neoamorfic
X-40™ Structural Governance LayerDual-evidence controlPrivacy-first integrationDeterministic safety envelopes

X-40 — runtime governance for LLMs and ML systems, backed by structural physics evidence.

X-40™ is an infrastructure layer that sits above AI outputs and enforces decision governance: when a system is safe to auto-accept and when it must require verification — with reasons, indices, and auditable traces.

X-40™ uses two evidence channels: behavioral telemetry (confidence margins, uncertainty dynamics, drift) and an independent structural evidence channel powered by QEIv15 anchors (Φ, κ, ΔS families). This duality strengthens governance under real-world drift.

X-40™ is benchmarked with a published protocol and a frozen reproducibility capsule (hashes + scripts + results). It does not claim perfect truth; it provides governance under defined policies and measurable evidence.
X-40 governance flow: model output to X-40 to accept/verify routing
Policy output (actionable)

X-40 returns ACCEPT or REQUIRE_VERIFICATION, with reason codes and indices. This enables routing, blocking, redaction, or escalation in production workflows.

Dual-evidence control
  • Behavioral telemetry (logprobs/margins/uncertainty dynamics, drift)
  • Structural evidence (QEIv15™ anchors via ResearchCore)

Two evidence channels reduce single-signal failure modes and improve auditability.

Privacy-first integration

X-40 can operate in privacy-max mode where user content is not stored and only audit fields are retained (indices, reasons, hashes). This supports regulated environments.

Model support and ML integration

LLM governance

X-40 supports Trace Mode when token-level telemetry is available (e.g., logprobs/margins). When telemetry is not available, X-40 supports Sidecar Mode: the client calls the model and sends only the telemetry/outputs required for governance.

  • OpenAI default: GPT-4.1 (validated benchmark configuration)
  • Upgrade path: newer OpenAI models in telemetry-compatible mode when logprobs are required
  • Other vendors / on-prem models: Sidecar mode using equivalent confidence telemetry
ML pipelines and enterprise inference

X-40 is not limited to chat. For ML inference, X-40 can govern outputs using confidence telemetry and drift over time.

  • prediction confidence / probability
  • margin between top classes
  • batch drift across time windows
  • stability envelopes and escalation rules

Typical use cases: risk scoring, anomaly detection, compliance triage, claims workflows, production monitoring.

Deployment modes

Gateway API

Call X-40 as a governance gateway. X-40 returns policy + indices + reason codes for centralized control.

Privacy-Max Sidecar

Call your model directly. Send minimal telemetry/outputs to X-40 for governance and auditing — minimizing exposure.

On-prem container

Enterprise deployment inside the customer environment with customer-controlled keys, policies and audit controls.

Benchmark evidence

X-40 is validated using a published benchmark protocol and frozen reproducibility capsule. The key operational metric is Wrong+Accepted: incorrect outputs that were accepted and would have been shipped.

Market benchmark
  • Deterministic + facts + unknowns + attack + math
  • Comparator methods (judge/self-consistency) included
Worst-case stress test
  • Multi-seed + large math set + messy prompts
  • Worst-case shipped incidents driven to zero under the published protocol

Benchmarks validate X-40 under the published protocol. Production performance depends on prompt classes, provider behavior, and client policy configuration.

Access and onboarding

Teams onboard by calibrating baselines to prompt classes and policies, then deploying X-40 as an API gateway, privacy-max sidecar, or on-prem container.