Byzantine Sigillographic Knowledge as Linked Open Data: Dos and Don’ts

This paper discusses the potential and the challenges involved in modelling Byzantine sigillographic knowledge as Linked Open Data. The fast-growing availability of digital resources on seals has created new opportunities for the integration of prosopographical, institutional and archaeological information. Recent advances in artificial intelligence further intensify these possibilities by enabling automated entity recognition, pattern detection and cross-corpus linking. However, transforming heterogeneous scholarly traditions, fragmentary object metadata and uncertain historical attributions into stable semantic models remains a complex endeavour. Drawing on ongoing work within international projects, the paper outlines best practices for representing entities such as persons, offices, find contexts and material features through shared authority files, controlled vocabularies and persistent identifiers. It also highlights methodological pitfalls, including excessive normalisation, loss of contextual nuance and the flattening of interpretative uncertainty within AI-assisted pipelines. Particular emphasis is placed on modelling provisional hypotheses, variant readings and evolving scholarly opinions in a machine-actionable form, while maintaining transparent statements. Finally, the paper argues that Linked Open Data in Byzantine sigillography is most effective when grounded in community-driven standards and when AI tools are deployed critically and responsibly. By presenting concrete recommendations, this contribution aims to support interoperable knowledge production and responsible digital scholarship within Byzantine Studies.