Data modelingData modeling implicitly makes assumptions. If those assumptions match the true system dynamics, the resulting model will be both insightful and predictive. If assumption alignment is not achieved, then we induce risk in using those models for prediction and action. Herein we argue that a good model consolidates energy (i.e., is parsimonious) and properly spans the interstitial regions between observed behavior points. From that viewpoint, we review and assess some of the common assumptions made in data modelingData modeling, in general, as well as in symbolic regressionSymbolic regression, in particular. We consider aspects of risk reduction, quality measures, functional building blocks, model representationRepresentation, search operators, selectionSelection strategies, and trustability.