A search for binary mergers in archival LIGO data using aframe, a machine learning detection pipeline

Aframe is a low-latency machine learning detection pipeline for gravitational waves targeting compact binary sources. In a separate presentation at this conference, we demonstrate aframe's state-of-the-art sensitivity for a subset of the binary black hole population over the LIGO-Virgo-KAGRA (LVK) collaboration's third observing run (O3) using simulations. In this work, we present aframe's results from a search over the entire O3, analyzing 10 years of background data to assign false alarm rates to detections. We compare aframe's detections with those reported by matched filtering searches as reported by the LVK in event catalog GWTC-3, discussing commonalities and differences in detections. We also discuss the prospects of machine learning approaches for real-time detection as well as end-to-end searches for gravitational-wave transients.