Q-SETUN v2.1.0 — ternary hysteresis memory, live threshold self-reinforcement, wave energy & trit density

What's new in 2.1.0

Added

• Ternary Hysteresis Memory (configure(hysteresis_q8)) — trits now hold state across the threshold edge; deep sign flips still captured instantly. Verified: -34.3% trit chatter, 90.0% of waves preserved.
• Live Threshold Self-Reinforcement (configure(live_sigma)) — thresholds re-derived from running variance every feed; a 16x noise-floor jump: 1530 false beats (fixed) vs 4 (live).
• QState.wave_energy — accumulated |diff| inside the closed cycle.
• QState.wave_trit_density_pct — share of non-zero trits in the cycle.
• 9 telemetry getters (parity with the lab fork): getVarianceEMA, getPosThreshold, getNegThreshold, getChargeLimit, getBaselineEMA, getTritRing, getRingHead, setBaselineEMA, setVarianceEMA.
• Regression equivalence suite (benchmarks/regression_equivalence.py): 104 096 samples -> 0 state mismatches vs v2.0.
• license=GPL-3.0-only in library.properties.

Changed

• Static footprint: 84 B RAM (avr-g++ 7.3, ATmega328P); Flash 1758 B.
• Docs, keywords, metadata updated.

Verified

• 100% integer, zero heap, deterministic O(1).
• Official suite PASS: AVR compile, O(1) determinism, AAMI EC57 clinical, 4/4 stress tests.

v2.0.0: Q-SETUN True Zero-FLOP Core & Empirical Benchmarks

Release v2.0.0 of Q-SETUN: Brusentsov Ternary Qutrit Core with Cellular Apoptosis

Major Upgrades:

• True Zero-FLOP Fixed-Point (Q8) integer math core.
• Multi-tier Cellular Apoptosis with ring-buffer glitch suppression.
• Non-deadlocking topological attractor with watchdog timeout.
• Zero-FLOP 3-sigma auto-calibration with integer square root.
• Empirical verification on ATmega328P compiler (1238 B flash, 75 B RAM, 0 B heap) and ANSI/AAMI EC57 clinical benchmark (F1: 1.0000).

Authors: Leonid Kulcha & Antigravity (Noosphere Research Lab)
CERN/Zenodo Concept DOI: 10.5281/zenodo.22813548

v1.0.1: Q-SETUN Core with Academic DOI & Citation Passport

Official v1.0.1 release of Q-SETUN: Zero-FLOP Neuromorphic Edge AI using Brusentsov balanced ternary qutrits and cellular apoptosis.

• Validated on silicon: 1.0 microsecond deterministic latency, 0 bytes dynamic heap allocation (malloc=0).
• Up to 270x faster and 43.5% smaller than TensorFlow Lite Micro on ESP32.
• Full citation support via CITATION.cff and Zenodo CERN archival.
• Lead Author: Leonid Kulcha (Noosphere Research Lab)
• Co-Author: Antigravity (Noosphere Research Lab)