clm_88e130d6512747f5b17e9c11aca87332_r1

IX2-0123

① SA Source

• Source: 開啟完整 SA 文章
• Section: GPT-OSS 120B
• Line hint: 188

Context Before

Source: SemiAnalysis InferenceX ↗

Evidence

Turning back to Nvidia’s systems, both Hopper and Blackwell saw a steady performance increase between vLLM 0.11.2 and 0.13.0

Context After

Source: SemiAnalysis InferenceX ↗

② Atomic Claim

回到 Nvidia 系統，Hopper 與 Blackwell 從 vLLM 0.11.2 升至 0.13.0 之間，都有穩定的效能提升。

• Epistemic Mode: ASSERTED
• Mapping Status: COMPLETE

③ Semantic Frame

{
  "attribute": "STABILITY",
  "context_nodes": [
    {
      "id": "04_knowledge_base/Hopper",
      "label": "Hopper"
    },
    {
      "id": "04_knowledge_base/Blackwell",
      "label": "Blackwell"
    },
    {
      "id": "04_knowledge_base/vLLM",
      "label": "vLLM"
    }
  ],
  "entity": {
    "id": "02_companies/NVDA",
    "label": "Nvidia"
  },
  "frame_type": "ATTRIBUTE",
  "qualifiers": {
    "condition_text": null,
    "numeric_mentions": [
      "0.11",
      "2",
      "0.13",
      "0"
    ],
    "temporal_mentions": []
  },
  "value": {
    "numeric_mentions": [
      "0.11",
      "2",
      "0.13",
      "0"
    ],
    "value_text": "回到 Nvidia 系統，Hopper 與 Blackwell 從 vLLM 0.11.2 升至 0.13.0 之間，都有穩定的效能提升。"
  }
}

④ Canonical Entity Mapping

Role	Surface Label	Canonical Target
entity	Nvidia	NVDA
context_0	Hopper	Hopper
context_1	Blackwell	Blackwell
context_2	vLLM	vLLM

⑤ 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。