Measurement decision
Study design and identity
Part, repeat, operator, configuration, reference, and environment identity define the measurement question.
metrology-study-designCurated evidence path
Metrology uncertainty to decision risk
Trace study design into variance components, guardband logic, and false-pass or false-fail risk without qualifying a gauge or disposing material.
Review question
How does measurement-system uncertainty change what a decision proxy can support?Permanent path link
- Nodes
- 5
- Bridge edges
- 3
- Stop edges
- 1
- Measured causal edges
- 0
Evidence classes
Read the label before the color.
- ProxyA proxy is not a physical prediction, calibration result, measurement, or causal proof.
- DerivedA derived result inherits every input and model assumption and is not measured evidence.
- ReproducedReproduction establishes the stated run result, not measured-silicon agreement or transfer to another context.
- MeasuredA measurement supports only its declared grain and conditions; it does not automatically prove cross-domain causality.
Ordered evidence chain
Follow each handoff. Stop at the stop.
Node order and edge fields are fixed by the V123 contract. No page interaction generates, ranks, or extends this chain.
- Derived evidence
Evidence bridge
study design to variance components
- Edge ID
- metrology-design-to-components
- From node
- metrology-study-design
- To node
- metrology-variation-components
- Unit or category
- variance / percent category
- Evidence class
- Derived
- Status
- Bridge
- Assumption
- The V122 replay deterministically calculates fields from synthetic states without fitting raw measurements.
- Bridge condition
- Use the decomposition only for the displayed crossed teaching design and preserve missing bias, stability, and reference evidence.
- Limitation
- No owned repeat measurements, randomization record, representative parts, instrument identity, environment, calibration, or residual analysis is included.
- Measured replacement slot
- Owned raw repeats with declared crossed or nested design, gauge/operator/configuration identity, references, environment, analysis, residuals, and uncertainty.
- Deep link
- Open this exact edge
Source artifacts
Measurement decision
Variation components
The deterministic replay separates repeatability, reproducibility, bias, stability, resolution, and uncertainty review.
metrology-variation-componentsProxy evidenceEvidence bridge
measurement uncertainty to decision guardband
- Edge ID
- metrology-components-to-guardband
- From node
- metrology-variation-components
- To node
- metrology-guardband-proxy
- Unit or category
- decision-threshold category
- Evidence class
- Proxy
- Status
- Bridge
- Assumption
- The guardband is an original teaching proxy and is not a customer or production acceptance rule.
- Bridge condition
- Use only to show why uncertainty must remain attached to a decision threshold.
- Limitation
- No specification authority, risk allocation, distribution validation, calibration chain, or product context establishes a usable limit.
- Measured replacement slot
- Approved specification, measurement uncertainty budget, decision rule, distribution evidence, risk allocation, and accountable quality review.
- Deep link
- Open this exact edge
Measurement decision
Guardband decision proxy
A bounded decision state illustrates how uncertainty changes interpretation without setting a production limit.
metrology-guardband-proxyProxy evidenceEvidence bridge
guardband to false-pass or false-fail risk
- Edge ID
- metrology-guardband-to-risk
- From node
- metrology-guardband-proxy
- To node
- metrology-false-decision-risk
- Unit or category
- risk / yield category
- Evidence class
- Proxy
- Status
- Bridge
- Assumption
- The linked artifacts use independent synthetic distributions and do not share production data or a validated classifier.
- Bridge condition
- Treat the relation as a decision-literacy question, not a quantified escape or yield prediction.
- Limitation
- No production distribution, correlation-to-final-test, sampling proof, coverage model, label quality, drift monitoring, or shipped-product outcome is present.
- Measured replacement slot
- Rights-cleared paired measurement and outcome data with sample plan, coverage, label definition, drift controls, uncertainty, and validation.
- Deep link
- Open this exact edge
System / yield proxy
False-pass / false-fail risk
Wafer-sort and virtual-metrology artifacts frame decision risk with synthetic data only.
metrology-false-decision-riskProxy evidenceEvidence stop
decision risk to wafer disposition
- Edge ID
- metrology-risk-to-disposition-stop
- From node
- metrology-false-decision-risk
- To node
- metrology-disposition-stop
- Unit or category
- unsupported authority category
- Evidence class
- Proxy
- Status
- Stop
- Assumption
- Public teaching proxies carry no authority to accept, reject, rework, release, or close an excursion.
- Bridge condition
- Stop before control-limit change, process adjustment, lot disposition, quality release, or root-cause closure.
- Limitation
- Structural evidence completeness does not establish measurement validity, causal attribution, or production authority.
- Measured replacement slot
- Qualified measurement system, approved procedures and limits, real genealogy and outcome data, uncertainty, validation, and accountable disposition authority.
- Deep link
- Open this exact edge
Evidence stop
Stop before disposition
No real study, customer specification, production distribution, or accountable authority is present.
metrology-disposition-stop
Path boundary
This path does not prove causality.
The navigator presents curated associations, assumptions, evidence classes, and replacement needs. It does not prove physical or statistical causality.
A stop is a product requirement, not missing UI. The page must not fill a stopped bridge with extrapolation, AI text, a recipe, an equipment setting, or an operating recommendation.
No public path authorizes process changes, equipment control, wafer disposition, qualification, signoff, product ranking, or production release.
Return to all causal chains