Approaching an unknown communication system by latent space exploration and causal inference
5 affiliations
- 1Department of Linguistics, University of California 1 , Berkeley, Berkeley, CA, USA
- 2Project CETI 2 , New York, NY, USA and Roseau, Dominica
- 3Department of Statistics, University of Michigan 3 , Ann Arbor, MI, USA
- 4Department of Biology, Carleton University 4 , Ottawa, Canada
- 5The Dominica Sperm Whale Project 5 , Roseau, Dominica
Abstract
We propose a methodology for discovering meaningful properties in data without ground truth by combining manipulation of the latent variables of generative models to extreme values with causal inference in an approach we call causal disentanglement with extreme values (CDEV). Using it, we investigate what properties the model encodes as meaningful when trained on raw audio of sperm whale (Physeter macrocephalus) communication. The method suggests that the model considers the number of clicks in a sequence, the regularity of their timing, as well as audio properties such as the spectral mean and the acoustic regularity of the sequences as the main components for generating believable and informative data. The first two are consistent with existing hypotheses, while the last two are proposed for the first time. We also argue that our models uncover rules that govern the structure of units in the communication system, suggesting the methodology as a viable strategy for approaching unknown data.
Related
- A hierarchical navigation decision-making method for UAV swarms in unknown communication-constrained environments
- Spatial cell-cell communication inference based on cell-spot-ligand-receptor heterogeneous graphs
- BoneGraph: A Domain-Specialised, Self-Correcting Reasoning System for Bone Science Retrieval, Grounded Inference, and Image Mechanics
- Assessment and Supplementation of Antioxidant Amines in Male Infertility—Are We Approaching Clinical Implementation?
- Thalamic stereo-EEG detects sleep stages N2 and N3 with discrimination approaching scalp EEG
BibTeX
@article{begus2026approaching,
title = {{Approaching an unknown communication system by latent space exploration and causal inference}},
author = {Gašper Beguš and Andrej Leban and Shane Gero},
journal = {Royal Society Open Science},
year = {2026},
month = aug,
doi = {10.1098/rsos.250829},
url = {https://doi.org/10.1098/rsos.250829},
note = {CC BY},
}
RIS
TY - JOUR
TI - Approaching an unknown communication system by latent space exploration and causal inference
AU - Gašper Beguš
AU - Andrej Leban
AU - Shane Gero
PY - 2026
DA - 2026/08/26
JO - Royal Society Open Science
DO - 10.1098/rsos.250829
UR - https://doi.org/10.1098/rsos.250829
AB - We propose a methodology for discovering meaningful properties in data without ground truth by combining manipulation of the latent variables of generative models to extreme values with causal inference in an approach we call causal disentanglement with extreme values (CDEV). Using it, we investigate what properties the model encodes as meaningful when trained on raw audio of sperm whale (Physeter macrocephalus) communication. The method suggests that the model considers the number of clicks in a sequence, the regularity of their timing, as well as audio properties such as the spectral mean and the acoustic regularity of the sequences as the main components for generating believable and informative data. The first two are consistent with existing hypotheses, while the last two are proposed for the first time. We also argue that our models uncover rules that govern the structure of units in the communication system, suggesting the methodology as a viable strategy for approaching unknown data.
SN - 2054-5703
ER -