Call for Help Digitizing HOTTP

Andrew Case is asking for volunteers to help digitize the Hebrew Old Testament Text Project volumes so that they can be easily distributed and translated. He has done initial AI-generated transcriptions and is asking for those with language/text-critical expertise to check and correct the transcriptions to ensure (and improve) accuracy using a user interface he has created for the purpose. If you have the relevant skills and would like to help make this resource more easily available, email him at andrewdcase [at] gmail [dot] com.

The Book of the Tales of Canterbury: A Critical Edition

Peter Robinson and Barbara Bordalejo announced the publication of their digital critical edition of some of Chaucer's (apparently wrongly named) Canterbury Tales. While the relevance for OTTC might not be obvious, a quick look at their edition might help give a little bit of vision of what an excellent digital edition of the Hebrew Bible text could look like in the 21st century. Robinson and Bordalejo have been at the forefront of developing tools and standards in the field, and they have been working on Canterbury Tales for many years. Their tools are in many ways similar to and in fact developed in relation to the Virtual Manuscript Room with which we are working to produce the Digital Critical Edition of the Hebrew Psalter. Congratulations to the editors for this great accomplishment, and I hope that scholars in our field will also catch the vision of what could be.

T'OMIM: Tanakh Observable Matches of Intertextual Mimesis

David Smiley has archived his T'OMIM: Tanakh Observable Matches of Intertextual Mimesis database on Zenodo. He provided the following description via Agade:

_______________________________________

A new dataset is now available that may be of interest to anyone working on inner-biblical allusion, synoptic parallels, or intertextuality more broadly. T'OMIM (תאומים, "twins" in Hebrew) is an open-access collection of labeled parallel passages in the Hebrew Bible, hosted on Zenodo.

Scholars have been cataloging parallelism and intertextual relationships since antiquity. But none of that accumulated work has existed until now in a structured, machine-readable format. T'OMIM was built to fill that gap.

The dataset pairs two corpora of known parallels. The first contains 554 narrative verse pairs drawn from the Chronicles synoptic tradition. The second contains 256 poetic half-verse pairs identified in the biblical parallelism literature. Both corpora are available at two levels of granularity: verse-level paired texts with source citations, and word-level tokens that carry the full ETCBC morphological annotation (part of speech, verbal stem, gender, number, person, lexeme, English gloss, and syntactic structure). Every word in every parallel passage is fully parsed.

For those working computationally, the word-level data can feed directly into natural language processing workflows. For scholars approaching these texts without a programming background, the verse-level files are structured as simple tabular data and can be opened in Excel or any spreadsheet application. Each row is a pair of passages, with columns for the source reference, the text, and the scholarly citation from which the parallel was drawn.

Coptic OT Trainee Position

Diliana Atanassova announced on Agade an opening for a trainee position on the Coptic Old Testament Project in Göttingen. See the opening and details below:

________________________________________

Dear Colleagues,

Our project, the Digital Edition of the Coptic Old Testament, at the Göttingen Academy of Sciences and Humanities in Lower Saxony is accepting applications for a trainee position beginning on the 1st of January 2026.

Further information about the position and application details can be obtained through the following link: https://coptot.manuscriptroom.com/blog/-/blogs/job-offer-trainee-positi-1

The deadline for applications is the 15th of October 2025. 

Please feel free to pass the information on to colleagues, students and any interested parties.

