Anti-Autoresearch — tool profile and history

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 classifier. The dual of ARIS.

Active

Canonical source ↗

Language
Python
License
MIT
Created
Last activity
Topics
  • ai-generated-content
  • ai-research
  • ai-scientist
  • aris
  • autoresearch
  • claude
  • claude-code
  • claude-code-skills
  • codex
  • forensics
  • gpt
  • llm
  • llm-agents
  • machine-learning
  • mcp
  • ml-research
  • openai
  • paper-review
  • peer-review
  • research-integrity

Current measurement

149GitHub stars+7 (+4.9 %)
measured growth

Momentum uses available readings from the last 7 days: measured with at least two comparable readings, estimated otherwise.

Reading history

90 days · 90 maximum readings
DateValueMetric
149GitHub stars
144GitHub stars
142GitHub stars
142GitHub stars
142GitHub stars
142GitHub stars
142GitHub stars
142GitHub stars
141GitHub stars
140GitHub stars
140GitHub stars
139GitHub stars
139GitHub stars
138GitHub stars
137GitHub stars
137GitHub stars
135GitHub stars
135GitHub stars
135GitHub stars
135GitHub stars
134GitHub stars
132GitHub stars

Classifications

Domains
Type
Other
Use cases

These entries declare the same topics. No similarity is inferred: only the shared topics are stated.