Assessing Simulated Software Graphs using Conditional Random Fields

In the field of software evolution, simulating the software development process is an important tool to understand the reasons why some projects fail, yet others prosper. For each simulation however, there is a need to have an assessment of the simulation results. We use Conditional Random Fields, specifically a variant based on the Ising model from theoretical physics, to assess software graph quality. The determination of the required parameters of our model is done using a training that we call the parsimonious community homogeneity training.