a group, or the joint knowledge they could obtain if they had unlimited means of communication. In epistemic logic, the formula D_Gφ is intended to express the fact that group G has distributed knowledge of φ, that there is enough information in the group to infer φ. But this is not the same as reasoning about what happens if the members of the group share their information. In this paper we introduce an operator R_G, such that R_Gφ means that φ is true after G have shared all their information with each other - after G's distributed knowledge has been resolved. The R_G operators are called resolution operators. Semantically, we say that an expression R_Gφ is true iff φ is true in what van Benthem [11, p. 249] calls (G's) communication core; the model update obtained by removing links to states for members of G that are not linked by all members of G. We study logics with different combinations of resolution operators and operators for common and distributed knowledge. Of particular interest is the relationship between distributed and common knowledge. The main results are sound and complete axiomatizations.