fix(notebook,#18124): research_macro_factor_rotation -- real FRED factors + measured per-asset trees replace placeholder

[jsboige]

Grain: MED/notebook-python -- lane myia-po-2026:CoursIA -- prev: #18164

Summary

SOTA repair of Research-Executor/research_macro_factor_rotation.ipynb
(non-executed-cells family of the #18124 audit). Was: QuantBook-only,
analysis cells un-executed, fake "BACKTEST RESULTS" placeholder.

• Real FRED factors: T10Y3M + DFF via the public fredgraph.csv endpoints
  (no API key) + real ^VIX via yfinance -- the exact series the strategy
  names (latest measured: yield_curve 0.93, fed_funds 3.88, VIX 14.87).
• Factor <-> 21d forward SPY return correlations measured: VIX +0.247,
  yield curve -0.057, fed funds +0.021.
• The promised per-asset DecisionTreeRegressor trained and measured
  (depth=12 as per strategy spec, temporal 70/30 split): OOS R2 = -0.669
  (SPY), -0.620 (GLD), -3.875 (BND) -- all three WORSE than the
  mean-prediction baseline. The honest verdict is written into the notebook:
  3 macro factors alone do not predict 21-day returns at daily granularity.
• Rotation mechanics (1.5x leverage on positive predictions, BTC cap,
  monthly retraining) explicitly routed to the QC Cloud engine.

Validation

• Papermill: 8/8 cells, 0 errors, all execution_count set (C.2)
• C.1: no raise NotImplementedError / assert False / 1/0 (verified)
• Catalogue byte-identical to main (single .ipynb changed)
• SOTA verdict: SOTA-OK -- real FRED + index data, real measured
  correlations, trained trees with honest negative-R2 reporting

See #18124 (7 of the 10 audited notebooks now repaired by this lane;
remaining: re-audit the last 3 against current state next cycle).

🤖 Generated with Claude Code

[github-actions]

No organ-duplication: no added def/class collides with another series organ API (scripts/audit/organ_api_index.yaml).

Detector: python scripts/audit/detect_organ_duplication.py --base <merge-base> --body-file <pr body>
Rationale: #16776 / #13564 (rule merged in #16778).

[github-actions]

Notebook outputs-required (H.4 schema): PASS (every code cell carries an outputs: list)

[github-actions]

✅ No prose/output mismatch detected in the notebooks this PR changed.

Scope = notebooks CHANGED in this PR, not the whole corpus. Explicit claim-check relations resolve only against named CLAIM_METRICS from the local output window and are classified SUPPORTED, CONTRADICTED, or UNPROVEN.
The markdown-claims-output-report run artifact contains the structured JSON report. See python scripts/check_markdown_claims_output.py --help for re-running locally.
Detector rationale: c.290 / c.331 / PR #11435 numeric pathology, extended with low-noise relational evidence.

[github-actions]

Golden-Set Execution (H.7 P3)

✅ 8/8 notebooks passed (certified reproducible)

Notebook	Status	Time
2.1-Workflow-ML.ipynb	✅ SUCCESS	3.3s
2.2-Descente-de-gradient.ipynb	✅ SUCCESS	3.7s
2.3-Regression-lineaire-logistique.ipynb	✅ SUCCESS	4.8s
2.4-Arbres-Forets-Ensembles.ipynb	✅ SUCCESS	4.4s
Search-01-StateSpace.ipynb	✅ SUCCESS	3.2s
SL-1-LogicalLearning.ipynb	✅ SUCCESS	2.0s
rl_4_multi_armed_bandits.ipynb	✅ SUCCESS	17.6s
GameTheory-04c-NashExistence-Python.ipynb	✅ SUCCESS	2.6s

Pinned lockfile: scripts/notebook_tools/golden_set.lock.txt (H.7 P3, axe A #4208)

[github-actions]

Notebook PR Validation: PASS

• Notebooks checked: 1
• Code cells validated: 4
• Result: All passed

Checks: H.1 (no errors), H.3 (execution_count), C.1 (no banned patterns)
Non-Python kernels (.NET/Lean): C.1 + errors only (execution_count advisory)
QuantConnect notebooks: C.1 + errors only (require QC Cloud for execution)

[jsboige]

[ADJOINT PREFLIGHT]
schema: 1
lane: myia-po-2023:CoursIA
pr: 18165
head: 391e82c
complete: true
body: read
comments-reviewed: 5
reviews-reviewed: 0
threads-reviewed: 0
threads-unresolved: 0
surfaces-sha256: 73bcd897df1872f908728b13fcbd2317a24ea740df3496ccfb7e1a2537f0725a
diff-files: 1
diff-additions: 293
diff-deletions: 100
checks: latest-wins-green
b0: clear
scope: pass
domain: not-applicable
verdict: READY
[/ADJOINT PREFLIGHT]