{
  "id": 16546,
  "url": "https://arxiv.org/abs/2608.03859v1",
  "title": "Beyond Representational Similarity: Source-Conditioned Description-Length Gain for Generative Plagiarism Detection and Candidate Source Reranking",
  "summary": "Large language models (LLMs) pose challenges to academic integrity and peer review. Yet generative plagiarism detection remains an underexplored and largely unresolved challenge. Prior work on LLM-generated-text detection targets AI involvement, which may be permissible, rather than source reuse, while similarity-based methods struggle after extensive rewriting and multi-source synthesis. Motivated by the description-length view of probabilistic prediction, in which relevant side information can",
  "authors": "Peijia Guo, Wenxuan Xie, ZiGuang Li, Ming Li",
  "category": "research",
  "topics": "copyright-ip",
  "orgs": null,
  "regions": null,
  "published_at": "2026-08-04T16:03:45.000Z",
  "fetched_at": "2026-08-05T05:10:44.550Z",
  "source_slug": "x-arxiv-cs-ai",
  "source_name": "arXiv cs.AI",
  "source_homepage": "https://arxiv.org/list/cs.AI/recent",
  "ethics_ai_record_url": "https://ethics.ai/record/16546",
  "original_url": "https://arxiv.org/abs/2608.03859v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}