Structural Pattern Mining in Inka Khipus: Unsupervised Clustering, Provenance Classification, and a Computational Validation of the Santa Valley Match
2026-06-30 • Computation and Language
Computation and Language
AI summaryⓘ
The authors studied khipus, the Inka Empire's knotted cords used for recording information, by analyzing a large public database with machine learning. They found three main structural groups of khipus and could predict where some khipus came from, especially those made during the Inka imperial period. They also discovered that how cords twist is a key feature distinguishing the imperial khipus. Additionally, they confirmed previous findings about a special two-sided structure in some khipus and showed that the order of knot sequences does not help identify origin. Their work is fully reproducible with public data and code.
KhipuInka EmpireMachine learningUMAPHDBSCANGradient boostingSHAP interpretabilityCord twist directionProvenance classificationRecto/verso structure
Authors
Maria Contreras
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, reaching F1 = 0.86 for the Inka Late Horizon imperial style; and (iii) SHAP-based interpretability, which identifies cord twist direction as the dominant structural discriminator of imperial khipus. We further report two findings of methodological interest. First, one cluster is dominated not by a geographic region but by nineteenth-century European museum collections, indicating that colonial acquisition and recording practices are structurally encoded in the corpus. Second, we provide an independent computational verification of the recto/verso (moiety) structure of the six Santa Valley khipus reported by Medrano and Urton (2018), reproducing both the aggregate attachment ratio and the identification of the single mixed specimen--using only the public OKR database, without physical access to the objects. We additionally report a negative result: knot-type sequence order, encoded as n-grams, adds no provenance signal beyond aggregate features. All code and data are openly available.