DSML KZ residents win SemEval-2026 Task 13 Subtask C

SemEval is an international series of NLP workshops and competitions. Task 13C classifies code authorship into four classes: Human, AI, Hybrid, and Adversarial AI.

Agzam and Yeraly built a multimodal ensemble that analyzes code from three perspectives: code semantics through UniXcoder with Multiple Instance Learning for long files; textual patterns through MazgaBERT, which identifies characteristic templates; and statistical anomalies through XGBoost using hand-crafted style and code-structure features.

Congratulations to our young residents, and we wish them many more victories!