← Archive
lm-004805 · 2026-10

Observer-Sovereign Rendering(OSR)整合技術白皮書

下載 MD 檔 ⬇
📎 附件 · Companion files — 隨文交付的程式 / 證明 / 資料,可獨立下載重驗
title
Observer-Sovereign Rendering(OSR)整合技術白皮書
english_title
Observer-Sovereign Rendering (OSR) Integrated Technical Whitepaper
author
Neo.K
ai_collaboration
GPT-5.6 Sol
institution
EveMissLab/一言諾科技有限公司
version
v0.1
date
2026-09-18
language
zh-TW
document_type
Integrated Technical Whitepaper / Engineering Specification
status
Architecture Baseline / MVP Handoff
source_series
OSR-00 · OSR-01 · OSR-02 · OSR-03 · OSR-04 · OSR-05 · OSR-06 · OSR-07

Observer-Sovereign Rendering(OSR)整合技術白皮書

從觀察者條件化顯現到 APR 驅動的 Local–Cloud AI 原生渲染 Runtime

Observer-Sovereign Rendering (OSR) Integrated Technical Whitepaper

From Observer-Conditioned Manifestation to an APR-Governed Local–Cloud AI-Native Rendering Runtime

作者: Neo.K
AI 協作: GPT-5.6 Sol
機構: EveMissLab/一言諾科技有限公司
版本: v0.1
日期: 2026 年 9 月 18 日
狀態: Architecture Baseline / MVP Handoff


0. 文件目的

本白皮書將 OSR-00 至 OSR-07 的理論系列壓縮為一個可交付本地端 Agent、Codex、Claude Code 或其他工程 AI 直接實作的技術基線。

本文件的工作不是再提出新的 OSR 理論,而是固定:

  1. Runtime component graph;
  2. canonical data contracts;
  3. OSR-IR;
  4. APR integration boundary;
  5. rendering backend/plugin ABI;
  6. truth / provenance contract;
  7. local–cloud carrier contract;
  8. temporal reconstruction path;
  9. PNCW / MRMIC-NVCL integration boundary;
  10. benchmark harness;
  11. failure / fallback semantics;
  12. MVP implementation phases;
  13. acceptance gates;
  14. non-goals。

本白皮書的最小工程目標是:

Observer State→Manifestation Obligations→OSR-IR→Heterogeneous Render Plan→Verified Visible Manifestation\boxed{ \text{Observer State} \rightarrow \text{Manifestation Obligations} \rightarrow \text{OSR-IR} \rightarrow \text{Heterogeneous Render Plan} \rightarrow \text{Verified Visible Manifestation} }

並在 runtime 中由 APR 持續治理:

when to observe+when to rerender+where to spend compute+when to stop\boxed{ \text{when to observe} + \text{when to rerender} + \text{where to spend compute} + \text{when to stop} }

1. 核心產品命題

OSR 不把 AI-native rendering 定義為:

用 AI 替代 rasterizer。

也不定義為:

每一幀送到雲端重新生成。

OSR 的工程命題是:

Rendering Policy\boxed{ \text{Rendering Policy} }

本身成為第一級 runtime computation。

對每個 observer、scope、時間與資源狀態,系統決定:

  • 要不要重新處理;
  • 哪些內容必須顯現;
  • 使用哪種 realization;
  • 表示深度多少;
  • 更新頻率多少;
  • 可否 reuse;
  • 是否需要 local neural;
  • 是否值得 cloud inference;
  • 是否需要 verification;
  • 失效後如何 fallback;
  • output 具有什麼 truth status。

2. 第一代 MVP 核心假說

第一代 MVP 不嘗試證明:

OSR>DLSS5OSR>DLSS5

或:

RTX3070+CloudAI=RTX5090.RTX3070+CloudAI=RTX5090.

只驗證:

∃D∗:OSR creates a useful operating point unavailable to simpler baselines.\boxed{ \exists\mathcal D^*: OSR \text{ creates a useful operating point unavailable to simpler baselines.} }

第一階段尤其測:

LocalConstrainedGPU+SparseCloudIntelligence+TemporalReuse\boxed{ \text{LocalConstrainedGPU} + \text{SparseCloudIntelligence} + \text{TemporalReuse} }

是否可在某些低至中等動態場景中,形成:

QOSR>QlocalQ_{OSR}>Q_{local}

且:

COSR<Cnaive−cloud,C_{OSR}<C_{naive-cloud},

同時:

WVR≤ϵW,WVR\le\epsilon_W, BaseContinuity=1.BaseContinuity=1.

3. 非目標

v0.1 不做:

  • 自研完整遊戲引擎;
  • 自研 production path tracer;
  • 仿製 NVIDIA DLSS 5;
  • 逆向任何 proprietary neural renderer;
  • 60 FPS general-purpose cloud image API;
  • production multiplayer anti-cheat;
  • production robotics / medical deployment;
  • 全平台 renderer backend;
  • 自動把 AI inference 寫回 canonical world;
  • production-grade provider SLA;
  • universal OSR quality score。

第一代應先證明 architecture semantics 與 controlled prototype utility。


4. 與現有 EveMissLab Runtime 的分工

OSR 不重寫已存在的 runtime。

4.1 APR

APR 已提供:

  • Persistent World State;
  • EvidenceStore;
  • Goal;
  • Budget;
  • PolicyController;
  • adapters / sources;
  • plugin registry;
  • hosted semantic inspectors;
  • image generation plugin boundary;
  • closed-loop observe / verify / recover。

OSR 直接消費 APR state。

不把:

  • raster;
  • ray;
  • cloud renderer;

硬寫進 APR core。


4.2 PNCW

PNCW 已提供:

REQUESTED→RESOLVED→READY→PROJECTED→VERIFIED→VISIBLE.REQUESTED \rightarrow RESOLVED \rightarrow READY \rightarrow PROJECTED \rightarrow VERIFIED \rightarrow VISIBLE.

