Daniel Kinitz: Deep Learning-Based OCR of Printed Arabographic Resources. Challenges and Best Practices in a Production Environment

While optical character recognition for printed Arabic and other right-to-left scripts has been principally solved, production-level deployment continues to pose critical challenges. These include demands of scale and precision, such as achieving near-perfect word accuracy, while navigating constraints like limited human resources and continually advancing technologies. Drawing on a use case centred on premodern named entities, we explore these challenges and identify best practices from a data engineering perspective. Rather than focusing on software development, the discussion addresses the practical realities of applications that remain perpetually evolving. Within this context, best practices designate kraken as the preferred OCR engine and eScriptorium as the primary tool for manual data manipulation.

Stefanie Brinkmann (ed.): Marginal Matters: Explorations into Commenting and Glossing Techniques in Arabic Manuscript Cultures

Verena Klemm: “At the High End of Learning: Note-Taking and Commentary Practices of a Nineteenth-Century Ismaili Scholar in India”

Stefanie Brinkmann: “Traces of Eager Studies”

Stefanie Brinkmann: “Struggling with the Margin: Studying Marginal Commentaries in a Hadith Collection: Al-Baghawī’s Maṣābīḥ al-sunna”

Stefanie Brinkmann: “Multilingualism in Ottoman Manuscripts” (revised reprint)

Stefanie Brinkmann: “Introduction: Mapping the Field”

Boris Liebrenz: “Putting Margins in Context: Some Practical Considerations”

Boris Liebrenz: “Partisan Readers: Fighting over the Interpretation of History in the Margins of MS BnF, Arabe 1825”

Boris Liebrenz and Moya Carey: New Blog "Reading the History of the Chester Beatty Fihrist"

Reading the History of the Chester Beatty Fihrist — Arabic Literature’s Foundational Book-List

Verena Klemm: "A Library in One Volume – The Notebook of the Nineteenth-Century Ismāʿīlī Scholar Sayyidī Muḥammad ʿAlī al-Hamdānī from Surat"

Boris Liebrenz: "The Arabic Aristotle in Byzantine Constantinople"

Stefanie Brinkmann: "Hadith Scholarship in Mongol Baghdad: al-Qazwīnī’s transmission of al-Baghawī’s Maṣābīḥ al-sunna”

Verena Klemm: "Effiziente Netzwerke – Hintergründe eines Handschriftenerwerbs"

Boris Liebrenz: “From Whom and for Whom? The Audience and Provenance of al-Jazzār’s Manuscripts”

Boris Liebrenz: “The Endowment Seals,” in The Library of Aḥmad Pasha al-Jazzār

Boris Liebrenz: “The Stars in Leiden: Listening to the Stories of Islamic Manuscripts”

Boris Liebrenz: Review of Ahmed El Shamsy, Rediscovering the Islamic Classics

Verena Klemm: A Library in One Volume: The Notebook of the Nineteenth-Century Ismāʿīlī Scholar Sayyidī Muḥammad ʿAlī al-Hamdānī from Surat

Verena Klemm: The Ismaʿili Manuscripts in University Library Tübingen: An Inquiry into Provenance

Verena Klemm: Notes About Notes: A 19th Century Ismaʿili Personal Manuscript From India

Stefanie Brinkmann: Contribution to “Exit Allowed: Iranian Artists meet Iranian Manuscripts”

Boris Liebrenz: "The Sciences in Two Private Libraries From Ottoman Syria," in: Routledge Handbook on the Sciences in Islamicate Societies, ed. Sonja Brentjes (London: Routledge, 2022), 787-797.

https://www.taylorfrancis.com/chapters/edit/10.4324/9781315170718-70/sciences-two-private-libraries-ottoman-syria-1-boris-liebrenz

Nadine Löhr: Off the Record - On Studying Lost Arabic Books and their Networks

Daniel Kinitz/Thomas Efer: Towards a Dynamic Knowledge Graph of a Non-Western Book Tradition

Introduction: How can we generate and integrate data on a pre-modern, Arabic book tradition in such a way that research can gain new insights? Within the long-term project “Bibliotheca Arabica” [Brinkmann/Löhr 2021], we are creating an agile knowledge graph integrating a wide range of data on (handwritten) Arabic manuscripts and their historical context. Our aim is to create a digital research environment to investigate the production, transmission and reception of Arabic manuscripts and their social environment as clusters of linked entities: scholars linked to works with students as readers, reproduced by scribes in manuscripts, linked by ownership notes and combined to historical libraries, etc.

Tariq Yousef/ Daniel Kinitz : Similarity-Based Clustering of Pre-Modern Arabic Names

Introduction: Data repositories must manage the identity of their entities. In the case of intellectual history, the challenge lies in premodern, and therefore non-standardised entity names. Our use case deals with Arabic persons related manuscripts (scholars, scribes, etc.). Thus, multiple occurrences of the same person with different spellings and name compositions must be identified and disambiguated. This paper presents a graph clustering approach that combines literal and numerical properties (name and year of event) with promising results. The particular challenge lies in the vast variability of name variants and sometimes unspecific dates.

Blecher, Joel and Brinkmann, Stefanie (eds.): "Hadith Commentary. Continuity and Change"

Blecher, Joel and Brinkmann, Stefanie (eds.): Hadith Commentary. Continuity and Change, Edinburgh: Edinburgh University Press 2023.

Brinkmann, Stefanie: “Between Philology and Hadith Criticism: The Genre of Sharḥ Gharīb al-Ḥadīth”

Brinkmann, Stefanie: “Between Philology and Hadith Criticism: The Genre of Sharḥ Gharīb al-Ḥadīth”. In: Blecher, Joel and Brinkmann, Stefanie (eds.): Hadith Commentary. Continuity and Change, Edinburgh: Edinburgh University Press 2023.

Verena Klemm: "Hidden Literary History. Ismaʿili Tradition in Syria"

Boris Liebrenz: "Curious Readers: The Bodleian’s Book of Curiosities as a Fatimid View of the World Through Ottoman Eyes"

Boris Liebrenz: "Curious Readers: The Bodleian’s Book of Curiosities as a Fatimid View of the World Through Ottoman Eyes," Journal of the Economic and Social History of the Orient 64 (2021), 404-424. https://brill.com/view/journals/jesh/64/4/article-p404_3.xml