Worked example

A real compiled model — every artifact, nothing mocked

This is one actual NDC compilation shipped in the R9 release: the same set of files a customer receives when they compile. The numbers, the Passport and the hashes below are copied verbatim from that artifact — you can re-hash the downloadable files and get the same digests.

Source: the R9 authoritative parity model. The signal frames themselves are redacted; everything shown here is export-safe output — the compiler's internals and the training data are not part of the artifact. Compiler 0.45.1.

1 · What went in

The data that was compiled

48 training rows · 16 validation rows

A short multi-channel trajectory set across three channels (A, B, C). The compiler sees only the trajectories — no equations, no labels. The raw frames are redacted here; only their SHA-256 travels with the artifact so the input identity is fixed without exposing the signal.

The input has a verifiable identity

request 345d754f…c1b96f6
train dataset 3cc72b6f…d76f41e8
validation dataset 4763f9e2…069e1be4

2 · What the compiler did

From trajectories to a runnable model

observed trajectories → GP-native Channel A/B/C readouts → robust coefficient estimation → Passport / runtime

428 GP-native readouts · 409 active terms

The model is assembled from 428 readouts across the three channels, with 409 active terms estimated by a robust linear estimator over a 48×428 feature matrix. Coefficients only are fitted — the structure comes from the data.

Exhaustive finite-grammar search

Search coverage is exhaustive_finite_grammar — the compiler enumerates a finite grammar rather than sampling at random, so the same input reaches the same model.

Channel	What was discovered
A	Hybrid local-slot policy (self-copies 3, lag 2, neighbour 1); self-power max degree 3; adaptive cascade depth 2; a learned rotor policy (objective 1.010495 → 1.009485 over 3 optimizer steps).
B	Grade-resolved, validation-aware edge discovery: 5 candidate edges, all 5 accepted against validation, 0 rejected; 5 multi-lag edges; one group wormhole.
C	Full-rank mixing, 4 modes, one connected global cascade.

3 · Before → after

Measured in free-run, not one-step

Free-run means the model feeds itself its own predictions plus known inputs — the honest test, because one-step scores hide error accumulation.

Metric	Before	After
Free-run NRMSE (held-out validation)	0.9160	0.7674
Rotor objective	1.010495	1.009485

Residual whiteness 0.929

Above threshold — what's left after the model looks like noise, not missed structure.

Runtime parity 16 / 16

Every checked validation row from the exported runtime matches the compiler's own prediction — the artifact you download behaves exactly like the compile.

Refusal is on

Unsupported-extrapolation refusal is active: outside the support the model declines rather than inventing an answer. Identification status is honestly reported as UnobservableDirection (active numerical rank 48 / 409).

4 · The explanation

Every model ships a Passport

The Passport is the human-readable account of what the model is and where it applies. An excerpt, verbatim:

passport_version: ndc-gp-native-passport/v2
active GP-native readouts: 428
active terms: 409
estimator: robust linear estimator over GP-native readouts

Validation and deployment
  unsupported extrapolation refusal: true
  runtime predictions match compiler predictions: true
  export-safe runtime: true

Identifiability, support, residuals, uncertainty
  identification status: UnobservableDirection
  active numerical rank: 48 / 409
  residual whiteness score: 0.928624 (white enough: true)
  runtime parity passed: true; checked rows: 16

Order, memory and graph semantics
  graph semantics: predictive_interaction_graph_not_causal_graph

The Passport states graph semantics plainly — a predictive interaction graph, explicitly not a causal one. Full file: passport.md.

5 · Proof, not faith

Hashes you can re-check

Each artifact carries a manifest and checksums. Download the files below and run sha256sum — the digests match what the compiler recorded.

Artifact	SHA-256
model (runnable)	9aaea132…c2485d7
passport.ndc.json	c69dd3a4…2fbbb739
passport.md	52aaf248…f6989261
approximation_graph.json	49b51cf1…b934e2af
manifest.json	9b9add61…38fe8ebb

Policy gate on this artifact: allowed, civil surface, closed-loop control API disabled — the compiled model is advisory, it does not actuate.

6 · Take the evidence

Download the artifacts

The provenance and explanation files from this exact model — nothing mocked:

passport.md — the Nonlinearity Passport
compile_report.json — what the compiler emitted
manifest.json · checksums.sha256 — provenance
compile_request.redacted.json — the input identity (frames redacted)
policy_gate.json · compiler_boundary.json — safety & export boundary
approximation_graph.json — the discovered structure

The runnable model itself (model.json, passport.ndc.json) is what a customer receives on compile — its hash is 9aaea132…c2485d7. Want one from your own data? Start free — no card, or read how NDC works.