Skip to content
AI News HubLIVE
Original source2 min read

Memory as transformation: LETHE, a self-referential gan-inspired architecture

Summary

arXiv paper introduces LETHE, a closed-loop GAN-inspired audio system in SuperCollider that evolves a 3x3 mixing matrix and delay lines via a discriminator comparing energy behavior to an initial-state archive, with ablation confirming the generator's necessity.

SourcearXiv Computational LinguisticsAuthor: Francesco Vitucci, Anthony Di Furia, Francesco Scagliola
Memory as transformation: LETHE, a self-referential gan-inspired architecture
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 3 Sep 2026]

Title:Memory as transformation: LETHE, a self-referential gan-inspired architecture

View a PDF of the paper titled Memory as transformation: LETHE, a self-referential gan-inspired architecture, by Francesco Vitucci and 2 other authors

View PDF HTML (experimental)

Abstract: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.

Comments: Accepted at XXV CIM - Colloquio di Informatica Musicale, L'Aquila, 2026

Subjects:

Computation and Language (cs.CL)

ACM classes: H.5.5

Cite as: arXiv:2609.04289 [cs.CL]

(or arXiv:2609.04289v1 [cs.CL] for this version)

https://doi.org/10.48550/arXiv.2609.04289

arXiv-issued DOI via DataCite

Submission history

From: Francesco Scagliola [view email] [v1] Thu, 3 Sep 2026 11:38:31 UTC (454 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Memory as transformation: LETHE, a self-referential gan-inspired architecture, by Francesco Vitucci and 2 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.CL

new | recent | 2026-09

Change to browse by:

cs

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

ResearchersAdvanced

Key points

  • LETHE uses a GAN-style generator-discriminator loop without external data, referencing only an archive of the initial state.
  • Audio passes through a 3x3 mixing matrix and two delay lines; nine coefficients and two delay times evolve via discriminator feedback.
  • In 15 ablation sessions, parameter change Δc22 was 0.000, proving the active generator is essential for parametric evolution.

Highlights and analysis are generated automatically and may contain errors. Check the original source.