This repository contains the artifacts for the following paper:

EXPLORA: AI/ML EXPLainability for the Open RAN
Claudio Fiandrino, Leonardo Bonati, Salvatore d'Oro, Michele Polese, Tommaso Melodia, Joerg Widmer
CoNEXT ’23, December 5–8, 2023, Paris, France
DOI: 10.1145/3629141

In this repository, we include all data and analysis scripts required to reproduce our results. Please see the README files in each sub-directory for further details.

This repository is structured into the following sub-directories:

1. scripts/: Contains the python code to reproduce our results.
2. data/: Contains the data required by the python scripts.
3. results/: Contains intermediate and final results.
4. paper-plots: Contains the TiKZ code to generate the figures of the manuscript.

Tested on Linux 5.11.0-22-generic #23~20.04.1-Ubuntu

• Make sure you have python Python 3.9.13 installed. Create a virtual environment and install the required dependencies (see requirements.txt in the scripts/ directory - run $ pip install -r requirements.txt). Install graphviz too via sudo apt-get install graphviz.
• Clone this repository.
• Follow the instructions in the README of the scripts/ sub-directory for the order of execution of the scripts. Check-back the data/ to make sense of the workflow.
• Find the results of the processing in results/ and the final plots of the paper in paper-plots.