Metraipolis › archive › dc_7a604d886893

Glyph: A Multi-Strategy Agentic System for Column Description and Sensitivity-Ontology Tagging of Enterprise Data Catalogs — arXiv:2609.10430

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.10430
License (as archived)
CC0-1.0
Archived
2026-10-16T07:23:52.076Z
SHA-256 of the archived text
9d9524e7c6a13a0abf2c04ab04838849bcb4c4be80247cff75529af0476d7dff
Stable URL of this page
https://metraipolis.com/documento/dc_7a604d886893

How to cite

Glyph: A Multi-Strategy Agentic System for Column Description and Sensitivity-Ontology Tagging of Enterprise Data Catalogs — arXiv:2609.10430 — arXiv (en), https://arxiv.org/abs/2609.10430 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7a604d886893 (Metraipolis archive dc_7a604d886893, sha256 9d9524e7c6a13a0abf2c04ab04838849bcb4c4be80247cff75529af0476d7dff)
BibTeX
@misc{dc7a604d886893,
  title = {Glyph: A Multi-Strategy Agentic System for Column Description and Sensitivity-Ontology Tagging of Enterprise Data Catalogs — arXiv:2609.10430},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.10430},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7a604d886893; sha256 9d9524e7c6a13a0abf2c04ab04838849bcb4c4be80247cff75529af0476d7dff},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.10430. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Enterprise data lakes accumulate tables faster than human stewards can document or classify them, leaving columns with missing descriptions and unassigned governance labels. This documentation debt undermines data discovery, access control, and regulatory compliance. We present Glyph, a production system that frames two coupled problems, column description generation and column type annotation for data classification, as cooperating LLM agents orchestrated as stateful graphs. The Descriptor grounds generation in the pipeline source code that produces each column, retrieved on demand from an enterprise GitHub via a reasoning--acting tool loop (active Retrieval-Augmented Generation). The Tagger assigns labels from a governed 275-leaf Data Classification Ontology by running three complementary strategies in parallel (a description tagger, a line-of-business regex tagger, and a metadata tagger backed by a fine-tuned contrastive encoder over a vector database), then fuses their ranked outputs with Reciprocal Rank Fusion (RRF). We fine-tune a 6-layer MiniLM metadata encoder with an in-batch contrastive objective, lifting same-tag retrieval on an in-distribution held-out split from NDCG@10 0.55 to 0.92 (MAP@100 $0.19 \rightarrow 0.90$) relative to the stock base encoder. We report end-to-end multi-label tagging quality under a recall-weighted F2 objective across three evaluation groups, an ablation isolating each strategy and the RRF fusion, and the engineering decisions that distinguish Glyph from prior column-type-annotation work and from commercial value/regex sensitivity scanners: value-free and code-grounded design, per-tag provenance, and graceful degradation. Together these make multi-agent LLM cataloging auditable and operable as a production service.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-10 in cs.MA).
Categorie arXiv: Multiagent Systems (cs.MA) ; Information Retrieval (cs.IR).
Pagina del lavoro: https://arxiv.org/abs/2609.10430 — 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 2026-10-16T06:59:55.754Z dalla pagina https://arxiv.org/catchup/cs.MA/2026-09-10?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).