Anti-Autoresearch 🛡️

🔬 The field has tolerated unreliable autoresearch long enough — Anti-Autoresearch is the read that finally catches it.

天下苦 autoresearch 久矣 —— Anti-Autoresearch 替研究者们一眼看穿不靠谱的工作。

🏆 Built on a battle-tested foundation: ARIS (~12.5k★ · HuggingFace Daily Papers #1 · 78+ skills across 7+ platforms). Anti-Autoresearch points ARIS's production audit DNA (experiment-audit · paper-claim-audit · citation-audit · kill-argument) outward — auditing a third party's submission instead of your own.

Autoresearch has gone mainstream, and a fast-growing share of what reaches the review pile is machine-generated — and a lot of it doesn't hold up: tables that don't match the text, baselines that aren't there, open-sourced code that won't reproduce its own paper. Reviewers, area chairs, and honest authors increasingly need to verify that, not just suspect it.

Regardless of who or what wrote a paper, does the science hold together and reflect its own evidence? Anti-Autoresearch audits a submission for self-consistency and fabrication, and produces a span-anchored, reviewer-ready report. It is not an opaque AI-text classifier (no authorship probabilities, no "AI-written" verdict) and does not judge misconduct — it surfaces discrepancies a human reviewer should investigate. Separately, it lists transparent, itemized AI writing-style impressions in a quarantined, zero-verdict-weight section (a paper can be integrity-CLEAN while listing many), because reviewers react to them.

---

🧭 What's inside

46 integrity patterns across 8 families — the coverage vocabulary every finding cites — plus 13 zero-weight AI writing-style impressions and 2 advisories:

	Family	Catches
A	Numeric self-consistency	数值自洽:table vs text vs delta arithmetic that doesn't add up
B	Method & scope	方法与范围:the described method/scope ≠ what was actually done
C	Baseline integrity	baseline 诚信:missing, weak, or unfairly configured comparisons
D	Experiment integrity	实验诚信:fake ground truth, phantom results, code ≠ numbers (needs code)
E	Citation integrity	引用诚信:fabricated, misattributed, or retracted references
F	Presentation & surface	表面信号:layout / prose / figure signals — capped at minor
G	Proof & derivation	证明诚信:skipped obligations, circular or invalid derivations
H	Evaluation design & validity	评测设计:data leakage, LLM-judge validity, selective reporting

Delivered as 11 skills + 1 orchestrating workflow on a deterministic spine: a span-anchored, hashed evidence ledger → LLM auditors that only propose findings → a rules-only reporter that lists every proposal with what the auditor said about it, and summarizes — with 8 patterns eval-gated end-to-end (GRIM · GRIMMER · statcheck · delta arithmetic · hedge-density · …) and the whole gate in CI.

---

📰 News