Mysteries Department
Sign inRequest access
Run · Voynich Manuscript

T43 generation 1: Gromov-Wasserstein word alignment, planted controls (N 300, epsilon 0.005)

Control: Pliny NH 16 enciphered with period.generate seed 77.

Fails its own control by two orders of magnitude, so the manuscript was not aligned. With homophones (4 per consonant), copied nulls and a different Latin text on the target side, co-occurrence spaces of ~5,000 words are too sparse for GW to find the word map even when one exists.word-spacing control 0.003 (GW 0.034); stream-spacing control 0.0014 (GW 0.037)0

Result

RunMeasuredResultAgainstDecisionDate
RunHeld-out word accuracy of the coupling's word map (bar 0.5)word-spacing control 0.003 (GW 0.034); stream-spacing control 0.0014 (GW 0.037)Gate 0.5Fails its own control by two orders of magnitude, so the manuscript was not aligned. With homophones (4 per consonant), copied nulls and a different Latin text on the target side, co-occurrence spaces of ~5,000 words are too sparse for GW to find the word map even when one exists.

What it used and found

Parameters

N = 300, window = 2, epsilon = 0.005, target_side = Latin herbal genre text (D-SECTIONS H), prepared as the setting prepares plaintext, control_setting = T39 best Herbal A setting with spacing 'word' (and 'stream')

Cite it

Mysteries Department. (2026). T43 generation 1: Gromov-Wasserstein word alignment, planted controls (N 300, epsilon 0.005) [Run RUN0DCF8N67G74D]. https://mysteriesdept.com/r/RUN0DCF8N67G74D
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.