Simulation Input Uncertainty Module (SIUM)
OOF™ Origin Open Foundation™
Independent Methodological Authority
Architecture Ecosystem: Structured Reality Standards™
Architecture Family: SIMULOS® — Simulation Governance Architecture
Parent Standard: Simulation Input & Data Standard (SIDS)
Operational Layer: Simulation Input & Data Governance Layer
Category: Governance & Enforcement
Subcategory: Simulation Governance
Type: Parent Standard Module
Governed Space: Simulation Input Uncertainty
Version: 1.0
Status: Canonical · Open Module
Effective Date: 18 August 2026
Compatibility: OOF® Methodology OS™ · GOA™ · ORA™ · VALIDOS® · INTEGROS® · ADIT® · AGA™ ·
AIG® · CLIA® · MGIA™ · ASGA™ · RIS™
AI-Readable: Yes
Authority: OOF®
Protection: MIP® — Methodological Intellectual Property
Canonical Language: English (UCL™)
Governed Space
Simulation Input Uncertainty
Canonical Definition
Simulation Input Uncertainty Module (SIUM) defines the governance frameworkthrough which uncertainty associated with Simulation Inputs is identified,
classified, bounded, quantified or qualitatively characterized where
appropriate, propagated into simulation execution, and preserved through
downstream interpretation so that uncertainty in the input basis cannot
disappear merely because the simulation produces precise outputs.
SIUM establishes the final internal governance layer of SIDS by governing the
transition:
Identified + Representative + Transformed + Temporally Governed Inputs → Input
Uncertainty Identification → Uncertainty Characterization → Dependency
Assessment → Uncertainty Propagation Requirements → Simulation Input
Uncertainty Status
Its purpose is not to eliminate uncertainty.
Its purpose is to ensure that uncertainty remains visible, attributable,
bounded, and operationally consequential wherever it can materially affect
simulation behavior or conclusions.
Operational Role
SIUM serves as the fifth and final internal governance space of the SimulationInput & Data Standard (SIDS).
The preceding modules establish:
SIIM — What information is entering the simulation?
SDRM — What reality can that information legitimately represent?
SDTM — What happened to that information before simulation use?
STDM — Is that information temporally appropriate for the reality and dynamics
being simulated?
SIUM asks:
What uncertainty remains in the complete Simulation Input basis, where does
that uncertainty originate, how may uncertainties interact, and what must
remain visible when the simulation uses those inputs?
The governed progression is:
Simulation Input Basis → Uncertainty Sources → Uncertainty Classification →
Uncertainty Magnitude / Character → Dependency → Materiality → Propagation
Requirement → Input Uncertainty Status → Simulation Use
Module Function
SIUM exists to prevent: uncertain inputs being represented as certain,estimated values being treated as observations, measurement uncertainty
disappearing during ingestion, transformation-induced uncertainty being
ignored, temporal uncertainty being lost, multiple uncertainties being assumed
independent without basis, uncertainty being hidden by numerical precision,
uncertainty ranges being collapsed into single values without justification,
incomplete information being interpreted as certainty, uncertainty being
averaged away, model inputs being presented as exact merely because the
simulation requires exact numerical values, simulation outputs appearing more
certain than their input basis legitimately supports, and downstream users
losing visibility into material uncertainty inherited from Simulation Inputs.
Simulation Input Uncertainty
Simulation Input Uncertainty is the material uncertainty associated with theidentity, value, state, origin, representation, transformation, timing,
completeness, or applicability of information entering a simulation.
It may concern:
What the value is
Whether the value is correct
Whether the value represents the intended
reality
When the value applies
How the value was produced
How complete the information is
or:How confidently the input may be relied upon within the simulation context.
Uncertainty Is Not Error
SIMULOS® establishes:Uncertainty does not necessarily mean that an input is wrong.
An input may be the best available representation while still containing
material uncertainty.
For example:
Temperature = 20°C ± 1°C
does not mean the measurement is invalid.It means the information basis contains a bounded uncertainty.
Error vs Uncertainty
SIUM distinguishes:Known Error
from:
Uncertainty.
A known incorrect value may require correction.
An uncertain value may remain legitimate if the uncertainty is sufficiently
understood and governed.
