The Universal Scaling of Subjectivity: Normalized Topological Entropy and the I-Index in Recursive Neural Graphs
The current Paper 41 benchmark does not claim that full subjective phenomenology has been derived from graph theory. It does show that, once recursive-resonance entropy is normalized by the theoretical maximum entropy at the same graph size, a sharp complexity threshold appears. In the present sweep the `N=5` branch remains subcritical with final normalized entropy `0.2576` and final I-index `2.7961`, while the `N=50` and `N=150` branches settle into a low-noise singular regime with final I-index `8.5336` and `9.5919`, respectively.
Authors
- Yaniv Cohen (ORCID: https://orcid.org/0009-0009-2809-0910)
Publication Details
- Journal
- Zenodo (CERN European Organization for Nuclear Research)
- Published
- 2026-05-18
- DOI
- https://doi.org/10.5281/zenodo.20271475
- Primary Topic
- Neural Networks and Applications
- Type
- preprint