Dataset associated to the publication "Convergent approaches to AI Explainability for HEP muonic particles pattern recognition", Leandro Maglianella, Lorenzo Nicoletti, Stefano Giagu*, Christian Napoli, and Simone Scardapane, submitted to Computing and Software for Big Science. *corresponding author: stefano.giagu [AT] uniroma1.it Description: provided as a compressed zip file. Contains 7 numpy .npy files: train_images_with_noise.npy: numpy array containing 850003 "images" of muonic tracks with detector noise (shape (850003, 9, 384)). Each image contains 1 muonic track. train_images_without_noise.npy: numpy array containing 850003 "images" of muonic tracks w/o detector noise (shape (850003, 9, 384)). Each image contains 1 muonic track. train_labels.npy: labels associated to each image (shape (850003, 5)), corresponding to (pT, eta, phi, 0, nhits) of the muonic track, with pT: transverse momentum, eta: pseudo-rapidity, phi: azimuthal angle, and nhits: the number of pixels turned on by the muon test_images_with_noise.npy: same as above for a 94445 images test set test_images_without_noise.npy: same as above for a 94445 images test set test_labels.npy: same as above for a 94445 images test set images_only_noise.npy: numpy array containing 944448 "images" w/o muons, containing detector noise only (shape (944448, 9, 384))

This research was funded by the CHIST-ERA grant number CHIST-ERA-19-XAI- 009.