Nikita Ganziuk, Innokentiy S. Humonen, Ilya Makarov, Pavel Lebedev · 2026 · arXiv (Cornell University)
DOI: 10.48550/arxiv.2610.28452 · cited by 0 works (OpenAlex) · open-access PDF
Presentamos una herramienta para el estudio comparativo de textos mitológicos y religiosos. El análisis manual tradicional es altamente laboroso y difícil de escalar. Para abordar esto, utilizamos modelos de lenguaje neural para embalar textos en un espacio semántico compartido, para que los usuarios puedan encontrar paralelos semánticos entre tradiciones culturales en una interfaz interactiva. Los fragmentos incorporados forman estructuras semánticas distintas cuya geometría grosera se alinea con relaciones históricas bien documentadas entre tradiciones. Cuantificamos cuánto de esa geometría ya se explica por la superposición léxica y por los nombres apropiados. El sistema actual está disponible en https://mythoscope.io, y el paquete instalable está disponible en https://github.com/haaf/MythoSemantic/blob/main/RUN.
Machine translation (Meta M2M100); the English original follows.
We present a tool for the comparative study of mythological and religious texts. Traditional manual analysis is highly labor-intensive and difficult to scale. To address this, we use neural language models to embed texts into a shared semantic space, so that users can find semantic parallels across cultural traditions in an interactive interface. Embedded fragments form distinct semantic structures whose coarse geometry aligns with well-documented historical relations between traditions. We quantify how much of that geometry is already explained by lexical overlap and by proper names. The current system is available at https://mythoscope.io, and the installable package is available at https://github.com/haafus/MythoSemantic/blob/main/RUN.md.
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
Topics: Parallels, Mythology, Linguistics, Computer science, Semantics (computer science), Perspective (graphical)
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.28452, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange