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 Plus annual

Presents the access of premium content as premium feature

Premium Content

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 Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The LHCb experiment at the Large Hadron Collider (LHC) is designed to performhigh-precision measurements of heavy-hadron decays, which requires thecollection of large data samples and a good understanding and suppression ofmultiple background sources. Both factors are challenged by a five-foldincrease in the average number of proton-proton collisions per bunch crossing,corresponding to a change in the detector operation conditions for the LHCbUpgrade I phase, recently started. A further ten-fold increase is expected inthe Upgrade II phase, planed for the next decade. The limits in the storagecapacity of the trigger will bring an inverse relation between the amount ofparticles selected to be stored per event and the number of events that can berecorded, and the background levels will raise due to the enlargedcombinatorics. To tackle both challenges, we propose a novel approach, neverattempted before in a hadronic collider: a Deep-learning based Full EventInterpretation (DFEI), to perform the simultaneous identification, isolationand hierarchical reconstruction of all the heavy-hadron decay chains per event.This approach radically contrasts with the standard selection procedure used inLHCb to identify heavy-hadron decays, that looks individually at sub-sets ofparticles compatible with being products of specific decay types, disregardingthe contextual information from the rest of the event. We present the firstprototype for the DFEI algorithm, that leverages the power of Graph NeuralNetworks (GNN). This paper describes the design and development of thealgorithm, and its performance in Upgrade I simulated conditions.

GNN for Deep Full Event Interpretation and hierarchical reconstruction of heavy-hadron decays in proton-proton collisions