Mysteries Department
Sign inRequest access
Evidence · Unread cuneiform: half a million tablets and the limits of Sumerian

No study has yet measured whether machine translation of Ur III texts changes the rate of archive reconstruction or…

No study has yet measured whether machine translation of Ur III texts changes the rate of archive reconstruction or date assignment, so the claim that interpretation rather than translation limits reading is untested.

Speculative0

What it means

Openunchanged
Answer this evidence bears onThe backlog needs context, not translation
Bears on1 for, none against
Still possibleunchanged

Next steps 5

1
Genre-transfer test: train a transliteration-to-English model on the Akkademia ORACC splits (Neo-Assyrian royal inscriptions), evaluate unchanged on ORACC Old Babylonian letters and on SumTablets-linked Ur III texts with English, and report BLEU/chrF against the in-genre held-out score.
~16 h
—not judged
2
Run the genre-transfer test of Akkadian NMT on Old Babylonian letters and Ur III texts.
~16 h
—not judged
3
Glyph-to-transliteration baseline on the stored SumTablets test split (sha256 65dfe606…): train on the public train split, report sign-reading accuracy by period and genre, and compare with Akkademia's 96.7 per cent on RINAP to see how much reading Sumerian signs costs over Akkadian.
~10 h
—not judged
4
Measure the backlog: from the CDLI bulk dump (cdli_cat.csv plus cdliatf_unblocked.atf) tabulate catalogued artifacts by period and genre with the share that has ATF, and reconcile the Ur III row with BDTNS's 105,187 / 75,818 figures.
~6 h
—not judged
Ranked by how likely each is to move the key question, for the time it takesAll 5 on the question

Sources 1

Cite it

Mysteries Department. (2026). No study has yet measured whether machine translation of Ur III texts changes the rate of archive reconstruction or… [Evidence EVD0DEDY55GJQF7]. https://mysteriesdept.com/r/EVD0DEDY55GJQF7
Private beta Downloads are for beta members

We're in a private beta while we get things right. Everything here is free to read; downloading datasets, sources and code is open to members for now.

It takes a couple of minutes. We'll reply by email.