AI Insight
Researchers developed ORCA (Organized Representation via Contrastive learning for Anomaly detection), a two-stage machine learning framework for detecting anomalous particle collision events at the Large Hadron Collider. The system first learns to organize different physics processes into distinct regions of an embedding space using contrastive learning, then applies anomaly detection in that space to identify potential new physics signals. Unlike previous approaches, ORCA not only improves detection sensitivity but also makes results interpretable by allowing researchers to determine which known physics processes anomalous events most closely resemble through statistical template fitting.
Why it matters
This approach could accelerate the discovery of new fundamental physics at particle colliders by making anomaly detection more sensitive and interpretable. The ability to characterize what unknown signals resemble in terms of known physics processes provides physicists with actionable insights for follow-up investigations, rather than just flagging events as anomalous without context.
Understand the Science
⚠️ Preprint – Noch nicht peer-reviewed
Dieser Artikel wurde noch nicht von unabhängigen Experten begutachtet. Die Ergebnisse sind vorläufig und sollten mit Vorsicht interpretiert werden.
Abstract: Generic event-level anomaly detection for collider physics has two recurring problems: anomaly scores are hard to interpret, and they correlate strongly with energy scale and object multiplicity. We present Organized Representation via Contrastive learning for Anomaly detection (ORCA), a two-stage framework that first learns an embedding space via supervised contrastive learning across a diverse set of physics processes, then runs a standard autoencoder in that space to generate event-level anomaly scores. On a simulated dataset consistent with conditions at the High-Luminosity Large Hadron Collider, ORCA delivers significant gains in both breadth and depth of sensitivity to new physics signals with respect to a baseline autoencoder architecture. Beyond improved sensitivity, the contrastive embedding makes the anomalous sample interpretable: because known processes occupy distinct regions of the space, a maximum-likelihood template fit to the embedding distributions can attribute events in an anomalous sample to template physics processes with quantified uncertainties. We demonstrate that the fit accurately recovers injected signal yields, including for signals excluded from the training of the embedding, and characterizes signals absent from the template library through the known processes they most resemble. These results establish ORCA as a route to interpretable anomaly detection-based searches at colliders, where the embedding geometry carries higher dimensional physics information compared to standard one-dimensional output fits, enhancing downstream statistical analysis.
Source: Contrastive Learning for Interpretable Anomaly Detection at Collider Experiments