Many thanks and kind regards,

Diliana Atanassova

Dr. Diliana Atanassova, stellv. Arbeitsstellenleiterin
Niedersächsische Akademie der Wissenschaften zu Göttingen

Langzeitprojekt „Digitale Gesamtedition und Übersetzung
des koptisch-sahidischen Alten Testamentes“ 

DFG-Projekt AT 193/2–1 „Digitale Edition 
und wissenschaftliche Erschließung des
koptischen Paschalektionars“ 

Friedländer Weg 11
D-37085 Göttingen
diliana.atanassova@adwgoe.de

Job Opening on the Corpus Masoreticum Project

The Corpus Masoreticum project in Heidelberg has posted a postdoc job opening working on editing the Masorah of early Ashkenazi manuscripts. See the advertisement below from Agade:

_____________________________

POSITION RESEARCH FELLOW
The Center for Jewish Studies Heidelberg (Hochschule für Jüdische Studien Heidelberg ) offers a vacant job position for a

Research Fellow Jewish Studies / Masorah Research (E 13 100%; fixed-term employment), start: January 1, 2026idelberg

The Long Term Project (12 years; 2018–2029) Corpus Masoreticum: The Inculturation of the Masorah into Jewish Law and Lore from the 11th to the 14th Centuries: Digital Acquisition of a Forgotten Domain of Knowledge funded by the German Research Foundation in 2018 at the University of Jewish Studies Heidelberg is looking for an exceptionally qualified research fellow (Post-Doc) willing to contribute his/her specialist competences to this project.

For being considered you need to have:
-       A completed dissertation in Biblical and/or Jewish Studies.
-       Very good knowledge of Hebrew and Aramaic.
-       Profound knowledge in the culture and literature theories relevant to the Western European Medieval Jewish Culture.
-       Willingness to acquaint yourself with Masorah Research.
-       Capacity for teamwork.
-       Experience with project research.
-       If possible: Experience in Manuscript Studies.

Part of the job will be:

-       Edition and annotation of the entire Masorah (masora magna; masora parva) in selected Ashkenazi Bible Codices from the 11th to the 14th centuries.
-       Further development of the project.
-       Communication of your research and results within the project as well as within the teaching and research activities of the Center for Jewish Studies Heidelberg.
-       Scientific preparation of and contribution to conferences and workshops of the project.

The University of Jewish Studies Heidelberg offers the scope for individual academic development and an inspiring research environment. The conception and commencement of a habilitation at the University of Heidelberg in the course of the project is possible.
The language of communication within the project and for the publications is German and English.

The compensation is made according to TV-L (E13); the position is initially limited to 18 months from the start date but may be extended into the next funding period following an interim evaluation. Applicants with disabilities who possess essentially equal qualifications will be given preference. The University of Jewish Studies Heidelberg is an equal opportunity employer committed to excellence through diversity, and therefore explicitly encourages women to apply.

Please submit your application and the following required application documents electronically as one PDF file)
(1) Application letter (letter of motivation)
(2) Curriculum vitae
(3) List of publications
(4) Degree certificates

exclusively via email to: hanna.liss at hfjs.eu

Digital Latin Library

I recently learned from Hugh Cayless about the Digital Latin Library, a very useful resource for accessing digital editions of Latin literature. They also provide a number of helpful videos reflecting on the work of textual criticism in Latin literature.

Radiocarbon Dating, AI, and Paleography

Mladen Popovic et al. have published their long-anticipated article from the ERC project at the University of Groningen entitled The Hands that Wrote the Bible: Digital Palaeography and Scribal Culture of the Dead Sea Scrolls. The article describes the process of extracting new radiocarbon dates from a selection of Dead Sea Scrolls, digitally extracting quantifiable features of their scripts, and building an automated date estimation system called "Enoch." Roughly 80% of the resulting estimates agree with traditional, qualitative paleographical datings, but the results of both the radiocarbon dating and Enoch predictions suggests that several manuscripts throughout the series may well have been earlier than commonly supposed. This research moves the field forward considerably by adding quantitative, computational tools to aid paleographers that are not dependent upon conventional models for script development. In many cases, these new tools support previous approaches by grounding them in more secure dates derived from scientific analysis of the material remains instead of the handwriting style. But the results sometimes challenge conventional wisdom and have potential to help refine our understanding of Hebrew script development in the Hellenistic and Roman periods. Congratulations to everyone involved for a job well done and a significant contribution to the field!

For a popular-level news report on the publication, see Science.

