Metraipolis › archive › dc_5dcc66615396

From Document Silos to Process Intelligence: A Multi-Layer Knowledge Graph for CMC Process Development — arXiv:2609.11493

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.11493
License (as archived)
CC0-1.0
Archived
2026-10-16T05:20:30.688Z
SHA-256 of the archived text
415d2840970b321a7ffa52a82e6997184d0e547198bf3ac20a86971d1c8a5280
Stable URL of this page
https://metraipolis.com/documento/dc_5dcc66615396

How to cite

From Document Silos to Process Intelligence: A Multi-Layer Knowledge Graph for CMC Process Development — arXiv:2609.11493 — arXiv (en), https://arxiv.org/abs/2609.11493 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5dcc66615396 (Metraipolis archive dc_5dcc66615396, sha256 415d2840970b321a7ffa52a82e6997184d0e547198bf3ac20a86971d1c8a5280)
BibTeX
@misc{dc5dcc66615396,
  title = {From Document Silos to Process Intelligence: A Multi-Layer Knowledge Graph for CMC Process Development — arXiv:2609.11493},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.11493},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5dcc66615396; sha256 415d2840970b321a7ffa52a82e6997184d0e547198bf3ac20a86971d1c8a5280},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.11493. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Chemistry, Manufacturing and Controls (CMC) process development generates an enormous body of technical information across a multi-stage, knowledge-intensive continuum from drug discovery to commercial manufacturing. This knowledge is traditionally fragmented across functions and heterogeneous formats, causing traceability gaps and significant knowledge-management costs during technology transfer and regulatory filing. We present a modular agentic-AI platform that converts a heterogeneous corpus of process-development documents into a queryable, dual-layer knowledge graph. A base knowledge layer builds a lexical graph with a Document-Section-Chunk hierarchy through lossless ingestion of digital, scanned, handwritten, and multilingual documents, while an intelligence layer extracts ontology-aligned entities and bridges cross-document concepts through a provenance-anchored domain graph. LLM agents operate across both layers, selecting the retrieval path best suited to each question. We evaluate the lexical layer with a novel three-tier protocol measuring the deployment-fidelity of a retrieval-augmented generation (RAG) system on proprietary data, demonstrated on 505 questions curated from 38 development reports of a Sanofi small-molecule program. Tier-1 multiple-choice accuracy of 95% signals strong platform reliability; the stricter Tier-2 LLM-judge pass rate of 85%, which degrades on comparative and corpus-wide questions, reveals a failure taxonomy that Tier-1 accuracy alone fails to capture. A router agent selects between layers according to question type. We anticipate this protocol will enable future designers of agentic platforms to assess their systems against nonpublic databases, and that graph-based architectures will see broader adoption in pharma as a means of transforming fragmented document repositories into structured process intelligence.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-11 in cs.MA).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Multiagent Systems (cs.MA).
Pagina del lavoro: https://arxiv.org/abs/2609.11493 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-16T05:15:07.143Z dalla pagina https://arxiv.org/catchup/cs.MA/2026-09-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).