Speaker
Description
Multiple proton-proton interactions occur in the same bunch crossing at the LHC (“pile-up”), with the mean number of interactions per bunch crossing reaching up to about 60 in Run 3 and up to about 200 at the High-Luminosity LHC. As a direct consequence, hadronic activity within each bunch crossing increases, making it more difficult to identify collisions of interest pertaining to multi-jet final states. This talk introduces DIPz, an uncertainty-aware Deep Sets–based machine-learning model that estimates each jet’s origin along the beam axis as a Gaussian likelihood using the set of charged-particle tracks matched to the jet. Next, the DIPz per-jet predictions inside an event are combined into a likelihood-based event-level discriminant, which is cut-optimised to select events compatible with having a collision producing a given jet multiplicity of interest. This combined approach provides robust pile-up rejection for multi-jet final states with negligible additional CPU cost, making it suitable for real-time event selection in the ATLAS High-Level Trigger (HLT). Deployed online and used in Run-3 data taking, it provides an early, flavour-agnostic pile-up jet rejection layer at the HLT preselection stage, offering a previously unavailable handle for high-multiplicity jet signatures targeted by the ATLAS experiment.
| I read the instructions above | Yes |
|---|