*Disclaimer: I worked with Mladen et al. on the project for several years during the foundational stages of the research, but I was not a co-author for this academic article.

CEHP Updates Blog

In case you haven't seen it yet, we have started posting updates about our progress on the Critical Edition of the Hebrew Psalter website blog. Not only will this be the first digital and eclectic critical edition of the Hebrew Psalms, but we are also piloting a crowdsourcing campaign that is yielding wonderful results.

Perceptions of Writing in Papyri Recordings Online

The video recordings of presentations from the Perceptions of Writing in Papyri conference are now available online. This is a great overview of current work on how digital tools have impacted the study of ancient manuscripts.

HT Isabelle Marthot-Santaniello

Postdoc on Ben Sira and AI

Frédérique Rey has posted an advertisement for a postdoc doing interesting work on the textual history of Ben Sira:

Description

Before the appearance of the printing press, the only way of reproducing and spreading a text in written form was manual copying. During this process, accidents, errors and intentional modifications occurred, progressively modifying the text of each witness. The revised text, whether modified deliberately or accidentally, then served as a template for other copyists and the changes would thereby be propagated. For the philologist interested in the reconstruction of text history and the texts genealogical relations (similar to a genealogical tree, called stemma codicum), it has been imperative to study these different variants and suggest methods for the objective construction of such trees (called stemmatology methods).
Retrieving the genealogical lineage of the Hebrew manuscripts of the Ben Sira (book of Ecclesiasticus or Sirach) has been one of the major focus of the laboratoire Écritures at the University of Lorraine. In this project, we suggest to improve the manual work performed in the critical edition of the Hebrew manuscripts of Ben Sira by applying the latest advances in applied mathematics and natural language processing to reconstruct the stemmas of the Ben Sira’s Hebrew manuscripts. This initial work will then be extended to other textual traditions. This project takes place as a partnership between the center of researchs Écriture, LORIA and IECL.
In this context, we are looking for a two years fellow for a post-doctoral position, to fulfill the objective of building the genealogical lineage of the Hebrew manuscripts of Ben Sira through computational stemmatology algorithms.

Fellow’s responsibilities
Over the course of the project, the fellow will be asked to lead and innovate to complete the following objectives:

Analysis, classification and typology of Hebrew manuscripts variants The postdoc’s task will be to collate, analyze and classify by typology all the variants of the Ben Sira manuscript and several Dead Sea scrolls selected for the project (1QIsa, 1QS, etc.). They will also be responsible for training automatic variant analysis models between manuscripts.

Modelization of scribal behavior In collaboration with mathematicians, the postdoc will have to provide field expertise and insights into scribal behavior according to previous observations, leading to statistical models.

Comparison of automatic stemmata to manual stemmata In collaboration with computer scientists and NLP specialists, the postdoc will analyze the automatically generated stemma and compare them to the existing "manual" stemmata, and in particular to the stemmata of the Dead Sea Scrolls and the Cairo Genizah manuscripts.

Draw original conclusions regarding the Ben Sira’s manuscripts geneaology Given the finally selected stemma, the candidate will draw original conclusions regarding the Ben Sira textual tradition and discuss their results to draw new conclusions regarding manuscripts transmission.

Required skills
Hebrew skills

• The candidate must have a PhD in Religious Sciences, Jewish Studies, Theology or Ancient Hebrew Linguistic.
• An experience in linguistic analysis of ancient Hebrew large corpora.

Textual criticism

• An excellent knowledge and expertise in textual criticism, philology and biblical studies.
• A knowledge of stemmatology methods and the current state of the art.

Technical skills

• Basic knowledge of JSON and XML TEI encoding as well as collation tools.
• Basic knowledge of SQL and NoSQL database management would be a plus (e.g. mongodb, MariaDB).
• Being familiar with the Python ecosystem for data manipulation and analysis (pandas, sklearn, tensorflow, Keras), would be a plus.

