{"slug": "memory-as-transformation-lethe-a-self-referential-gan-inspired-architecture", "title": "Memory as transformation: LETHE, a self-referential gan-inspired architecture", "summary": "Researchers introduced LETHE (Latent-parameter Evolution with Temporal Hierarchical quasi-Equilibrium), a self-referential sonic-oblivion system implemented in SuperCollider that adapts GAN-inspired architecture without external datasets. In 15 ablation sessions, the active generator was necessary for parametric evolution, with Δc22 = 0.000 in all cases, confirming its role in the closed-loop system.", "body_md": "arXiv:2609.04289v1 Announce Type: new \nAbstract: LETHE (Latent-parameter Evolution with Temporal Hierarchical quasi-Equilibrium) is a self-referential sonic-oblivion system implemented in SuperCollider. It adopts the formal vocabulary of Generative Adversarial Networks in a closed configuration without external datasets or supervision after initialization. Audio is processed by a 3 x 3 mixing matrix built around two delay lines; its nine coefficients and two delay times evolve through the interaction of a five-feature linear discriminator and a random-perturbation optimizer analogous to single-sample REINFORCE. The discriminator compares current energy behavior with an archive of the initial state and guides parameter updates. Circular, fixed, and live sources can be mixed independently. Across fixed and circular sessions with an ablation control, the active generator is necessary for parametric evolution ($\\Delta c_{22}=0.000$ in all 15 ablation sessions). Situated in the tradition of self-referential electroacoustic music, LETHE delegates the sonic outcome to an adaptive closed loop whose parametric space is defined by the composer.", "url": "https://wpnews.pro/news/memory-as-transformation-lethe-a-self-referential-gan-inspired-architecture", "canonical_source": "https://arxiv.org/abs/2609.04289", "published_at": "2026-09-07 04:00:00+00:00", "updated_at": "2026-09-07 04:25:23.182591+00:00", "lang": "en", "topics": ["artificial-intelligence", "machine-learning", "generative-ai"], "entities": ["LETHE", "SuperCollider"], "alternates": {"html": "https://wpnews.pro/news/memory-as-transformation-lethe-a-self-referential-gan-inspired-architecture", "markdown": "https://wpnews.pro/news/memory-as-transformation-lethe-a-self-referential-gan-inspired-architecture.md", "text": "https://wpnews.pro/news/memory-as-transformation-lethe-a-self-referential-gan-inspired-architecture.txt", "jsonld": "https://wpnews.pro/news/memory-as-transformation-lethe-a-self-referential-gan-inspired-architecture.jsonld"}}