以及:

  • versioned projection contract;
  • deterministic identity;
  • source / surface authority separation;
  • freshness / integrity verification;
  • fail-closed;
  • idempotent visibility commit。

OSR 不重寫可見性狀態機。


4.3 MRMIC / NVCL

MRMIC/NVCL 已提供:

  • Canvas-first visual world;
  • geometry / projection;
  • provider-owned resource boundary;
  • secure principal;
  • native resource portal;
  • mounted / visible / focused / controlOwner separation;
  • visual observe / repair loop。

OSR 不重寫 Canvas。


5. OSR 新增的工程層

OSR 真正新增:

Observer Adapter
    ↓
Manifestation Obligation Builder
    ↓
Perceptual Rendering Compiler (PRC)
    ↓
OSR-IR
    ↓
Heterogeneous Field Solver
    ↓
Backend Execution
    ↓
Truth / Verification Gate
    ↓
Temporal Reconstruction
    ↓
Projection Bridge

也就是:

APR→OSR→PNCW/MRMIC\boxed{ APR \rightarrow OSR \rightarrow PNCW/MRMIC }

6. 系統總架構

┌──────────────────────────────────────────────────────────┐
│                    Canonical World                       │
│      engine state / scene graph / physics / IDs          │
└───────────────────────┬──────────────────────────────────┘
                        │
                        ▼
┌──────────────────────────────────────────────────────────┐
│ APR World/Evidence Layer                                 │
│ goal / belief / freshness / uncertainty / risk / budget  │
└───────────────────────┬──────────────────────────────────┘
                        │
                        ▼
┌──────────────────────────────────────────────────────────┐
│ OSR Observer Layer                                       │
│ camera + goal + profile + authority + runtime state      │
└───────────────────────┬──────────────────────────────────┘
                        │
                        ▼
┌──────────────────────────────────────────────────────────┐
│ Manifestation Obligation Builder                         │
│ minimum / preferred / deadline / provenance / forbidden  │
└───────────────────────┬──────────────────────────────────┘
                        │
                        ▼
┌──────────────────────────────────────────────────────────┐
│ Perceptual Rendering Compiler                            │
│ capability matching / hard gates / cost / utility        │
└───────────────────────┬──────────────────────────────────┘
                        │
                        ▼
┌──────────────────────────────────────────────────────────┐
│ OSR-IR / Heterogeneous Rendering Field                   │
│ raster / ray / reuse / local neural / cloud / semantic   │
└──────────────┬────────────────────────────┬──────────────┘
               │                            │
               ▼                            ▼
       Local Execution               Cloud Intelligence
               │                            │
               └─────────────┬──────────────┘
                             ▼
┌──────────────────────────────────────────────────────────┐
│ Truth Firewall / Verification                            │
│ structural / identity / temporal / provenance / policy   │
└───────────────────────┬──────────────────────────────────┘
                        │
                        ▼
┌──────────────────────────────────────────────────────────┐
│ Local Temporal Reconstruction / Compositor               │
└───────────────────────┬──────────────────────────────────┘
                        │
                        ▼
┌──────────────────────────────────────────────────────────┐
│ PNCW Projection Lifecycle                                │
│ PROJECTED → VERIFIED → VISIBLE                           │
└───────────────────────┬──────────────────────────────────┘
                        │
                        ▼
┌──────────────────────────────────────────────────────────┐
│ MRMIC / Engine Surface / Final Display                   │
└──────────────────────────────────────────────────────────┘

7. Runtime Package Boundary

建議新 repo:

osr-runtime/

或:

Observer-Sovereign-Rendering/

v0.1 建議結構:

osr-runtime/
├─ osr_core/
│  ├─ observer.py
│  ├─ obligations.py
│  ├─ compiler.py
│  ├─ ir.py
│  ├─ field_solver.py
│  ├─ truth.py
│  ├─ receipts.py
│  └─ errors.py
├─ osr_apr/
│  ├─ world_adapter.py
│  ├─ policy_adapter.py
│  ├─ evidence_adapter.py
│  └─ runtime_metrics.py
├─ osr_backends/
│  ├─ base.py
│  ├─ raster_mock.py
│  ├─ reuse.py
│  ├─ local_neural.py
│  ├─ cloud_image.py
│  └─ semantic.py
├─ osr_temporal/
│  ├─ warp.py
│  ├─ confidence.py
│  ├─ compositor.py
│  └─ cache.py
├─ osr_truth/
│  ├─ contracts.py
│  ├─ verifier.py
│  ├─ provenance.py
│  └─ writeback_firewall.py
├─ osr_bridge/
│  ├─ pncw.py
│  ├─ mrmic.py
│  └─ engine_protocol.py
├─ contracts/
│  ├─ observer-state-v1.schema.json
│  ├─ manifestation-obligation-v1.schema.json
│  ├─ backend-capability-v1.schema.json
│  ├─ osr-ir-v1.schema.json
│  ├─ truth-record-v1.schema.json
│  ├─ cloud-request-v1.schema.json
│  └─ cloud-response-v1.schema.json
├─ engines/
│  ├─ godot_reference/
│  └─ simulator/
├─ benchmarks/
│  ├─ fixtures/
│  ├─ scenarios/
│  ├─ metrics/
│  └─ runner/
├─ tests/
├─ examples/
├─ docs/
└─ artifacts/

8. 語言與程序邊界

v0.1 建議:

  • OSR control plane:Python 3.10+;
  • APR:直接 Python import;
  • engine adapter:engine-native;
  • local high-frequency temporal path:engine / native side;
  • cloud adapter:Python;
  • contracts:JSON Schema;
  • benchmark data:JSONL / CSV / PNG / MP4。

重要:

Python control loop≠per-pixel rendering loop.\boxed{ \text{Python control loop} \neq \text{per-pixel rendering loop}. }

Python 不負責 120 Hz per-pixel warp。


9. 控制面與資料面的分離

Control Plane

負責:

  • observer;
  • obligation;
  • APR;
  • compiler;
  • backend selection;
  • truth contract;
  • cloud request;
  • receipts。

Data Plane

負責:

  • RGB;
  • depth;
  • normal;
  • motion;
  • masks;
  • GPU textures;
  • warp;
  • compositor。

Control plane 盡量傳:

metadata+handles.metadata+handles.

不是每幀把 4K texture 複製進 Python。


10. ObserverState v1

{
  "schema": "osr-observer-state/v1",
  "observer_id": "player-1",
  "revision": 12,
  "camera": {
    "id": "main",
    "revision": 144
  },
  "goal": {
    "mode": "dialogue",
    "targets": ["npc_07"]
  },
  "profile": {
    "style": "default",
    "accessibility": []
  },
  "authority": {
    "world_read": true,
    "cloud_export": true,
    "hidden_state_read": false
  },
  "risk": {
    "level": "low"
  },
  "budget_ref": "budget-822"
}

11. ManifestationObligation v1

{
  "schema": "osr-manifestation-obligation/v1",
  "id": "obl-face-007",
  "scope": {
    "kind": "object_region",
    "object_id": "npc_07",
    "subregion": "face"
  },
  "minimum": {
    "representation_depth": 2,
    "identity_fidelity": 0.99
  },
  "preferred": {
    "representation_depth": 4
  },
  "deadline_ms": 33,
  "mandatory": false,
  "forbidden_modes": [],
  "truth": {
    "preserve_identity": true,
    "world_writeback": false
  },
  "provenance_required": true
}

