docs(splat-native): D-SPLAT-4 ADR-024 adoption callout (symmetric to cesium-osm §11)

OGAR #39 ADR-024 (Palette256 + HHTL codec — universal compression
primitive) § Consequences names BOTH **D-OSM-2** (geographic
adopter) AND **D-SPLAT-4** (anatomical / volumetric adopter) as
queued ADR-024 adopters. The geographic side already landed its
adoption note in `cesium-osm-substrate-v1.md §11` (PR #475). This
PR ships the symmetric anatomical-side adoption note for
D-SPLAT-4 so the cross-arc references resolve.

## What this PR ships

Inline ADR-024 adoption paragraph + amended test plan on D-SPLAT-4
in `splat-native-ultrasound-v1.md` §3. Single-file edit; no other
sections touched.

The new adoption note maps ADR-024's four-step checklist onto
D-SPLAT-4 specifics:

1. **Prefix** = FMA NiblePath + SH basis-id (per-region spatial frame).
2. **Palette domain** = quantized SH coefficients (16 coeffs at ℓ=3)
   clustered per FMA region; per-region palette captures dominant
   tissue echo signatures (planar fascia / spherical organ surfaces
   / Doppler-flow vascular).
3. **ρ-vs-reference target ≥ 0.99** matching the `lance-graph-arm-
   discovery` aerial-codebook empirical anchor (ρ = 0.9973 vs
   cosine). Reference = analytic SH evaluation at the same view
   direction. Report empirical ρ on the **first FMA-region palette
   build** (default region: femur cortical bone — smallest
   tractable corpus; cf. OGAR PR #30 §6 FMA-bones litmus).
4. **Decode = const-table lookup**; per-region SH palette runtime
   const-table; zero-allocation; compile-time HHTL where the
   palette is shared across regions (global basis-ID lookup for the
   256 SH signatures).

The 256-ceiling escape hatches from ADR-024 are mapped:
- **Per-region palettes** (cheapest) — different FMA region,
  different 256 SH-signature entries.
- **Hierarchical palettes** (coarser at OrganSystem level, finer
  per Bone leaf) mirror the SH ℓ=0/ℓ=1 vs ℓ=2/ℓ=3 split.
- **Palette-64K** reserved for measured-cardinality escalation.

## Amended test plan

The existing D-SPLAT-4 test plan keeps its two tests (palette compose
vs ground-truth Gaussians; SH-basis discrimination cosine ≥ 0.95 vs
analytic SH on phantom data). The ADR-024 adoption adds:

- **NEW**: empirical ρ-vs-reference reported on first FMA-region
  palette build (target ≥ 0.99).
- **NEW**: per-region palette cardinality distribution (mean / p95 /
  p99) at FMA-region granularity — escape-hatch selection from
  measurement, not speculation.

## Cross-references

- **ADR-024**: `OGAR/docs/ARCHITECTURAL-DECISIONS-2026-06-04.md §
  ADR-024` (OGAR PR #39, merged 2026-06-05). The § Consequences
  names both D-OSM-2 and D-SPLAT-4 as queued adopters.
- **Geographic-side companion**: `cesium-osm-substrate-v1.md §11`
  (lance-graph PR #475). Same four-step adoption mapping with
  Cesium TMS quadkey + per-tile OSM tag palette specifics.
- **Empirical anchor**: `lance-graph-arm-discovery` aerial codebook
  ρ = 0.9973 vs cosine — the FINDING-grade floor that new
  ADR-024 adopters target (≥ 0.99).

## Test plan

- [x] Docs/plan only — no source code; no build/test invoked.
- [x] Single-file edit; no governance-file churn (the D-SPLAT-4
      STATUS_BOARD row + INTEGRATION_PLANS entry don't change —
      this is a clarification of an existing deliverable's
      acceptance criteria, not a new deliverable).
- [x] Symmetric to PR #475 (cesium-osm §11 ADR-024 adoption);
      same four-step mapping pattern.
- [x] D-SPLAT-4 existing tests preserved; ADR-024 adds ρ-vs-
      reference + cardinality distribution as NEW test requirements.
- [ ] Codex review on this PR (light — single-paragraph addition).

Author: claude

.claude/plans/splat-native-ultrasound-v1.md

@@ -152,7 +152,16 @@ The palette codec is currently `(centroid_palette: u8, edge_weight: u8, scent: u
 
 **Compose-table size doubles** (from 256×256×1 B to 256×256×2 B) — still fits in 128 KB, still L1-resident.
 
-**Tests:** palette compose against ground-truth Gaussians; SH-basis discrimination (cosine ≥ 0.95 against analytic SH on phantom data).
+**ADR-024 adoption (palette256 + HHTL codec, OGAR #39).** D-SPLAT-4 is named in `OGAR/docs/ARCHITECTURAL-DECISIONS-2026-06-04.md § ADR-024 Consequences` as one of the two queued ADR-024 adopters (paired with D-OSM-2 — see `cesium-osm-substrate-v1.md §11` for the geographic-side adoption note). Mapping ADR-024's four-step adoption checklist onto D-SPLAT-4:
+
+1. **Prefix.** FMA NiblePath + SH basis-id — the per-region spatial frame (FMA class identity within the atlas + ℓ=3 SH basis index).
+2. **Palette domain.** Quantized SH coefficients (16 coeffs at ℓ=3) clustered per FMA region. Per-region palette captures dominant tissue echo signatures (planar fascia / spherical organ surfaces / Doppler-flow vascular).
+3. **ρ-vs-reference target ≥ 0.99**, matching the `lance-graph-arm-discovery` aerial-codebook empirical anchor (ρ = 0.9973 vs cosine). Reference: analytic SH evaluation at the same view direction (the same reference used in the D-SPLAT-4 test plan below). Report empirical ρ on the **first FMA-region palette build** (default region: femur cortical bone — smallest tractable corpus; cf. OGAR PR #30 §6 FMA-bones litmus).
+4. **Decode = const-table lookup.** Per-region SH palette is runtime const-table; decode path is zero-allocation. Compile-time HHTL where the palette is shared across regions (e.g. global basis-ID lookup for the 256 SH signatures).
+
+The 256-ceiling escape hatches from ADR-024 apply directly: per-region palettes are the cheapest answer (different FMA region, different 256 SH-signature entries); hierarchical palettes (coarser at OrganSystem level, finer per Bone leaf) mirror the SH ℓ=0/ℓ=1 vs ℓ=2/ℓ=3 split. Palette-64K is reserved for measured-cardinality escalation, not speculation.
+
+**Tests:** palette compose against ground-truth Gaussians; SH-basis discrimination (cosine ≥ 0.95 against analytic SH on phantom data); **NEW: empirical ρ-vs-reference reported on first FMA-region palette build (target ≥ 0.99 per ADR-024 adoption contract)**; per-region palette cardinality distribution (mean / p95 / p99) at FMA region granularity.
 
 **Gates on:** D-SPLAT-1.