plateau-triage 0.1.1

Post-disaster building damage record layer: 🔴危険 / 🟡要注意 / 🟢調査済 / ⬜未調査 + confidence + provenance, bound to persistent building IDs. Honest by construction: covered=false ⇒ value=null.

plateau-triage 🚩

災害建物トリアージ — 被災後の建物損傷記録層
Post-disaster building damage record layer

被災影像を、逐栋・公式建物ID紐付け・確信度＋出処つきの損傷状態記録に変える。
そして何より 「まだ確認していない建物」を明示する。
Turn disaster imagery into a per-building, ID-bound record of damage state — with confidence, provenance, and, above all, an explicit "not yet surveyed".

pip install -e . · docs · DESIGN · Code Apache-2.0 · Data CC BY 4.0

地震の後で本当に知るべきは「壊れた建物」ではなく、「まだ確認していない建物」です。
After the quake, the most important thing to know is not which buildings are broken — it's which ones you haven't checked yet.

_{Noto demo: 🔴危険 / 🟡要注意 / 🟢調査済 extruded by severity, ⬜未調査 as the visible grey gaps, with the coverage meter. make demo && make viz-dev}

被災都市のすべての建物 = 1 つの誠実な記録。4 状態のいずれか × 確信度 × 出処。 Every building in a stricken city is one honest record, in one of four states:

	状態 / state	意味 / meaning	record
🔴	危険	dangerous	covered=true, value="危険"
🟡	要注意	needs caution	covered=true, value="要注意"
🟢	調査済	inspected, safe	covered=true, value="調査済"
⬜	未調査	not yet surveyed = unknown	covered=false, value=null

最初の 3 つは応急危険度判定の赤黄緑に対応します。第 4 の 未調査 は、スタック共通の 誠実性不変条件 covered=false ⇒ value=null の字面化です——誰も見ていない建物は 決して「安全」に既定されません。護城河は損傷識別モデルではなく、この誠実契約 ＋ 公式建物IDへの紐付けです。

The first three mirror Japan's 応急危険度判定 red/yellow/green tags. The fourth, 未調査, is the literal form of the stack-wide honesty invariant covered=false ⇒ value=null: a building nobody has looked at is never defaulted to "safe". That honesty contract — plus binding to a persistent building ID — is the moat, not the damage-classification model.

---

Quickstart

pip install plateau-triage          # from PyPI (pydantic, jsonschema, shapely, duckdb)
plateau-triage demo --out out/      # runs on the bundled Copernicus Noto sample
# point at your own data:  plateau-triage demo --input your_footprints.geojson --out out/
# from a clone, for dev:    pip install -e ".[dev,shacl]"   # + ruff, pyshacl/rdflib

plateau-triage — Noto demo
  ingested 12 footprints from fixtures/copernicus_noto_sample.geojson
  coverage: 8 / 12 assessed; 33% unknown
  state breakdown:
    🔴 危険    danger          3
    🟡 要注意   caution         3
    🟢 調査済   inspected       2
    ⬜ 未調査   unsurveyed      4
  outputs:
    geojson      out/triage.geojson      # red/yellow/green/grey choropleth (plateau-r3f / any viewer)
    coverage     out/coverage.json       # the coverage meter
    duckdb       out/records.duckdb       # the record layer (DuckDB; also writes .parquet on request)
    support_csv  out/support_system.csv  # 被災者支援システム screening feed
    risai_csv    out/risai_shomei.csv    # 罹災証明 pre-fill candidate feed (認定調査 still required)

これは Noto go/no-go デモです。現場作業ゼロ・PLATEAU/ネットワーク依存ゼロ。 This is the Noto go/no-go demo: zero fieldwork, zero PLATEAU/network dependency. 輪島は PLATEAU 未収録のため dataset_footprint ID で紐付け・2.5D 描画 します（PLATEAU 建物ID＋3D は生産経路）。It uses public Copernicus-shaped damage footprints near Wajima (輪島), which is not in PLATEAU — so records bind dataset_footprint IDs. Binding to PLATEAU 建物ID + 3D is the production path.

同梱 fixture は実 Copernicus EMS Noto 2024 スキーマと同形の 12 棟合成サンプルです。 The shipped fixture is a 12-footprint synthetic sample mirroring the Copernicus EMS Noto 2024 schema. Point --input at the real FeatureCollection to run it for real.

可視化 / Visualisation (plateau-r3f)

赤黄緑灰の 2.5D 着色 ＋ カバレッジ計 ＋ クリック溯源。日英バイリンガル UI。 The red/yellow/green/grey 2.5D choropleth + coverage meter + click-to-trace, bilingual JP/EN.

make demo && make viz-data      # writes the feed into viz/public/demo.geojson
make viz-install                # cd viz && npm install
make viz-dev                    # http://localhost:5173   (or: make viz-build)

_{クリック溯源 / click-to-trace: 状態・確信度・データセット・観測日時・ID 紐付け確信度。未調査の建物は「安全と見なさない」と明示。}

現場採集 / Field capture (drone · street)

python -m plateau_triage.cli capture --input fixtures/drone_capture_sample.json --out out/

弱い検出・未観測の建物は 未調査へ棄権し、決して「安全」に既定しません（§6.2 優雅な劣化）。VSRD/SfM/SAM は差し替え可能なプラグ。A weak or unseen building abstains to 未調査, never defaulted to safe; VSRD/SfM/SAM are pluggable backends.

