English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

The operating conditions defining the current data taking campaign at theLarge Hadron Collider, known as Run 3, present unparalleled challenges for thereal-time data acquisition workflow of the LHCb experiment at CERN. To addressthe anticipated surge in luminosity and consequent event rate, the LHCbexperiment is transitioning to a fully software-based trigger system. Thisevolution necessitated innovations in hardware configurations, softwareparadigms, and algorithmic design. A significant advancement is the integrationof monotonic Lipschitz neural networks into the LHCb trigger system. These deeplearning models offer certified robustness against detector instabilities, andthe ability to encode domain-specific inductive biases. Such properties arecrucial for the inclusive heavy-flavour triggers and, most notably, for thetopological triggers designed to inclusively select $b$-hadron candidates byexploiting the unique kinematic and decay topologies of beauty decays. Thispaper describes the recent progress in integrating Lipschitz neural networksinto the topological triggers, highlighting the resulting enhanced sensitivityto highly displaced multi-body candidates produced within the LHCb acceptance.

Applications of Lipschitz neural networks to the Run 3 LHCb trigger system