Uncertainty Source
Every material uncertainty should be attributable, where possible, to anidentifiable source.
Possible sources include: measurement process, sensor precision, sampling,
source reliability, missing information, estimation, transformation,
interpolation, extrapolation, temporal misalignment, synthetic generation,
model-derived inputs, classification, environmental variability, or unresolved
knowledge limitations.
Measurement Uncertainty
Measurement systems have finite accuracy and precision.A measured value may therefore represent:
Observed Value ± Measurement Uncertainty
rather than an exact physical state.Where material, the uncertainty should remain connected to the input.
Observational Uncertainty
Some phenomena cannot be observed perfectly.Observational uncertainty may arise from: incomplete visibility, ambiguous
detection, limited sensor coverage, human observation, environmental
interference, or indirect observation.
Sampling Uncertainty
A sample represents only part of a broader population, period, environment, orstate space.
Sampling uncertainty asks:
How uncertain is the inference from the observed sample to the reality the
simulation intends to represent?
SDRM governs representativeness.
SIUM governs the uncertainty remaining within that representation.
Representativeness Uncertainty
A dataset may be accepted as sufficiently representative while stillcontaining uncertainty about how completely it captures: rare conditions,
subpopulations, environmental variation, extreme behavior, or future
conditions.
Acceptance under SDRM does not eliminate that uncertainty.
Transformation-Induced Uncertainty
SDTM may introduce uncertainty through: filtering, aggregation, interpolation,extrapolation, imputation, normalization, data fusion, synthetic
supplementation, or derived-variable construction.
SIUM consolidates these uncertainty contributions into the governed Simulation
Input basis.
Temporal Uncertainty
STDM may identify uncertainty involving: timestamps, synchronization, latency,event timing, temporal alignment, applicability periods, drift, or regime
transition.
SIUM ensures material temporal uncertainty remains part of the complete
uncertainty basis.
Estimation Uncertainty
Estimated inputs should preserve uncertainty associated with the estimationmethod.
Conceptually:
Observed Basis + Estimation Method → Estimated Input + Estimation Uncertainty
Interpolation Uncertainty
Values generated between observations may contain uncertainty dependent upon:
distance between observations, variability, interpolation method, system
dynamics, and missing-data structure.
Extrapolation Uncertainty
Extrapolation extends beyond observed information.Uncertainty may increase as extrapolation moves further from the observed
basis.
SIMULOS® establishes:
Numerical continuation beyond observed data does not establish equivalent
informational confidence.
Imputation Uncertainty
An imputed value may be necessary for simulation execution.But the simulation should preserve that:
Imputed Value ≠ Observed Value
and that the imputation carries uncertainty derived from its method and basis.Synthetic Input Uncertainty
Synthetic information may represent plausible conditions without being directobservation.
Where synthetic inputs are used, SIUM governs uncertainty associated with:
generation assumptions, generator limitations, distribution fit, scenario
coverage, and divergence from observed reality.
Parameter Uncertainty
Simulation Inputs may include parameters whose exact values are unknown.A parameter may therefore be represented as:
Fixed Estimate
RangeDistribution
Scenario Set
or:Unknown within defined bounds.
The representation should reflect the available basis rather than artificial
precision.
Classification Uncertainty
Some inputs depend upon classification.For example:
an object may be classified as:
Pedestrian
with:
92% confidence.
Where classification uncertainty can materially affect simulation behavior, it
should remain visible.
Missing-Information Uncertainty
Missing information creates uncertainty even where no substitute value isinserted.
SIMULOS® establishes:
Unknown does not become known merely because the simulation can execute
without the missing information.
Known Uncertainty
A Known Uncertainty has an identifiable source and sufficiently characterizedeffect or range.
Example:
Sensor accuracy ±0.5°C Partially
Characterized Uncertainty
A Partially Characterized Uncertainty is known to exist but cannot be fullyquantified or bounded.
It should remain explicitly represented.
Unresolved Uncertainty
An Unresolved Uncertainty exists where material uncertainty is known but itsmagnitude, distribution, or consequences cannot yet be sufficiently
established.
Unresolved uncertainty may require: restriction, sensitivity analysis,
scenario expansion, additional evidence, or downstream limitation.