The candidate is expected to have a good level in English. Knowledge of French would be a plus.

Terms and tenure
This two-year position will be based at the centre of research Ecritures (EA3943), Ile du Saulcy, 5700 Metz. The duration can not exceed 24 months.

The target start date for the position is 1st November 2023, with some flexibility on the exact start date.

IWCP 2023, San Jose

Thanks to Isabelle Marthot-Santaniello, I was able to attend the IWCP workshop on computational paleography at the ICDAR 2023 conference in San Jose, CA today. It was great to finally meet in person many with whom I had only interacted online in the past and to hear about the exciting work that is being done in the area of digital paleography.

Dominique Stutzmann started out with a keynote overview of the state of the art where he suggested that many of the basic problems in the field are essentially already solved (e.g., writer identification, style classification, dating), after which he pointed towards more difficult challenges that remain (e.g., degraded and/or small corpora, other difficulties in providing reliable labelled data). Momina Moetesum discussed a project on computerized restoration of broken ink strokes in Greek papyri, where they trained a network to be able to reconstruct Greek letters that had been artificially degraded. Vasiliki Kougia gave an update on a project using dated Greek literary hands to automatically classify (and date) Greek manuscripts. And Isabelle Marthot-Santaniello and Marie Beurton-Aimar presented their work on stylistic clustering based on clips of individual characters.

After the break, Julius Tabin discussed a project to capture and annotate Hieratic characters from facsimiles of Egyptian texts in a way that can be used to illuminate style development. Anguelos Nicolaou described an approach to quickly (manually) label regions on medieval charters to identify features for further analysis. In this presentation, he made the interesting observation that the more detail and discussion needed for a classification/label, the more likely that labelers will have difficulty providing consistent and clear labelling, so we should be careful of too much precision in labels. Of course, it is precisely the difficult, transitional, and contested areas that are generally of most interest to humanities scholars, as Dominique Stutzmann pointed out in the discussion. And Sojung Lucia Kim talked about a project using deep learning to classify Korean records in Chinese characters.

In the final discussion, two questions dominated. First, the question of whether manuscript dating is a problem of classification into discrete categories (e.g., date ranges by century) or regression (i.e., placing on a continuous timeline. The general consensus was that it depends upon the nature of the labelled data and what it allows. I pointed out that radiocarbon dating has much potential to change the nature of the data and allows for more regression models in corpora for which this hasn't in the past been possible, but this is still only a dream for many corpora. 

The second questions was whether it is better to create "end-to-end" products that move directly from input to the final desired result or "modular" products that break the process into various (intermediate) steps, each with their own data records. The modular approach actually (perhaps counterintuitively) decreases accuracy, but allows for the explication of various stages in the analysis that may be useful for humanities scholars. All in all, it was a great day of meeting and learning, and I'm very grateful to have been able to attend.

MIDRASH – Migrations of Textual and Scribal Traditions via Large-Scale Computational Analysis of Medieval Manuscripts in Hebrew Script

A recent news release describes the newly funded ERC Synergy Grant "MIDRASH – Migrations of Textual and Scribal Traditions via Large-Scale Computational Analysis of Medieval Manuscripts in Hebrew Script." Congratulations to all who are involved in this exciting new project to combine the latest in handwriting recognition and the KTIV database for Jewish manuscripts.

Digital Palaeography and Hebrew/Aramaic Scribal Culture Recordings Online

I am happy to announce that the recordings from the 2021 Groningen International Symposium "Digital Palaeography and Hebrew/Aramaic Scribal Culture" are now available online. These are great resources for those interested in the current state of digital paleography and the study of Hebrew/Aramaic scripts.

You can find the program and direct links on the conference web page.

The videos are hosted on the University of Groningen YouTube channel on a dedicated playlist. 

