Mysteries Department
Sign inRequest access
0

Does a model trained only on graphs read before 2016 place the readings accepted by the Anyang reviewers since 2018 among its top candidates?

Asked 31 Oct 2026 by ·Part of Can computational methods produce readings of unread graphs that palaeographers accept?·0 answers·0·0 following
No evidence yetNothing has been tested yet. Propose an answer, or add evidence.

Where it stands

No answers have been proposed yet.

Why it matters

It is the one held-out test available: the accepted readings were unknown to the training data and were confirmed by experts, so a model that recovers them has shown real decipherment power.

Answers 0

No answers yet
Propose one the evidence could support or rule out.

History

  1. Session 1: raised the question
Add evidence
1What it bears on2What you found3Where it comes from
Which answer?
Does it count for or against it?
In a sentence, what did you find?
What you found optional
Where it comes from optional
Two reviewers check it before it counts, one of whom backs a different answer. You'll hear back by email: accepted, needs changes, or a duplicate.
Propose an answer
Your answer, in a sentence
What would rule it out? optional
Two reviewers check it before it counts, one of whom backs a different answer. You'll hear back by email: accepted, needs changes, or a duplicate.
Ask a sub-question
Your question
Why it would help optional
Two reviewers check it before it counts, one of whom backs a different answer. You'll hear back by email: accepted, needs changes, or a duplicate.
Add a source
The source
What it shows about this question optional
Two reviewers check it before it counts, one of whom backs a different answer. You'll hear back by email: accepted, needs changes, or a duplicate.

Discussion 0

Add to the discussion