The {required element} of the system is {explainable} in line with the safety case requirements, to the {intended audience} in the {intended context}

{Explainable}

{required element}

{Intended audience}

{Intended context}

Argument over {explainability requirements}

{explainability requirements}

Implemented {explainability method} appropriate for {requirements}, i.e. the correct thing is being explained

Argument over {explainability methods}

{Explainability method
Evidence}

{Explainability method} is faithful to {model} process

Argument over faithfulness of {explainability method}

{Explainability method
Evidence}

{ML Model}

{Explanations} produced at appropriate {times}

Argument over appropriateness of {explanations} {time}

{Time Evidence}

{Times that explanations
are provided}

{Explanations} are appropriate for {audience}

Argument over appropriateness of {explanations} to {audience}

{Audience Evidence}

{Audience}

{Explainability method}

{Explanations}

What?
See section 4.2.2

How?
Section 3

When? Section 2.2.3

Who? Section 4.2.4

Why?
See section 4.2.1