Speaker
Description
Identification (“tagging") of hadronic jets associated with charm and bottom quarks is crucial for many experimental signatures explored with the ATLAS detector at the LHC. Soft Muon Tagging (SMT) is a tagging technique based on the identification of muons from b/c -> mu + X within hadronic jets, complementary to other jet-based algorithms. With the SMT algorithm, muons can be used as a proxy of heavy flavour hadrons for measurements, with benefits for numerous analyses in terms of available features and sensitivity to systematic uncertainties. The current cut-based tagger in ATLAS has a margin for improvement, that can be addressed by efficient Machine Learning (ML) algorithms. This contribution presents MIDDLE, the new ML-based soft muon tagger developed within the ATLAS Collaboration. After presenting its architecture and the development considerations behind it, its computing and physics performance is discussed, showing the significant benefit it can provide to several analysis activities while preserving the advantages of the cut-based tagger, together with ideas and plans for its further development.