# The readings reflect real ink, as shown by independent imaging and independent readers.

> Most likely: The readings reflect real ink, as shown by independent imaging and independent readers.

Source: https://mysteriesdept.com/mysteries/herculaneum-papyri/answers/ANS0D367Z565VAY/the-readings-reflect-real-ink-as-shown-by-independent  
Publisher: Mysteries Department  
Licence: CC BY 4.0 (credit Mysteries Department and link the page)  

---

[Questions](https://mysteriesdept.com/questions)[Herculaneum Papyri and the Vesuvius Challenge](https://mysteriesdept.com/mysteries/herculaneum-papyri)[Are the machine-learning ink readings real ancient text rather than artefacts of the models?](https://mysteriesdept.com/mysteries/herculaneum-papyri/questions/QST0D367VQT7R26/are-the-machine-learning-ink-readings-real-ancient-text)Answer

Answer · Herculaneum Papyri and the Vesuvius Challenge

# The readings reflect real ink, as shown by independent imaging and independent readers.

The readings reflect real ink, as shown by independent imaging and independent readers.

**Most likely** Answers **1** questionPublished0

## Where it stands

**Most likely** Its tests supported it: three pieces of evidence for, none against. It needs two reviews to be accepted.

## What it predicts

- Where the scan resolves ink directly, it matches the model output stroke for stroke.
- Independent teams using different models read the same letters in the same place.
- Held-out columns never seen in training yield coherent Greek.

## What would rule it out

- A direct-imaging scan of a model-read region shows no ink where the model placed letters.

## Evidence 3 for · none against

[For PHerc. 1667 a held-out column was used for validation and text emerged in it as training iterated.](https://mysteriesdept.com/mysteries/herculaneum-papyri/evidence/EVD0D367ZWM726M/for-pherc-1667-a-held-out-column-was-used-for-validation-and)

Suggestive

FOR

[In the 2.4 µm BM18 scan of PHerc. Paris. 4, ink deposits 10 to 20 µm thick are directly visible and match the…](https://mysteriesdept.com/mysteries/herculaneum-papyri/evidence/EVD0D367ZD04989/in-the-2-4-m-bm18-scan-of-pherc-paris-4-ink-deposits-10-to)

Established

FOR

[The title of PHerc. 172 was read independently by Sean Johnson and by a Würzburg pair at about the same time.](https://mysteriesdept.com/mysteries/herculaneum-papyri/evidence/EVD0D367ZMT5K90/the-title-of-pherc-172-was-read-independently-by-sean)

Supported

FOR

## The questions it answers

[Are the machine-learning ink readings real ancient text rather than artefacts of the models?](https://mysteriesdept.com/mysteries/herculaneum-papyri/questions/QST0D367VQT7R26/are-the-machine-learning-ink-readings-real-ancient-text)

Part of [Can the sealed Herculaneum rolls be read in full, non-invasively, at the scale of the whole library?](https://mysteriesdept.com/mysteries/herculaneum-papyri/questions/QST0D367VG00XNS/can-the-sealed-herculaneum-rolls-be-read-in-full-non)

AnsweredNo answer ahead

## Cite it

```
Mysteries Department. (2026). The readings reflect real ink, as shown by independent imaging and independent readers. [Answer ANS0D367Z565VAY]. https://mysteriesdept.com/r/ANS0D367Z565VAY
```

Key

**ANS** 0D367Z565VAY

Kind

Answer · hypothesis

Origin

Published

Version

1

Added by

[apollo](https://mysteriesdept.com/u/apollo)

The record

Every record is open data. Take this one as JSON, with its links and its history.

[JSON](https://mysteriesdept.com/api/v1/records/ANS0D367Z565VAY)