Library of Congress Innovator in Residence graphic
Calling all technologists, artists and other creative visionaries:
The Library of Congress has opened the call for the next Innovator in Residence!
Apply by 2pm ET April 10
newsroom.loc.gov/news/library...
The plenary videos from the CNI meeting are now available:
🤝Shaping CNI’s Future Together
📚A Landscape of AI in Libraries @bcgl.bsky.social
🏆AUPresses Stand UP Award
@brettbobley.bsky.social @aupresses.bsky.social
💰The State of Funding for US Higher Ed, Science, and Technology in a Time of Change
Publication day! My article on how to read an 18C newspapers, on digital remediation, and on the unfree press out in the world. Thanks @andy-schocket.bsky.social @historymatterssyd.bsky.social & M. Karrs for making it all possible. @universitypress.cambridge.org
lnkd.in/eEwbdbSw
Figured I’d wait to post anything for this, but I can’t tell you how excited I am for us to have the opportunity to be funded to do this work. We really do believe that our project connecting communities, digital archives of the early Black press, and human-AI systems will have a large impact
I really appreciate your kind words!
For "Communities in the Loop: AI for Cultures & Contexts in Multimodal Archives," congrats to: Jim Casey, Christopher Dancy, @snblickhan.bsky.social, Tiffany Smith, Benjamin Lee. (And I must also include @profgabrielle.bsky.social !)
Seconding all of this — so much fun not work with so many people I deeply admire, and we can’t wait to share out as our project progresses!
I can confirm, thinking with this crew is honestly wonderful, 10/10, Dream Team experience. I have more to say but a meeting to facilitate! More soon.
Honored to be giving an opening plenary talk on AI & libraries later today at CNI 2025! I’m excited for the conversation with Kate Zwaard and for the full program by @cni-org.bsky.social!
www.cni.org/events/membe...
I am beyond thrilled to share some good news:
1. I've moved to a new job at UC Santa Barbara.
2. We have been selected for a 2025 Humanities and AI Virtual
Institute award from @schmidtsciences.bsky.social!
Both, we hope, will allow us to continue building the work! +
hfa.ucsb.edu/news/schmidt...
Guest Post on GovScape. It is a great example of how we can build on each other's systems and work to enable access to government information! Follow @govscape.bsky.social for more!
www.datarescueproject.org/guest-post-g...
Thank you to @datarescueproject.org for publishing this blog post by @kdeeds.bsky.social and myself on GovScape! Extremely grateful to @datarescueproject.org for all their incredible work!
Very excited to have a software paper with @yh-huang.bsky.social in the CHR journal on the Digital Collections Explorer, our open-source multimodal viewer for digital collections!
New Research Tool: GovScape (US Gov PDFs)
govscape.net ||| Research Paper (preprint) About #GovScape arxiv.org/abs/2511.11010 #govdocs @eotarchive.org
Anyone interested in govt transparency and public access should check out GovScape from @bcgl.bsky.social and his team👇
It's an incredibly powerful tool that allows visual, semantic text, and keywords search of 10 million U.S. government PDFs (70 million pages!) and counting: www.govscape.net
Thanks so much! Truly appreciate it!
Thanks so much!
We’re live! Search 10 million+ U.S. government PDFs (70 million pages)! GovScape offers visual search, semantic text search, and keyword search. Explore below:
Website: govscape.net
ArXiv link: arxiv.org/abs/2511.11010
Huge step forward in enabling access and use of content archived from government websites!
7/ Lastly, we’d love to hear your feedback on GovScape at bcgl@uw.edu! For more updates on GovScape, follow: @govscape.bsky.social
7/ A particular thank-you to @kdeeds.bsky.social for leading this project with me and for making this possible! And to @yh-huang.bsky.social, who did an incredible job with the front-end and dev-ops!
6/ GovScape is the result of a multidisciplinary collaboration, co-led by myself and @kdeeds.bsky.social. We’re enormously grateful to the team: Ying-Hsiang Huang, Claire Gong, Shreya Shaji, Alison Yan, Leslie Harka, @tjowens.bsky.social, @vphill.bsky.social, @shannonshen.bsky.social, and SJ Klein!
5/ Interested in learning more? Visit GovScape at: www.govscape.net – try some searches and read the FAQ! You can also watch a demo video here: www.youtube.com/watch?v=mNda...
A visual search for "redacted documents" showing a number of documents with heavy redactions.
4/ What does visual search do? Here’s a visual search for “redacted documents”
A diagram showing the GovScape architecture, including the client, server, and databases.
3/ The full GovScape architecture is detailed in this figure, showing how the client interacts with the server, DBs, and indices. We utilize FAISS for text embeddings and for CLIP embeddings, and SQLite FTS5 for keyword indexing.
An diagram showing the GovScape PDF pre-processing pipeline, including PDF identification, rendering, and semantification (including embedding generation).
2/ The pre-processing pipeline ingests PDFs, renders them, generates CLIP and BGE embeddings of individual pages, and indexes the text. The total compute cost for GovScape's pre-processing pipeline for 10 million PDFs was approximately $1,500. Our code is available at: github.com/bcglee/govsc....
A diagram showing the three central query methods within GovScape: semantic text search, visual search, and keyword search.
2/ GovScape is built on top of the End of Term Web Archive (eotarchive.org) and currently contains all renderable PDFs (50 pages or fewer) from the 2020 crawl, documenting the first Trump administration. An overview of GovScape’s search functionality can be found in this diagram.
1/ Announcing GovScape – a public search system for 10 million U.S. government PDFs (70 million pages)! GovScape offers visual search, semantic text search, and keyword search. Explore below:
Website: www.govscape.net
ArXiv link: arxiv.org/abs/2511.11010
Assistant Professor Ben Lee @bcgl.bsky.social's essay on the topic of AI and Holocaust Memory, “Uncanny Testimony,” was published by @longreads.com: longreads.com/2025/09/25/a...
Thanks so much, I appreciate it!
