Hello everyone!

I would like to invite you to the competition of Authorship Identification of SOurce COde (AI-SOCO) that is prepared by justHusam, alfadel and myself.

This is no competitive programming competition, but it is very much related to it. :)

This is more of an Artificial Intelligence / Machine Learning competition but it is centered around the Codeforces competitions community and the problems we face.

In this competition, participants are required to build a system that can identify the author of a given source code.

This can help in identifying whether a submitted code in some contest does actually belog to the user who submitted it or not, thus minimizing cheating in Codeforces. =D

The dataset is composed of source codes collected from the open submissions in the Codeforces, we selected 1,000 users and collected 100 source codes from each one. So, the total number of source codes is 100,000. All collected source codes are correct, bug-free, compile-ready and written using the C++ programming language using different versions. For each user, all collected source codes are from unique problems.

For more details on the competition, please visit the website here.

The competition will be organized as a PAN track at FIRE 2020 10 — 13 December Virtual Conference

Best of luck for all participants!