Skip to main content

Resurrect an ancient library from the ashes of a volcano.
Win $1,000,000+.

The Vesuvius Challenge is a machine learning and computer vision competition to read the Herculaneum Papyri.

79 AD
Mount Vesuvius erupts.

In Herculaneum, twenty meters of hot mud and ash bury an enormous villa once owned by the father-in-law of Julius Caesar. Inside, there is a vast library of papyrus scrolls.
The scrolls are carbonized by the heat of the volcanic debris. But they are also preserved. For centuries, as virtually every ancient text exposed to the air decays and disappears, the library of the Villa of the Papyri waits underground, intact.

1750 AD
A farmer discovers the buried villa.

While digging a well, an Italian farmworker encounters a marble pavement. Excavations unearth beautiful statues and frescoes – and hundreds of scrolls. Carbonized and ashen, they are extremely fragile. But the temptation to open them is great; if read, they would more than double the corpus of literature we have from antiquity.
Early attempts to open the scrolls unfortunately destroy many of them. A few are painstakingly unrolled by an Italian monk over several decades, and they are found to contain philosophical texts written in Greek. More than six hundred remain unopened and unreadable.
What's more, excavations were never completed, and many historians believe that thousands more scrolls remain underground.
Imagine the secrets of Roman and Greek philosophy, science, literature, mathematics, poetry, and politics, which are locked away in these lumps of ash, waiting to be read!

2015 AD
Dr. Brent Seales pioneers virtual unwrapping.

Using X-ray tomography and computer vision, a team led by Dr. Brent Seales at the University of Kentucky reads the En-Gedi scroll without opening it. Discovered in the Dead Sea region of Israel, the scroll is found to contain text from the book of Leviticus.
This achievement shows that a carbonized scroll can be digitally unrolled and read without physically opening it. Virtual unwrapping has since emerged as a growing field with multiple successes.
But the Herculaneum Papyri prove more challenging: unlike the denser inks used in the En-Gedi scroll, the Herculaneum ink is carbon-based, affording no X-ray contrast against the underlying carbon-based papyrus.

2019 AD
Enter the particle accelerator.

Determined to apply virtual unwrapping to the Herculaneum Papyri, Dr. Seales and his team set out to test a new idea. Under infrared light, some detached fragments of the papyri are readable, and it seems possible that these can be used as ground truth data for a machine learning model that could detect otherwise invisible ink from X-rays.
To get X-rays at the highest possible resolution, the team uses a particle accelerator to scan two full scrolls and several fragments. At 4-8µm resolution, with 16 bits of density data per voxel, they believe machine learning models can pick up subtle surface patterns in the papyrus that indicate the presence of carbon-based ink.

You can solve this ancient puzzle.

In early 2023 Dr. Seales’s lab achieves a breakthrough: their machine learning model successfully recognizes ink from the X-ray scans, demonstrating that it is possible to apply virtual unwrapping to the Herculaneum scrolls using the scans obtained in 2019, and even uncovering some characters in hidden layers of papyrus.
After 275 years, the ancient puzzle of the Herculaneum Papyri has been reduced to a software problem – one that you can help solve!

The Vesuvius Challenge

Grand Prize


First team to read a scroll by December 31st 2023

Success requires that the Review Team can:

Read at least 4 separate passages of continuous and plausible text from the scrolls, each at least 140 characters long

In each passage, at most 15% of the characters can be missing or illegible

Qualifying submissions reviewed by team of developers and papyrologists for legitimacy and plausibility

Ink Detection Prize


Detect ink from X-rays by June 14th 2023

A Kaggle competition to detect ink in detached fragments of papyri

Uses ground truth data obtained from infrared imaging

Real-time leaderboard and multiple prizes

$380,000 more in prizes TBA




EduceLab funders

The Arts & Humanities Research Council of Great Britain

The Lighthouse Beacon Foundation — Stanley and Karen Pigman

John & Karen Maxwell

Lee & Stacie Marksbury


Days Remaining