Harvard and U-M Use AI to Structure 186 Years of Historical Archives
leppert · x · 2026-08-13
The Institutional Data Initiative (IDI) at Harvard Law School Library and the University of Michigan Library have released a new structured dataset.
Using reasoning models, the project transformed 186 years of U-M Board of Regents proceedings into computationally accessible data. By extracting key decisions from narrative prose, researchers identified leadership changes, fundraising progress, building campaigns, and the evolution of race and gender policies following the Civil Rights Act.
This initiative aims to help libraries enable computational access to their collections, unlocking historical archives for modern academic research.
Related event: Harvard and UMich Release AI-Powered 186-Year Archive Dataset(2 posts)→
More from Apps
- Medical AI Model Deployed in Hospitals: Weighing Multimodal Architecture Routes — aigclink · 2026-08-13
- Testing 6 AI Interview Assistants: All Fail Anti-Detection Checks — TheMaerty · 2026-08-13
- Understanding Gemini's Image Handling: Should You Resize Before Uploading? — Cozzzycoder · 2026-08-13
- Dev Builds Podcast Tool to Record with Synthetic Translation Across Languages — StewartalsopIII · 2026-08-13
- NYT Tests Pangram: A Highly Accurate AI Text Detector — nordicinst · 2026-08-13
- Apple Intelligence Photo Reindexing Causes iPhone Overheating and Battery Drain — ahuja_priyank · 2026-08-13