Convergent approaches to AI Explainability for HEP muonic particles pattern recognition Dataset

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