PAN@FIRE: Overview of CL-SOCO Track on the Detection of Cross-Language SOurce COde Re-use

The detection of source code re-use is an important research field for both software industry and academia fields. This paper summarizes the goals, organization and results of the second SOCO competitive evaluation campaign for systems that automatically detect the source code re-use phenomenon. PAN@FIRE shared task, named Cross-Language SOurce COde Re-use (CL-SOCO), focused on the detection of crosslingual re-used source codes in C and Java programming languages. Participant systems were asked to annotate several source codes as whether or not they represent cases of cross-lingual source code re-use. In total five teams participated and submitted 12 runs. The training and test collections were generated using an automatic translation tool establishing a standard evaluation framework for future research works in cross-language source code re-use detection. Although the results obtained by the participants look promising, the problem requires more efforts to be accurately solved.