The Interconnectedness of All Things: Understanding Digital Collections Through File Similarity

Abstract

Abstract Archives that house digital collections often struggle with rapidly evolving workflows and the intrinsic difficulties in managing disordered records. Both physical and digital records may have complex relationships with other records such as drafts of the same document or one document that is included in another, but digital records offer the possibility that a computer may analyze the collection and automatically discover such relationships. An analytical tool for digital collections would employ a model that can represent the network of relationships between files instead of the hierarchical model used in traditional archival arrangement and description. A proof-of-concept of such a tool, employing techniques such as fuzzy and perceptual hashes, demonstrates the viability of this approach and suggests avenues for future research and development.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 1 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.