{
  "id": 70735,
  "title": "ExtractBench: A Benchmark for Schema-Guided Enterprise Document Extraction",
  "url": "https://urgent.news/2026/07/31/extractbench-a-benchmark-for-schema-guided-enterprise-document",
  "topic": "ai",
  "section": "AI",
  "published": "2026-07-31T17:55:58.000Z",
  "source": {
    "name": "arXiv cs.AI",
    "slug": "arxiv-cs-ai",
    "url": "https://arxiv.org/abs/2607.29677v1"
  },
  "original_language": "en",
  "account": null,
  "summary": "Enterprise workflows increasingly rely on agents for \\emph{schema-guided extraction}: given a document and a user-defined schema, the agent faithfully follows the schema to produce the correct output with source evidence as grounding metadata. We present ExtractBench, a benchmark for schema-guided extraction and, to our knowledge, the first to score value accuracy, record completeness at scale,…",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}