Nexus Concordat. Gold dragon in a hexagonal frame beside the wordmark.
Director Update · 31 May 2026

What the cardiac brain learned, by head and by step

Four independently-seeded neurons, four learning rules, one shared cardiac substrate of 3,470 tokens. After 10,000 training steps, this is the cardiac vocabulary each head emits at temperature 6, where the model's full distribution is visible rather than the EOS-collapsed greedy mode. Two stories at once: vocabulary acquisition over training time, and head-by-head specialization on identical input.

What this is

The OrganVoice cluster is a four-neuron cardiac specialist. Each neuron is its own small transformer, each trained with a different learning rule (Adam, Hormone-modulated LR, Hebbian-blend, STDP), all on the same curated cardiac vocabulary and corpus. After training, each was sampled across five cardiac prompts: heart, chest, hypertension, STEMI, warfarin. The tables below count which cardiac words each head actually emitted at each training checkpoint.

Substrate: 523-entry curated cardiac vocabulary built from 278 cardiology Q&A pairs across 9 specialty sub-corpora (ECG, dose titration, contraindication, hemodynamic, interaction check, risk stratification, referral, differential diagnosis, general pairs). Training corpus: 3,470 tokens. Sampling: 30 samples per prompt at temperature 6, top_k 30, deterministic seed schedule across all 20 checkpoints (4 heads × 5 step milestones).

Vocabulary acquisition by head and step

Head A — Adam (vocabulary specialist)

StepCardiac words emitted at this checkpoint (most frequent first)
2Kcardiovascular 11, diabetes 11, digoxin 10, ef 10, check 10, angina 10, daily 9, and 9, female 9, between 9, diagnosis 8, contraindicated 8, high 7
4Kedema 12, daily 12, ck 11, bid 10, bp 10, amiodarone 10, and 10, cardiovascular 9, ef 9, diagnosis 9, contraindicated 9, elevation 8, dry 8, female 7
6Kaortic 11, and 11, chest 11, ef 10, daily 10, diagnosis 10, 50mg 10, ecg 9, contraindicated 9, evaluation 9, context 9, cardiovascular 8, 80mg 7
8Kadult 12, ef 12, diagnosis 11, given 11, for 9, chest 9, evaluation 9, dyspnea 8, and 8, dissection 8, in 8, dyns/cm5 8, aortic 7
10Kelevation 12, gradient 11, cardiac 10, contraindicated 10, diagnosis 10, and 10, ef 9, context 9, icu 9, chest 9, iii 8, exertion 8, ci 8, in 7

Head B — Hormone-LR (POS · context)

StepCardiac words emitted at this checkpoint
2Kfemale 12, bp 11, cardiovascular 10, and 10, contraindicated 10, angina 10, between 9, context 9, describe 9, digoxin 8, block 8, given 8, 80mg 8
4Kdaily 15, between 12, angina 11, ck 10, bp 10, cardiovascular 9, and 9, dry 9, contraindicated 9, amiodarone 8, diagnosis 7, apixaban 7, fibrillation 5
6Kaortic 12, 80mg 12, diagnosis 11, contraindicated 11, daily 10, 20mg 10, chest 9, 50mg 9, 70kg 9, cardiology 9, context 8, dyns/cm5 8, ecg 8
8Kdyns/cm5 14, diagnosis 12, in 11, adult 11, ef 10, contraindicated 9, l/min 8, ecg 8, daily 8, cardiology 8, l/min/m2 7, medical 7
10Kiii 12, diagnosis 12, gradient 12, contraindicated 11, cardiac 10, exertion 10, and 10, ecg 9, ct 8, l/min 8, mental 8, elevation 7, corpulmonale 7

Head C — Hebbian-blend (opcode · association)

StepCardiac words emitted at this checkpoint
2Kcardiovascular 12, diabetes 10, diagnosis 10, atorvastatin 10, amiodarone 10, bp 9, angina 9, 80mg 9, between 9, and 9, digoxin 8, contraindicated 8, ef 8
4Kedema 13, daily 12, bp 11, between 11, and 11, cardiovascular 10, contraindicated 9, apixaban 9, fibrillation 8, dry 8, contraceptive 8, bid 8, furosemide 7, given 7
6Kecg 14, contraindicated 12, hfref 11, aortic 11, and 10, given 9, between 8, context 8, in 8, interaction 8, diagnosis 8, ef 7, 80mg 7
8Kin 14, ef 11, adult 10, and 10, for 9, dyns/cm5 9, contraindicated 8, given 8, ecg 8, diagnosis 8, dissection 8, cardiovascular 8, dyspnea 7
10Kelevation 12, jvp 11, chest 11, and 11, gradient 10, in 10, interaction 10, given 9, l/min 8, exertion 8, ecg 8, ct 7, ldl 7, mental 7

