ReX-XAI/ReX
Causal Responsibility EXplanations for Image Classifiers and Tabular Data
This tool helps data scientists and machine learning engineers understand why an AI model made a specific decision on an image or tabular data. You feed it an input image or dataset and the AI's classification, and it produces a 'responsibility map' showing the exact pixels or data points that causally led to that decision, along with a minimal explanation. This allows for deep insights into model behavior without needing to know its internal workings.
Use this if you need to understand the causal reasons behind your AI model's image or tabular data classifications, especially for black-box models.
Not ideal if you are looking for explanations for text-based models or if you need to interpret the internal mechanisms of a white-box AI.
Stars
41
Forks
8
Language
Python
License
MIT
Category
Last pushed
Feb 23, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/ReX-XAI/ReX"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
shap/shap
A game theoretic approach to explain the output of any machine learning model.
mmschlk/shapiq
Shapley Interactions and Shapley Values for Machine Learning
iancovert/sage
For calculating global feature importance using Shapley values.
aerdem4/lofo-importance
Leave One Feature Out Importance
predict-idlab/powershap
A power-full Shapley feature selection method.