Structural Pattern Mining in Inka Khipus: Unsupervised Clustering, Provenance Classification, and a Computational Validation of the Santa Valley Match
arXiv:2607.00185v1 Announce Type: new Abstract: Khipus--knotted cord devices--were the primary recording medium of the Inka Empire (c. 1400-1532 CE), yet their system remains undeciphered. We present a reproducible machine-learning pipeline applied to the Open Khipu Repository (OKR), a public database of 619 khipus comprising 54,403 cords and 110,677 knots. We engineer 27 structural features per khipu and apply (i) unsupervised clustering via UMAP and HDBSCAN, recovering three structurally distinct groups (silhouette = 0.769); (ii) supervised provenance classification via gradient boosting, re
The application of modern machine learning techniques to historical artifacts is a continuous process as computational methods improve and datasets become more accessible.
While interesting from an academic perspective, this research offers minimal immediate strategic relevance to contemporary geopolitical or economic structures.
This research potentially aids in understanding ancient Inka civilization but does not alter current technological, economic, or political landscapes.
- · Archaeologists
- · Historians
- · Academics in computational linguistics
The immediate effect is a new computational method for analyzing historical data sets.
This might inspire similar machine learning applications across other undeciphered historical records or complex symbolic systems.
Long-term, improved understanding of ancient civilizations could subtly influence cultural perceptions but has no direct strategic impact.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.CL