Maya-Smriti: Episodic Memory as a Biological Prior 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; no claim is retracted.The +0.77 pp margin over replay-only sits below the 1.77 pp configuration variance this series later demonstrated, so it cannot be attributed to a mechanism at n = 1; and "affective quiescence" is the observation that the paper's own detector never activates, not a discovered property.Replay's +13.09 pp contribution is large, real, and the paper's actual finding; the buffer is standard experience replay and is now named as such. 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 Two framings it repeats have since been withdrawn in full — the Bhaya Quiescence Law and the Buddhi S-Curve. Both are addressed in Maya-Meta P1, now superseded, and in the self-audit of Maya-Meta P2.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-Smriti extends the Maya affective spiking neural network architecture to class-incremental learning on Split-CIFAR-10, addressing the longstanding problem of catastrophic forgetting by incorporating episodic memory replay drawn from how biological brains consolidate experience during rest. The system introduces Buddhi — discriminative intellect — as a fifth affective dimension that governs how quickly the network transitions from reactive emotional states to stable wisdom, and shows that this dimension follows a characteristic S-shaped recovery curve after each new task is introduced. A key empirical finding is that episodic replay does more than preserve accuracy across tasks: it actively suppresses fear-analogue activity in the network, allowing knowledge consolidation to proceed without affective disruption. Buddhi S-Curve Determinism (R²=1.0000) and the Bhaya Quiescence Law (β* ≤ 0.32%) are confirmed, consistent with all prior papers in the series. This work is the fourteenth contribution to the Maya Research Series from Nexus Learning Labs, Bengaluru, India, which implements the Advaita Vedantic Antahkarana — the fourfold inner instrument of mind — as computational primitives in spiking neural networks. 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-Smriti 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