@inproceedings{rayhan-ruskanda-2026-farhan,
    title = "Farhan Nafis Rayhan at {S}em{E}val-2026 Task 13: Supervised Contrastive Learning Approach with Gated Multiclass Decomposition Ensemble Architecture for Code Authorship Identification",
    author = "Rayhan, Farhan  and
      Ruskanda, Fariska",
    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-1.431/",
    pages = "3485--3494",
    ISBN = "979-8-89176-414-9",
    abstract = "This paper present our submission for SemEval-2026 Task 13 Subtask B, which requires the multi-class attribution of code snippets across 10 distinct AI generator families and a human baseline. Our proposed system utilizes a three-stage ensemble architecture specifically designed to navigate extreme class imbalance and capture subtle stylometric fingerprints. Initially, we employ Supervised Contrastive Learning to fine-tune a UniXcoder and ModernBERT backbone. Resulting embeddings are then processed by five heterogeneous shallow experts, each utilizing a multiclass decomposition to master specific generator lineages through specialized architectures. A Human Shield acts as a hierarchical safety auditor as an aggressive binary layer of human vs machine. Finally, a Context-Aware Gated Meta-Learner dynamically aggregates these expert opinions into a final predictions. Our experiments reveal that streamlining the system to a pure UniXcoder backbone fine-tuned with supervised contrastive learning improves performance, outclassing the official CodeBERT baseline with a final Macro-F1 score of 0.31389, ranking 26th overall."
}