Workflow · workflow
Students use AI models and GitHub Copilot to decode 2,000-year-old Herculaneum scrolls
The Herculaneum Papyri are too fragile to open due to carbonization, and the ancient ink did not show up in standard X-ray and tomography scans, making any reading of the texts impossible without an AI-based approach.
How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · Scroll scans captured
Scientists captured tomography scans of the Herculaneum papyri, which technologists worldwide then set out to analyze.
Tools used
GitHub CopilotVisual Studio CodeGitHubDiscord
Outcome
The team won the Vesuvius Challenge grand prize of $700,000 and decoded portions of the 2,000-year-old scrolls, with Julian's automated segmentation software covering around 1600 cm^2 of scroll surface.
What failed first
Scientists had applied virtual unwrapping with tomography and X-rays—a technique that succeeded on the Dead Sea Scrolls—but the same approach failed on the Herculaneum texts because the ink remained invisible in scans.
Results
Volumearound 1600 cm^2
Cost replaced$700,000
Running sinceMarch 2023
Grounding & classification
Source type: vendor customer story
20 fields verified against source quotes.
code generationcomputer visiondocument aifailure mode describedhuman review describedmetric backednamed customertools describedworkflow describededucationemployee productivityvendor customer storydocument to record