A new arXiv paper presents SQuIREL, a framework designed to measure entity richness in Wikidata. The authors argue that Wikidata's size and heterogeneity make data quality metrics context-dependent, and that the "richness" metric in particular has received little attention and is typically restricted to the ontology level.
SQuIREL shifts the focus to individual entities, using a context-relative approach to assess how richly an entity is described. This is meant to account for the fact that what counts as "rich" data can vary across different domains or use cases within the same knowledge graph.
The paper is positioned as a step toward more nuanced data quality assessment for Wikidata, though the abstract does not detail experimental results or comparisons with existing methods. As a single-source digest, this summary reflects only the framework's stated motivation and design.