★ GWAK2: Gravitational Wave Anomalous Knowledge using SSL ★

          @misc{ scivideos_oai:cds.cern.ch:3025623,
            doi = {},
            url = {https://videos.cern.ch/record/3025623},
            author = {},
            keywords = {},
            language = {en},
            title = {* GWAK2: Gravitational Wave Anomalous Knowledge using SSL *},
            publisher = {},
            year = {2026},
            month = {may},
            note = {oai:cds.cern.ch:3025623 see, \url{https://scivideos.org/cern-cds/3025623}}
          }
          

Abstract

Since the first gravitational-wave detection by ground-based interferometers, after more than a decade of observations has yielded over one hundred compact binary coalescence (CBC) events, whose waveforms can be well-modeled by general relativity. These well-modeled signals enable detection pipelines based on matched filtering, which search for waveform consistency against the CBC template bank. However, within the sensitivity band of the LIGO–Virgo–KAGRA Collaboration detectors, a broader class of astrophysical sources such as core-collapse supernovae and other transient phenomena are poorly modeled or inherently unpredictable. Consequently, these sources cannot be efficiently captured by template-based searches, motivating the need for waveform-agnostic detection strategies. To address this challenge, we develop Gravitational Wave Anomalous Knowledge (GWAK), a machine learning–based search framework designed for generic transient detection. GWAK employs a semi-supervised embedding model using Self Supervised Learning to learn a low-dimensional representation of detector data, followed by a metric model trained on noise data to define a discriminative search space. This approach enables waveform-agnostic searches for gravitational-wave transients and improves the identification and characterization of unexpected signals.

00:00:00 Slide 1
00:00:29 Slide 2
00:01:06 Slide 3
00:01:29 Slide 4
00:02:29 Slide 5
00:03:09 Slide 6
00:03:50 Slide 7
00:04:14 Slide 8
00:04:40 Slide 9
00:05:30 Slide 10
00:05:45 Slide 11
00:06:08 Slide 12
00:06:25 Slide 13
00:06:56 Slide 14
00:07:48 Slide 15
00:09:17 Slide 16
00:10:08 Slide 17
00:10:56 Slide 18
00:11:30 Slide 19
00:11:48 Slide 20
00:12:09 Slide 21
00:12:27 Slide 22
00:13:42 Slide 23
00:15:33 Slide 24
00:18:45 Slide 25
00:19:19 Slide 26
00:19:37 Slide 27
00:20:10 Slide 28
00:21:32 Slide 29
00:22:21 Slide 30