12. Manifestation Obligation 不包含 Backend

不能寫:

use_cloud = true

在 obligation 層。

因為:

What is needed≠How it is realized.\boxed{ \text{What is needed} \neq \text{How it is realized}. }

Backend 由 compiler 決定。


13. BackendCapability v1

{
  "schema": "osr-backend-capability/v1",
  "backend_id": "cloud-image-A",
  "revision": "2026-09-18",
  "modes": ["cloud_neural"],
  "inputs": [
    "rgb",
    "depth",
    "motion",
    "mask",
    "text_control"
  ],
  "outputs": [
    "pixel_anchor"
  ],
  "region_support": true,
  "temporal_state": false,
  "deterministic": false,
  "network_required": true,
  "world_write_authority": false,
  "cost_model": "provider-metered",
  "limits": {
    "max_width": 2048,
    "max_height": 2048
  }
}

14. Backend ABI

所有 backend 實作:

class RenderBackend:
    def capability(self) -> BackendCapability:
        ...

    def estimate(self, request, runtime_state) -> CostEstimate:
        ...

    def execute(self, request) -> BackendResult:
        ...

    def validate_result(self, result) -> ValidationResult:
        ...

Async backend 可額外:

submit()
poll()
cancel_local_interest()

注意:

cancel_local_interest\text{cancel\_local\_interest}

不代表 remote operation 一定取消。


15. APR Plugin 重用策略

OSR 優先重用 APR PluginRegistry。

建議 component kinds:

osr_backend
osr_verifier
osr_partition
osr_cost_model
osr_scheduler
osr_engine_adapter
osr_temporal

APR discovery 原則繼續保留:

Discover≠Execute.\boxed{ \text{Discover} \neq \text{Execute}. }

Plugin registration 不:

  • 開網路;
  • 讀 credential;
  • 載入大型模型;
  • 啟動 GPU 工作;
  • 啟動 engine process。

16. OSR-IR v1

{
  "schema": "osr-ir/v1",
  "plan_id": "plan-...",
  "world_revision": 9221,
  "observer_revision": 12,
  "policy_revision": 8,
  "capability_revision": "cap-331",
  "obligations": [],
  "nodes": [],
  "edges": [],
  "verification": [],
  "fallbacks": [],
  "commit": [],
  "truth": [],
  "receipts": {
    "plan": true,
    "execution": true,
    "truth": true
  }
}

17. OSR-IR Node

{
  "id": "node-face-cloud",
  "probe_mode": "cloud_neural",
  "backend_id": "cloud-image-A",
  "scope_ref": "obl-face-007",
  "inputs": [
    "base_rgb:face",
    "depth:face",
    "motion:face",
    "mask:face"
  ],
  "outputs": [
    "anchor:face"
  ],
  "budget": {
    "cloud_calls": 1
  },
  "deadline_ms": 1200,
  "blocking": false,
  "truth_output_class": "generated_appearance"
}

18. Dependency Edge

{
  "from": "node-face-cloud",
  "to": "node-face-verify",
  "relation": "requires_output"
}

19. Plan Identity

PlanID=Hash(WorldRevision,ObserverRevision,ObligationSet,PolicyRevision,CapabilityRevision).\text{PlanID} = \text{Hash}( \text{WorldRevision}, \text{ObserverRevision}, \text{ObligationSet}, \text{PolicyRevision}, \text{CapabilityRevision} ).

deterministic mode 下:

same input⇒same semantic plan.\text{same input} \Rightarrow \text{same semantic plan}.

20. Compiler Pipeline

normalize obligations
    ↓
resolve world + runtime capabilities
    ↓
partition scopes
    ↓
generate probe candidates
    ↓
hard-gate invalid candidates
    ↓
estimate cost / utility / truth risk
    ↓
solve minimum contracts
    ↓
allocate preferred upgrades
    ↓
insert verification
    ↓
attach fallback
    ↓
schedule
    ↓
emit OSR-IR

21. Compiler Hard Gates

候選在 scoring 前先檢查:

  • authority;
  • privacy;
  • export;
  • mandatory visibility;
  • truth preservation;
  • deadline impossibility;
  • unsupported carrier;
  • world revision;
  • provider capability;
  • deterministic-only mode;
  • multiplayer authorization。

不合法:

F=0.F=0.

不是:

Score=−10.\text{Score}=-10.

22. Cost Model

Creal=Cgpu+Ccpu+Cmemory+Ctransfer+Csync+Cnetwork+Cprovider+Cverify+Ccompile.\boxed{ C_{real} = C_{gpu} + C_{cpu} + C_{memory} + C_{transfer} + C_{sync} + C_{network} + C_{provider} + C_{verify} + C_{compile}. }

第一代每個項目可以只是 measured scalar。

不需要一開始建立 perfect learned predictor。


23. Utility Model

不採 universal score。

Compiler 內部可以為單一 domain 使用 utility heuristic:

U=Qexpected+TaskValue−Cost−TruthRisk.U = Q_{expected} + \text{TaskValue} - \text{Cost} - \text{TruthRisk}.

但 benchmark 不用同一 scalar 宣稱整體勝負。


24. Global Budget Closure

流程:

  1. mandatory obligations;
  2. safety reserve;
  3. minimum contracts;
  4. exploration reserve;
  5. preferred upgrades;
  6. stability penalty;
  7. global resource closure。

若 minimum 都不可滿足:

NO_FEASIBLE_PLAN.\text{NO\_FEASIBLE\_PLAN}.

25. APR Integration Contract

OSR 從 APR 取得:

Goal
WorldState
Evidence
Freshness
Uncertainty
Risk
Budget

再補 engine runtime:

GPU utilization
VRAM
frame time
network RTT
bandwidth
cloud budget
backend availability

形成:

StOSR.S_t^{OSR}.

26. APR → OSR Need Adapter

class OSRNeedAdapter:
    def build_observer_state(apr_state, engine_state):
        ...

    def build_obligations(observer, world, scene):
        ...

    def rerender_need(scope, history):
        ...

27. NO_RERENDER

v0.1 必須把:

NO_RERENDER

實作成正常 decision。

而不是:

special optimization

條件:

  • freshness pass;
  • significant delta low;
  • risk low;
  • reuse valid;
  • minimum contract remains satisfied。

28. Refresh Levels

L0 = no rerender
L1 = local refresh
L2 = regional refresh
L3 = global refresh

Full refresh 不是 default。


29. Significant Delta

v0.1 不必先做 AI delta predictor。

先以 engine-native state delta:

  • transform;
  • visibility;
  • material revision;
  • animation revision;
  • camera;
  • gameplay event;

建:

Δsig.\Delta^{sig}.

