In 2023, we turned a wild dream into reality. When we launched Vesuvius Challenge, no text had ever been recovered noninvasively from inside a complete Herculaneum scroll. Months went by before this changed. By the end of the year, what started as a few characters and then words jumped to more than 2,000 characters - 15 columns - of Greek philosophy recovered from the ashes.
This year, we’re doing it again.
Our goal for 2024 is to go from reading 5% of one scroll to reading 90% of four scrolls. Today we’re providing the rubric for this Grand Prize challenge, which now outlines in greater detail what we hope to accomplish. To better reflect the ambition of the challenge, we are also doubling the prize from $100,000 to $200,000.
To continue moving towards this goal, we’re investing heavily in the community of contributors that got us across the finish line last year. We’ve doubled the progress prize pool, already yielding great strides in the engineering, tooling, data, and other resources that will be required to pull this off - all advancements that are now open and shared with the community. We’re also working with our team and partners to push the techniques forward, provide more resources and data, and offer support. We are on a mission to read these scrolls.
The $200,000 2024 Grand Prize criteria are listed below and on our website. On the path towards this target, there remains much low hanging fruit, and we stand by ready to reward its picking. Will you join us?
The $200,000 2024 Grand Prize will go to the first person or team to read 90% of Scrolls 1-4, using the following criteria:
1. Segmentation
Compute the total surface area (in sq. cm) of papyrus sheets present in all four complete scrolls combined.
We may compute and specify this value ourselves as the year progresses, in which case you can skip this step.
Compute the same measure for the papyrus sheets actually segmented in your submission. You must segment 90% or more of the total from all scrolls (not per-scroll).
Segments should be flattened and shown in 2D as if the scroll were unrolled. Each scroll is ideally captured by a single segmentation (or each connected component of the scroll) rather than separate overlapping segmentations.
Segments should pass geometric sanity checks; for example, no self-intersections. We will evaluate stretch metrics to measure distortion.
2. Ink detection
Generate ink predictions on the segments.
The entire submission is too large to transcribe quickly, so the papyrological team will evaluate each line as:
✅ readable (could read 85% of the characters),
❌ not readable (couldn't),
🟡 maybe (would have to stop and actually do the transcription to determine), or
🔷 incomplete (line incomplete due to the physical boundaries of the scroll)
90% of the total complete lines (incomplete lines will not be judged) must be either 🟡 maybe or ✅ readable. Multiple papyrologists may review each line, in which case ties will be broken favorably towards the submission.
As a baseline, here's how the 2023 Grand Prize banner would have scored:
Total lines: 240. Complete lines: 206. Passing lines: 137. Pass rate: 137 / 206 = 67% (needs to be 90%).
More and larger segmentations are needed, as well as improvements to ink recovery. Already both fronts are moving forward!
In 2023, we got from 0% to 5% of one scroll. Reading 90% of each of our scrolls will lay the foundation to read all 300 scrolls. The 2024 criteria are designed to be as permissive, flexible, or favorable as possible within the high level objective of reading the scrolls. Favorable adjustments will be made if required (for example, if it is discovered conclusively that a scroll does not contain writing). Our mission is to read scrolls. We want to award this prize!!
Multiple submissions are permitted, and we can provide feedback for early or partial submissions. If no team meets the above criteria by the deadline, Vesuvius Challenge may award the prize to the team(s) that were closest. These and other awards are at the sole discretion of Vesuvius Challenge.