Speaker
Jannicke Pearkes
(University of Colorado Boulder (US))
Description
Anomaly detection triggers offer a model-agnostic approach to capturing a wide range of beyond the Standard Model (BSM) signatures, including those from long-lived particles (LLPs). This talk presents an overview of the two machine learning-based anomaly detection triggers deployed in the CMS Level-1 trigger in 2024: AXOL1TL and CICADA. I will discuss their design, implementation, and integration into the CMS trigger. The talk will also outline future directions for enhancing sensitivity to LLPs with such triggers by incorporating Level-1 tracking and precision timing information.
