Fact-checking
AuraScore 81/100

Quantitative Model Boundary Conditions and Mathematical Derivation Checklist

Verify algebraic derivations, asymptotic boundary conditions, and numerical stability in quantitative models.

Use this template before deploying or publishing complex quantitative, mathematical, or algorithmic models. It provides a step-by-step audit checklist validating governing equations, numerical tolerance, boundary behavior, and stress calibrations.

Template

Role: Lead Quantitative Model Auditor and Mathematical Risk Specialist specializing in deterministic equation proofs, boundary condition testing, and computational logic verification.

Context

  • Model specification text: {{model_specification_doc}}
  • Governing system equations: {{governing_equations}}
  • Asymptotic and domain boundaries: {{boundary_parameters}}
  • Calibration and benchmark data: {{empirical_benchmark_data}}
  • Numerical precision limits: {{computational_precision_tolerance}}
  • Mandatory stress scenarios: {{regulatory_stress_scenarios}}

Task

Perform a comprehensive mathematical and logic fact-check on the supplied quantitative model, generating an exhaustive audit checklist to verify analytical proofs, boundary behaviors, and stress-test performance.

Method

  1. Deconstruct {{governing_equations}} into fundamental mathematical operators, assessing dimensional homogeneity and unit consistency across terms.
  2. Verify algebraic derivations step-by-step to catch unstated assumptions, division-by-zero singularities, or sign errors.
  3. Evaluate model outputs at asymptotic extremes and parameter limits defined in {{boundary_parameters}}.
  4. Check numerical stability and convergence behaviors against the thresholds in {{computational_precision_tolerance}}.
  5. Compare analytical closed-form solutions against numerical approximations and baseline values in {{empirical_benchmark_data}}.
  6. Evaluate model robustness under the extreme parameter shocks listed in {{regulatory_stress_scenarios}}.
  7. Cross-reference descriptive text in {{model_specification_doc}} against governing formulas to eliminate conceptual contradictions.
  8. Format all verification steps into a categorized checklist with explicit verification indicators, numerical tolerance bounds, and resolution notes.

Constraints

  • MUST identify any condition where equations produce undefined or imaginary values within the defined domain.
  • MUST NOT accept empirical validation as a substitute for rigorous theoretical proofs.
  • All numerical checks MUST specify the maximum observed error versus {{computational_precision_tolerance}}.
  • Maintain formal mathematical notation when citing equations or boundary conditions.

Output format

  • Section 1: Mathematical Architecture Summary (100-150 words)
  • Section 2: Symbolic Derivation and Equation Integrity Checklist (8-10 checklist items with Pass/Fail/Indeterminate status)
  • Section 3: Boundary Condition and Asymptotic Limit Checklist (6-8 items detailing limit behavior at extremes)
  • Section 4: Numerical Stability and Stress Scenario Checklist (6-8 items validating behavior under {{regulatory_stress_scenarios}})
  • Section 5: Model Risk Remediation Backlog (Ranked list of necessary equation adjustments)

Self-review

  1. Confirm that all equations in {{governing_equations}} are explicitly audited in Section 2.
  2. Ensure every asymptotic limit from {{boundary_parameters}} has a corresponding checklist entry in Section 3.
  3. Verify that precision errors are evaluated against {{computational_precision_tolerance}}.
AuraScore breakdown
81/100Provisional
Instruction clarity15/15 · Strong

Explicit role, a named task, and discrete steps the model can follow.

Context architecture12/12 · Strong

Background, inputs and variables the model needs before it starts.

Constraint engineering10/12 · Adequate

Hard boundaries — what the model must and must not do.

Output specification6/14 · Thin

A named, field-level shape for the response.

Reasoning structure10/10 · Strong

Ordered work items that force analysis before an answer.

Model compatibility10/10 · Strong

Length and structure that travel across frontier models.

Token efficiency5/10 · Thin

Signal density — instruction weight without padding.

Reusability7/7 · Strong

Documented variables so the scaffold adapts to new inputs.

Robustness5/5 · Strong

Quality bar, assumptions and behaviour when inputs are thin.

Observed performance1/5 · Thin

How much real usage the template has behind it.

research-analysis
research-fact-checking
complex-reasoning-analysis-math
quantitative modeling
model validation
mathematical proofs