dennisthiessenandClaude Opus 5
8453b87290
total_debt read LongTermDebt, else LongTermDebtNoncurrent/Current, plus one of ShortTermBorrowings/CommercialPaper. That misses two whole tagging styles, and it feeds net_debt -> net_debt_to_ebitda -> the categorical leverage read, so the misses were not absences but confident wrong answers: Coca-Cola scored on 0.25bn of commercial paper against ~39bn of debt, Verizon on 21.78bn of current maturities against ~165bn, AT&T and Exxon produced no value at all against 134bn and 33bn tagged. Measured over 19 large caps and 14 REITs, 11 were wrong or absent and the rest are unchanged. Each concept's span is now respected. LongTermDebt already includes current maturities (Apple tags all three: 71.34 + 11.01 = 82.30), so only true short-term borrowing is added. LongTermDebtAndCapitalLeaseObligations — what KO, HD, T, XOM and CVX tag, and nothing read before — is noncurrent and takes a current complement, and DebtCurrent *is* that whole complement rather than an addition to it. The REIT branch needed disambiguating: NotesPayable is not the same line across issuers. MAA tags NotesPayable 5.66bn = UnsecuredDebt 5.30bn + SecuredDebt 0.36bn exactly, so there it is the total and adding the secured side double-counts; EQR tags it alongside a larger SecuredDebt, where it is only the unsecured component. UnsecuredDebt's presence separates them. A component alone is no longer reported as a total. Chevron tags full debt only in its 10-K, so its 10-Q carried 0.40bn of short-term borrowing; Boston Properties tags SecuredDebt 4.28bn against ~15bn real. net_debt needs both sides and yields nothing when either is missing, so None costs a leverage read where the fragment produced a confidently wrong one. Snapshots are immutable, so this corrects new filings only; stored history needs scripts/reparse_fundamentals.py, which cannot complete until the EQR/931182 collision is retired. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_016Lo99z3jWqu9X9ueBU3Z3D
Backtest report index
Reports dated 2026-07-11 or earlier are the historical production research record and remain untouched.
The completed 2026-07-12/13 S/R and Gate Target Ladder research is preserved as compact decision evidence instead of full per-arm replay output:
sr-v2-validation-comparison.jsonandsr-v2-validation-cohorts.csvrecord the held-out detector comparison.sr-full-production-vs-candidate-comparison.jsonand its cohort CSV record the full-period clean-structure replacement decision.sr-explicit-target-ladder-comparison.jsonand its cohort CSV record exact GTL parity: 202,765 candidates, 1,086 qualified setups, 321 book trades, Sharpe 2.03, CAGR 50.0%, and max drawdown 21.4% in both arms.- The three
backtest-20260713-gtl-*.json/.mdpairs record the tuning, confirmation, and strength-sensitivity decisions. No stable improvement was found, so the production GTL stayed frozen.
The large backtest-sr-*.json replay files were removed after consolidation.
They duplicated hundreds of thousands of candidate rows while adding no
decision information beyond the compact comparisons and the narrative in
docs/research/sr-levels-and-exits.md. The original raw files remain available
in Git history if a forensic reconstruction is ever necessary.
The initial untracked backtest-20260712-sr-detector-rewrite.json is local-only
and is intentionally not part of the repository.
The 2026-07-17 post-stop re-entry decision is preserved in
daily_reentry_matrix.json. It is the canonical source for the nine-policy
daily replay, production-like full-universe ranking, the disjoint 2025+ book,
and the cost/capacity sensitivity matrix. The interpretation and production
decision live in
docs/research/post-stop-reentry.md.
The earlier post-stop-reentry-20260717.json,
post-stop-cooldown-sweep-20260717.json, and
gate-protected-stop-20260717.json reports were removed as superseded
intermediate experiments. They used weekly/hybrid entry cadence or tested the
rejected stop-adjustment path, and add no decision evidence beyond the final
daily matrix and narrative. Their matching one-off runners were removed too.
All remain recoverable from Git history. Rebuildable candidate pickle caches
are intentionally ignored and must not be committed.
Phase B fip breadth IC (2026-07-18/19) — compact evidence
Canonical artifacts:
fip-reconcile-20260719-000520.json— single-sourced authoritative ICs (unconditional liquid fip, tiers, prod-subset, mom-conditional, context signals). Membership symbol dumps stripped after the decision; narrative indocs/research/fip-breadth-ic.md.fip-breadth-20260718-211440-fingerprint.json— prod-snapshot fingerprint pass (fip IC −0.045 / t −2.91).
Removed as superseded / dangerous intermediate noise (recoverable from Git):
fip-breadth-20260718-211440-breadth.json(+ wrapper) — orphaned +0.0575 / t +5.12 from racing a partialresearch.sqlite. Kept out of the tree so it cannot be re-mythologized.fip-breadth-20260718-194828*.json— fingerprint-only partial run.fip-breadth-diagnostics-20260718-213705.jsonand…-213908.json— dual-path diagnostics superseded by the single-sourced reconcile.