aloth/JudgeGPT

JudgeGPT: An empirical research platform for evaluating the authenticity of AI-generated news. (arXiv:2601.21963 and arXiv:2601.22871)

38
/ 100
Emerging

This platform helps journalists, fact-checkers, and media consumers assess the authenticity of news articles in the age of AI. You provide text fragments, and the system evaluates how well humans distinguish between AI-generated and human-written content, as well as legitimate versus fake news. The output includes quantitative perception data, enabling insights into human susceptibility to AI-generated misinformation.

Use this if you are a researcher or media professional focused on understanding human perception of AI-generated news and misinformation, and need to collect large-scale empirical data on authenticity judgments.

Not ideal if you are looking for an automated tool to detect AI-generated content or fake news without human input, or if you need to evaluate content beyond news articles.

media-literacy misinformation-research journalism-ethics AI-impact-studies public-perception
No Package No Dependents
Maintenance 10 / 25
Adoption 4 / 25
Maturity 16 / 25
Community 8 / 25

How are scores calculated?

Stars

8

Forks

1

Language

Python

License

GPL-3.0

Last pushed

Mar 07, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/generative-ai/aloth/JudgeGPT"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.