Nociceptive Metaplasticity and Graceful Decay in Spiking Neural Networks: Towards Survival-Driven Continual Learning

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 adds disclosures; no claim is retracted.The 66.6% elevated learning velocity is shown to be arithmetic — 0.016655 / 0.009999 = 1 + 4 × lability — so no run could have returned another ratio; "identical across three seeds" is a re-run of a deterministic system, not a replication; and the asymmetric-protection claim was never measurable, since the decay term moves both pathways by ~0.5% over 50 ticks.The dual-rule mechanism, the Phase B null (40 pain injections, zero weight change), and the pre-retrofit decay rate of 0.0001 all stand. 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 Two framings it repeats have since been withdrawn in full — the Bhaya Quiescence Law and the Buddhi S-Curve. Both are addressed in Maya-Meta P1, now superseded, and in the self-audit of Maya-Meta P2. This paper introduces Maya, a spiking neural network architecture that addresses a core limitation in artificial intelligence — the inability to simultaneously learn new information and retain existing knowledge — by drawing on biological mechanisms of pain signalling and selective memory consolidation. The system implements two concurrent processes on a shared synaptic weight matrix: nociceptive metaplasticity, which uses pain-like signals to accelerate learning on threat-relevant pathways, and Vairagya-governed heterosynaptic decay, which selectively protects high-salience connections while allowing low-salience ones to fade gracefully. Experiments across a four-phase controlled protocol (N=3, fully deterministic across seeds) demonstrate asymmetric synaptic protection, with the fear→trust pathway emerging from zero to 0.191 under pain-induced metaplasticity while the simultaneously active trust→aliveness pathway strengthened independently to 0.497 — both operating on the same weight matrix within the same temporal window, representing a 66.6% increase in learning velocity on threat-relevant pathways. This work is part of the Maya Research Series from Nexus Learning Labs, Bengaluru, India — a thirteen-paper programme implementing the Advaita Vedantic Antahkarana as computational primitives in spiking neural networks — with the Bhaya Quiescence Law (β* ≤ 0.32%) and Buddhi S-Curve Determinism (R²=1.0000) confirmed across the series. Series: Part of the Maya Research Series — 13 papers implementing the Advaita Vedantic Antahkarana as computational primitives in spiking neural networks. Bhaya Quiescence Law (β* ≤ 0.32%) and Buddhi S-Curve Determinism (R²=1.0000) confirmed across all papers. Links: GitHub Repository (private — to request access: email research@nexuslearninglabs.in with subject Code Access Request — Maya-Nexus-Core and your research context) | 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