Reconstructing Fragmentary Inscriptions with M-RADAR: Cross-Inscription Computational Analysis of the Singapore Stone and the Karimun Inscription
Abstract
The decipherment of fragmentary inscriptions remains a major challenge in epigraphy, historical linguistics, and digital paleography, particularly when the surviving textual evidence is severely degraded or incomplete. The Singapore Stone, one of Southeast Asia’s most enigmatic inscriptions, has resisted definitive interpretation for nearly two centuries due to its fragmentary condition and the absence of a systematic computational framework for comparative analysis. This study uses M-RADAR (Maritime Reconstruction via Automated Digital Analysis and Restoration), a computational epigraphy framework that facilitates cross-inscription morphological comparison and predictive reconstruction. Using the better-preserved Karimun Inscription as a morphological reference corpus, the framework combines high-resolution noise reduction, vector-based graphemic analysis, nearest-neighbor classification, and probabilistic syntactic modeling. The study reveals a 78.4% morphological correspondence between the two inscriptions and achieves an 89% predictive reconstruction accuracy for damaged textual segments. In addition, it identifies previously unrecognized diacritic markers and supports a Sanskrit-Kawi hybrid linguistic structure as the most probable interpretation of the inscription. These findings provide new empirical evidence for a shared paleographic tradition within the maritime Malay Archipelago and demonstrate the effectiveness of cross-inscription computational reconstruction. More broadly, this study contributes a reproducible methodological framework for the analysis, restoration, and digital preservation of fragmentary epigraphic materials in Southeast Asia.
[Pembacaan dan rekonstruksi prasasti fragmentaris masih menjadi salah satu tantangan utama dalam kajian epigrafi, linguistik historis, dan paleografi digital, terutama ketika bukti tekstual yang tersedia berada dalam kondisi rusak dan tidak lengkap. Batu Singapura, yang merupakan salah satu prasasti paling enigmatik di Asia Tenggara, telah luput dari penafsiran yang meyakinkan selama hampir dua abad akibat kondisi fragmentarisnya serta belum tersedianya kerangka komputasional yang sistematis untuk analisis komparatif. Penelitian ini menggunakan M-RADAR (Maritime Reconstruction via Automated Digital Analysis and Restoration), sebuah kerangka epigrafi komputasional yang dirancang untuk mendukung perbandingan morfologis lintas prasasti dan rekonstruksi prediktif. Dengan memanfaatkan Prasasti Karimun sebagai korpus referensi morfologis yang lebih terpelihara, kerangka ini mengintegrasikan reduksi derau beresolusi tinggi, analisis grafemis berbasis vektor, klasifikasi nearest-neighbour, serta pemodelan sintaktis probabilistik. Hasil penelitian menunjukkan adanya korespondensi morfologis sebesar 78,4% antara kedua prasasti serta tingkat akurasi rekonstruksi prediktif sebesar 89% pada bagian teks yang rusak. Selain itu, penelitian ini juga berhasil mengidentifikasi penanda diakritik yang sebelumnya tidak terdeteksi dan menunjukkan bahwa struktur linguistik hibrida Sanskerta-Kawi merupakan interpretasi yang paling mungkin bagi prasasti tersebut. Temuan ini memberikan bukti empiris baru mengenai keberadaan tradisi paleografis bersama di kepulauan Melayu maritim serta menunjukkan efektivitas pendekatan rekonstruksi komputasional lintas prasasti. Penelitian ini menawarkan kerangka metodologis yang dapat direplikasi untuk analisis, restorasi, dan pelestarian digital prasasti fragmentaris di Asia Tenggara.]
Keywords
Copyright
Copyright Holder: Tehreem Zahra, Francesco Perono Cacciafoco, I-Shiang Lee
Copyright Year: 2026
License: Creative Commons Attribution 4.0 International License
References
Assael, Y., Sommerschield, T., Shillingford, B., Bordbar, M., Pavlopoulos, J., Chatzipanagiotou, M., Androutsopoulos, I., Prag, J., & de Freitas, N. (2022). Restoring and Attributing Ancient Texts Using Deep Neural Networks. Nature, 603(7900), 280–283. https://doi.org/10.1038/s41586-022-04448-z
Begbie, P. J. (Peter J. (with University of Michigan). (1834). The Malayan Peninsula: Embracing its History, Manners, and Customs of the Inhabitants, Politics, Natural History. Vepery Mission Press. http://archive.org/details/malayanpeninsul00begbgoog
Bland, W. (1837). Inscription on the Jetty at Singapore. Journal of the Asiatic Society of Bengal, 6(70), 680–682.
Caldwell, I., & Hazlewood, A. A. (1994). ‘The Holy Footprints of the Venerable Gautama’: A New Translation of the Pasir Panjang Inscription. Bijdragen Tot de Taal-, Land- En Volkenkunde / Journal of the Humanities and Social Sciences of Southeast Asia, 150(3), 457–480. https://doi.org/10.1163/22134379-90003073
Casparis, J. G. de. (1975). Indonesian Palaeography: A History of Writing in Indonesia from the Beginnings to C. A.D. 1500. BRILL.
