The objective of the Vesuvius Challenge is to make history by reading an unopened Herculaneum scroll for the very first time. We believe that an open competition will accelerate progress and enable us to achieve this goal in 2023.

We are providing all contestants with the following resources:

• Prizes: $1,000,000+ in prizes, including a $700,000 Grand Prize and the rest in Progress Prizes. The first progress prize is a $100,000 ink detection competition on Kaggle. We also have some smaller Open Source Prizes.
• Data: 3D X-ray scans of two unopened scrolls from Herculaneum, and scans and images of three papyrus fragments
• Tutorials and tools: the current best tools and techniques for virtually unwrapping papyrus scrolls
• Community: a Discord server where you can connect with other contestants and the Vesuvius Challenge team

• Join our Discord server to ask questions, learn about what is going on, hang out with fellow contestants and interested onlookers, and perhaps find teammates.
• Receive updates every 1-2 weeks from our mailing list on Substack.
• Follow @scrollprize on Twitter.

Our team is available for any questions and feedback on Discord. You can also email us at [email protected].

Grand Prize ($700,000)​

The Grand Prize will go to the first team to read four passages of text from the inside of the two intact scrolls. More details on the qualifying criteria are available here.

Here are the scrolls in question:

We have provided you with 8µm 3D X-ray scans of each of these scrolls, which you can find here. Your job is to extract the text from these scans.

You can approach this challenge through any means necessary: machine learning, computer vision, or machine-assisted tools operated by humans.

Why is this difficult?​

As you will read in the tutorials, advanced tools and techniques exist for virtually unwrapping papyrus scrolls. This was demonstrated in 2015 when Dr. Seales’s team unwrapped the En-Gedi scroll, and in their recent result identifying ink from 3D X-ray scans in the Herculaneum scrolls.

But the Herculaneum scrolls have proved more challenging. The remaining challenges include:

• Segmenting the scrolls. The Herculaneum scrolls are especially long, tightly wrapped, damaged, and distorted. To date, no one has successfully done a large-scale segmentation of these scrolls to identify the surfaces of all the rolled layers.
• Finding the ink. The ink used in the Herculaneum scrolls is radiolucent, making it difficult to see in the