Research note · June 13, 2026
I’ve been building LinkedCulture — a project that finds connections across museum colle...
Full transparency: two of the co-hosts (Eulalia and Shay) are AI-generated avatar personas — I’m also testing AI video pipelines as part of this. The art history itself is fact-checked and sourced...
museumtechdigitalhumanitiesaiarthistoryopendata
I’ve been building LinkedCulture — a project that finds connections across museum collections worldwide (currently 220k+ objects from the Getty, Rijksmuseum, Met, Art Institute of Chicago, Cleveland Museum of Art, Harvard Art Museums, and others). As part of that, I’m experimenting with video formats for surfacing these connections. First pilot: “Crossings” — a short podcast-style episode tracing one biblical scene, “Rest on the Flight into Egypt,” across 8 artists and 6 museums over 450 years. None of these artists knew of each other, but seen together they say a lot about what each one actually cared about — landscape, virtuosity, status, faith.
Full transparency: two of the co-hosts (Eulalia and Shay) are AI-generated avatar personas — I’m also testing AI video pipelines as part of this. The art history itself is fact-checked and sourced directly from museum open-access collections (all CC0 / public domain).
Curious what people think: both about the format and about the underlying idea of “linking” cultural collections that were never meant to be seen side by side.
The research behind this series is documented in several papers: Paper 1: Discovery architecture for cultural heritage: layered retrieval, institutional authority, and the limits of keyword search https://linkedculture.org/research/discovery-architecture-for-cultural-heritage
Paper 2: Discovery architecture for cultural heritage: layered retrieval, institutional authority, and the limits of keyword search https://linkedculture.org/research/embedding-cultural-heritage-metadata
Paper 3: Semantic Clusters and Language Partitioning in a Multi-Institutional Cultural Heritage Index https://linkedculture.org/research/semantic-clusters-language-partitioning
Learn more about LinkedCulture and the work behind it: https://linkedculture.org/