Chua, S. H. (2018). Crypto-Linguistics in Singapore: Deciphering the Singapore Stone [Undergraduate Final Year Project, Nanyang Technological University]. https://hdl.handle.net/10356/76546
Cornelius-Takahama, V. (2016). Singapore Stone. National Library Board Singapore. https://www.nlb.gov.sg/main/article-detail?cmsuuid=0a757a02-5f6b-483a-8a32-97a09953da63
Griffin, S. M. (2023a). Digital Libraries, Epigraphy and Paleography: Bring Records from the Distant Past to the Present: Part II. International Journal on Digital Libraries, 24(3), 139–147. https://doi.org/10.1007/s00799-023-00381-2
Griffin, S. M. (2023b). Special Issue: Epigraphy and Paleography: Bringing Records from the Distant Past to the Present. International Journal on Digital Libraries, 24(2), 77–85. https://doi.org/10.1007/s00799-023-00371-4
Griffiths, A. (2014). Early Indic Inscriptions of Southeast Asia. In J. Guy (Ed.), Lost Kingdoms: Hindu-Buddhist Sculpture of Early Southeast Asia (pp. 53–57). Yale University Press; The Metropolitan Museum of Art. https://shs.hal.science/halshs-01958897
Griffiths, A. (2018). The Corpus of Inscriptions in the Old Malay Language. In D. Perret (Ed.), Writing for Eternity: A Survey of Epigraphy in Southeast Asia (Vol. 30, pp. 275–283). École Française d’Extrême-Orient. https://hal.science/hal-01920769
Heng, D. T. S. (2009). Sino–Malay Trade and Diplomacy from the Tenth through the Fourteenth Century (1st ed). Ohio University Press.
Laidlay, J. W. (1848). Note on the Inscriptions from Singapore and Province Wellesley: Forwarded by the Hon. Col. Butterworth, C.B., and Col. J. Low. Journal of the Asiatic Society of Bengal, 17(2), 66–72.
Lee, I.-S., & Perono Cacciafoco, F. (2023). Unravelling the Mystery of the Singapore Stone: A Comparative Analysis with the Calcutta Stone and the Possible Kawi Connection. Histories, 3(3), 261–270. https://doi.org/10.3390/histories3030018
Miksic, J. N. (1985). Archaeological Research on the “Forbidden Hill” of Singapore: Excavations at Fort Canning, 1984. National Museum. https://catalog.hathitrust.org/Record/000486909
Miksic, J. N. (2013). Singapore and the Silk Road of the Sea, 1300-1800. NUS Press.
Perono Cacciafoco, F. (2026, March 12). Cracking the Code: How a “Prediction Machine” is Resurrecting the Singapore Stone. The Conversation. https://doi.org/10.64628/AAN.q7cgr4hmx
Seales, W. B., & Chapman, C. Y. (2023). From Stone to Silicon: Technical Advances in Epigraphy. International Journal on Digital Libraries, 24(2), 129–138. https://doi.org/10.1007/s00799-023-00362-5
Sinclair, I. (2018). New Light on the Karimun Besar Inscription (Prasasti Pasir Panjang) and the Learned Man from Gaur. NSC Highlights, 11, 16–17.
Stokes, P. A. (2009). Computer-Aided Palaeography, Present and Future. In M. Rehbein, P. Sahle, & T. Schaßan (Eds.), Kodikologie und Paläographie im Digitalen Zeitalter (pp. 309–338). Books on Demand.
Wang, Z., Li, Y., & Li, H. (2025). Chinese Inscription Restoration Based on Artificial Intelligent Models. Npj Heritage Science, 13(1), 326. https://doi.org/10.1038/s40494-025-01900-x
Yap, K. C., Jiao, T. (Wenyao), & Perono Cacciafoco, F. (2023). The Singapore Stone: Documenting the Origins, Destruction, Journey and Legacy of an Undeciphered Stone Monolith. Histories, 3(3), 271–287. https://doi.org/10.3390/histories3030019
Zaccheus, M. (2019, December 22). Singapore may be 1,000 Years Old, not just 700 as Believed: Study. The Straits Times. https://www.straitstimes.com/singapore/spore-may-be-1000-years-old-not-just-700-as-believed-study
Zahra, T., & Ahmed, S. (2025). Generational Differences in Emoji Interpretation: A Study of Millennial, Gen Z, and Baby Boomers. Advance Social Science Archive Journal, 3(2), 857–864.
Zahra, T., Ali, P., Qureshi, J., & Fatima, M. (2025a). Emoji Aesthetics in the Digital Age: A Comparative Analysis of User Preferences for Apple, Android Emoji Style. Sociology & Cultural Research Review, 3(2), 214–216.
Zahra, T., Ali, P., Qureshi, J., & Fatima, M. (2025b). Emoji Prediction in Text Based Communication: A Study of Machine Learning Approaches. Sociology & Cultural Research Review, 3(1), 1334–1337.
Zahra, T., & Perono Cacciafoco, F. (2025a). Telegram and WhatsApp in Blended Learning: Impact on Online Community and Academic Achievement Among Graduate Students. Idil Journal of Art and Language, 14, 467–488. https://doi.org/10.7816/idil-14-118-03
Zahra, T., & Perono Cacciafoco, F. (2025b). The Etymological Roots of Emoji Miscommunication: A Comparative Study of Eastern and Western Emoji Usage. SKASE Journal of Literary and Cultural Studies, 7(1), 94–112.
Zahra, T., & Perono Cacciafoco, F. (2025c). Use of Emojis as Discourse Markers in WhatsApp Conversations: A Multimodal Perspective. Annals of the University of Craiova. Series Philology. Linguistics, 47(1–2), 226–237. https://doi.org/10.52846/aucssflingv.v47i1-2.190
Zahra, T., & Perono Cacciafoco, F. (2026). Emoji Rich vs Emoji Poor Communication Across Cultures. Scientia Fructuosa, 165(1), 162–176. https://doi.org/10.31617/1.2026(165)11
Zahra, T., Perono Cacciafoco, F., & Zamir, M. T. (2026). Data-Driven Reconstruction of the Singapore Stone: A Numerical Imputation Method of Epigraphic Restoration. Information, 17(2), 170. https://doi.org/10.3390/info17020170