Head D — STDP (voice · causal-temporal)

StepCardiac words emitted at this checkpoint
2Kdaily 15, atorvastatin 12, high 11, angina 10, in 9, inr 8, female 8, cardiology 8, diabetes 7, chest 7, differential 7, context 7, is 7
4Kfamily 13, angina 12, bid 11, edema 11, bp 10, context 9, asymptomatic 9, contraindicated 8, furosemide 8, gold 7, evaluation 7, and 7, hfref 6
6Kcontext 28, 70kg 15, and 13, 5mg 8, 100mg 8, bid 8, clearance 8, atorvastatin 7, 50mg 7, apixaban 6
8Kchronic 16, context 13, and 13, dyns/cm5 9, dyspneic 8, elevation 7, evaluation 7, death 7, contraindicated 6, 5mg 6, 55yo 6
10Kand 15, elevation 13, icu 10, in 9, gold 8, contraindicated 6, dyspnea 6, at 6, apixaban 6, iii 5, back 5, hocm 4

Head specialization at the final checkpoint

Same substrate. Same data. Four learning rules. Four distinct emission profiles after 10,000 steps.

HeadDistinct cardiac wordsTop 8 by frequency
A · Adam14elevation, gradient, cardiac, contraindicated, diagnosis, and, ef, context
B · Hormone-LR13iii, diagnosis, gradient, contraindicated, cardiac, exertion, and, ecg
C · Hebbian14elevation, jvp, chest, and, gradient, in, interaction, given
D · STDP12and, elevation, icu, in, gold, contraindicated, dyspnea, at

Head C's emission of jvp (jugular venous pressure, the classic bedside exam finding for heart failure) at step 10K reflects exactly what the Hebbian-blend rule is supposed to do. It rewards co-occurrence patterns, and JVP travels in a tight semantic cluster of exam findings. Head B's emission of iii at top frequency is NYHA Class III, the regulatory functional class in heart failure. Head D's tilt toward connectors (and, in, at) and critical-care vocabulary (icu, gold for GOLD criteria) is the voice integrator behaving the way the architecture predicts: it commits to sentence-level temporal structure rather than picking content words.

Full lexicon observed across the run

77 distinct cardiac clinical words emitted across all four heads and all five checkpoints. Frequency in parentheses.

and176 contraindicated143 diagnosis116 context100 daily91 ef86 cardiovascular77 in76 ecg64 angina62 bp61 elevation59 between58 chest56 given52 dyns/cm548 80mg43 aortic41 bid37 female36 edema36 adult33 gradient33 evaluation32 atorvastatin29 diabetes28 amiodarone28 apixaban28 digoxin26 50mg26 exertion26 dry25 iii25 icu23 chronic16 70kg24 cardiology25 cardiac20 ck21 dyspnea17 furosemide15 interaction18 fibrillation13 hfref17 family13 l/min16 jvp11 gold15 20mg10 mental15 5mg14 dissection16 describe9 block8 check10 asymptomatic9 contraceptive8 clearance8 inr8 differential7 l/min/m27 medical7 ldl7 ct8 corpulmonale7 death7 dyspneic8 ci8 back5 hocm4 at6 100mg8 high11 for9 is7 55yo6 hold3

What to take from this

Each head was trained from a fresh random initialization with its own seed. The fact that four independent runs over the same substrate produce overlapping cardiac vocabularies is evidence that the substrate has organized the cardiac domain consistently, not that the four heads are copies of each other.

Vocabulary grows over training steps. Words like gradient, jvp, iii (NYHA Class III), icu, exertion, and dyspnea appear at step 10K, not at step 2K. The substrate is acquiring real cardiac clinical content over training, not just smoothing a prior.

The four heads specialize differently. Head C surfaces an exam-finding cluster (jvp + chest + interaction). Head B surfaces a functional-class cluster (iii + diagnosis + exertion). Head A surfaces a metrics-and-anatomy cluster (gradient + cardiac + ef). Head D commits to sentence-boundary structure and critical-care endpoints. Same data, four learning rules, four distinct emission profiles. That is the architectural claim demonstrated on disk.

The freeze that makes this safe is byte-identical. Once a head is trained, freezing it lets the other three heads continue training without disturbing the frozen head's row tables by a single bit. The proof is on disk at business_suite/docs/organ_voice_phase1_proven_2026-05-31.md. That is what makes catastrophic forgetting structurally impossible across the four-neuron cluster.