@inproceedings{gainulla-shamsadinov-2026-youngdsmlkz,
    title = "{Y}oung{DSMLKZ} at {S}em{E}val-2026 Task 13: {MIL}-{U}ni{X}coder with Meta-Stacking and Handcrafted Features for {AI}-Generated Code Detection",
    author = "Gainulla, Yeraly  and
      Shamsadinov, Agzam",
    editor = "Kochmar, Ekaterina  and
      Ghosh, Debanjan  and
      North, Kai  and
      Komachi, Mamoru",
    booktitle = "Proceedings of the 20th {I}nternational {W}orkshop on {S}emantic {E}valuation (2026)",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.semeval-1.137/",
    pages = "994--999",
    ISBN = "979-8-89176-414-9",
    abstract = "We propose and validate a multi-view ensemble framework for 4-class AI-generated code detection (Human, AI, Hybrid, Adversarial) in realistic long-form repositories. Our system, Team YoungDSMLKZ, ranked 1st out of 50+ teams in SemEval-2026 Task 13 Subtask C with a macro F1 of 0.7855 (+5.2 over runner-up). The framework combines: (i) a Dynamic Multiple Instance Learning (MIL) pipeline over UniXcoder chunks for O(N)-scalable long-context detection, (ii) transformer-based meta-stacking (UniXcoder and ModernBERT), and (iii) an XGBoost classifier on 200+ handcrafted stylometric features. Evidence localization analysis shows that 62.4{\%} of decisive AI-detection signals reside beyond the standard 512-token window, validating the MIL design."
}