Abstract
This Letter describes a search for narrowly resonant new physics using a machine-learning anomaly detection procedure that does not rely on signal simulations for developing the analysis selection. Weakly supervised learning is used to train classifiers directly on data to enhance potential signals. The targeted topology is dijet events and the features used for machine learning are the masses of the two jets. The resulting analysis is essentially a three-dimensional search π΄ βπ΅β’πΆ, for ππ΄ βΌπͺβ‘(TeV), ππ΅,ππΆ βΌπͺβ‘(100ββGeV) and π΅, πΆ are reconstructed as large-radius jets, without paying a penalty associated with a large trials factor in the scan of the masses of the two jets. The full run 2 βπ =13ββTeV πβ’π collision dataset of 139ββfbβ1 recorded by the ATLAS detector at the Large Hadron Collider is used for the search. There is no significant evidence of a localized excess in the dijet invariant mass spectrum between 1.8 and 8.2 TeV. Cross-section limits for narrow-width π΄, π΅, and πΆ particles vary with ππ΄, ππ΅, and ππΆ. For example, when ππ΄ =3ββTeV and ππ΅ β³200ββGeV, a production cross section between 1 and 5 fb is excluded at 95% confidence level, depending on ππΆ. For certain masses, these limits are up to 10 times more sensitive than those obtained by the inclusive dijet search. These results are complementary to the dedicated searches for the case that π΅ and πΆ are standard model bosons.