Code Coverage Validation

[rbonifacio]

We have to certify that droidxp does not compromise the execution of the tools. To this end, we should conduct an experiment checking if the code coverage of the tools running without the benchmark is similar to the code coverage we get running the benchmark. We should use the small set of apps in this study, running it with one minute, three minutes, and ten minutes, using three repetitions.

• compare droidmate (a) using droidxp and (b) without using droidxp
• compare droidbot (a) using droidxp and (b) without using droidxp
• compare monkey (a) using droidxp and (b) without using droidxp
• compare Sapienz (a) using droidxp and (b) without using droidxp
• compare humanoid (a) using droidxp and (b) without using droidxp