Beschreibung:
<jats:title>A<jats:sc>bstract</jats:sc>
</jats:title><jats:p>We leverage representation learning and the inductive bias in neural-net-based Standard Model jet classification tasks, to detect non-QCD signal jets. In establishing the framework for classification-based anomaly detection in jet physics, we demonstrate that, with a <jats:italic>well-calibrated</jats:italic> and <jats:italic>powerful enough feature extractor</jats:italic>, a well-trained <jats:italic>mass-decorrelated</jats:italic> supervised Standard Model neural jet classifier can serve as a strong generic anti-QCD jet tagger for effectively reducing the QCD background. Imposing <jats:italic>data-augmented</jats:italic> mass-invariance (and thus decoupling the dominant factor) not only facilitates background estimation, but also induces more substructure-aware representation learning. We are able to reach excellent tagging efficiencies for all the test signals considered. In the best case, we reach a background rejection rate of 51 and a significance improvement factor of 3.6 at 50% signal acceptance, with the jet mass decorrelated. This study indicates that supervised Standard Model jet classifiers have great potential in general new physics searches.</jats:p>