Glyph: A Multi-Strategy Agentic System for Column Description and Sensitivity-Ontology Tagging of Enterprise Data Catalogs
Published 16 Sept 2026arXiv:2609.10430
Updated 9 h ago · first seen 17 Sept 2026
paper_01M2RME12R2ZG3RGSSJZ24BEH5
Abstract
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…
Organizations
Organizations 2
Models
Models introduced or described 0
Inbound described_by relations from model cards and documentation.
No model links this paper yet
Datasets
Datasets used 0
No dataset relation recorded.
Benchmarks
Benchmarks used 0
No benchmark relation recorded.
Code
Repositories & frameworks 0
No repository linked.
Timeline
Timeline 1
- New paperPaperGlyph: A Multi-Strategy Agentic System for Column Description and Sensitivity-Ontology Tagging of Enterprise Data CatalogsApple
New paper: Glyph: A Multi-Strategy Agentic System for Column Description and Sensitivity-Ontology Tagging of Enterprise Data Catalogs (Apple)
apple_ml
Sources
Sources 2
Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.