Virtually Unrolling New Dead Sea Scrolls

Ariel David gives a survey of ongoing work by Brent Seales and the IAA to virtually unroll additional Dead Sea Scrolls, beyond EGLev. These include a Herculaneum papyrus (which Seales is confident they will be able to read) and two more DSS: 4Q82 (4QXII^g) and 11Q4 (11QEzekiel).

Neo-Paleography: Analysing Ancient Handwritings in the Digital Age

Isabelle Marthot-Santaniello has posted videos with slides and audio for each of the presentations at the recent conference Neo-Paleography: Analysing Ancient Handwritings in the Digital Age (Basel, 27-29 January 2020). This is a great resource for understanding the current state of digital paleographic tools, especially for Hebrew, Greek, Coptic, and Latin scripts. See below the full conference program.

Programme

Monday 27 January

14:00	Welcome
14:15	Nachum Dershowitz, Adiel Ben-Shalom in abs., Lior Wolf in abs. (Tel Aviv): Computerized Paleography: Tools for Historical Manuscripts
14:45	Mladen Popović, Lambert Schomaker, Maruf Dhali (Groningen): Digital Palaeography of the Dead Sea Scrolls for Dating Undated Manuscripts
15:15	Gemma Hayes, Maruf Dhali (Groningen): Identifying Dead Sea Scribes: A Digital Palaeographic Approach
15:45	Discussion
16:00	Coffee break
16:30	Vinodh Rajan Sampath (Hamburg): Script Analyzer: A Tool for Quantitative Paleography
17:00	Timo Korkiakangas (Helsinki): Quantifying Medieval Latin handwriting with Script Analyzer
17:30	Elena Nieddu, Serena Ammirati in abs. (Roma): IN CODICE RATIO: a gateway to paleographical thesauri
18:00	Discussion
18:30	Buffet in Dep. Altertumswissenschaften (for the speakers)

Tuesday 28 January

9:00	Peter Stokes (Paris): (Still) Describing Handwriting: With Archetype and Beyond
9:30	Simona Stoyanova (Nottingham): The Python in the letterbox – epigraphic palaeography with Archetype
10:00	Lorenzo Sardone (San Marino): For a Palaeography of Demosthenic Papyri
10:30	Discussion
10:45	Coffee break
11:00	Yasmine Amory (Ghent): More than a simple intuition. Towards a categorisation of palaeographical features
11:30	Loreleï Vanderheyden (Heidelberg): How to unmask a digraph scribe? Apollos’ Greek and Coptic styles in the Aphrodito Byzantine Archive
12:00	Discussion
12:30	Lunch
14:00	Anne Boud’hors (Paris): Identifying hands and styles in the Coptic papyri from Edfu (Papas' archive)
14:30	Esther Garel (Strasbourg): The Fayyumic Coptic Documentary Papyri: Issues of Palaeography, Formats and Dating
15:00	Christian Askeland (Cambridge): On the History of the Alexandrian Majuscule
15:30	Discussion
15:45	Coffee break
16:00	Katharina Schröder (Münster): Searching for Relatives: Palaeographical Analysis of Coptic New Testament Manuscripts in the Institute for New Testament Textual Research Münster
16:30	Alin Suciu, Ulrich Schmid in abs. (Göttingen): Digital Support for a Paleographical Assessment of the White Monastery Manuscripts
17:00	Discussion
19:00	Dinner (for the speakers)

Wednesday 29 January

9:00	Marie Beurton-Aimar, Cecilia Ostertag in abs. (Bordeaux): Re-assembly Egyptian potteries with handwritten texts
9:30	Vincent Christlein (Nuremberg): Writer identification in historical document images
10:00	Imran Siddiqi (Islamabad): Dating of Historical Manuscripts using Image Analysis & Deep Learning Techniques
10:30	Discussion
10:45	Coffee break
11:00	Tanmoy Mondal (Montpellier): Efficient technique for Binarization, Noise Cleaning and Convolutional Neural Network Based Writer Identification for Papyri Manuscripts
11:30	Andreas Fischer (Fribourg): Recent Advances in Graph-Based Keyword Spotting for Supporting Quantitative Paleography
12:00	Discussion
12:30	Coffee break
14:00	Vlad Atanasiu, Peter Fornaro (Basel): On the utility of color in computational paleography
15:00 - 17:00	Visit of the Digital Humanities Lab and the papyrus collection in the University Library

Dhali et al. 2020 - Feature-extraction methods for historical manuscript dating based on writing style development

Maruf Dhali et al. from the Groningen ERC team just published a paper on the use of digital feature-extraction methods for dating Dead Sea Scrolls.