Unknown Uncertainty
Not every uncertainty can be anticipated.SIUM does not claim to identify unknowable conditions.
It requires that known limitations in the ability to characterize uncertainty
remain visible.
Quantitative Uncertainty
Where appropriate, uncertainty may be expressed through: range, interval,probability distribution, confidence interval, variance, standard deviation,
tolerance, error bound, or another justified quantitative representation.
Qualitative Uncertainty
Not all uncertainty should be forced into numerical form.Qualitative states may include:
Low
Moderate
High
Material but Unquantified
Unresolvedor another governed classification.
No False Quantification Principle
SIMULOS® establishes:Uncertainty should not be assigned artificial numerical precision where the
available information cannot legitimately support it.
Uncertainty Bounds
Where uncertainty can be bounded, the relevant range should be identified.For example:
Input X ∈ [8.5, 10.2]
A bounded range should reflect the available evidence rather than an arbitraryconvenience range.
Unbounded or Open Uncertainty
Some uncertainty may not have a defensible upper or lower bound.Such uncertainty should not be converted into a narrow interval merely to
satisfy a simulation interface.
Point Estimate Governance
A simulation may technically require a single value.Where a point estimate represents an uncertain quantity, the record should
preserve:
Point Estimate + Uncertainty Basis
rather than allowing the estimate to become indistinguishable from exactobservation.
No Point-Estimate Certainty Principle
A single numerical input does not become certain merely because the simulationengine accepts only one number.
Uncertainty Dependency
Uncertainties may be dependent.For example:
multiple inputs derived from the same sensor may share the same measurement
uncertainty.
Treating them as independent may underestimate total uncertainty.
Correlated Uncertainty
Where uncertainty in one input is materially correlated with another, therelationship should be preserved where feasible.
Conceptually:
Uncertainty A ↔ Uncertainty B
rather than:Uncertainty A + Independent Uncertainty B
Shared-Source Uncertainty
Multiple inputs may inherit uncertainty from a common source.For example:
Input A
Input B
and:
Input C
may all depend upon:
Sensor S
A failure or bias in Sensor S may therefore affect all three inputs
simultaneously.
No Independence-by-Default Principle
SIMULOS® establishes:Input uncertainties must not be assumed independent merely because they are
represented as separate variables.
Compounded Uncertainty
Multiple uncertainties may interact.Conceptually:
Measurement Uncertainty + Transformation Uncertainty + Temporal Uncertainty +
Parameter Uncertainty
may create a broader uncertainty condition than any individual contribution
alone.
Uncertainty Aggregation
Where multiple uncertainty contributions are aggregated, the aggregationmethod should be: identifiable, appropriate, reproducible where required, and
bounded by known dependencies.
No Simple Addition Rule
Uncertainty components should not automatically be added, averaged, ormultiplied without a justified methodological basis.
Uncertainty Materiality
Not every uncertainty requires the same governance intensity.An uncertainty is material where it could reasonably affect: simulation
behavior, scenario outcome, output interpretation, validation, operational
decision, or reliance.
Materiality Is Context-Dependent
An uncertainty of:±1 mm
may be irrelevant in one simulation and critical in another.
Therefore:
Uncertainty Magnitude ≠ Uncertainty
Materiality
Materiality depends upon the Simulation Purpose and the sensitivity of thesimulated system.
Uncertainty Sensitivity
A simulation may respond differently to uncertainty across inputs.Some inputs may have little effect.
Others may produce major output changes.
SIUM therefore supports identification of:
Uncertainty-Sensitive Inputs
where uncertainty requires stronger downstream attention.Sensitivity Requirement
Where material uncertainty exists, downstream simulation design may requiresensitivity analysis.
The relevant later SIMULOS® governance spaces determine how that analysis is
executed.
SIUM establishes that the uncertainty requiring examination must not disappear
before reaching them.
Uncertainty Propagation
Input uncertainty may propagate through:Simulation Inputs
↓Simulation Model
↓Simulation Execution
↓Simulation Outputs
↓Simulation Interpretation
↓Operational Reliance
SIUM governs the input-side uncertainty basis and establishes propagationrequirements for later SIMULOS® stages.
