quantmodel — Hard reverse-engineer Novell SPY-COMP (±DB) and Bond-COMP vs AS

Objective

Hard reverse-engineer Novell SPY-COMP (±DB) and Bond-COMP vs AS.

Notes: COMP family RE+replicated 2015+: spy-comp corr 0.983 CAGRΔ -0.95%; db 0.981 Δ -1.26%; bond-comp 0.988 Δ -0.22%. Spec/port backtest/novell_comp.py. Findings: as-novell-comp-re.md

Approach

Reuses existing report research/findings/as-novell-comp-re.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 t103):

6c89fb97 research: t103 Novell COMP family reverse-engineered (corr 0.983/0.981/0.988) (#88)
6c89fb97 research: t103 Novell COMP family reverse-engineered (corr 0.983/0.981/0.988) (#88)
Source report: research/findings/as-novell-comp-re.md
Task-history entry: research/findings/task-history.json#t103

Results

Key table from source report (preserved):

date	SPY-COMP	SPY-COMP DB	Bond-COMP
2026-03-31	IEF 100%	Cash 100%	GLD/IEF/TLT/Cash 25%
2026-04-30	SPY 100%	SPY 100%	HYG/LQD/BNDX/EMB 25%

Conclusions and metrics are in research/findings/as-novell-comp-re.md; see detail page for preserved tables/metrics.

Conclusions

COMP family RE+replicated 2015+: spy-comp corr 0.983 CAGRΔ -0.95%; db 0.981 Δ -1.26%; bond-comp 0.988 Δ -0.22%. Spec/port backtest/novell_comp.py. Findings: as-novell-comp-re.md

Problems / follow-ups

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