Maruf A. Dhali et al., “Feature-Extraction Methods for Historical Manuscript Dating Based on Writing Style Development,” Pattern Recognition Letters 131 (2020): 413–20. https://doi.org/10.1016/j.patrec.2020.01.027.

Highlights

•

Proposes feature-extraction techniques for dating of the Dead Sea Scrolls (DSS).

•

A grapheme-based method with a self-organized time map outperforms textural methods.

•

A codebook size of 225 performs the best with a Mean Absolute Error (MAE) of 23.4 years.

•

Cumulative Score (α = 25) improves with an increase in the sub-codebook size.

•

The result is positioned as a basic benchmark for further work on dating for the DSS.

Abstract

Paleographers and philologists perform significant research in finding the dates of ancient manuscripts to understand the historical contexts. To estimate these dates, the traditional process of using classical paleography is subjective, tedious, and often time-consuming. An automatic system based on pattern recognition techniques that infers these dates would be a valuable tool for scholars. In this study, the development of handwriting styles over time in the Dead Sea Scrolls, a collection of ancient manuscripts, is used to create a model that predicts the date of a query manuscript. In order to extract the handwriting styles, several dedicated feature-extraction techniques have been explored. Additionally, a self-organizing time map is used as a codebook. Support vector regression is used to estimate a date based on the feature vector of a manuscript. The date estimation from grapheme-based technique outperforms other feature-extraction techniques in identifying the chronological style development of handwriting in this study of the Dead Sea Scrolls.

Joint Venture of the FJMS and NLI!

Just announced... a new cooperation between the FJMS and NLI! This looks very promising for future resources for studying Hebrew manuscripts!

The Friedberg Jewish Manuscript Society (FJMS) and the National Library of Israel (NLI) are proud to announce a historic cooperation agreement

The Friedberg Jewish Manuscript Society (FJMS), and The National Library of Israel (NLI)  are proud to announce a historic cooperation agreement that will guarantee the long-term stability and development of the most advanced digital projects related to Hebrew manuscript research in the world, merging the cutting-edge resources of the FJMS with the NLI's vast collection. The NLI is the world's largest and most comprehensive repository of Jewish books, manuscripts, periodicals, and archives, in both physical and digital formats. The FJMS, for nearly twenty years, has developed multiple digital humanities projects designed to enable research into Hebrew manuscripts.  According to the newly signed agreement, the projects affiliated with the FJMS will be gradually integrated into the NLI's technological infrastructure, allowing the resources of both projects to mutually support one another. The FJMS's flagship digital initiative is the Friedberg Genizah Project, created under the Direction of Professor Yaacov Choueka, which allows scholars to view, read, and annotate hundreds of thousands of images of fragments and documents from the famed Cairo Genizah. The website's advanced technologies assist in identifying separate fragments that originally stem from the same document. The hundreds of thousands of visits to the site demonstrate its unparalleled contribution to learning and research. In addition, the FJMS sponsors Hachi Garsinan, a website that provides images and transcripts of textual variants of the Babylonian Talmud; Yad HaRambam, which will providea synoptic text of Maimonides' influential code of Jewish Law, based on early printings and manuscripts; an online collection of important Judeo-Arabic texts and annotated bibliography of the field; the comprehensive Sussmann Thesaurus of Talmudic Manuscripts; and the Yemenite manuscripts from the collection of Yehuda Levi Nahum.  FJMS is currently developing a Dynamic site where researchers can use unique tools to create synoptic transcriptions of textual variants of their choosing. The FJMS is the brainchild of Albert Dov Friedberg, a Toronto-based philanthropist and investment manager, whose concern for Jewish sacred texts has made him a leading supporter of Jewish manuscript research. Over the course of 125 years, the National Library of Israel has developed into the world's leading Judaica library. Through its current renewal process the NLI has also now emerged as a technological leader, with a world-class online catalog and digital presence. Particularly relevant in this context is Ktiv: The International Collection of Digitized Hebrew Manuscripts, which aims to provide centralized online access to all of the world's Hebrew manuscripts. Millions of images of nearly 50,000 manuscripts are already available on the Ktiv website (ktiv.nli.org.il), which was launched in August 2017.  Ktiv is a joint venture of Albert D. and Nancy Friedberg through FJMS and the National Library of Israel, in cooperation with the Israeli Ministry of Jerusalem and Heritage's Landmarks project. According to Oren Weinberg, Director General of the NLI, this agreement will "bring the technological developments of both bodies into conversation with one another, allowing the best minds and products of the Jewish digital humanities to cross-pollinate." Albert Dov Friedberg added, "Our agreement assures that this work, to which I have dedicated so much of my concern and resources, will continue to grow, develop, and be preserved into the future."

