docs(notebooks): add README for encrypted fairness-metrics notebook

[Bader (BAder82t)]

Summary

Adds a companion README for the fairness-dashboard-encrypted-metrics.ipynb notebook that landed in #2623.

The README documents:

• The drop-in fairlearn ↔ fairlearn_fhe import swap
• Trust models (Mode A: encrypted predictions only / Mode B: encrypted predictions + sensitive features) with the exact trust_model envelope field strings (plaintext_sensitive_features / encrypted_sensitive_features)
• The intended party split (data owner / auditor / decryptor) and what FHE alone does not give you
• The audit-envelope flow (audit_metric → MetricEnvelope → JSON Schema → sign_envelope Python API → fairlearn-fhe verify CLI with --max-age / --min-security-bits / --max-depth / --public-key)
• Handoff to raiwidgets.FairnessDashboard for the analyst-facing view
• CKKS parameter knobs (build_context real signature, defaults at poly_modulus_degree=16384, scale_bits=40, depth-6 chain, 128-bit security target) and how to override
• Sample output, requirements (Python >=3.10, <3.13, fairlearn >=0.10, etc.), and per-metric circuit depths (DP=3, equalized-odds/equal-opportunity=6) read from observed_depth in the envelope

[Copilot]

Pull request overview

Adds a companion README for the encrypted fairness-metrics notebook (fairness-dashboard-encrypted-metrics.ipynb) to explain the fairlearn → fairlearn_fhe swap, trust models, audit-envelope flow, and CKKS parameterization for fairlearn-fhe.

Changes:

• Add README-fairlearn-fhe.md documenting the notebook’s purpose, workflow, trust models, and audit-envelope verification flow.
• Document CKKS context defaults/overrides and provide expected sample output and runtime notes.

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[Ilya Matiach (imatiach-msft)]

this looks great, let me just wait for all tests to run and then I will merge

[Ilya Matiach (imatiach-msft)]

it seems like you need to run prettier on the readme, but I can just fix that in another PR:

$ /home/runner/work/responsible-ai-toolbox/responsible-ai-toolbox/node_modules/.bin/prettier . --check
Checking formatting...
[warn] notebooks/individual-dashboards/fairness-dashboard/README-fairlearn-fhe.md
[warn] Code style issues found in the above file(s). Forgot to run Prettier?
error Command failed with exit code 1.
info Visit https://yarnpkg.com/en/docs/cli/run for documentation about this command.
error Command failed with exit code 1.
info Visit https://yarnpkg.com/en/docs/cli/run for documentation about this command.
error Command failed with exit code 1.
info Visit https://yarnpkg.com/en/docs/cli/run for documentation about this command.
Error: Process completed with exit code 1.