Skip to main content

Resurrect an ancient library from the ashes of a volcano.

Win Prizes. Make History.

Vesuvius Challenge is a machine learning, computer vision, and geometry competition that is reading the carbonized Herculaneum scrolls without opening them.

Open problems

Virtual Unwrapping

A CT scan yields voxels, not columns: the writing surface must be segmented, meshed, and flattened. The pipeline fails where adjacent sheets are densely packed, or tear. Tracing remains semi-automated. Fully automating it is an open problem.

geometry processing3D computer visionoptimizationC++
Solve it, win$1,000,000 2027 Grand Prize · $590,000 per year in Progress Prizes →Current Path
AfterBefore

Ink Detection

Carbon ink is nearly indistinguishable from papyrus in X-ray CT. Models train on fragments with visible ink and infer it inside sealed scrolls; iterative pseudo-labeling bootstraps legibility. Ink has surfaced on 9 of the 45 scanned scrolls and fragments, not always legibly. Generalization is the open problem.

machine learningcomputer visiondomain generalization
Solve it, win$500,000 First Letters · $50,000 PHerc. Paris 4's Title →Find a Letter
AfterBefore

Our story

The backstory79 AD – 2015 AD · how we got here

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 significantly increase 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 a monk over several decades, and they are found to contain philosophical texts written in Greek. More than six hundred remain unopened and unreadable.

Carbonized Herculaneum scroll

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.

Virtual unwrapping has since emerged as a growing field with multiple successes. Their work went on to show the elusive carbon ink of the Herculaneum scrolls can also be detected using X-ray tomography, laying the foundation for Vesuvius Challenge.

2023 AD

A remarkable breakthrough.

Vesuvius Challenge launched in March 2023 with a Grand Prize for the first team to recover four passages of 140 characters from a Herculaneum scroll. Within a year, the prize was claimed. The quest was just beginning.

Herculaneum scroll panorama

2026 AD

The first scroll is read.

In 2026, PHerc. 1667 became the first Herculaneum scroll to be virtually unwrapped and read end to end. The challenge now moves onto its next stage: reading multiple entire scrolls.

The unwrapped writing surface of PHerc. 1667, showing columns of ancient Greek textPHerc. 1667 as a sealed CT scan, before virtual unwrapping
See all open prizes

Team

Created by

Nat FriedmanInstigator, Director & Founding Sponsor
Daniel GrossFounding Sponsor
Brent SealesPrincipal Advisor, PhD

Led by

Giorgio AngelottiProject & Tech Team Lead, PhD

Tech Team

Sean JohnsonResearch Assistant
Hendrik SchillingComputer Vision & AI Expert, PhD
Paul HendersonComputer Vision & AI Expert, PhD
Johannes RudolphPlatform Engineer

Papyrology Team

Federica NicolardiTeam Lead and Assistant Professor, University of Naples Federico II
Marzia D'AngeloPostdoctoral Fellow, University of Naples Federico II
Kilian FleischerResearch Director and Papyrologist, University of Tübingen
Alessia LavorantePostdoctoral Fellow, University of Naples Federico II
Michael McOskerResearcher, University College London
Maria Chiara RobustelliPostdoctoral Fellow, University of Naples Federico II
Claudio VergaraPostdoctoral Fellow, University of Naples Federico II
Rossella VillaResearch Assistant, University of Salerno

Annotation Team

David JoseyTeam Lead, PhD
Kendra BrownAnnotation Specialist
Laura TrojakAnnotation Specialist
EduceLab Team (Partners) (7)
Brent SealesPrincipal Investigator, Professor of Computer Science
Seth ParkerResearch Manager
Christy ChapmanResearch & Partnership Manager
Mami HayashidaResearch Staff
James BrusuelasAssociate Professor of Classics
Beth LutinCollege Business Analyst
Roger MacfarlaneProfessor of Classical Studies
Advisors & Alumni (20)
JP PosmaProject Lead
Stephen ParsonsProject Lead, PhD
Youssef NaderMachine Learning Researcher
Ben KylesSegmentation Team Lead
Julian SchilligerSoftware Engineer
Forrest McDonaldSoftware Engineer
Adrionna FeyAnnotation Specialist
Cooper MillerAnnotation Specialist
Eric ThvedtAnnotation Specialist
Konrad RosenbergAnnotation Specialist
Raymond GasperAnnotation Specialist
Sarah MorejohnAnnotation Specialist
Sergei PnevAnnotation Specialist
TechjaysAnnotation Services
Daniel HavířMachine Learning
Garrett RyanClassics
Dejan Gotić3D Animator
Jonny Hyman2D Animator
Papyrology Advisors (5)
Daniel DelattreEmeritus Research Director and Papyrologist, CNRS and IRHT
Gianluca Del MastroProfessor of Papyrology, l'Università della Campania «L. Vanvitelli»
Robert FowlerFellow of the British Academy; Professor Emeritus of Classics, Bristol University
Richard JankoFellow of the American Academy of Arts and Sciences; Professor of Classics, University of Michigan
Tobias ReinhardtCorpus Christi Professor of the Latin Language and Literature, Oxford

Partners

EduceLabInstitut de FranceBiblioteca Nazionale di NapoliGettyKaggle