Researchers from the team Archaeology have developed a system for detecting AI-generated code, participating in SemEval-2026 Task 13. Their approach involves fine-tuning several pre-trained code models, including CodeBERT and CodeT5+, using distinct strategies for binary classification of AI-generated code and multi-class attribution of the generating model. Their best submissions achieved competitive results, ranking 6th out of 81 teams for binary classification and 7th out of 34 for model attribution. AI
IMPACT This research contributes to the ongoing challenge of distinguishing between human-written and AI-generated code, which has implications for academic integrity and software development.
RANK_REASON This is a research paper detailing a system submitted to a shared task for AI-generated code detection. [lever_c_demoted from research: ic=1 ai=1.0]
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