這比 pixel-only 更可靠。


30. Truth Classes

canonical_world_fact
derived_fact
inferred_appearance
generated_appearance

Reuse / style / semantic overlay 作 lineage mode,不另升 authority。


31. TruthRecord v1

{
  "schema": "osr-truth-record/v1",
  "scope": "npc_07.face",
  "source": "engine:npc_07",
  "source_revision": 9221,
  "truth_class": "generated_appearance",
  "transform_chain": [
    "base_raster",
    "cloud_image_A",
    "local_temporal_warp"
  ],
  "backend_revision": "opaque",
  "confidence": null,
  "freshness_ms": 180,
  "verification": [
    "identity",
    "structural"
  ],
  "reversible": true,
  "world_writeback": false,
  "output_hash": "sha256:..."
}

32. Truth Firewall

核心 API:

truth_firewall.can_display(result, obligation)
truth_firewall.can_export(carrier, observer, policy)
truth_firewall.can_write_world(result)

v0.1:

can_write_world(generated_appearance) = false
can_write_world(inferred_appearance) = false

無 exception。


33. Reverse Channel

未來若 vision inference 要更新世界:

Inference
→ WorldUpdateProposal
→ Evidence
→ Authorized Verification
→ World Commit

v0.1 OSR MVP 不實作 auto world promotion。


34. Preservation Contract

每個 cloud / neural scope:

{
  "preserve": {
    "object_count": true,
    "identity": true,
    "pose": true,
    "silhouette": true,
    "mandatory_objects": ["weapon_1"]
  },
  "allow_generate": [
    "microtexture",
    "skin_scattering",
    "hair_lighting"
  ],
  "forbid": [
    "semantic_category_change",
    "object_addition",
    "object_removal"
  ]
}

35. Verification Ladder

V0 none
V1 structural
V2 identity / semantic
V3 temporal
V4 world / policy

v0.1 不對所有 pixel 做 V4。


36. Verifier ABI

class Verifier:
    def verify(self, candidate, reference, contract) -> VerificationResult:
        ...

第一代 verifier 優先 deterministic:

  • mask IoU;
  • object count;
  • pose;
  • required-object presence;
  • hash / revision;
  • simple identity fixture。

之後再加 VLM verifier。


37. Cloud Plane 原則

LocalFirst,CloudOptional.\boxed{ \text{LocalFirst}, \text{CloudOptional}. }

v0.1 cloud 不允許成為 minimum manifestation 唯一來源。


38. Cloud Request v1

{
  "schema": "osr-cloud-request/v1",
  "request_id": "rid-...",
  "world_revision": 9221,
  "camera_revision": 144,
  "scope": "npc_07.face",
  "carrier_schema": "pixel-anchor-input/v1",
  "carrier_hash": "sha256:...",
  "preservation_contract": {},
  "generation_contract": {},
  "deadline_ms": 3000,
  "export_policy_revision": 3
}

39. Cloud Response v1

{
  "schema": "osr-cloud-response/v1",
  "request_id": "rid-...",
  "source_world_revision": 9221,
  "backend_id": "general-cloud-image-A",
  "backend_revision": "opaque",
  "output_class": "pixel_anchor",
  "output_hash": "sha256:...",
  "latency_ms": 1730,
  "provenance": {
    "provider": "provider-A"
  }
}

40. Cloud Carrier v0.1

第一版只需要:

base RGB ROI
depth ROI
object mask
motion ROI
text / structured control

如果 provider 不能消費 depth / motion:

第一代 general cloud adapter 可以只用:

RGB + mask + prompt/control

但 contract 仍保留其他欄位。


41. 第一代 Cloud Output

只做:

PixelAnchor.\text{PixelAnchor}.

不先做 latent protocol。

理由:

  • 可視;
  • 易 debug;
  • provider 通用;
  • 無 shared decoder;
  • benchmark 容易。

42. 第二代 Output

再加入:

residual
latent
material latent
lighting latent

43. Revision Binding

每個 cloud result 必須綁:

  • world revision;
  • camera revision;
  • scope;
  • request ID。

回來後先:

revision check
↓
scope check
↓
truth check
↓
verification
↓
commit

44. Late Result

若:

WorldRevisionnowWorldRevision_{now}

已不相容:

VISIBLE_COMMIT = DENY

但可:

CACHE_ONLY

如果 carrier 仍有 asset-level reuse value。


45. Idempotency

同一:

RequestID\text{RequestID}

最多 visible commit 一次。

duplicate result:

IGNORE

46. Temporal Reconstruction v0.1

第一版不訓練新 model。

流程:

cloud anchor
+ current depth
+ motion vectors
+ current base frame
    ↓
depth-aware warp
    ↓
confidence mask
    ↓
blend with current base
    ↓
final region

47. Temporal Confidence

CT(x)=f(age,motion,depth,disocclusion,worldDelta,cameraDelta).C_T(x) = f( \text{age}, \text{motion}, \text{depth}, \text{disocclusion}, \text{worldDelta}, \text{cameraDelta} ).

v0.1 可以 heuristic。


48. Composition

Ft(x)=CT(x)Atwarp(x)+(1−CT(x))Bt(x).F_t(x) = C_T(x)A^{warp}_t(x) + (1-C_T(x))B_t(x).

之後才替換成 learned compositor。


49. Disocclusion

若:

history invalid

則:

base fill
→ optional local enhance
→ optional cloud refresh

不得用 hallucinated old anchor 補 canonical structure。


50. Camera Cut

立即:

invalidate temporal region history
keep base renderer
schedule optional new anchors

51. Anchor Cache

Key:

scene_revision
object_id
scope
view_cell
lighting_state
style_contract
backend_revision

Value:

anchor
truth_record
quality
timestamp
validity

52. Semantic Render Cache

未來可以更一般:

K=(scene,object,view,lighting,style,LOD).K = ( \text{scene}, \text{object}, \text{view}, \text{lighting}, \text{style}, LOD ).

第一代先 object/scope cache。


53. PNCW Bridge

OSR plan node 完成:

READY

backend 產出:

PROJECTED

truth / verification pass:

VERIFIED

visibility commit:

VISIBLE

如果 PNCW 尚未作 runtime dependency:

v0.1 可先提供 adapter interface + mock lifecycle。


54. PNCW Bridge Interface

class ProjectionBridge:
    def requested(self, manifest):
        ...
    def projected(self, output):
        ...
    def verified(self, verification):
        ...
    def visible(self, commit):
        ...

55. MRMIC / Surface Bridge

v0.1 不要求真正把 game frame 畫進 MRMIC。

只需:

  • contract adapter;
  • artifact projection demo;
  • truth/provenance surface。

真正 engine display 由 engine 自己完成。


56. EngineAdapter v1

class EngineAdapter:
    def world_revision(self):
        ...

    def observer_state(self):
        ...

    def list_scopes(self):
        ...

    def capture_base(self, scope):
        ...

    def capture_depth(self, scope):
        ...

    def capture_motion(self, scope):
        ...

    def capture_mask(self, scope):
        ...

    def apply_region_output(self, scope, output):
        ...

    def runtime_metrics(self):
        ...

