Foundations of model construction in feature-based semantic science

The aim of what semantic science is to have scientific ontologies, data and hypotheses represented and published in machine understandable forms that enable predictions on new cases. There is much work on developing scientific ontologies and representing scientific data in terms of these ontologies. The next step is to publish hypotheses that can make (probabilistic) predictions on the published data and can be used for prediction on new cases. The published data can be used to evaluate hypotheses. To make a prediction in a particular case, hypotheses are combined to form models. This article considers feature-based semantic science where the data and new cases are described in terms of features. A prediction for a new case is made by building a model made up of hypotheses that fit together, are consistent with the ontologies used, and are adequate for the case. We give some desiderata for such models, and show how the construction of such models is a form of abduction. We provide a definition for models that satisfies these criteria and prove that it produces a coherent probability distribution over the values of interest.