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.

Tool for automatically detecting predatory journals and conferences using multiple authoritative data sources

A beta version of the GAIDeT Declaration Generator — a lightweight HTML tool to help researchers transparently disclose which scientific tasks were delegated to generative AI, based on the GAIDeT taxonomy.

Distributed integrity infrastructure for collusion-resistant independent verification. Blind peer validation of any verifiable claim — scientific, regulatory, or institutional — recorded as tamper-evident Harmony Records. Built in Rust on Holochain.

Lightweight git hook to detect hallucinated citations in AI-generated text

🪞 Catch false positives/negatives in AI eval claims — pre-registration, fair-baseline, small-sample CI. Zero training, zero deps.

Cite Lens: An AI Tool for Detecting Out-of-Scope and Out-of-Context Citations; Conference paper accepted at TPDL 2025

A CLI and library that verifies academic reference lists against open scholarly databases to detect hallucinated or metadata-corrupted citations.

AI for Qualitative Analysis: A Practical Guide for Researchers

Open Research Integrity: evidence-backed manuscript review test runner and AI reviewer protocol

Responsible use of generative AI in assisted coding

超级耿同学 — 学术论文多维度异常检测框架。不简单给二值判断，用贝叶斯证据网络对每条证据建模，输出带不确定性的后验造假概率。理工科7维+文科5维+因果推断+图像法医。

AI-assisted screening for data-integrity fingerprints in scientific papers · 学术论文数据完整性筛查流水线(耿同学)

Agentic LLM research transparency pipeline: Lancet Digital Health Viewpoint with reproducible oncology case study, AI disclosure ledger, reviewer transcripts, and three-layer audit architecture for research integrity.

Statistical anomaly screener for tabular research data — flags anomalies, never fraud; 30 detectors + plugin system + optional multi-tenant Web UI.

An independent, power-aware falsification referee for quantitative finance claims. Multiple-testing-aware and self-calibrating; a referee for research, not a trading system.

Pre-submission research data audit toolkit for reproducibility checks, statistical consistency screening, manuscript/material review, and research integrity workflows.

Open-source medical citation verifier: catches fabricated DOI/PMID/NCT references with CLI, MCP, and Claude Code skill.

Run unit tests on your manuscript. Check every manuscript claim against its cited evidence. Human-first, AI-second, Zotero-audited, local-first.

Sanitized software R&D methodology case study with honest NO-GO track closure.