# The 2026 OpenEtruscan classifiers are scored against labels produced by language-model consensus rather than by…

> The 2026 OpenEtruscan classifiers are scored against labels produced by language-model consensus rather than by Etruscologists, so they cannot show…

Source: https://mysteriesdept.com/mysteries/etruscan-language/evidence/EVD0DEECNS17GKW/the-2026-openetruscan-classifiers-are-scored-against-labels  
Publisher: Mysteries Department  
Licence: CC BY 4.0 (credit Mysteries Department and link the page)  

---

[Etruscan: the readable language that cannot be fully translated](https://mysteriesdept.com/mysteries/etruscan-language)Evidence

Evidence · Etruscan: the readable language that cannot be fully translated

# The 2026 OpenEtruscan classifiers are scored against labels produced by language-model consensus rather than by…

The 2026 OpenEtruscan classifiers are scored against labels produced by language-model consensus rather than by Etruscologists, so they cannot show whether machine learning adds new knowledge.

Suggestive0

## What it means

Key question[How far can the combinatory method and computational analysis extend the roughly 250 securely understood Etruscan words?](https://mysteriesdept.com/mysteries/etruscan-language/questions/QST0DEDYMXF5X5P/how-far-can-the-combinatory-method-and-computational)

2 answers, none ahead yet

**Open** unchanged

Answer this evidence bears on[Machine-learning translation trained on the existing translated inscriptions cannot go beyond the formulae that are…](https://mysteriesdept.com/mysteries/etruscan-language/answers/ANS0DEEBGH0MHWY/machine-learning-translation-trained-on-the-existing)

Bears on1 for, none against

**Still possible** unchanged

## Next steps 1

1

Run a distributional (co-occurrence and position) analysis over the Larth/OpenEtruscan corpora restricted to pre-1991 ET texts, propose meanings for frequent unglossed words, and score them on the c. 1,100 texts added in ET 2014 as a held-out set.

~20 h

[On: How far can the combinatory method and computational analysis extend the roughly 250 securely understood Etruscan words?](https://mysteriesdept.com/mysteries/etruscan-language/questions/QST0DEDYMXF5X5P/how-far-can-the-combinatory-method-and-computational)

**—** not judged

Ranked by how likely each is to move the key question, for the time it takes

## Sources 1

[Etruscan Machine Learning Corpus (OpenEtruscan), version 1.1.0](https://mysteriesdept.com/sources/SRC0DEDNJXGHT8R/etruscan-machine-learning-corpus-openetruscan-version-1-1-0)

Panichi 2026

SRC

## Cite it

```
Mysteries Department. (2026). The 2026 OpenEtruscan classifiers are scored against labels produced by language-model consensus rather than by… [Evidence EVD0DEECNS17GKW]. https://mysteriesdept.com/r/EVD0DEECNS17GKW
```

Key

**EVD** 0DEECNS17GKW

Kind

Evidence

Tier

Suggestive

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/EVD0DEECNS17GKW)