| _version_ | 1866901187723264000 |
|---|---|
| author | Jacobs, A. |
| author_facet | Jacobs, A. |
| contents | <p>Recursive Compression is a foundational mechanism describing how systems reduce complexity into representations and iteratively reuse those representations over time.</p> <p>Through repeated cycles of compression, storage, and recursion, systems generate increasingly efficient internal models, enabling scale, coordination, and intelligence. This process underlies physical, biological, cognitive, and symbolic systems.</p> <p>The paper also examines how degradation of fidelity within this process leads to drift, as systems increasingly operate on representations of prior representations rather than direct inputs from reality.</p> |
| format | Recurso digital |
| id | zenodo_https___doi_org_10_5281_zenodo_19928672 |
| institution | Zenodo |
| language | eng |
| publishDate | 2026 |
| publisher | Zenodo |
| record_format | zenodo |
| spellingShingle | Recursive Compression: Iterative Modeling and System Scale Jacobs, A. recursive compression information compression system scaling model recursion representation learning abstraction feedback loops semantic fidelity AI systems cognitive systems complexity reduction model drift <p>Recursive Compression is a foundational mechanism describing how systems reduce complexity into representations and iteratively reuse those representations over time.</p> <p>Through repeated cycles of compression, storage, and recursion, systems generate increasingly efficient internal models, enabling scale, coordination, and intelligence. This process underlies physical, biological, cognitive, and symbolic systems.</p> <p>The paper also examines how degradation of fidelity within this process leads to drift, as systems increasingly operate on representations of prior representations rather than direct inputs from reality.</p> |
| title | Recursive Compression: Iterative Modeling and System Scale |
| topic | recursive compression information compression system scaling model recursion representation learning abstraction feedback loops semantic fidelity AI systems cognitive systems complexity reduction model drift |
| url | https://doi.org/10.5281/zenodo.19928672 |