LAB Blog Post on Two Significant Uses of the Dead Sea Scrolls

I just posted a short blog post on two ways to use Logos Bible Software Dead Sea Scrolls resources to help in Biblical Studies. Thanks to Tavis Bohlinger and Logos for the opportunity!

A Digital Palaeographic Approach towards Writer Identification in the Dead Sea Scrolls

The University of Groningen and KU Leuven ERC project "The Hands that Wrote the Bible: Digital Palaeography and Scribal Culture of the Dead Sea Scrolls" has produced its first publication, A Digital Palaeographic Approach towards Writer Identification in the Dead Sea Scrolls. Congratulations to Maruf, Sheng, Mladen, Eibert, and Lambert for a job well done, as well as to Ruwan van der Iest for all of his behind-the-scenes work on this pilot project. This article was an attempt to use digital images of the Dead Sea Scrolls to determine how accurately existing digital tools are able to distinguish the scripts of samples from a limited number of scribes from different parts of documents and across different documents considered by paleographers to have been written by the same scribe. The computer ranks all samples in relation to a query sample and produces a ranked hitlist of samples that most closely match the query sample. Overall competence in automated handwriting recognition peaked at 80% correct identification of the scribe in the first position in the hitlist. The ability of the computer to correctly place samples of the scribe within the top 10 of the hitlist peaked at about 95%. These results will provide an important benchmark as we now seek to increase our precision by using the higher-quality IAA images and tailoring the measured features better to our documents. The field of paleography of the Dead Sea Scrolls is now well on its way to becoming truly digital, and it will be exiting to see the results over the next couple of years.

Abstract

To understand the historical context of an ancient manuscript, scholars rely on the prior knowledge of writer and date of that document. In this paper, we study the Dead Sea Scrolls, a collection of ancient manuscripts with immense historical, religious, and linguistic significance, which was discovered in the mid-20th century near the Dead Sea. Most of the manuscripts of this collection have become digitally available only recently and techniques from the pattern recognition field can be applied to revise existing hypotheses on the writers and dates of these scrolls. This paper presents our ongoing work which aims to introduce digital palaeography to the field and generate fresh empirical data by means of pattern recognition and artificial intelligence. Challenges in analyzing the Dead Sea Scrolls are highlighted by a pilot experiment identifying the writers using several dedicated features. Finally, we discuss whether to use specifically-designed shape features for writer identifica tion or to use the Deep Learning methods on a relatively limited ancient manuscript collection which is degraded over the course of time and is not labeled, as in the case of the Dead Sea Scrolls.