Xai Library

Xai library logo

Our Python library designed to develop explainable machine learning models.

The library provides an integrated pipeline to set up and execute explanation methods for black boxes.

Lore (Stable and Actionable version)

Lore sa image

a local rule-based model-agnostic explanation method providing stable and actionable explanations

ISIC Explanation with ABELE

Isic image

A dedicated interface for an explainer, based on ABELE, for a black-box to classify instances of skin lesions images. The interface is developed to help physicians in the diagnosis of skin cancer. Following the principles of using multiple explanation methods, after classifying an instance, users are presented with two different explanation methods. A counterexample that shows an image classified differently, and a set of exemplar images with the same classification.


reasonX image

REASONX offers declarative, interactive explanations for decision trees, which can be either the primary ML models or global/local surrogate models of any black-box model, making it model-agnostic. It can also integrate background or common sense knowledge through linear constraints. Explanations are presented as factual and contrastive rules, as well as the closest contrastive examples optimized via MILP.

Dr Xai

DrXai logo

Doctor XAI offers explanations for predicting a patient's next most probable diagnoses based on their recent clinical history. We developed a visual interface utilizing progressive disclosure to present information related to a specific instance being classified and explained.

Repositories of selected projects

The following repositories are related to the projects we are working on.

selected publications

  1. Explainable AI for Time Series Classification: A Review, Taxonomy and Research Directions
    Andreas Theissler, Francesco Spinnato, Udo Schlegel, and Riccardo Guidotti
    IEEE Access, Dec 2022
  2. A Survey of Methods for Explaining Black Box Models
    Riccardo Guidotti, Anna Monreale, Salvatore Ruggieri, Franco Turini, Fosca Giannotti, and 1 more author
    ACM Computing Surveys, Aug 2018
  3. Factual and Counterfactual Explanations for Black Box Decision Making
    Riccardo Guidotti, Anna Monreale, Fosca Giannotti, Dino Pedreschi, Salvatore Ruggieri, and 1 more author
    IEEE Intelligent Systems, Nov 2019
  4. Data-Agnostic Local Neighborhood Generation
    Riccardo Guidotti, and Anna Monreale
    In 2020 IEEE International Conference on Data Mining (ICDM) . More Information can be found here , Nov 2020
  5. GLocalX - From Local to Global Explanations of Black Box AI Models
    Mattia Setzu, Riccardo Guidotti, Anna Monreale, Franco Turini, Dino Pedreschi, and 1 more author
    Artificial Intelligence, May 2021

Dissemination toolbox

In this page you can find the elements that make up the corporate image of the XAI Project.


The official logo of the XAI project is composed of two parts: the project mark and the project name. There are also a black and white variant to be used only if the background colour on which the logo is to be placed does not allow for adequate legibility.

xai logo

Official Logo

xai logo

Black and white version

xai logo black

Official Logo - no text

xai logo

Black and white version - no text

xai logo black

You can download the complete logo pack at the following link



The font used is Poppins. Please use preferably total black for the body of the text (#000000).


Primary colors

The official Primary colors of the XAI project are two:



Suggested support colors

The Secondary colors are complementary to our official colors, but are not recognizable identifiers for Xai project. Secondary colors should be used sparingly, that is, in less than 10 percent of the palette in one piece. Use them to accent and support the primary color palette.






Light color palette

Dark color palette


XAI project ack:

This work is supported by the European Community programme under the funding schemes: ERC-2018-ADG G.A. 834756 “XAI: Science and technology for the eXplanation of AI decision making”

SoBigData++ project ack:

This work is supported by the European Union – Horizon 2020 Program under the scheme “INFRAIA-01-2018-2019 – Integrating Activities for Advanced Communities”, Grant Agreement n.871042. “SoBigData++: European Integrated Infrastructure for Social Mining and Big Data Analytics”.