Anti-Autoresearch
OtherGitHubActivePython
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.
Description provenance: Original source
Measured: Oct 21, 2026 · 69 observations
Domains & Uses
- Domains
- Agents, skills and MCP
- Uses
- Code assistants
Check at the source
Compatibility and prerequisites must be checked in the official documentation.
https://github.com/wanshuiyin/Anti-AutoresearchClassifications
- Nature
- Tool
Measurement history
Comparable readings are grouped by signal and unit.
Stars
166stars · Oct 21, 2026
+3 (+1.8 %)since Oct 15, 2026
Exact values · 7 readings
| Measured | stars | Change |
|---|---|---|
| 166 | 0 | |
| 166 | +1 | |
| 165 | 0 | |
| 165 | +1 | |
| 164 | +1 | |
| 163 | 0 | |
| 163 | · |