Aad, G.Abbott, B.Abeling, K.Abicht, N. J.Abidi, S. H.Aboulhorma, A.Çetin, Serkant Ali2024-05-192024-05-1920231748-0221https://doi.org10.1088/1748-0221/18/11/P11006https://hdl.handle.net/20.500.12713/5653The ATLAS experiment relies on real-time hadronic jet reconstruction and b-tagging to record fully hadronic events containing b-jets. These algorithms require track reconstruction, which is computationally expensive and could overwhelm the high-level-trigger farm, even at the reduced event rate that passes the ATLAS first stage hardware-based trigger. In LHC Run 3, ATLAS has mitigated these computational demands by introducing a fast neural-network-based b-tagger, which acts as a low-precision filter using input from hadronic jets and tracks. It runs after a hardware trigger and before the remaining high-level-trigger reconstruction. This design relies on the negligible cost of neural-network inference as compared to track reconstruction, and the cost reduction from limiting tracking to specific regions of the detector. In the case of Standard Model HH -> b (b) over barb (b) over bar, a key signature relying on b-jet triggers, the filter lowers the input rate to the remaining high-level trigger by a factor of five at the small cost of reducing the overall signal efficiency by roughly 2%.eninfo:eu-repo/semantics/openAccessTrigger AlgorithmsTrigger Concepts And Systems (Hardware And Software)Article1811WOS:0011237919000042-s2.0-85180406982N/A10.1088/1748-0221/18/11/P11006Q2