Well-Stratified Linked Data for Well-Behaved Data Citation

TL;DR

This paper proposes a minimal, type-based approach to linked data citation that simplifies provenance and subset identification, advocating for external citation handling with specialized languages.

Contribution

It introduces a simple type system for linked data citation, reducing complexity compared to reification, and suggests external citation management with dedicated languages.

Findings

Type system effectively captures citation requirements

Type checking simplifies provenance and subset identification

External citation languages are recommended for flexibility

Abstract

In this paper we analyse the functional requirements of linked data citation and identify a minimal set of operations and primitives needed to realize such task. Citing linked data implies solving a series of data provenance issues and finding a way to identify data subsets. Those two tasks can be handled defining a simple type system inside data and verifying it with a type checker, which is significantly less complex than interpreting reified RDF statements and can be implemented in a non data invasive way. Finally we suggest that data citation should be handled outside of the data, possibly with an ad-hoc language.