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

Open canonical 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-Autoresearch

Classifications

Nature: Tool

Measurement history

Comparable readings are grouped by signal and unit.

Stars

166stars · Oct 21, 2026

+10 (+6.4 %)since Sep 22, 2026

Exact values · 30 readings

Measured	stars	Change
Oct 21, 2026	166	0
Oct 20, 2026	166	+1
Oct 19, 2026	165	0
Oct 18, 2026	165	+1
Oct 17, 2026	164	+1
Oct 16, 2026	163	0
Oct 15, 2026	163	+1
Oct 14, 2026	162	+2
Oct 13, 2026	160	0
Oct 12, 2026	160	0
Oct 11, 2026	160	0
Oct 10, 2026	160	-1
Oct 9, 2026	161	0
Oct 8, 2026	161	+1
Oct 7, 2026	160	+1
Oct 6, 2026	159	+2
Oct 5, 2026	157	0
Oct 4, 2026	157	0
Oct 3, 2026	157	0
Oct 2, 2026	157	-1
Oct 1, 2026	158	0
Sep 30, 2026	158	+1
Sep 29, 2026	157	+1
Sep 28, 2026	156	0
Sep 27, 2026	156	0
Sep 26, 2026	156	0
Sep 25, 2026	156	0
Sep 24, 2026	156	0
Sep 23, 2026	156	0
Sep 22, 2026	156	·