既存システムへ供給 / Feed existing systems

python -m plateau_triage.cli export --records out/records.duckdb --out out/feed.csv --format both

被災者支援システム ＋ 罹災証明（被害認定調査の事前入力候補——証明そのものでは ありません）。Both the 被災者支援システム feed and the 罹災証明 pre-fill candidate (never the certificate itself — the 認定調査 always governs). See docs/integration.md.

---

Pipeline

                         GeoJSON footprints + damage_grade        drone / street capture session
                                  │  accrue.ingest_batch                  │  accrue.ingest_capture
                                  │  (missing grade ⇒ 未調査)              │  (weak / unseen ⇒ 未調査)
                                  ▼                                       ▼
                                       honest Records  ── accrue.state_extract (honesty policy)
                                            │  bind   (resolve() → persistent id + geom_binding_conf)
                                            ▼
   ┌──────────────────────────── record layer (store: GeoParquet / DuckDB) ────────────────────────────┐
   │  query (RecordIndex: by id / bbox / triage queue / explicit unknown) ── caveat-mcp mounts this      │
   │  coverage ("8 / 12 assessed; 33% unknown")                                                          │
   │  viz (red/yellow/green/grey GeoJSON → plateau-r3f)                                                  │
   │  export (被災者支援システム · 罹災証明 pre-fill)                                                       │
   │  eval (self-proving: calibration + symmetric honesty penalty)                                       │
   └─────────────────────────────────────────────────────────────────────────────────────────────────┘

module	role
plateau_triage.record	the one honest record contract (states + model + frozen-schema validator)
plateau_triage.accrue.ingest_batch	batch import of public damage datasets → records
plateau_triage.accrue.ingest_capture	drone/street capture session → records (unseen ⇒ 未調査)
plateau_triage.accrue.state_extract	per-building damage extraction + the honesty/abstention policy
plateau_triage.bind	pin records to a persistent building id (Resolver plug; StubResolver for the demo)
plateau_triage.coverage	the coverage meter + triage ordering
plateau_triage.store	record-layer persistence (flat GeoParquet / DuckDB)
plateau_triage.query	honest query surface (by id / bbox / triage queue / explicit unknown) — caveat-mcp mounts it
plateau_triage.viz	red/yellow/green/grey GeoJSON feed for plateau-r3f
plateau_triage.export	被災者支援システム + 罹災証明 screening feeds
plateau_triage.eval	self-proving honesty eval (ECE + symmetric penalty)
viz/	the plateau-r3f front-end (Vite + React Three Fiber, bilingual)

Honesty, enforced everywhere / 誠実性は多重に強制される

不変条件は独立に多重防御されており、ドリフトは静かな退行ではなくテスト失敗になります。 The invariant is guarded independently so drift is a test failure, not a silent regression — see docs/honesty-spec.md:

1. Write side — Record (pydantic) makes it structurally impossible to build a covered=false record with a value or a confidence.
2. Wire side (JSON) — validate_record() checks the serialised record against the frozen contracts/record.schema.json shared by all seven repos. Wire side (RDF) — the optional [shacl] extra validates the same invariant natively in SHACL over a SOSA/PROV-O projection (docs/standards.md).
3. Extraction — field perception abstains to 未調査 below its confidence threshold.
4. Ingest — an unseen / poorly-localised AOI building is explicitly 未調査; a later "safe" reading can never bury an earlier danger.
5. Export — refuses to emit a known/safe claim for an unsurveyed building (FalseSafeError).
6. Query — answers "unknown, not safe" for a building it has no record of.

Contract

record.schema.json is the frozen, shared "universal honest record" plug (state, rules and hazard are the same shape — only attribute differs). It is vendored at plateau_triage/contracts/record.schema.json; binding to a persistent id is delegated to plateau-id-resolve via the Resolver interface. The same record also projects onto SOSA + PROV-O (record.context.jsonld) and is checkable in SHACL (record.shacl.ttl) — standards alignment, not a new standard (docs/standards.md).

Test

python -m pytest             # 114 tests (incl. SHACL when the extra is installed)
pip install -e ".[shacl]"    # optional: RDF/SHACL honesty check (rdflib + pyshacl)
cd viz && npm run build      # the plateau-r3f front-end builds clean

Docs / ドキュメント

• docs/honesty-spec.md — 誠実性の不変条件と強制箇所 / the invariant and where it's enforced
• docs/standards.md — SOSA・PROV-O・nilReason 整合と SHACL / standards alignment + SHACL
• docs/data-sources.md — データソース・PLATEAU 被覆・ライセンス / data, PLATEAU coverage, licensing
• docs/integration.md — 既存システム・caveat-mcp・plateau-r3f 連携 / integration

License / ライセンス

コード Apache-2.0（LICENSE）、データ CC BY 4.0 （LICENSE-DATA、PLATEAU / Copernicus 署名を含む）。 Code Apache-2.0; data CC BY 4.0 (incl. PLATEAU / Copernicus attribution).

本プロダクトは既存システムへ供給する スクリーニング層であり、人が署名する法定 被害認定調査の代替ではありません。A screening layer that feeds existing systems — not a replacement for the legal 被害認定調査 a human signs.

---

Yodo Labs · PixelX Inc. / ピクセルエックス株式会社
yodolabs.jp · [e-mail]