@inproceedings{naswan-etal-2026-astranet,
    title = "{AST}ra{N}et at {S}em{E}val-2026 Task 13: Not All Code Looks the Same: Multi-View Structural and Semantic Detection of Machine-Generated Code",
    author = "Naswan, Ruwad  and
      Saha, Dipit  and
      Kabir, Md.  and
      Tahseen, Nabiha",
    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-1.402/",
    pages = "3209--3217",
    ISBN = "979-8-89176-414-9",
    abstract = "The growing adoption of large language models for code generation poses challenges for code quality, security, and authorship verification{---}particularly when test conditions involve unseen programming languages, generators, or application domains. We present our system, which combines three code-pretrained transformer encoders (CodeT5p-220M, CodeBERT, UniXcoder) with a structure-first Flow-Augmented AST (FA-AST) encoder implemented as a Gated Graph Neural Network. On Subtask A our best single model achieves macro F1 of 0.559; a post-competition layered rank-fusion ensemble across all three encoders raises this to 0.643. On Subtask C we obtain 0.585 officially; a three-stage ensemble combining neural probabilities with LightGBM-based features and class-priority routing raises this to 0.652. Our contributions include a language-agnostic structural detector, a diversity-driven rank-fusion strategy exploiting low inter-model correlation for binary classification, and a meta-learner stacking pipeline for multi-class detection under distribution shift."
}