Belief revision by examples
This work addresses a specific issue in belief revision for AI and knowledge representation, offering a method to infer source reliability from merging results, which is incremental as it builds on existing assumptions in the field.
The paper tackles the problem of determining the reliability of information sources in belief revision, given the outcome of a previous merging process, and demonstrates its application by assessing the relative reliability of two sensors based on certain observations.
A common assumption in belief revision is that the reliability of the information sources is either given, derived from temporal information, or the same for all. This article does not describe a new semantics for integration but the problem of obtaining the reliability of the sources given the result of a previous merging. As an example, the relative reliability of two sensors can be assessed given some certain observation, and allows for subsequent mergings of data coming from them.