Maya-Viveka: Viveka-Gated Synaptic Discrimination for Class-Incremental Learning in Affective Spiking Neural Networks

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 and supplies a missing specification.The +0.63 pp Viveka effect is below this series' own noise floor, and the restatement as "approximately 630 additional correct classifications" was off by a factor of ten on a 10,000-image test set; the δ(s,t) rule, described only as "high if consistent", is now given in full from the implementation so the method is reproducible.The buffer-size result (+4.10 pp for M = 20 → 50), replay's +8.50 pp, and the honestly reported orthogonal-head collapse 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 Two framings it repeats have since been withdrawn in full — the Bhaya Quiescence Law and the Buddhi S-Curve. Both are addressed in Maya-Meta P1, now superseded, and in the self-audit of Maya-Meta P2. Maya-Viveka introduces a sixth affective dimension — Viveka (discernment) — into the Maya spiking neural network architecture, enabling the system to distinguish synapses that encode stable, task-general features from those encoding transient, task-specific activations during class-incremental learning on Split-CIFAR-100 across 100 classes and 10 sequential tasks. Inspired by norepinephrine gain-amplification models from neuroscience, Viveka acts as a cross-task synaptic consistency tracker that modulates the strength of memory consolidation protection based on how reliably each synapse fires across task boundaries, making consolidation selective rather than indiscriminate. In a six-condition ablation study, Viveka-gated selective protection achieves an average accuracy of 16.03% with a backward transfer of −50.50% on this challenging benchmark, outperforming configurations that apply uniform consolidation regardless of synaptic history. This work is the latest entry in the Maya Research Series — 13 papers 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 all papers in 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-Viveka and your research context) | Interactive Dashboard | 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