AmirhosseinHonardoust/Cognitivelens-AI-Human-Comparison
CognitiveLens is a Streamlit-powered analytics tool for exploring alignment between human and AI decisions. It visualizes fairness, calibration, and interpretability through metrics like Cohen’s κ, AUC, and Brier score. Designed for ethical AI, bias auditing, and decision transparency in machine learning systems.
This tool helps AI ethics officers, data scientists, and risk managers understand how well AI decision-making aligns with human judgment. You input data containing both human decisions and AI predictions, along with sensitive demographic features. It then outputs visual dashboards and metrics that highlight areas of agreement, disagreement, and potential biases in the AI's performance across different groups.
Use this if you need to evaluate the fairness, consistency, and ethical implications of your AI models by directly comparing their decisions against human experts or ground truth.
Not ideal if you're only interested in optimizing AI model performance metrics like accuracy, without needing to scrutinize the ethical alignment or interpretability of its decisions.
Stars
22
Forks
—
Language
Python
License
MIT
Category
Last pushed
Nov 05, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/AmirhosseinHonardoust/Cognitivelens-AI-Human-Comparison"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
KOKOSde/localmod
Self-hosted content moderation API that outperforms Amazon Comprehend. 100% offline, your data...
Kalebu/Plagiarism-checker-Python
A python project for checking plagiarism of documents based on cosine similarity
credo-ai/credoai_lens
Credo AI Lens is a comprehensive assessment framework for AI systems. Lens standardizes model...
jina-ai/example-app-store
App store search example, using Jina as backend and Streamlit as frontend
ogulcanaydogan/AI-Provenance-Tracker
Open-source multi-modal AI content detection platform, analyses text, images, audio, and video...