A Fast and Scalable Transformer Pipeline for Binary Black Hole Detection

arXiv:2609.00339 · gr-qc, astro-ph.GA · Submitted 2026-08-31 · Read on arXiv

gr-qc, astro-ph.GA

Submitted: 2026-08-31

Updated: 2026-09-23

Code: https://github.com/chayanchatterjee/castor

License: http://creativecommons.org/licenses/by/4.0/

The gist: With the projected increase in the detection rate of compact-binary coalescences in the coming decade, there is critical need to develop fast, robust, and scalable alternatives to matched filtering

Terminology

Abstract

With the projected increase in the detection rate of compact-binary coalescences in the coming decade, there is critical need to develop fast, robust, and scalable alternatives to matched filtering for gravitational-wave searches. Transformer models have revolutionized natural language and audio processing but their application to gravitational-wave astronomy is still largely unexplored. In this work, we introduce, a transformer-based coincident search pipeline for detecting binary black hole gravitational-wave signals from Advanced LIGO detectors. One of the major features of our model is that it allows the false-alarm rate to be estimated via time slides cheaply without requiring repeated evaluations of the neural network. We evaluate on datasets from the Machine-Learning Gravitational-Wave Search Challenge (MLGWSC-1) and on approximately five months of real O3b observing strain. When tested on benchmark datasets, ranks among the most sensitive machine-learning pipelines and successfully recovers the majority of confident events from the GWTC-3 catalog that lie within its training range. We also benchmark against another transformer architecture, GW-Whisper, a domain-adaptation of OpenAI's audio foundation model. We find that substantially outperforms the repurposed audio model in sensitivity and also reduces the computational cost of background estimation by a factor of 20. Our results demonstrate a highly practical, scalable approach for deep-learning gravitational wave searches and empirical background estimation for future observing runs.

Sources

Related papers