Maya-Vaidya P3: Simulating Dravet Syndrome In Silico — Vairagya-BCM Inhibitory Collapse in a Paediatric SNN with Cross-Patient Seizure Detection

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 withdraws the disease claim in the title.No subject in the study has SCN1A status — chb12, chb13 and chb06 are ordinary refractory paediatric epilepsy cases from CHB-MIT — and the "haploinsufficiency" is a spike-output clamp with no sodium conductance, NaV1.1 or channel kinetics; what remains is an interneuron-ablation study on refractory paediatric epilepsy EEG.Two further corrections: chb13's AUC of 0.357 at zero deficit is far below chance and unremarked, so the rise to 0.743 is recovery rather than generalisation; and the direction test fails on two of three patients while the abstract headlines the one that passed. 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 Two framings it repeats have since been withdrawn in full — the Bhaya Quiescence Law and the Buddhi S-Curve. Both are addressed in Maya-Meta P1, now superseded, and in the self-audit of Maya-Meta P2.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-Vaidya P3 presents DravetSNN, a spiking neural network simulation of Dravet Syndrome built to model the progressive silencing of inhibitory interneurons that underlies this severe infant-onset epilepsy, trained and evaluated on real paediatric EEG recordings from the CHB-MIT Scalp EEG dataset across three paediatric subjects and sixty total experimental runs. The model encodes SCN1A haploinsufficiency as a conductance deficit applied to its inhibitory (Vairagya) neuron population, and confirms exact inhibitory collapse — Vairagya firing reaching 0.000 at full deficit across all patients and random seeds — while achieving a cross-patient seizure detection AUC of 0.743 ± 0.073 on chb13 and an unsupervised ictal chrono_signal of 0.555 above the 0.5 detection threshold, with flat AUC on chb06 confirming that the model captures phenotype specificity rather than noise. This work is the third entry in the Maya-Vaidya Series and confirms the PAIN_DECAY_RATE empirical constant at 0.002315 across three canonical positions, extending the BCM-derived inhibitory collapse architecture first introduced in Maya-Vaidya P2 into a paediatric disease-simulation context. As part of India's first neuromorphic clinical AI research series, Maya-Vaidya P3 represents a proof-of-concept mechanistic study only and is not a licensed medical device; CHB-MIT subjects carry no confirmed SCN1A genetic status, and all findings are preliminary pending replication on genetically validated cohorts. Series: Part of the Maya-Vaidya Series — neuromorphic AI for clinical pain analysis. India-first. Research prototype only — NOT a licensed medical device. For medical emergencies in India: 112. Links: GitHub Repository (private — to request access: email research@nexuslearninglabs.in with subject Code Access Request — Maya-Vaidya-P3 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