trop: CI codex R9 P2 fix — visible v2-pinning note in METHODOLOGY_REVIEW + REGISTRY

Address single P2 from CI codex R9 on PR #491 (verdict was ✅ Looks
good; no P0/P1).

P2 - Version-pinning visibility: the v2→v3 paper-version gap surfaced
as a P3 in R5 (general acknowledgement) and R6 (specific Section 5.1.1
delta noted in paper review file). R9 escalates because the paper
review honestly admits the gap but the TROP entry in METHODOLOGY_REVIEW
and REGISTRY still says "Complete" without a visible caveat, making
the methodology sign-off version-ambiguous at the exact sections
newly promoted (Eqs. 2-3, Algorithms 1-3, Section 2.2, Section 5.2-5.3,
Section 6.1-6.2, Theorem 5.1, Corollary 1, Appendix Theorem 8.1).

Added a visible "**Version Pinning**" subsection to METHODOLOGY_REVIEW
TROP entry immediately below the Status row, and a "**Note (version
pinning):**" annotation to REGISTRY ## TROP section immediately below
the Primary source line. Both:
  - Anchor the promotion on arXiv:2508.21536v2 explicitly
  - List the current version (v3, submitted 2026-02-09)
  - Enumerate the sections covered by the promotion that have NOT
    been v2→v3 delta-checked
  - Cite the known v3 structural change (Section 5.1.1 added)
  - Action-item to refresh when paper-author reference implementation
    lands

Status row also updated to "**Complete** (paper `method="local"`,
version-pinned to arXiv v2 — see Version Pinning below)" so the
caveat is visible even from a quick scan of the status table.

No source-code changes to diff_diff/trop*.py.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

Author: igerber

METHODOLOGY_REVIEW.md

@@ -826,9 +826,11 @@ These three are feature deferrals (paper-supported extensions that the library h
 | Module | `trop.py`, `trop_local.py`, `trop_results.py` (paper-aligned local method); `trop_global.py` (library-side efficiency adaptation — see "Scope" below) |
 | Primary Reference | Athey, Imbens, Qu & Viviano (2025), *Triply Robust Panel Estimators*, arXiv:2508.21536 |
 | R Reference | Paper-author reference implementation (not yet released as CRAN package) |
-| Status | **Complete** (paper `method="local"`) |
+| Status | **Complete** (paper `method="local"`, version-pinned to arXiv v2 — see Version Pinning below) |
 | Last Review | 2026-05-24 |
 
+**Version Pinning:** This methodology promotion is anchored on **arXiv:2508.21536v2** (the version covered by the paper review on file at `docs/methodology/papers/athey-2025-review.md`). The current arXiv version is **v3** (submitted 2026-02-09). A formal v2→v3 source delta-check has NOT been performed for the sections this PR promotes (Eqs. 2-3, Algorithms 1-3, Section 2.2, Section 5.2-5.3, Section 6.1-6.2, Theorem 5.1, Corollary 1, Appendix Theorem 8.1). Known v2→v3 change surfaced by CI codex during PR #491 review: v3 adds a `5.1.1 Conditions for exact unbiasedness` subsection that is not present in v2 — appears to be restructuring of the Corollary 1 material rather than a methodological change. **Action item:** when the paper-author reference implementation lands (currently "forthcoming"), refresh the paper review against the most recent arXiv version and re-validate the verified-component checklist; until then the promotion stays v2-anchored.
+
 **Scope:** This methodology promotion covers the paper-aligned `method="local"` path (paper Algorithm 2: per-(i, t) estimation with observation-specific weights). The library also exposes `method="global"`, documented in `REGISTRY.md` as a "computationally efficient adaptation using the (1-W) masking principle from Eq. 2" — a library-side adaptation, NOT the paper's full Algorithm 2 estimator. Defensive coverage of the global method lives in `tests/test_trop.py::TestTROPGlobalMethod` (704 lines, ~30 tests for the global-method-specific surface) and is not duplicated in the methodology walk-through. Methodology promotion of `method="global"` as a primary surface would require either (a) a paper-side derivation of the global adaptation's equivalence to Algorithm 2 under specific conditions, or (b) a separate library-extension methodology review; both are deferred.
 
 **Verified Components:**

docs/methodology/REGISTRY.md

@@ -2244,6 +2244,8 @@ confidence bands (sup-t) for event study.
 
 **Primary source:** [Athey, S., Imbens, G.W., Qu, Z., & Viviano, D. (2025). Triply Robust Panel Estimators. arXiv:2508.21536.](https://arxiv.org/abs/2508.21536)
 
+**Note (version pinning):** the methodology promotion (`METHODOLOGY_REVIEW.md` `#### TROP` → **Complete** as of 2026-05-24) is anchored on **arXiv:2508.21536v2**; the current arXiv version is **v3**. A formal v2→v3 source delta-check has NOT been performed for the sections covered by the promotion (Eqs. 2-3, Algorithms 1-3, Section 2.2, Section 5.2-5.3, Section 6.1-6.2, Theorem 5.1, Corollary 1, Appendix Theorem 8.1). Known v2→v3 change surfaced during PR #491 review: v3 adds a `5.1.1 Conditions for exact unbiasedness` subsection (restructuring of the existing Corollary 1 material, not a methodological change to the conditions themselves, pending v3 PDF audit). See `docs/methodology/papers/athey-2025-review.md` "Version-pinning note" for the action item.
+
 **Key implementation requirements:**
 
 *Assumption checks / warnings:*