Uncertainty Does Not End at Input Boundary
SIMULOS® establishes:Material uncertainty attached to an input remains relevant until a governed
downstream process demonstrates why it no longer materially affects the
simulation result.
No Uncertainty Erasure Principle
A transformation, model, or simulation execution must not silently erasematerial uncertainty merely because the downstream output is deterministic.
Deterministic Model ≠ Certain Result
A deterministic simulation may produce exactly the same output from exactly
the same input.
That does not mean the simulated result is certain where the input itself is
uncertain.
Precision vs Certainty
A simulation may produce:0.87346192
from uncertain input data.
The number of decimal places does not determine the certainty of the result.
No Precision-to-Certainty Principle
SIMULOS® establishes:Computational precision must not be represented as evidentiary certainty.
Uncertainty Scenario Representation
Where uncertainty cannot be adequately represented through a single input, thesimulation may require multiple input conditions.
For example:
Low Estimate
Central Estimate
High Estimate
or:Multiple Probability-Based Samples
SIUM establishes the uncertainty basis requiring such treatment.Boundary Conditions
Uncertain inputs may require simulation at boundary values.This can reveal whether conclusions remain stable across plausible input
ranges.
Worst-Credible Input Condition
Where consequence is high, the simulation may need to examine credible adverseinput combinations.
SIUM identifies the uncertainty basis.
Scenario governance determines how those conditions are represented.
Uncertainty Interaction With Scenario
Design
SIUM connects directly to the subsequent Simulation Scenario Standard (SSS).Uncertainty may require scenarios that explore: plausible ranges, adverse
combinations, edge conditions, uncertainty distributions, alternative input
states, and unresolved input assumptions.
SIUM does not design those scenarios.
It establishes what uncertainty the scenario design must be capable of
addressing.
Uncertainty Register
Material input uncertainties should be capable of being preserved within aSimulation Input Uncertainty Register.
The register may identify: uncertainty identifier, affected input, uncertainty
source, uncertainty type, magnitude or characterization, dependency,
materiality, downstream relevance, condition, and current status.
Uncertainty Identifier
A material uncertainty may receive a persistent identifier.For example:
SIU-0047
This allows later simulation records to reference the same uncertainty across:
scenario design, execution, output interpretation, validation, and reliance.
Uncertainty Status
Possible uncertainty statuses may include:Characterized
Partially Characterized
BoundedConditionally Bounded
UnresolvedMaterial Unquantified
or:Not Material for Defined Simulation Use
Uncertainty Acceptance
An uncertainty may be accepted for simulation use where: it is sufficientlyunderstood, its effect is bounded, required downstream treatment exists, and
the Simulation Purpose permits reliance upon that uncertainty level.
Acceptance does not mean the uncertainty disappears.
Conditional Uncertainty Acceptance
A Simulation Input may remain usable subject to conditions.For example:
Input accepted only if sensitivity testing covers ±10% variation.
Uncertainty Restriction
An input may be restricted where uncertainty prevents broader use.For example:
Suitable for exploratory simulation only.
but:
Not suitable for safety-critical operational reliance.
Uncertainty Rejection
Where uncertainty is too great or too poorly understood for the intendedsimulation purpose, the input may be rejected.
Uncertainty Undetermined
Where the available information is insufficient to assess uncertainty, thecorrect state may be:
Uncertainty Undetermined
rather than an assumed acceptable level.Uncertainty Threshold
A simulation may define thresholds beyond which input uncertainty requires:additional evidence, broader scenarios, stronger sensitivity testing,
restriction, or rejection.
Thresholds should derive from the Simulation Purpose and consequence rather
than convenience.
Uncertainty Budget
Where appropriate, a simulation may establish an Input Uncertainty Budgetdefining how much uncertainty can be tolerated across material input
categories.
The budget should not permit one uncertainty to disappear merely because
another input is highly precise.
No Precision Compensation Principle
SIMULOS® establishes:High certainty in one Simulation Input cannot automatically compensate for
material uncertainty in another input upon which the simulated outcome
critically depends.
Uncertainty Concentration
A simulation may contain many high-quality inputs but depend critically uponone highly uncertain variable.
