This community may be interested in recent preservation-related videos from the Coalition for Networked Information (CNI), a joint project of EDUCAUSE and the Association of Research Libraries that focuses on the intersection of technology and information management/libraries, especially in higher education and the research enterprise:

Archivault: Processing Digital Collections at Scale with Generative Artificial Intelligence
Watch at: https://youtu.be/twb3t-Jg6BI

Vanderbilt University has a rich history of advancing digital projects and stewarding its assets for perpetual preservation. However, it has long wrestled with questions around the extensibility and reproducibility of its core digital projects. To this end, the University is refocusing efforts on developing and deploying discrete digital solutions that advance these projects locally in ways that can be adopted globally. The briefing will share the vision, mission, staffing structures, and key industry partnerships that make this approach possible, and it will introduce one such solution, Archivault, a modular platform for processing and enriching digitized archival images. Archivault automates resource-intensive steps such as document boundary detection, transcription, and metadata generation via cloud-based infrastructure that lowers the technical barrier to entry. The platform supports both rapid prototyping for individual projects and scalable deployment for large repositories. In doing so, it demonstrates how targeted, reusable services can address heterogeneous scholarly and institutional needs.


Artificial Intelligence-Assisted Music Cataloging Project
Watch at: https://youtu.be/ATYiwDRR_T8

At the University of Texas at Austin Libraries, the AI-Assisted Music Cataloging Project demonstrates how libraries can leverage large language models alongside other tools to automate copy-cataloging workflows while maintaining quality control. The system generates metadata from images of CDs and LPs, queries OCLC WorldCat for matching records, and uses a large language model to evaluate matches and assign confidence scores. Confidence scores are then adjusted with automated comparisons of track titles and publication years. The workflow creates a number of cataloging tools, including a batch upload file; a physical sorting spreadsheet; and an optional HTML review interface that allows catalogers to visually compare OCLC records with object images, approve or reject matches, and export their decisions for integration into cataloging files. Institutions can choose their level of verification before proceeding to batch upload, supported by a script that creates bibliographic, holdings, and item records in Alma from OCLC data. The open-source toolkit emphasizes batch processing optimization for cost efficiency and models a replicable method for institutions seeking to responsibly integrate AI into their technical services operations.


Metadata Matters: Modernizing the Vanderbilt Television News Archive Database
Watch at: https://youtu.be/TyGM0NMGpxI

The Vanderbilt Television News Archive will share the results of its recently completed database migration project. Vanderbilt’s database of one million tv news stories and half-a-million commercial breaks, 1968 to present, has undergone several transformations over the decades. Starting as a print catalog in the 1970s, then debuting as an early website in the mid-1990s, the most recent project migrated the on-premise MySQL server to AWS Aurora via Database Migration Services. Rebuilding the database enabled the Archive to include transcripts, linked data, artificial intelligence-generated titles and descriptions, as well as the International Press Telecommunications Council (IPTC) Media Topics, all within the American Archive of Public Broadcasting’s metadata standard PBCore. This project offers television news archive users better search capabilities as well as new text and data mining services.


The videos are openly available; please reach out if you have any questions!

Sincerely,

Paige Pope, CNI Communications Manager

########################################################################

to manage your NDSA-ALL subscription, visit ndsa.org/ndsa-all