Farhan Nafis Rayhan at SemEval-2026 Task 13: Supervised Contrastive Learning Approach with Gated Multiclass Decomposition Ensemble Architecture for Code Authorship Identification
Year: 2026
Type: conference-paper
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 threestage 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 26 th overall.
Authors: Farhan Rayhan, Fariska Ruskanda
Institution: Bandung Institute of Technology
Language: English
Subfield: Information Systems
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
Funder: Institut Teknologi Bandung
OpenAlex ID: W7166890394