SIUM therefore assesses uncertainty according to influence, not merely average
input quality.
Weakest Critical Input Principle
Where an outcome materially depends upon a highly uncertain critical input,the simulation conclusion should remain bounded by that uncertainty.
Uncertainty Change
Input uncertainty may change when: new evidence becomes available, sensors arerecalibrated, source reliability changes, transformation logic changes,
temporal distance increases, missing values increase, new environments are
introduced, or Simulation Scope changes.
Uncertainty Reassessment Trigger
Material changes should trigger reassessment of the affected uncertaintybasis.
Scope Expansion and Uncertainty
Expanding Simulation Scope may expose uncertainty that was immaterial underthe original scope.
For example:
an input sufficiently certain for:
normal operating conditions
may be insufficiently characterized for:
extreme operating conditions.
Version Change and Uncertainty
A new input version should not automatically inherit the uncertaintycharacterization of its predecessor.
The new version may require reassessment where: source, measurement,
transformation, temporal basis, or distribution
has materially changed.
Uncertainty Traceability
SIUM establishes:Simulation Input
↓Uncertainty Source
↓Uncertainty Type
↓Magnitude / Characterization
↓Dependency
↓
Materiality
↓
Propagation Requirement
↓Condition / Restriction
↓Uncertainty Status
↓Simulation Use Input Uncertainty Basis
The final SIUM result should establish a coherent Simulation Input UncertaintyBasis for the complete Simulation Input Set.
This basis should identify: material uncertainties, their origins, their
relationships, their characterization, unresolved uncertainty, downstream
treatment requirements, and limitations upon simulation use.
Input-Set Uncertainty
Individual inputs may each have acceptable uncertainty while their combinationcreates material uncertainty.
SIUM therefore distinguishes:
Input-Level Uncertainty
from:Input-Set Uncertainty.
Input-Set Uncertainty Coherence
The complete uncertainty basis should account for: shared sources,dependencies, correlations, transformation chains, temporal relationships, and
interacting uncertainty.
Simulation Input Readiness
After SIUM, the complete SIDS input basis may receive an overall readinessstatus such as:
Simulation Input Ready
Conditionally Simulation Input Ready
Partially Simulation Input Ready
Simulation Input Not Ready
or:Simulation Input Readiness Undetermined
This status represents completion of the SIDS input-governance sequence.Input Readiness Does Not Mean Simulation
Validity
SIMULOS® establishes:Simulation Input Readiness confirms only that the input basis is sufficiently
governed for its defined simulation use. It does not establish that the model,
scenarios, execution, outputs, or simulation itself are valid.
Those questions belong to subsequent SIMULOS® Parent Standards.
Minimum Implementation Framework
1. Identify Material Input UncertaintiesDetermine which Simulation Inputs contain uncertainty capable of materially
affecting simulation behavior or interpretation. 2. Identify Uncertainty
Sources
Bind each material uncertainty to its known or suspected origin. 3. Classify
Uncertainty
Determine whether uncertainty is associated with: measurement, observation,
sampling, representativeness, transformation, time, estimation, interpolation,
extrapolation, imputation, synthetic generation, parameterization,
classification, or another relevant source.
4. Characterize Uncertainty
Use justified: quantitative bounds, distributions, qualitative
classifications, or explicit unresolved status.
5. Assess Dependencies
Determine whether material uncertainties are: independent, correlated,
shared-source, sequentially dependent, or otherwise linked.
6. Assess Materiality
Determine whether each uncertainty can materially affect the Simulation
Purpose, behavior, outputs, or downstream reliance. 7. Establish Propagation
Requirements
Identify which uncertainties must remain visible through subsequent simulation
stages. 8. Establish Conditions and Restrictions
Define limitations upon simulation use where uncertainty remains material. 9.
Assign Uncertainty Status
Classify material uncertainties as: Characterized, Partially Characterized,
Bounded, Conditionally Bounded, Unresolved, Material Unquantified, or Not
Material for Defined Simulation Use.
10. Assess Input-Set Uncertainty
Evaluate interactions across the complete Simulation Input basis. 11.
Determine Simulation Input Readiness
Establish whether the governed input basis is: Ready, Conditionally Ready,
Partially Ready, Not Ready, or Readiness Undetermined.
