{
  "$schema": "https://themachinepress.com/schemas/story-v1.schema.json",
  "schema_version": "1.0.0",
  "document_type": "machine_press_story",
  "story": {
    "story_id": "mp-2026-08-18-008",
    "source_story_id": "tmp-story-impression-share-offline-evaluation",
    "edition_id": "mp-2026-08-18-morning-0040",
    "edition_url": "https://themachinepress.com/edition/2026-08-18",
    "position": 8,
    "story_type": "dispatch",
    "section": "infrastructure",
    "editorial_classification": "editorial",
    "headline": "The Offline Test Predicted Who Would Get the Impressions",
    "slug": "the-offline-test-predicted-who-would-get-the-impressions",
    "dek": "A counterfactual evaluation task estimates how a candidate ranker would redistribute traffic before it reaches an online A/B test.",
    "summary": "A counterfactual evaluation task estimates how a candidate ranker would redistribute traffic before it reaches an online A/B test.",
    "body_text": "Accuracy metrics can improve while a ranking model shifts impressions among click, video-view or other objective buckets in ways that hurt downstream utility. The proposed task models those shares from observational data using candidate confidence and delivery capacity. A random forest cut L1 error by 49 percent for model families seen in training, but failed against the baseline during the hardest first hour for held-out models; a two-hour rollout architecture recovered a 22 percent gain there. The result exposes both the promise and the cold-start limit of offline traffic-allocation forecasts.",
    "why_it_matters": "A counterfactual evaluation task estimates how a candidate ranker would redistribute traffic before it reaches an online A/B test.",
    "limitations": [],
    "importance": 8,
    "canonical_url": "https://themachinepress.com/story/mp-2026-08-18-008/the-offline-test-predicted-who-would-get-the-impressions",
    "json_url": "https://themachinepress.com/story/mp-2026-08-18-008.json",
    "first_published_at": "2026-08-18T09:00:00.000-04:00",
    "modified_at": "2026-08-18T09:00:00.000-04:00",
    "content_status": "new",
    "is_carryover": false,
    "carryover_reason": null,
    "key_claims": [
      {
        "claim_id": "claim-mp-2026-08-18-008-001",
        "text": "A counterfactual evaluation task estimates how a candidate ranker would redistribute traffic before it reaches an online A/B test.",
        "source_ids": [
          "source-2026-08-18-008"
        ],
        "qualification": null
      }
    ],
    "source_ids": [
      "source-2026-08-18-008"
    ],
    "tags": [
      "ranking systems",
      "offline evaluation",
      "causal inference",
      "A/B testing"
    ],
    "image_url": "https://themachinepress.com/issues/2026-08-18/ranking-infrastructure-file-image.webp",
    "corrections": []
  },
  "sources": [
    {
      "source_id": "source-2026-08-18-008",
      "title": "arXiv preprint 2608.16872",
      "publisher": "arXiv",
      "url": "https://arxiv.org/abs/2608.16872",
      "canonical_url": "https://arxiv.org/abs/2608.16872",
      "source_type": "primary_research",
      "is_primary_source": true,
      "published_at": "2026-08-16T20:00:00.000-04:00",
      "accessed_at": "2026-08-18T08:25:00.000-04:00",
      "supports_claim_ids": [
        "claim-mp-2026-08-18-008-001"
      ]
    }
  ],
  "corrections": [],
  "publisher": {
    "name": "The Machine Press",
    "url": "https://themachinepress.com",
    "description": "A daily newspaper for the age of artificial intelligence."
  },
  "cite_this_report": {
    "title": "The Offline Test Predicted Who Would Get the Impressions",
    "publisher": "The Machine Press",
    "published_at": "2026-08-18T09:00:00.000-04:00",
    "canonical_url": "https://themachinepress.com/story/mp-2026-08-18-008/the-offline-test-predicted-who-would-get-the-impressions"
  }
}