Uncertainty Quantification and Propagation for ACORN, a geometric deep learning tracking pipeline for HEP experiments

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Péron, Lukas, Calafiura, Paolo, Ju, Xiangyang, Chan, Jay
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908499309494272
author Péron, Lukas
Calafiura, Paolo
Ju, Xiangyang
Chan, Jay
author_facet Péron, Lukas
Calafiura, Paolo
Ju, Xiangyang
Chan, Jay
contents We have developed an Uncertainty Quantification process for multistep pipelines and applied it to the ACORN particle tracking pipeline. All our experiments are made using the TrackML open dataset. Using the Monte Carlo Dropout method, we measure the data and model uncertainties of the pipeline steps, study how they propagate down the pipeline, and how they are impacted by the training dataset's size, the input data's geometry and physical properties. We will show that for our case study, as the training dataset grows, the overall uncertainty becomes dominated by aleatoric uncertainty, indicating that we had sufficient data to train the ACORN model we chose to its full potential. We show that the ACORN pipeline yields high confidence in the track reconstruction and does not suffer from the miscalibration of the GNN model.
format Preprint
id arxiv_https___arxiv_org_abs_2508_16518
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Uncertainty Quantification and Propagation for ACORN, a geometric deep learning tracking pipeline for HEP experiments
Péron, Lukas
Calafiura, Paolo
Ju, Xiangyang
Chan, Jay
High Energy Physics - Experiment
Data Analysis, Statistics and Probability
We have developed an Uncertainty Quantification process for multistep pipelines and applied it to the ACORN particle tracking pipeline. All our experiments are made using the TrackML open dataset. Using the Monte Carlo Dropout method, we measure the data and model uncertainties of the pipeline steps, study how they propagate down the pipeline, and how they are impacted by the training dataset's size, the input data's geometry and physical properties. We will show that for our case study, as the training dataset grows, the overall uncertainty becomes dominated by aleatoric uncertainty, indicating that we had sufficient data to train the ACORN model we chose to its full potential. We show that the ACORN pipeline yields high confidence in the track reconstruction and does not suffer from the miscalibration of the GNN model.
title Uncertainty Quantification and Propagation for ACORN, a geometric deep learning tracking pipeline for HEP experiments
topic High Energy Physics - Experiment
Data Analysis, Statistics and Probability
url https://arxiv.org/abs/2508.16518