{
  "apiVersion": "v1",
  "passage": {
    "id": "airbnb-fine-tuning-gemma4-e2b-lifts-f1-2026",
    "text": "Fine-tuning Gemma4-E2B on hundreds of thousands of domain-specific examples lifts its F1 from 0.563 to 0.902, on par with the best proprietary models, while median latency stays at 35ms.",
    "context": null,
    "speaker": null,
    "speakerId": null,
    "speakerUrl": null,
    "speakerLevel": null,
    "role": null,
    "voice": "organization",
    "organization": "Airbnb",
    "organizationId": "airbnb",
    "organizationUrl": "https://the-ai-record.com/organizations/airbnb",
    "aiVendor": false,
    "work": {
      "title": "Frontier quality at 1% of the cost: a production benchmark of LLM classifiers",
      "type": "post",
      "date": "2026-11-03",
      "publisher": "Airbnb Tech blog",
      "locator": "Quality vs. latency",
      "url": "https://airbnb.tech/ai-ml/frontier-quality-at-1-of-the-cost-a-production-benchmark-of-llm-classifiers/"
    },
    "grade": "B",
    "gradeMeaning": "The organization's own post, paper or talk.",
    "verification": {
      "status": "verified",
      "meaning": "An independent second reader re-fetched the source and confirmed the wording.",
      "reviewedOn": "2026-11-05"
    },
    "topics": [
      "measuring-impact",
      "internal-tools",
      "choosing-models",
      "ai-evals"
    ],
    "functions": [
      "engineering"
    ],
    "figures": [
      {
        "metric": "f1-after-fine-tuning",
        "value": 0.902,
        "unit": "score",
        "period": "2026 benchmark",
        "definition": "max F1 of fine-tuned Gemma4-E2B on a held-out set of 10,000 weighted examples, up from 0.563 before fine-tuning",
        "level": "n/a"
      }
    ],
    "url": "https://the-ai-record.com/passages/airbnb-fine-tuning-gemma4-e2b-lifts-f1-2026",
    "json": "https://the-ai-record.com/api/v1/passages/airbnb-fine-tuning-gemma4-e2b-lifts-f1-2026.json"
  },
  "notice": [
    "Every passage is reproduced word for word from the cited source.",
    "Check the verification status: \"reported\" means not yet confirmed by an independent second reader.",
    "Organizations flagged aiVendor sell AI tools or services and have a reason to publish flattering numbers.",
    "An empty result means the archive holds nothing on it, not that nobody has said anything."
  ]
}