quantmodel — Port + verify Risk Premium Value Best + Weighted vs AS metrics

Objective

Port + verify Risk Premium Value Best + Weighted vs AS metrics.

Notes: RPV Best+Weighted replicated 2015+: best corr 0.911 CAGRΔ +0.04%; weighted corr 0.953 Δ -0.61%. DGS20 long rate critical. Spec/backtest/rpv.py + runners. Findings: rpv-scale-batch.md.

Approach

Reuses existing report research/findings/rpv-scale-batch.md — tables/metrics preserved verbatim via source_report pointer. Body below summarizes grounded evidence from that report and adjacent artifacts.

Files / code / data changed

Associated commits (inferred from log grep t46):

181d0755 research: t45 block Novell SPY-COMP; t46 RPV Best+Weighted replicated (#43)
181d0755 research: t45 block Novell SPY-COMP; t46 RPV Best+Weighted replicated (#43)
Source report: research/findings/rpv-scale-batch.md
Task-history entry: research/findings/task-history.json#t46

Results

Key table from source report (preserved):

Asset	Risk premium
TLT	long − short Treasury yield
LQD	IG corporate − long Treasury yield
SPY	S&P 500 earnings yield − long Treasury (earnings lagged ≥4 months)

Conclusions and metrics are in research/findings/rpv-scale-batch.md; see detail page for preserved tables/metrics.

Conclusions

RPV Best+Weighted replicated 2015+: best corr 0.911 CAGRΔ +0.04%; weighted corr 0.953 Δ -0.61%. DGS20 long rate critical. Spec/backtest/rpv.py + runners. Findings: rpv-scale-batch.md.

Problems / follow-ups

See source report or PR discussion for follow-ups. No unsupported follow-ups fabricated.