# Explainability

> The degree to which a model's decision comes with the evidence or attribution a reviewer needs to understand it.

Record: `architecture:explainability`
Kind: quality-attribute
Layer: [Correctness Core](https://banes-lab.com/records/layer/correctness-core.md)
Severity: contextual
Scope: model, model-backed system, decision flow
Canonical: https://banes-lab.com/ontology#architecture-explainability

Listed in [Architecture principles](https://banes-lab.com/api/records/architecture.md), after [Knowledge Graphs](https://banes-lab.com/records/architecture/knowledge-graphs.md) and before [Model Safety](https://banes-lab.com/records/architecture/model-safety.md).

## Repair

- Refactored by: Add Explanation Layer, Add Evidence Trace
- Detected by: missing rationale/feature attribution/citations
- Violated by: consequential model decisions without explanation/evidence
- Measured by: explanation coverage/quality
- Enforced by: model governance gates

## Requires

- [Traceability](https://banes-lab.com/records/architecture/traceability.md)
- [Rationale/Evidence](https://banes-lab.com/records/lexicon/rationale-evidence.md)

## Reinforces

- [Governance](https://banes-lab.com/records/architecture/governance.md)
- [Trust](https://banes-lab.com/records/lexicon/trust.md)

## Enables

- [Audit and Debugging](https://banes-lab.com/records/lexicon/audit-and-debugging.md)

## Conflicts with

- [Opaque Black-Box Decisions](https://banes-lab.com/records/lexicon/opaque-black-box-decisions.md)

## In tension with

- [Model Complexity](https://banes-lab.com/records/lexicon/model-complexity.md)
- [Artificial Intelligence Architecture](https://banes-lab.com/records/architecture/artificial-intelligence-architecture.md)
- [Artificial Intelligence Architecture / Explainability](https://banes-lab.com/records/tension/artificial-intelligence-architecture-explainability.md)

## Tensions

- [Explainability / Model Complexity](https://banes-lab.com/records/tension/explainability-model-complexity.md)

## Severity

- [contextual](https://banes-lab.com/records/vocabulary/severity-contextual.md)

## Category

- [Model Architecture](https://banes-lab.com/records/architecture-category/model-architecture.md)

## Reinforced by

- [Retrieval-Augmented Generation](https://banes-lab.com/records/architecture/retrieval-augmented-generation.md)
- [Knowledge Graphs](https://banes-lab.com/records/architecture/knowledge-graphs.md)
- [Agentic Architecture](https://banes-lab.com/records/architecture/agentic-architecture.md)

## Linked from

- [Systems built around a model](https://banes-lab.com/software-architecture/scale/systems-built-around-a-model.md)
- [Model Architecture](https://banes-lab.com/ontology/principles/architecture-category-model-architecture.md)
- [Observability / Auditability / Traceability](https://banes-lab.com/ontology/principles/architecture-category-observability-auditability-traceability.md)
- [Security / Privacy / Compliance / Governance](https://banes-lab.com/ontology/principles/architecture-category-security-privacy-compliance-governance.md)
- [Model Architecture](https://banes-lab.com/ontology/lexicon/lexicon-category-model-architecture.md)
- [Severity levels](https://banes-lab.com/ontology/schema/the-vocabulary-severity.md)
- [The resolutions](https://banes-lab.com/ontology/schema/the-resolutions.md)