research-integrity

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

Find and repair substance defects in AI-assisted prose, code, docs, and agent output. Reports defects, never authorship. Structural tests over model judgement, because LLM judges agree with human slop labels at chance.

TRACE protocol for auditing decision-provenance in AI-assisted scientific workflows

Evidence-grounded AI research workflow for traceable claims, explicit uncertainty, causal-language checks, and reviewable JSON, Markdown, and Excel exports.

Linter de integridade científica para Python e Jupyter: detecta data leakage, falta de reprodutibilidade e armadilhas metodológicas. Zero dependências.

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

Evidence-first Agent Skill for Codex & Claude Code: research papers, literature reviews, rebuttals, thesis writing, and academic integrity.

Two-stage adversarial validity audit for AI-produced work: mechanical checks plus an independent cold reviewer, gate freeze, miss ledger, and golden-case recall benchmarks.

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

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。

Local CLI for research-paper reference integrity: fetch reference PDFs, scan for plagiarism & paraphrase, verify citations (flag fabricated + retracted), and auto-fix bib metadata. Stdlib-only.

A small, docs-first workflow for AI-assisted research that keeps claims, sources, uncertainty, review findings and human decisions inspectable.

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

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

A skill for verifying academic citations, source sentences, DOI metadata, and evidence alignment.

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

Responsible use of generative AI in assisted coding