First machine learning gravitational-wave search mock data challenge

We present the results of first Machine Learning Gravitational-Wave Search Mock Data Challenge (MLGWSC-1). For this challenge, participating groups had to identify gravitational-wave signals from binary black hole mergers increasing complexity and duration embedded in progressively more realistic noise. The final 4 provided datasets contained real noise O3a observing run up a 20 seconds with inclusion precession effects higher order modes. average sensitivity distance runtime for 6 entered algorithms derived 1 month test data unknown participants prior submission. Of these, are machine learning algorithms. find that best based able achieve 95% sensitive matched-filtering production analyses simulated Gaussian at false-alarm rate (FAR) one per month. In contrast, noise, leading search achieved 70%. FARs differences shrink point where select submissions outperform traditional $\geq 200$ on some datasets. Our show current may already be enough limited parameter regions useful settings. To improve state-of-the-art, need reduce rates which they capable detecting extend their validity space modeled searches computationally expensive run. Based our findings we compile list research areas believe most important elevate an invaluable tool signal detection.