Principles and Examples of Plausible Reasoning and Propositional Plausible Logic
This work addresses the challenge of reasoning under inherent imprecision for fields like AI and logic, offering a foundational approach, though it appears incremental as it builds on existing non-monotonic logic concepts.
The paper tackles the problem of formalizing plausible reasoning without numerical quantification by presenting a set of principles and introducing Propositional Plausible Logic (PPL), which is shown to be the only non-numeric non-monotonic logic satisfying these principles and correctly handling key examples.
Plausible reasoning concerns situations whose inherent lack of precision is not quantified; that is, there are no degrees or levels of precision, and hence no use of numbers like probabilities. A hopefully comprehensive set of principles that clarifies what it means for a formal logic to do plausible reasoning is presented. A new propositional logic, called Propositional Plausible Logic (PPL), is defined and applied to some important examples. PPL is the only non-numeric non-monotonic logic we know of that satisfies all the principles and correctly reasons with all the examples. Some important results about PPL are proved.