57. Reference Engine

v0.1 建議:

Godot reference adapter\boxed{ \text{Godot reference adapter} }

理由:

  • open source;
  • 容易建立小場景;
  • 可直接保存完整 fixture;
  • 不需處理商業引擎 license / opaque renderer;
  • 適合 repo-based Agent 開發。

OSR core 保持 engine-neutral。


58. Godot Adapter 第一版

不需要改 renderer source。

只需要取得:

  • base viewport;
  • depth;
  • motion 若可取得;
  • object mask;
  • camera;
  • object transform;
  • scene revision。

若 motion buffer 第一版取得困難:

可用:

Transformt−Transformt−1Transform_t-Transform_{t-1}

先做 object-level warp fixture。


59. Offline Simulator 先行

真正接 Godot 前,

先做:

SyntheticWorldAdapter

輸出:

  • deterministic frames;
  • masks;
  • motion;
  • depth;
  • scripted world deltas。

這可以先把:

  • PRC;
  • truth;
  • cloud mock;
  • temporal;
  • benchmark;

全部驗證。


60. Offline Simulator 不是多餘

它允許:

control-plane correctness before graphics integration.\boxed{ \text{control-plane correctness before graphics integration}. }

避免一開始 debug engine / network / AI / compiler 四層。


61. MVP Phase 0|Contract Closure

交付:

  • schemas;
  • Python dataclasses;
  • validation;
  • deterministic IDs;
  • receipts;
  • mocks。

Acceptance:

all schemas round-trip
invalid truth writeback rejected
same input → same plan ID

62. MVP Phase 1|Offline OSR Compiler

交付:

  • ObserverState;
  • obligations;
  • PRC;
  • backend capability;
  • OSR-IR;
  • field solver;
  • NO_RERENDER;
  • fallback。

Backend 全 mock。

Acceptance:

  • mandatory preserved;
  • budget closure;
  • no-feasible-plan;
  • deterministic plan;
  • cloud-denied scope never selects cloud。

63. MVP Phase 2|Truth Firewall

交付:

  • TruthRecord;
  • preserve / generate contract;
  • structural verifier;
  • writeback firewall;
  • truth receipts。

Acceptance:

  • generated output cannot mutate world;
  • addition / omission fixture rejected;
  • base fallback works;
  • provenance survives reuse chain。

64. MVP Phase 3|Temporal Reconstruction Offline

交付:

  • anchor;
  • warp;
  • confidence;
  • blend;
  • disocclusion;
  • camera-cut invalidation。

Acceptance:

  • one anchor → multiple output frames;
  • stale history rejected;
  • confidence fallback to base;
  • no blank frame。

65. MVP Phase 4|Godot Base Scene

場景:

room
character
reflective object
hazard
background

交付:

  • base RGB;
  • object masks;
  • depth / approximate depth;
  • scripted camera;
  • scripted object motion;
  • scene revision。

66. MVP Phase 5|Real General Cloud Anchor

第一個真 provider 只做:

face / character ROI

不做全畫面。

流程:

Godot ROI
→ export gate
→ cloud image adapter
→ result
→ truth/structure verify
→ local compose

Acceptance:

  • real call;
  • result receipt;
  • latency recorded;
  • cost recorded;
  • failure preserved;
  • invalid result fallback。

67. MVP Phase 6|APR Runtime Integration

不是 mock APR。

真接:

WorldState
EvidenceStore
Goal
Budget
Policy
PluginRegistry

新增 OSR adapter。

Acceptance:

  • fresh stable scene → NO_RERENDER;
  • uncertainty → refresh;
  • risk event → mandatory refresh;
  • budget pressure → preferred quality drops before minimum。

68. MVP Phase 7|Benchmark Harness

實作 OSR-07 最小版:

B0 Local Raster
B2 Dynamic Quality
B3 Local Neural/mock
B4 Naive Cloud
O0 OSR Local
O1 OSR Cloud Anchor

測:

  • quality;
  • structure;
  • temporal;
  • latency;
  • cost;
  • cloud call efficiency;
  • truth violations;
  • reuse。

69. MVP Phase 8|Evidence Package

每次 run:

run_manifest.json
plan_receipts.jsonl
execution_receipts.jsonl
truth_receipts.jsonl
metrics.csv
frames/
summary.md

70. MVP Phase 9|E1 Decision

最後只回答:

∃D∗?\boxed{ \exists\mathcal D^*? }

若沒有:

停止擴張。

先修 architecture。

若有:

才進 dedicated neural renderer / latent / higher-frequency cloud。


71. 本地 3070 驗證策略

RTX 3070 不當:

large neural renderer target

而當:

base render
buffer producer
temporal reconstructor
compositor
local verifier

第一代測:

3070+OSR\boxed{ 3070+OSR }

能否找到相對於:

3070 local-only3070\ \text{local-only}

新的 Pareto operating point。


72. General Cloud 第一代用途

不要測:

60 cloud calls/sec

先測:

1 anchor / 2–10 sec
scene anchor
dialogue face
photo mode
slow camera

73. 最適合 MVP 的場景

優先:

slow-to-medium camera+character-centric\boxed{ \text{slow}\text{-}\text{to}\text{-}\text{medium}\ \text{camera} + \text{character}\text{-}\text{centric} }

例如:

  • 對話;
  • RPG;
  • strategy;
  • photo mode。

不先做高速 FPS。


74. 第一個 Demo

建議:

OSR Dialogue Lab

場景:

  • NPC 站在室內;
  • 玩家可慢速繞行;
  • 光源可移動;
  • NPC 有 face region;
  • 背景 static;
  • 一個 hazard toggle。

Modes:

Local Base
Naive Cloud
OSR Cloud Anchor
OSR Offline/Network-Failure

75. Demo UI

顯示:

FPS
GPU frame time
current renderer per region
cloud request state
anchor age
truth class
verification status
cloud cost
network latency
NO_RERENDER count

76. Developer Overlay

Region 顏色:

raster      green
reuse       blue
local neural purple
cloud       red
semantic    white
verification-failed orange
stale       gray

僅 debug。


77. Benchmark Fixtures

至少:

static
dialogue
slow orbit
fast motion
disocclusion
hazard
camera cut
network jitter
cloud outage
truth addition
truth omission

78. 指標 v0.1

必要:

Q,S,T,L,C,B,W,R,A.Q, S, T, L, C, B, W, R, A.

