Tag
This paper presents evidence supporting the Pastiche Hypothesis for the Voynich Manuscript by applying large language models to analyze its structure and generative grammar.
The article explores the potential of using latest AI models to attempt deciphering the Voynich Manuscript, a centuries-old unsolved code, amid recent announcements of other historical puzzles being solved.
This paper challenges the standard assumptions about the linguistic units of the Voynich manuscript, showing through quantitative analysis that glyphs, tokens, and spaces do not correspond to letters, words, and word spaces as commonly believed.
ArXiv preprint quantifies layered RTL and LTR constraints in the Voynich Manuscript, showing 97 % of cross-boundary mutual information lies in specific grapheme transitions and that simple generative models cannot simultaneously reproduce all observed structural signatures.