ARIN22 · Layer 0 · Deterministic Kernel
A deterministic computational core for systemic risk.
A class-routed deterministic acceleration layer — deterministic where it provably can be, Monte-Carlo-challenged where it must be, every verdict hash-logged. ARIN22 is a US-registered name for the deterministic risk-core; the construction is a protected trade secret. Embeddable beside Aladdin, Bloomberg, Murex, and MSCI — not a replacement for full-stack risk platforms.
US-registered name · ~99 µs CPU split (D=4) · < 0.05% q99.9 vs MC · 8.8 B paths / backend · CRN 99.9 PASS.
S2 · Signature proof
The evidence is the page hero.
Three quiet proofs. A worst-tail CPU↔GPU parity scatter that lies exactly on the y = x line. A 24-million-tick latency histogram with the p99 and p999 markers labelled. And a determinism check across a thousand fresh processes that produces a single hash.
CRN 99.9 GPU↔CPU parity
R² 1.0000 · RMSE 0.0000100 worst-tail cases · 100 M paths per backend · Δmax 0.000 bp · PASS. Regression y = 1.0000·x. Every dot lies on the reference line.
Underlying table · 6-of-100 sample
| Case | CPU CVaR 99.9 | GPU CVaR 99.9 | Δ bp |
|---|---|---|---|
| WT-001 | 0.010% | 0.010% | 0.000 |
| WT-020 | 0.018% | 0.018% | 0.000 |
| WT-040 | 0.025% | 0.025% | 0.000 |
| WT-060 | 0.031% | 0.031% | 0.000 |
| WT-080 | 0.040% | 0.040% | 0.000 |
| WT-100 | 0.050% | 0.050% | 0.000 |
Tick-replay latency
p99 0.625 · p999 0.710 msN = 24,000,000 · Run 11/12 · 8×H100 · NVIDIA Innovation Lab · May 2026. Distribution centred near 0.4 ms with a tightly bounded right tail.
Underlying percentiles
| Quantile | Latency | Sample |
|---|---|---|
| p50 | 0.388 ms | 24,000,000 |
| p90 | 0.524 ms | 24,000,000 |
| p99 | 0.625 ms | 24,000,000 |
| p999 | 0.710 ms | 24,000,000 |
Deterministic where it publishes. Monte-Carlo-challenged where it must be.
PASS lane · Challenger lane · fail-closed.
S3 · The challenge
Why a deterministic core matters.
Pure Monte Carlo degrades in wall-clock time as scenario complexity grows — more factors, deeper cascades, heavier tails demand exponentially more paths. For desks, risk committees, and agent loops that need near-real-time risk, that latency ceiling is the bottleneck. ARIN22 replaces brute-force path enumeration with a deterministic computation across contagion and covariance structure, holding wall-clock cost near-constant as complexity grows. The construction is a protected trade secret; what follows is capability, performance envelope, and integration surface only.
S4 · CPU posture
Kernel correctness is CPU-bound. GPU is for scale.
The kernel validates identically on a commodity ARM CPU and an 8×H100 cluster. Every result is stamped with a hardware fingerprint and a run SHA for cross-environment replay. Precise numerics — µs, speedup×, q999%, fingerprint, run SHA — are released to bank model-risk teams under NDA.
S5 · Three core capabilities
What the kernel does, in three lines.
Constant-cost compute.
Wall-clock cost shows weak dependence on the equivalent MC path count. Verified across Enterprise Wave v2 — 8,800 cases, 8.8 B paths per backend, zero failures.
Adaptive tail controller.
Class-routing holds target accuracy under jumps, regime-shifts, and vol-clustering. Deterministic where it provably publishes; CRN-anchored at 99.9; 10 M MC challenger on hard regimes; no silent degradation.
Cross-asset contagion.
Hidden-channel detection across the covariance and contagion structure. Every verdict is hash-chained; replay is bit-exact under a recorded hardware fingerprint.
S6 · Mode catalogue
One kernel, many class-routed modes.
Six layers, A through F. Each layer publishes enum-named surfaces a reviewer can audit; the construction sitting beneath them — the splitting operator, the generator decomposition — remains NDA-bound. The published list is the IP boundary.
Institutional reviewers need a written IP boundary — what is auditable publicly (input → output → hash → lineage) versus what is only auditable under NDA (the how of construction). This catalogue is that boundary.
S7 · Performance envelope
Workload, envelope, scale.
