Run · Voynich Manuscript
T40 rung A, planted control: key recovery with the true sign boundaries
The setting is the best Herbal A draw of T39 round 1. Rung A says the fitted family is not intrinsically unbreakable; what limits it is finding where one sign ends and the next begins.
Result
| Run | Measured | Result | Against | Decision | Date |
|---|---|---|---|---|---|
| Run | Held-out key accuracy by use / character similarity to the true plaintext / dictionary coverage (true plaintext's) | 300k iterations: 0.627 / 0.634 / 0.294 (0.697); 1.5M iterations: 0.706 / 0.728 / 0.336 (0.697) | Protocol bar: 70 % of the plaintext's dictionary coverage (0.49) or 50 % word accuracy | Partly passes: the key is largely recoverable when the boundaries are known (held-out decode '...sce mpesr ibusme a ... risior e u a smon t iusex e...' for '...in campestribus melior autem ... crispiora quae in montibus excepti...'), but coverage stays below the bar |
What it used and found
Latin genre texts
DATDataset
ZL3b transcription
DATDataset
Latin as a re-spaced homophonic stream (period practices)
ANSAnswer it tests
Parameters
pages = Herbal A, training / held-out per D-HERBAL-SPLIT, setting = {'K': 50, 'h_c': 4, 'h_v': 1, 'lam': 0.5, 'Ssyl': 0, 'abbrev': 0, 'p_copy': 0.3, 'p_stay': 0.9, 'window': 5, 'novowel': 0, 'p_break': 0.5, 'spacing': 'stream', 'simplify': 1}, plaintext = Pliny NH 16, iterations = [300000, 1500000]Cite it
Mysteries Department. (2026). T40 rung A, planted control: key recovery with the true sign boundaries [Run RUN0DCBBPFSJ189]. https://mysteriesdept.com/r/RUN0DCBBPFSJ189
@misc{mysteriesdept_run0dcbbpfsj189,
title = {T40 rung A, planted control: key recovery with the true sign boundaries},
author = {{Mysteries Department}},
year = {2026},
note = {Run, catalog key RUN0DCBBPFSJ189},
url = {https://mysteriesdept.com/r/RUN0DCBBPFSJ189}
}