clm_8a64b457605442128504abc9886b6acb_r1

SA260324R-0214::SPLIT01

回到這篇 SA Coverage

① SA Source

• Source: 開啟完整 SA 文章
• Section: Nvidia’s CPO Roadmap
• Line hint: 247

Context Before

NVL288 – Kyber rack all copper scale up with copper connecting 2 racks together

Evidence

NVL576 – 8x Oberon Racks copper scale up within rack and CPO on switch between racks in a two tier all to all topology. This would be low volume for test purposes

Context After

Feynman:

② Atomic Claim

For the Rubin Ultra roadmap estimate: NVL576 由 8 個 Oberon racks 組成。

• Epistemic Mode: ESTIMATED
• Mapping Status: COMPLETE

③ Semantic Frame

{
  "additional_nodes": [],
  "frame_type": "RELATION",
  "object": {
    "id": "04_knowledge_base/NVIDIA Oberon",
    "label": "Oberon"
  },
  "predicate": "COMPRISES",
  "qualifiers": {
    "condition_text": "SemiAnalysis best-estimate roadmap",
    "numeric_mentions": [
      "8"
    ],
    "temporal_mentions": []
  },
  "subject": {
    "id": "04_knowledge_base/NVL576",
    "label": "NVL576"
  }
}

④ Canonical Entity Mapping

Role	Surface Label	Canonical Target
subject	NVL576	NVL576
object	Oberon	04_knowledge_base/NVIDIA Oberon

⑤ V2 Draft（需要修正時直接編輯）

Inline repair

只編輯以下三個 Draft 區塊。完成後將 review_action 設為 REQUEST_REPAIR，再手動執行 Repair Preview。
執行腳本前，Draft 不會寫入 Claim Store 或 Graph。

V2 Atomic Claim Draft

For the Rubin Ultra roadmap estimate: NVL576 由 8 個 Oberon racks 組成。

V2 Semantic Frame Draft

{
  "additional_nodes": [],
  "frame_type": "RELATION",
  "object": {
    "id": "04_knowledge_base/NVIDIA Oberon",
    "label": "Oberon"
  },
  "predicate": "COMPRISES",
  "qualifiers": {
    "condition_text": "SemiAnalysis best-estimate roadmap",
    "numeric_mentions": [
      "8"
    ],
    "temporal_mentions": []
  },
  "subject": {
    "id": "04_knowledge_base/NVL576",
    "label": "NVL576"
  }
}

V2 Revision Metadata Draft

{
  "epistemic_mode": "ESTIMATED",
  "mapping_status": "COMPLETE"
}

⑥ Human Review

請在 Properties 逐項確認：

• 原文 → Atomic Claim 是否忠實
• Atomic Claim → Semantic Frame 是否忠實
• Canonical Entity mapping 是否正確
• Epistemic mode 是否保留原文語氣
• 最後選擇 review_action

Review state

Markdown 內文不是正式 approval。只有 Apply bridge 寫入的 Decision Ledger event 才是正式決策。