第一版不必全做 LPIPS / FLIP。

最小:

  • SSIM / simple perceptual;
  • mask IoU;
  • identity fixture;
  • warp error;
  • p50/p95 latency;
  • cloud calls;
  • bytes;
  • WVR;
  • reuse;
  • fallback。

之後再加 FLIP / LPIPS。


79. Cloud Cost

所有 provider adapter 必須輸出:

estimated_cost
pricing_basis_date
usage

若未知:

estimated_cost = null

不可猜。


80. Network Metrics

記:

  • request submit;
  • first response;
  • complete response;
  • validation;
  • commit。

可分:

Ltransport,Lprovider,Lverify,Lcommit.L_{transport}, L_{provider}, L_{verify}, L_{commit}.

81. Tail Latency

至少:

P50,P95,P99.P50, P95, P99.

如果 sample 太少:

明確標:

insufficient sample count

82. Failure Semantics

統一 enum:

CAPABILITY_UNAVAILABLE
NO_FEASIBLE_PLAN
EXPORT_DENIED
TIMEOUT
REMOTE_ERROR
INVALID_RESPONSE
STALE_RESPONSE
TRUTH_VIOLATION
VERIFICATION_FAILED
BUDGET_EXCEEDED
LOCAL_BACKEND_FAILED

83. Failure 不自動 Retry

v0.1:

Retry=explicit.\boxed{ \text{Retry}=\text{explicit.} }

APR 可下一輪重新決策。


84. Fallback Semantics

fallback 只能:

  1. 滿足 minimum;
  2. 或清楚標記 DEGRADED;
  3. 否則 BLOCKED。

不可 silent success。


85. Runtime State

Scope state:

STABLE
SUSPECT
REFRESHING
VERIFYING
VISIBLE
DEGRADED
BLOCKED

86. Cloud Request State

CREATED
SUBMITTED
RETURNED
STALE
REJECTED
VERIFIED
COMMITTED
FAILED

87. Credential Boundary

Credential:

  • 不進 OSR-IR;
  • 不進 receipts;
  • 不進 benchmark artifacts;
  • 不進 engine payload。

由 provider adapter lazy read。

沿用 APR plugin 的安全習慣。


88. Privacy

ExportPolicy:

{
  "allow_pixels": true,
  "allow_depth": true,
  "allow_semantics": false,
  "allow_object_ids": false,
  "allow_text": false
}

89. Sensitive Scope

Scope 可以標:

private
restricted
public

compiler hard gate cloud。


90. Cloud Provider 不可變成 Source Authority

Cloud result 永遠:

truth_class = inferred_appearance | generated_appearance
world_write_authority = false

第一代固定。


91. Deterministic Offline Tests

CI 不呼叫真 cloud。

provider 用 fixture。

真 provider test:

explicit opt-in
call cap
cost cap
no retry

92. Test Layers

Unit

  • schema;
  • compiler;
  • truth;
  • cache;
  • revision;
  • fallback。

Integration

  • APR adapter;
  • engine simulator;
  • cloud mock;
  • temporal。

Live

  • real engine;
  • real provider;
  • benchmark。

93. Golden Test 01

Stable scene:

input unchanged
→ NO_RERENDER
→ no cloud call
→ output remains valid

94. Golden Test 02

Face close-up:

preferred depth ↑
→ cloud candidate selected
→ base visible first
→ cloud returns
→ identity verify
→ late upgrade

95. Golden Test 03

Cloud timeout:

base remains visible
→ cloud node fails
→ no blank frame
→ receipt records timeout

96. Golden Test 04

World revision changes during cloud request:

response stale
→ visible commit denied

97. Golden Test 05

Cloud adds forbidden object:

structural verify fail
→ fallback base
→ truth violation receipt

98. Golden Test 06

Hazard microchange:

pixel delta small
significant delta high
→ mandatory refresh

99. Golden Test 07

GPU pressure:

preferred local enhancement drops
minimum remains

100. Golden Test 08

Export denied:

cloud quality high
but privacy policy denies
→ cloud never called

101. Golden Test 09

Camera cut:

temporal cache invalidated
→ base immediate
→ optional new cloud anchor

102. Golden Test 10

Same deterministic input:

same semantic OSR plan

103. Acceptance Gate v0.1

Phase 0–3:

100% deterministic offline tests pass
truth writeback violations = 0
stale visible commits = 0

Phase 4–6:

engine base continuity = 100%
cloud failure blank-frame = 0
export-denied calls = 0

Phase 7:

至少找到一個 controlled domain:

D∗\mathcal D^*

使 OSR 有 practical Pareto improvement。


104. 不預先保證 D∗\mathcal D^* 存在

如果不存在:

D∗=∅,\mathcal D^*=\varnothing,

這是有效研究結果。

不要為了「OSR 必須成功」改 threshold。


105. E0 Gate

只證明:

  • architecture runs;
  • contracts work;
  • failure semantics work。

106. E1 Gate

至少:

  • 一個 domain;
  • 一個 baseline;
  • practical gain;
  • hard constraints pass。

107. E2 Gate

未來才要求:

  • interactive p95;
  • temporal;
  • tail jitter;
  • sustained session。

108. E3 Gate

未來:

  • long duration;
  • production security;
  • provider SLA;
  • real users;
  • regression;
  • deployment。

109. GitHub / Repository Strategy

建議新 repo 不塞進 APR。

原因:

APR=domain-general perception runtime\boxed{ APR = \text{domain-general perception runtime} }

而:

OSR=rendering-domain runtime.\boxed{ OSR = \text{rendering-domain runtime.} }

APR 作 dependency / sibling project。


110. Repository Names

建議優先:

osr-runtime

或:

observer-sovereign-rendering

避免只叫:

renderer

失去研究識別。


111. README 第一頁要寫的限制

必須明確:

Research prototype.
Not a DLSS replacement.
Not a production cloud-gaming stack.
Not proven to improve all workloads.
General cloud image APIs are anchor backends, not assumed real-time renderers.

112. License / External Assets

MVP scene 使用:

  • 自製;
  • CC0;
  • permissive;
  • engine primitives。

不要直接拿商業遊戲 asset 上傳 cloud。


113. Cloud Provider Test Data

第一代 cloud live test 使用:

  • 自製 character;
  • synthetic scene;
  • no personal data;
  • no proprietary assets。

114. Security

Cloud output 永遠 untrusted input。

必須驗:

  • MIME;
  • dimensions;
  • size;
  • request ID;
  • revision;
  • hash;
  • schema。

不執行 remote code。


115. Resource Limits

每個 cloud request:

max input bytes
max output bytes
timeout
call cap
budget cap

全部 explicit。


116. Logging

不 log:

  • credentials;
  • secret pixels 若 privacy 禁止;
  • raw provider error body 若可能含敏感內容。

log:

  • error class;
  • latency;
  • request ID;
  • bounded provider code;
  • byte counts;
  • cost metadata。

117. Benchmark Evidence Ready

所有結果都可回到:

world fixture
plan receipt
execution receipt
truth receipt
frame
metric

這是 OSR-07 的核心。


118. 白皮書到 MVP 的交接句

本白皮書完成後,本地 Agent 不需要再問:

OSR 是什麼?

