@inproceedings{ispas-nisioi-2026-archaeology,
    title = "Archaeology at {S}em{E}val-2026 Task 13: Fine-Tuning Pre-Trained Code Models for {AI}-Generated Code Detection",
    author = "Ispas, Jany-Gabriel  and
      Nisioi, Sergiu",
    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-1.383/",
    pages = "3052--3059",
    ISBN = "979-8-89176-414-9",
    abstract = "This paper describes the system submitted by team Archaeology to SemEval-2026 Task{\textasciitilde}13 on AI-generated code detection. The shared task consists of three subtasks; we participate in Subtask-A (binary classification: human-written vs.{\textbackslash} AI-generated code) and Subtask-B (11-class attribution of the generating model).Starting from a TF-IDF and Logistic Regression baseline, we fine-tune four pre-trained code models (CodeBERT, GraphCodeBERT, UniXcoder, and CodeT5+) with separate strategies for each subtask.For Subtask-A, we use leave-one-language-out cross-validation, code augmentation, chunked inference with trimmed-mean aggregation, and threshold calibration on a difficult dataset.For Subtask-B, we use sandwich token packing, class-balanced loss, and multi-seed ensembling with test-time augmentation. Our best submissions obtain macro-F1 scores of 0.737 on Subtask-A and 0.422 on Subtask-B."
}