Using Monte Carlo Dropout on the ACORN tracking pipeline, the authors find that epistemic (model) uncertainty is small, aleatoric (data) uncertainty dominates, and tracking efficiency varies by only about 0.04% due to upstream uncertainties.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
hep-ex 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Uncertainty Quantification and Propagation for ACORN, a geometric deep learning tracking pipeline for HEP experiments
Using Monte Carlo Dropout on the ACORN tracking pipeline, the authors find that epistemic (model) uncertainty is small, aleatoric (data) uncertainty dominates, and tracking efficiency varies by only about 0.04% due to upstream uncertainties.