它只需要從:

Phase 0\boxed{ \text{Phase 0} }

開始建立 contracts 與 deterministic simulator。


119. 第一個實作順序

contracts
→ dataclasses
→ mock registry
→ compiler
→ truth firewall
→ offline temporal
→ simulator benchmark
→ engine adapter
→ real cloud anchor
→ APR integration
→ benchmark

不要反過來先接 cloud API。


120. 第一個 Commit 建議

feat: bootstrap OSR contracts and deterministic offline runtime

內容只要:

  • package;
  • schemas;
  • IDs;
  • errors;
  • mock backend;
  • tests。

121. 第二個 Commit

feat: add manifestation obligations and perceptual render compiler

122. 第三個 Commit

feat: add truth firewall and provenance receipts

123. 第四個 Commit

feat: add temporal anchor reconstruction simulator

124. 第五個 Commit

feat: add APR adapter and no-rerender policy

125. 第六個 Commit

feat: add Godot reference engine adapter

126. 第七個 Commit

feat: add opt-in general cloud anchor backend

127. 第八個 Commit

feat: add OSR benchmark harness and E1 acceptance report

128. Runtime Invariants

第一代至少固定以下 invariants。

I1

WorldWrite(Generated)=DENY.\text{WorldWrite}(\text{Generated})=\text{DENY}.

I2

CloudFailure⇒BaseVisible.\text{CloudFailure} \Rightarrow \text{BaseVisible}.

I3

StaleCloud⇒NoVisibleCommit.\text{StaleCloud} \Rightarrow \text{NoVisibleCommit}.

I4

ExportDenied⇒NoNetworkCall.\text{ExportDenied} \Rightarrow \text{NoNetworkCall}.

I5

VerificationFail⇒FallbackOrBlocked.\text{VerificationFail} \Rightarrow \text{FallbackOrBlocked}.

I6

Mandatory⊄OptionalBudget.\text{Mandatory} \not\subset \text{OptionalBudget}.

I7

NO_RERENDER\text{NO\_RERENDER}

是合法 action。

I8

SameDeterministicInput⇒SameSemanticPlan.\text{SameDeterministicInput} \Rightarrow \text{SameSemanticPlan}.

I9

Visible⇏WorldFact.\text{Visible} \not\Rightarrow \text{WorldFact}.

I10

Provider≠WorldAuthority.\text{Provider} \neq \text{WorldAuthority}.

129. 第一代性能假說

不把任何數字寫成保證。

只測:

H1:CloudCallRateOSR<CloudCallRatenaive.H_1: CloudCallRate_{OSR} < CloudCallRate_{naive}. H2:BaseContinuity=1.H_2: BaseContinuity=1. H3:TruthViolationOSR<TruthViolationno−firewall.H_3: TruthViolation_{OSR} < TruthViolation_{no-firewall}. H4:StableSceneRenderWorkOSR<FullRefresh.H_4: StableSceneRenderWork_{OSR} < \text{FullRefresh}. H5:∃D∗:QOSR>QlocalH_5: \exists\mathcal D^* : Q_{OSR}>Q_{local}

在可接受成本內。


130. External Technical Context

2026 年 DLSS 5 已公開展示:

  • real-time generative neural rendering;
  • engine frame grounding;
  • color / motion vectors;
  • surface / lighting attributes;
  • deterministic output;
  • temporal stability;
  • traditional rendering + neural appearance。

OSR 不複製其模型。

OSR 利用這個產業進展確認:

neural appearance is now a legitimate real-time rendering stage.\boxed{ \text{neural appearance is now a legitimate real-time rendering stage}. }

OSR 的獨立研究問題則是:

who decides where, when, how deeply, and under what truth contract such a stage should run?\boxed{ \text{who decides where, when, how deeply, and under what truth contract such a stage should run?} }

131. Long-Term Architecture

若 MVP 成立,後續可以:

v0.2

  • stronger temporal;
  • FLIP / LPIPS;
  • better cost model;
  • multiple cloud adapters。

v0.3

  • latent return;
  • local decoder;
  • persistent cloud session;
  • speculative anchor。

v0.4

  • ray / path backend;
  • LoD/reuse;
  • higher-frequency cloud。

v0.5

  • dedicated neural renderer;
  • engine-native GPU path;
  • E2 interactive benchmark。

v1.0 candidate

只有在:

E3E3

證據成熟後考慮。


132. 與未來硬體的關係

如果未來 local GPU 足夠強:

CloudNeed↓.CloudNeed\downarrow.

OSR 不失效。

Compiler 只會把:

cloud_neural→local_neural.cloud\_neural \rightarrow local\_neural.

因為:

Probe≠Backend.Probe\neq Backend.

133. 與未來 Cloud 的關係

若 cloud latency 更低:

CloudValue↑.CloudValue\uparrow.

OSR 也可提高:

νcloud.\nu_{cloud}.

架構不需要重寫。


134. 與 AI Agent 的關係

AI agent observer 不一定需要 RGB。

OSR 未來可輸出:

  • semantic carrier;
  • object graph;
  • state;
  • task view。

同一 world 同時:

Mhuman≠MAI.M_{human}\neq M_{AI}.

但:

FWF_W

共享。


135. 與 AR / XR 的關係

OSR 的:

  • observer;
  • manifestation obligation;
  • truth class;
  • reversible mediation;
  • local/cloud;
  • reprojection;

都可自然延伸 XR。

但第一代不展開。


136. 整合技術定義

本文將 OSR Runtime 定義為:

ROSR=(W,O,U,C,P,H,T,D,E)\boxed{ \mathcal R_{OSR} = ( W, O, U, C, P, H, T, D, E ) }

其中:

  • WW:world/evidence interface;
  • OO:observer;
  • UU:manifestation obligations;
  • CC:compiler;
  • PP:OSR-IR / plan;
  • HH:heterogeneous rendering field;
  • TT:truth / provenance;
  • DD:distributed local-cloud runtime;
  • EE:evaluation / evidence layer。

137. 一個完整 Step

1. engine advances world
2. APR updates world/evidence/budget
3. OSR builds observer state
4. obligations are updated
5. significant delta determines affected scopes
6. PRC patches OSR-IR
7. local base renders
8. optional cloud requests are submitted
9. temporal path maintains high-frequency display
10. cloud result returns
11. truth / revision / structure verification
12. compatible result late-upgrades region
13. receipts are emitted
14. benchmark/evidence records metrics

138. 這就是第一代 MVP

第一代不需要:

  • 重新發明 neural renderer;
  • 重新發明 path tracing;
  • 等全新 GPU。

它需要的是:

把現有世界、APR、renderer、cloud model、temporal reuse 與 truth governance 正確接起來。\boxed{ \text{把現有世界、APR、renderer、cloud model、temporal reuse 與 truth governance 正確接起來。} }

139. 最終工程判定

完成 v0.1 後只問三件事:

139.1 架構能不能跑?