The canonical envelope, end-to-end. Numbers are reproducible from the run SHA and hardware fingerprint released under NDA; the public surface publishes the envelope itself.
| Workload | Envelope | Scale · lane |
|---|---|---|
| Intraday tick replay | p99 0.625 ms · p999 0.710 ms | N = 24,000,000 · 8×H100 |
| Pre-trade mixed gate | p99 1.064 ms | N = 24,000,000 · ALLOW 21.32 M / REVIEW 2.64 M / BLOCK 38.5 K |
| Enterprise Wave v2 canonical | 0 failures | 8,800 cases · 8.8 B paths / backend |
| CRN 99.9 parity | PASS · Δmax 0.000 bp | 100 worst-tail cases · 100 M paths / backend |
| 10 M MC challenger | CVaR 99.9 p95 0.015% · max 0.035% | 50 cases × 200 reference runs · 2.0 B paths |
| Determinism | 1 hash · 0.0% drift | 1,000 fresh processes |
| CPU split kernel | ~99 µs · q99.9 dev < 0.05% | D = 4 · commodity ARM |
All numbers are public-tier. Precise µs, speedup×, full q999 distribution, hardware fingerprint, and run SHA are released to bank model-risk teams under NDA.
S8 · Validation evidence
Enterprise Wave v2 — the canonical pack.
MC-challenger-anchored, class-routed, no silent degradation. V1 aggregate (the 1.06 T-path headline) is superseded as a headline number; it is preserved as lineage inside the Layer-1 data room.
Phase 5 closed · Run 11/12 audit closed · negative controls fail-closed · sampler-independent across PRNG / Sobol / LHS.
S9 · STAC-inspired wave
GPU lane — MC throughput on 8×H100. Self-run, not STAC-audited.
Built to STAC archetypes, self-run. The four lanes below are the GPU-throughput envelope; independent STAC benchmarking is the deliberate next step.
Two worlds, never conflated. Monte-Carlo throughput → GPU lane (scale). Deterministic kernel → commodity CPU (correctness). The GPU lane is where MC throughput is measured; the deterministic kernel is where correctness is anchored. Archive SHA + 77 hashed artifacts available under NDA.
S10 · Claim boundaries
What is claimed. What is not.
Claimed
- Deterministic where it provably publishes — not “always replaces Monte Carlo.”
- CRN-anchored 99.9 parity on the worst-tail subset.
- 10 M MC-challenger backing on hard regimes with hash-logged routing.
- Tick p99 0.625 / p999 0.710 ms over 24 M ticks.
- Pre-trade gate p99 1.064 ms over 24 M; ALLOW / REVIEW / BLOCK published.
- Determinism: 1 hash / 1,000 repeats / 0.0% drift.
- CPU correctness on commodity ARM at ~99 µs split, < 0.05% q99.9.
- Negative controls fail-closed.
- Sampler-independence across PRNG, Sobol, LHS.
Not claimed
- Not a realised regulatory backtest PASS — Shadow Ledger ARMED, 250-observation floor not yet met.
- Not a live-production sign-off at any bank or G-SIB.
- Not “always replaces Monte Carlo.”
- Not EVT 99.9 long-horizon promotable — WATCH_SUPPRESSED.
- Not STAC-certified — self-run.
- Not a market-maker pricing service.
- Not a full-stack platform — embeddable layer beside Aladdin / Bloomberg / Murex / MSCI.
S11 · Economic value
Five mechanism-anchored drivers.
Per-bank ROI is established during pilot, not asserted up front. Quantification and sensitivity envelope are released under NDA. No headline dollar number.
Latency value
Recomputation cost on intraday-risk loops compresses toward the kernel envelope — the slowest layer is replaced.
Anchor · tick p99 0.625 ms
GPU utilisation
An 8×H100 cluster is freed for paths that actually need MC challenge; deterministic work runs on commodity ARM.
Anchor · 8.8 B / backend
Compliance velocity
Hash-chained verdicts and run-SHA replay shorten audit cycles — an external reviewer reconstructs decisions deterministically.
Anchor · 1 hash / 1,000 repeats
Decision quality
CRN-anchored deep tails carry the worst-case decision surface; agents and committees act on a stable target accuracy.
Anchor · CVaR 99.9 max 0.035%
Audit velocity
Bit-exact replay across hardware fingerprints shortens model-risk reviews from days to a single deterministic re-run.
Anchor · 0 failures / 8,800 cases
S12 · Architecture integration
Embeddable beside Aladdin, Bloomberg, Murex, MSCI.
ARIN22 is a layer, not a platform. Three calm integration targets — one for risk platforms, one for trading systems, one for sovereign & central use cases.
Affiliations: NVIDIA Inception · NVIDIA Innovation Lab · Google for Startups · AWS Activate. ARIN22 is a US-registered name; the construction is a protected trade secret. Pre-client diligence-ready with a strong public-portfolio H100 validation package; not externally production-approved.