PrototypeCommon
wanshuiyin/Anti-Autoresearch
Don't trust an autoresearch paper at face value. Reviewer-side integrity forensics (self-consistency + fabrication), deterministic verdict. 61 signals: 46 integrity hack-patterns (families A–H, verdict-bearing) + 13 zero-weight AI writing-style impressions (AIS) + 2 advisory. Not an opaque AI-text…
- Owner
- wanshuiyin (personal account)
- Stars
- Stars: 176
- Forks
- Forks: 8
- Language
- Python
- License
- MIT
- Created
- 2026
- Topics
- ai-generated-contentai-scientistautoresearchforensicsllm-agentspeer-reviewresearch-integrityai-researcharisclaude
- Tier
- Prototype (100 to 249 ★) What this tier means
More repos by wanshuiyin
All 4 repos by wanshuiyin- wanshuiyin/Auto-claude-code-research-in-sleepStars: 18,595PythonStable
- wanshuiyin/HERO-Anti-OverDefenseStars: 762PythonBeta
- wanshuiyin/ARIS-in-AI-OfferStars: 635PythonAlpha
Nearby in Python
All Python repos- seedleap/zing-world-modelStars: 176PythonPrototype
- Lucasuiii/modeling-workbenchStars: 176PythonPrototype
- GroundedCoreAI/nexusdeskStars: 176PythonPrototype
- MacSysadmin/pymacadminStars: 176PythonPrototype
- leah/python-oauthStars: 176PythonPrototype
- tobami/overmindStars: 176PythonPrototype