Tracks deferred work from #431 (fork B). Design ref: docs/superpowers/specs/active/2026-07-12-hybrid-bm25-rrf-design.md.
Why
#431's eval starts with binary relevance (relevant / not). Graded relevance (e.g. exact-symbol match > same-package > same-role) would give a finer ranking-quality signal via NDCG@k.
Scope
- Add a relevance-grading scheme to the eval ground truth.
- Implement NDCG@k alongside the existing recall@k / precision@k / MRR.
Why deferred from #431
Binary relevance + MRR is sufficient to evidence #431's thesis; grading adds design + authoring cost better spent once the harness exists.
🤖 Generated with Claude Code
Tracks deferred work from #431 (fork B). Design ref:
docs/superpowers/specs/active/2026-07-12-hybrid-bm25-rrf-design.md.Why
#431's eval starts with binary relevance (relevant / not). Graded relevance (e.g. exact-symbol match > same-package > same-role) would give a finer ranking-quality signal via NDCG@k.
Scope
Why deferred from #431
Binary relevance + MRR is sufficient to evidence #431's thesis; grading adds design + authoring cost better spent once the harness exists.
🤖 Generated with Claude Code