{"slug": "why-ai-detection-fails-for-academic-integrity", "title": "Why AI Detection Fails for Academic Integrity", "summary": "A new arXiv study (2608.11256v1) finds that commercial AI detectors cannot reliably distinguish AI-assisted editing from full AI drafts, flagging guideline-compliant 'refine abstract only' edits at 64–80% rates (Pangram/GPTZero) while unmodified 2023–2025 originals are flagged at 9–15%, with non-STEM rates significantly higher (p<0.001). After Undetectable AI humanization, fewer than 4% of AI-labeled rewrites remain flagged (FNR >96%), meaning honest AI editing carries higher sanction risk than evasion, so detector scores should not be standalone misconduct evidence.", "body_md": "arXiv:2608.11256v1 Announce Type: new\nAbstract: Institutions use commercial AI detectors for academic integrity, yet detectors cannot distinguish AI editing from full LLM drafts and may treat both as misconduct. In a controlled study of published English abstracts (four domains; 2013 to 2015 vs. 2023 to 2025), we quantify this policy failure under proxy human/AI labels at tau=0.50. Light \"refine abstract only\" edits, a proxy for guideline-compliant AI assistance, are flagged at 64 to 80% (Pangram/GPTZero). Unmodified 2023 to 2025 originals are flagged at 9 to 15%, with non-STEM rates far above STEM (p<0.001); elevated scores track long-token and Academic Word List density, not authorship intent alone. After Undetectable AI humanization, evasion is near-total: fewer than 4% of AI-labeled rewrites remain flagged (post-humanization detection rate <4%; FNR >96%). Honest AI-editing results in a higher sanction risk than humanizer-assisted evasion. Therefore, detector scores should not serve as standalone misconduct evidence.", "url": "https://wpnews.pro/news/why-ai-detection-fails-for-academic-integrity", "canonical_source": "https://arxiv.org/abs/2608.11256", "published_at": "2026-08-13 04:00:00+00:00", "updated_at": "2026-08-13 04:14:15.856041+00:00", "lang": "en", "topics": ["artificial-intelligence", "ai-policy", "ai-ethics"], "entities": ["arXiv", "Pangram", "GPTZero", "Undetectable AI"], "alternates": {"html": "https://wpnews.pro/news/why-ai-detection-fails-for-academic-integrity", "markdown": "https://wpnews.pro/news/why-ai-detection-fails-for-academic-integrity.md", "text": "https://wpnews.pro/news/why-ai-detection-fails-for-academic-integrity.txt", "jsonld": "https://wpnews.pro/news/why-ai-detection-fails-for-academic-integrity.jsonld"}}