Abstract
Proceedings of the 16th International Workshop on Non-Monotonic Reasoning (NMR 2016), Cape Town, South Africa; April 22-24, 2016. We are interested in belief revision involving conditional statements where the antecedent is almost certainly false. To represent such problems, we use Ordinal Conditional Functions that may take infinite values. We model belief change in this context through simple arithmetical operations that allow us to capture the intuition that certain antecedents can not be validated by any number of observations. We frame our approach as a form of finite belief improvement, and we propose a model of conditional belief revision in which only the "right" hypothetical levels of implausibility are revised.,Conference paper,Published.