12. Preserve Uncertainty Traceability
Maintain:
Input → Uncertainty → Source → Characterization → Dependency → Materiality →
Propagation → Condition → Status → Simulation Use
Governance Outputs
SIUM may produce: Simulation Input Uncertainty Register, Input UncertaintyIdentifier, Uncertainty Source Record, Measurement Uncertainty Record,
Observational Uncertainty Record, Sampling Uncertainty Record,
Representativeness Uncertainty Record, Transformation-Induced Uncertainty
Record, Temporal Uncertainty Record, Estimation Uncertainty Record,
Interpolation Uncertainty Record, Extrapolation Uncertainty Record, Imputation
Uncertainty Record, Synthetic Input Uncertainty Record, Parameter Uncertainty
Record, Classification Uncertainty Record, Missing-Information Uncertainty
Record, Quantitative Uncertainty Assessment, Qualitative Uncertainty
Assessment, Uncertainty Bound, Uncertainty Distribution Record, Unresolved
Uncertainty Record, Uncertainty Dependency Map, Correlated Uncertainty Record,
Shared-Source Uncertainty Record, Compounded Uncertainty Assessment,
Uncertainty Materiality Assessment, Uncertainty Sensitivity Signal,
Uncertainty Propagation Requirement, Input Uncertainty Budget, Uncertainty
Condition Record, Uncertainty Restriction Record, Uncertainty Status,
Input-Set Uncertainty Assessment, Simulation Input Uncertainty Basis,
Simulation Input Readiness Status, Uncertainty Reassessment Trigger, and
Simulation Input Uncertainty Traceability Map.
Use Case 1 — Autonomous Robot Simulation
ScenarioA robot-navigation simulation receives: object-position measurements with
sensor error, estimated surface-friction values, partially observed pedestrian
movement, and interpolated localization data.
Each input is technically usable.
However, each contains a different
uncertainty basis. Application
SIUM identifies: measurement uncertainty in object position, estimationuncertainty in surface friction, observational uncertainty in pedestrian
movement, and interpolation uncertainty in localization.
Dependencies between localization and object-position measurements are also
identified because both depend partly upon the same sensor system. Result
The input basis becomes:
Conditionally Simulation Input Ready
with a requirement that material uncertainty be propagated into subsequentscenario and execution governance rather than treating the nominal input
values as exact reality. Use Case 2 — Energy Infrastructure Simulation
Scenario
A long-term energy simulation uses: historical demand, future population
projections, weather forecasts, estimated technology adoption, and assumed
future industrial demand.
The simulation produces precise annual
energy-demand figures. Application
SIUM distinguishes:Observed Historical Inputs
from:Projected Inputs
Estimated Inputs
and:Assumed Inputs.
The largest material uncertainty is found in future industrial demand.
Sensitivity to this input is high. Result
The simulation may continue, but the uncertainty basis requires downstreamscenarios covering materially different industrial-demand conditions.
The final simulation cannot legitimately present the central numerical
trajectory as a certain future state.
Architectural Position
Simulation Input Uncertainty is the fifth and final internal governance spaceof the Simulation Input & Data Standard (SIDS).
The complete SIDS progression is:
Simulation Input Identification
↓Simulation Data Representativeness
↓Simulation Data Transformation
↓Simulation Temporal Data
↓Simulation Input Uncertainty
Together, the five modules answer:What information is entering the simulation?
↓
What reality can it legitimately represent?
↓
What happened to it before simulation use?
↓
Is it temporally appropriate?
↓
What uncertainty remains in the complete input basis?
The resulting:
Simulation Input Uncertainty Basis
and:Simulation Input Readiness Status
provide the governed input foundation required by subsequent SIMULOS®lifecycle spaces.
The next Parent Standard, Simulation Scenario Standard (SSS), governs which
scenarios must be designed to examine expected conditions, variations, edge
cases, stresses, uncertainty, and materially relevant alternatives.
Foundational Principle
Simulation Inputs become uncertainty-governed only when material uncertaintyremains identifiable from its source through its characterization,
dependencies, conditions, and downstream propagation requirements, so that
computational precision cannot transform uncertain information into an
appearance of certain reality.