Colorful Insights from an AI Khipukamayuq

The color of each cord is often highlighted as one of the primary sites of meaning on an Inka khipu -- the mostly undeciphered recording device of the Inka empire. However, while there are a variety of historical, ethnographic, and archaeological suggestions for how the semantics of color worked, none of these approaches systematically explains how Inka khipu cord colors denoted meaning. Instead, they present a range of fragmented, sometimes contradictory snapshots of a much larger, more complex system. This study aims to address the question: is there even a "system" of color that can be discovered and deciphered? If so, how did it work? Or is the sheer variety of uses discussed in prior studies an empirical indication that color had limited semiotic consistency for Inka khipukamayuqs ("khipu makers/interpreters" in Quechua)? To answer these questions, I employ an AI khipukamayuq -- a custom "transformer" deep learning model trained to parse all of the cord colors in the Open Khipu Repository (OKR) -- to analyze the semantic space of Inka khipu cord color. My findings reveal a coherent system of color signs, wherein different colors occupy distinct, relationally-opposed semantic domains, with many colors demonstrating polysemy. This suggests a versatile set of color signs adaptable to various contexts and domains of representation, akin to other linguistic media. In the domain of khipus and beyond, this study points toward the importance of continued interaction with AI models as archaeologists learn (together with machines) to systematically represent and delineate the past.

Authors

Publication Details

Published
2025-10-03
DOI
https://doi.org/10.31235/osf.io/4p7s5_v2
Primary Topic
Image Processing and 3D Reconstruction
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Colorful Insights from an AI Khipukamayuq

Jon Clindaniel
Image Processing and 3D Reconstruction
article

Colorful Insights from an AI Khipukamayuq

Jon Clindaniel
article en

Abstract

The color of each cord is often highlighted as one of the primary sites of meaning on an Inka khipu -- the mostly undeciphered recording device of the Inka empire. However, while there are a variety of historical, ethnographic, and archaeological suggestions for how the semantics of color worked, none of these approaches systematically explains how Inka khipu cord colors denoted meaning. Instead, they present a range of fragmented, sometimes contradictory snapshots of a much larger, more complex system. This study aims to address the question: is there even a "system" of color that can be discovered and deciphered? If so, how did it work? Or is the sheer variety of uses discussed in prior studies an empirical indication that color had limited semiotic consistency for Inka khipukamayuqs ("khipu makers/interpreters" in Quechua)? To answer these questions, I employ an AI khipukamayuq -- a custom "transformer" deep learning model trained to parse all of the cord colors in the Open Khipu Repository (OKR) -- to analyze the semantic space of Inka khipu cord color. My findings reveal a coherent system of color signs, wherein different colors occupy distinct, relationally-opposed semantic domains, with many colors demonstrating polysemy. This suggests a versatile set of color signs adaptable to various contexts and domains of representation, akin to other linguistic media. In the domain of khipus and beyond, this study points toward the importance of continued interaction with AI models as archaeologists learn (together with machines) to systematically represent and delineate the past.

Openalex Percentile: Top 73%
Image Processing and 3D Reconstruction
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Colorful Insights from an AI Khipukamayuq — Jon Clindaniel · (2025) | TGRS Research Map | TGRS