Statistical Structure in Indus Sign Sequences

Tanishk Tiwari


Abstract
This paper introduces a computational frameworkfor evaluating structural properties ofthe undeciphered Indus script.The study usesa corpus of 6,579 inscriptions.The analyticalapproach combines unsupervised visual clusteringof sign morphology, entropy-based sequenceanalysis, Kullback-Leibler divergencecomparison, and neural sequence modeling(BiLSTM). The results indicate directionalasymmetry and structured combinatorial patternsin sign sequences. We conclude that theIndus sign sequences exhibit statistical propertiesconsistent with structured symbolic systemsand not easily explained by random generation.
Anthology ID:
2026.nlp4dh-1.28
Volume:
Proceedings of the 6th International Conference on Natural Language Processing for the Digital Humanities
Month:
July
Year:
2026
Address:
San Diego, USA
Editors:
Sil Hamilton, Emily Öhman, Rebecca M. M. Hicke, Yuri Bizzoni, Axel Bax, Jacob A. Matthews, Mika Hämäläinen
Venues:
NLP4DH | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
314–319
Language:
URL:
https://preview.aclanthology.org/ingest-acl-workshops/2026.nlp4dh-1.28/
DOI:
Bibkey:
Cite (ACL):
Tanishk Tiwari. 2026. Statistical Structure in Indus Sign Sequences. In Proceedings of the 6th International Conference on Natural Language Processing for the Digital Humanities, pages 314–319, San Diego, USA. Association for Computational Linguistics.
Cite (Informal):
Statistical Structure in Indus Sign Sequences (Tiwari, NLP4DH 2026)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingest-acl-workshops/2026.nlp4dh-1.28.pdf