added citation accuracy regression eval script

[sap6011]

Pull Request

Description

Type of Change

• 🐛 Bug fix (non-breaking change that fixes an issue)
• ✨ New feature (non-breaking change that adds functionality)
• 💥 Breaking change (fix or feature that would cause existing functionality to not work as expected)
• 📝 Documentation update
• ♻️ Code refactoring (no functional changes)
• ⚡ Performance improvement
• ✅ Test update

Related Issues

Changes Made

Testing

• Unit tests pass (pytest)
• E2E tests pass (if applicable)
• Manual testing completed
• All checks pass (opendraft verify)

Test details:

Screenshots (if applicable)

Checklist

• My code follows the project's code style
• I have run linting (pylint or ruff)
• I have added tests that prove my fix is effective or that my feature works
• I have updated the documentation accordingly
• I have added myself to CONTRIBUTORS.md (if applicable)
• My changes generate no new warnings
• Any dependent changes have been merged and published

Additional Context

[sap6011]

Hey can you review the pr?

[federicodeponte]

Maintainer triage after the Quality Gates fix and #43 packaging merge: leaving this unmerged.

This overlaps with #41/#44/#39 around data/eval_topics.json and scripts/eval_regression.py. I also found a concrete path issue: the script inserts REPO_ROOT / "opendraft" / "engine" into sys.path, but this repo's engine is at REPO_ROOT / "engine". The live-validation workflow addition would run a costly live eval path once secrets are present, so it needs a corrected path, baseline story, and CI evidence before merge.