E0?E0?

139.2 有沒有至少一個有用工作域?

E1?E1?

139.3 值不值得繼續投入更低延遲 dedicated neural backend?

Go/NoGo?Go/NoGo?

140. Go 條件

至少:

  • E0 全通過;
  • 一個 D∗\mathcal D^* ;
  • truth / privacy invariants pass;
  • cloud sparse 比 naive cloud 有意義;
  • local base continuity;
  • compiler overhead 未抵銷收益。

141. No-Go / Redesign 條件

如果:

  • cloud output 不可穩定 preserve structure;
  • temporal reconstruction 無法維持;
  • compiler overhead 太大;
  • general cloud 成本不合理;
  • local-only 已全面支配;

則:

不硬推 cloud。

OSR 仍可保留:

APR+HRF+LocalNeural+Reuse+Truth.APR + HRF + \text{LocalNeural} + \text{Reuse} + \text{Truth}.

142. 最終結論

OSR 技術白皮書的真正核心不是:

「我們有一套新的 AI renderer。」

而是:

we have a runtime contract for deciding when rendering computation is justified, what may perform it, and what the result is allowed to mean.\boxed{ \text{we have a runtime contract for deciding when rendering computation is justified, what may perform it, and what the result is allowed to mean.} }

這個 contract 將:

  • observer intent;
  • world state;
  • APR;
  • renderer diversity;
  • local/cloud;
  • temporal reuse;
  • truth authority;
  • verification;
  • evidence;

放入同一個可執行系統。

對第一代 MVP 而言,最值得驗證的也不是「AI 是否能畫出最漂亮的一幀」,而是:

能否讓一張受限的本地 GPU,透過稀疏、受治理、可驗證的遠端 AI intelligence,得到原本本地預算無法提供的顯現品質,同時不失去互動、世界真值、fallback 與可測量性。\boxed{ \text{能否讓一張受限的本地 GPU,透過稀疏、受治理、可驗證的遠端 AI intelligence,得到原本本地預算無法提供的顯現品質,同時不失去互動、世界真值、fallback 與可測量性。} }

如果答案是 yes,

OSR 就得到 E1 級實證。

如果答案是 no,

OSR-07 已經規定怎麼讓它失敗,而不是靠理論敘事逃避。

因此,本白皮書之後的正確下一步不是再寫 OSR-08。

而是:

build Phase 0 of the MVP.\boxed{ \text{build Phase 0 of the MVP.} }

參考文件

OSR 第一卷

  1. OSR-00 — 從萬能光到觀察者主權渲染:理論譜系重構與研究綱領。
  2. OSR-01 — 我們到底想看什麼?觀察者、目的與顯現場。
  3. OSR-02 — 從射線到觀察探針:廣義觀察算子與感知渲染編譯器。
  4. OSR-03 — 異質渲染場:Raster、Ray、Neural、Semantic 與 Reuse 的統一選擇。
  5. OSR-04 — APR 治理的自適應渲染:感知預算、表示深度與動態重算。
  6. OSR-05 — 世界真值與顯現真值:生成式渲染中的一致性、幻覺與表示主權。
  7. OSR-06 — 分散式 AI 原生渲染:Local World、Cloud Intelligence 與 Temporal Reconstruction。
  8. OSR-07 — 可反證的觀察者渲染:品質、延遲、成本、一致性與結構保真。

EveMissLab Runtime

  1. APR — Adaptive Perceptual Reading / Agentic Perception Runtime. https://github.com/kakon77777-commits/APR
  2. MRMIC/NVCL. https://github.com/kakon77777-commits/MRMIC_NVCL
  3. PNCW — Projection-Native Computational World. https://github.com/kakon77777-commits/PNCW

External Technical Context

  1. NVIDIA ADLR. DLSS 5: Generative Neural Rendering. 2026. https://research.nvidia.com/labs/adlr/DLSS5/
  2. NVIDIA GeForce. DLSS 5 3D-Guided Neural Rendering. 2026. https://www.nvidia.com/en-us/geforce/news/dlss-5-3d-guided-neural-rendering/
  3. NVIDIA CloudXR SDK. Network Setup / Network Quality. https://docs.nvidia.com/cloudxr-sdk/
  4. Perel, O., et al. TRON: Tracing Rays to Orchestrate a Neural Renderer for 3D Gaussian Reconstructions. 2026. https://research.nvidia.com/labs/sil/projects/tron/
  5. Wang, Y.-C., et al. Real-Time Level-of-Detail Rendering with ReSTIR. SIGGRAPH 2026.
  6. Hong, P., et al. Multi-Layer Reservoir Splatting for Temporal Reuse under Disocclusion. SIGGRAPH 2026.
  7. Andersson, P., et al. FLIP: A Difference Evaluator for Alternating Images. HPG 2020.

附錄 A|MVP 最短交接

GOAL:
Build E0→E1 OSR prototype.

HARD INVARIANTS:
- generated output cannot mutate world
- cloud failure cannot blank minimum view
- stale cloud result cannot visible-commit
- denied scope cannot leave device
- verification fail must fallback/block
- deterministic offline plan test must pass

PHASE ORDER:
0 contracts
1 compiler
2 truth firewall
3 offline temporal
4 Godot scene
5 real cloud anchor
6 APR integration
7 benchmark
8 evidence package
9 E1 decision

DO NOT:
- build full engine
- build custom path tracer first
- optimize 60 FPS cloud first
- add latent protocol before pixel-anchor MVP
- hide failures

附錄 B|一句話版本

OSR v0.1 的工程實作不是打造另一個 DLSS,而是建立一個 APR 驅動、真值可治理、local-first、cloud-optional 的渲染控制 Runtime:先由觀察者與世界狀態產生顯現義務,再由 PRC 編譯成異質 Render Plan,本地永遠維持最低可用世界畫面,雲端只對高價值 scope 提供稀疏 appearance intelligence,本地以 temporal reconstruction 擴展並驗證後才 commit,最後用 OSR-07 的 benchmark 決定它到底值不值得繼續。