Maya-Morphe: Bioelectric Gradient Fields as Computational Topology Primitives for Self-Organising Neural Architectures

Version 2 (2026-08-04). Revised to the NLL Universal Paper Format v6. The original text is retained in full; nothing has been deleted. Corrections appear as marked blocks placed at the section that carries the claim, and each one states what the paper said, what the data show, the corrected claim, why it happened, and what still stands. This version corrects the load-bearing comparison.99.7% recovery is reported against a fixed-topology arm the paper itself defines as 0.0% twice, and the code confirms that branch returns before any timestep runs; the only informative comparison is against the scripted timer — 99.7% vs 99.5% overall, 98.7% vs 98.1% at the largest amputation.The voltage-propagation mechanism stands and does win narrowly at the hardest damage level; Mordvintsev et al. (2020), Growing Neural Cellular Automata, is now cited as the nearest prior work. Everything below this line is the original description from version 1. It is retained unchanged for the record. Where it conflicts with the corrections above, the corrections stand. Two framings it repeats have since been withdrawn in full — the Bhaya Quiescence Law and the Buddhi S-Curve. Both are addressed in Maya-Meta P1, now superseded, and in the self-audit of Maya-Meta P2. Maya-Morphe introduces a morphogenetic computing framework in which neural network topology self-organises through spatial bioelectric voltage gradient fields, drawing direct inspiration from Michael Levin's research on bioelectric tissue regeneration in planaria flatworms — asking, in computational form, whether a neural network can regrow what it loses. The framework formalises Functional Recovery Rate (FRR) as the first dedicated evaluation metric for morphogenetic topology repair, providing a rigorous basis for comparing self-organising and fixed-architecture systems. Across 36 systematic ablation trials (3 conditions × 4 damage fractions × 3 seeds), voltage-driven spatial field repair achieved 99.7% mean FRR with 12/12 full recoveries at all tested damage fractions, compared to 0.0% FRR for the fixed-topology baseline — a gap of 99.7 percentage points constituting the paper's central empirical claim. As part of the Maya-Morphe Series on morphogenetic neural networks for biological wound repair simulation, this work also tests the Bhaya Quiescence Law from the Maya SNN series and reports it as modified in dynamic-topology substrates, with wound-response crisis fractions of approximately 4.87% against the expected 0.32%, a deviation that is biologically predicted and validated; the Vairagya decay constant (0.002315) is embedded in all canonical hyperparameters as a tamper-evident provenance marker. Series: Part of the Maya-Morphe Series — morphogenetic neural networks for biological wound repair simulation. Bhaya Quiescence Law applies in modified form: dynamic-topology substrates show elevated β during active wound repair — biologically predicted and validated. Links: GitHub Repository (private — to request access: email research@nexuslearninglabs.in with subject Code Access Request — Maya-Morphe-P1 and your research context) | Interactive Dashboard | FAQ | Full Series Index — venky2099.github.io Nexus Learning Labs, Bengaluru · UDYAM-KR-02-0122422 · BHASKAR IN-0526-9452JSORCID: 0000-0002-3315-7907 · VAIRAGYA_DECAY_RATE = 0.002315 — an ORCID-derived provenance mark, not an experimental parameter. Each paper's disclosure block states whether it reached a result in that paper.Canary: MayaNexusVS2026NLL_Bengaluru