Originally published on the Department of Art & Archaeology.

In the 1930s, the Excavation of the Athenian Agora commissioned M. Messinesi to photograph the Vrysaki neighborhood at the center of Athens before demolishing it to begin digging.  After that, the “lost neighborhood” existed only in Messinesi’s work, split between a set of lantern slides in the archives of the Agora excavation, and the Messinesi Photographs Collection, housed in the Department of Art & Archaeology’s Visual Resources (VR) collections.  In summer 2025, the intensive five-day workshop “Visualizing the Past: Mapping Athens’ Lost Neighborhood” brought together a group of nine graduate students from Princeton and Greece to digitally revive it.

Hosted by the Princeton Athens Center, the workshop focused on the theory and practice of digital mapping in the humanities, critically engaging with a variety of historical sources, utilizing tools and methods for spatial analysis, and creating visual representations of complex historical narratives. 

As part of an ongoing partnership between Princeton’s Center for Digital Humanities (CDH) and Seeger Center for Hellenic Studies, the workshop drew on expertise from VR and Princeton University Library, as well as partners from the MSc Program in Digital Methods for the Humanities at the Athens University of Economics and Business (AUEB) and Cyprus Institute. Leading the workshop were CDH’s executive director Natalia Ermolaev, VR’s Curator of Asian Collections and Digital Specialist Yichin Chen, and Digital Scholarship Specialist at Princeton University Library Bryan Winston.

“This workshop exemplifies what makes digital humanities summer institutes so valuable—they create a space where humanists and technologists can work side-by-side, bringing their different disciplinary perspectives to bear on complex historical questions,” said Ermolaev. “We’re not just practicing cross-disciplinary collaboration, we’re actively building intellectual bridges between institutions and scholars in the US and Greece. When you have an international group with archaeologists, architects, historians, computer scientists, and curators working together to tell the story of a complex cultural moment, you get richer conversations, more innovative approaches, and lasting international partnerships that extend well beyond the workshop itself.”

Workshop participants stemmed from a variety of disciplines including history, archeology, comparative literature, cultural heritage management, and computer science. “The workshops created a collaborative environment where participants could share methods, critique, and ideas,” said participant Florian Endres, Ph.D. Candidate in the Department of Comparative Literature. A&A graduate student Katy Knortz agreed “It was a real strength of the program that, rather than focusing on a single discipline, it encouraged cross-disciplinary engagement and truly collaborative discussions.”

Examining the Messinesi Photographs Collection in A&A’s Visual Resources

To open the workshop, VR’s Yichin Chen introduced participants to Messinesi’s collection of 75 photographic prints, part of VR’s larger Homer Thompson Collection.  

The series also includes an original map hand-drawn from 1930 which indicates the location and angle from which each photograph was taken. “It is uncommon for a photographer to document both the location and angle of each photograph. The map of Vrysaki is therefore an invaluable resource and a primary source for reconstructing the lost neighborhood,” said Chen. “By connecting the 75 points marked on the map, we are able to gain a rare glimpse into a forgotten community that once existed.”

In addition, Chen described her digitization of VR’s extensive collection of Greek glass lantern slides. This unique collection contains over 4000 high-quality slides depicting sites, monuments, and aspects of daily life across Greece between 1920 and 1940. In Chen’s presentation, she outlined both the methodologies employed and the challenges encountered in developing a digital project, with particular emphasis on the critical role of cataloging and data management.

“Data wrangling and management are essential yet frequently overlooked components of digital projects,” said Chen. “By revealing the process behind the scenes, we wanted to share practical methodologies and the importance of long-term data preservation with the participants.”

Director of VR Julia Gearhart is thrilled to see collections brought to life. “Our efforts to digitize these collections are not only to allow remote researchers access to these resources, but also to encourage their use in innovative, interdisciplinary, projects like this one,” she said.  Facilitating this kind of scholarship, Leigh Anne Lieberman, the Digital Project Specialist in A&A, also works closely with faculty and students in the department and beyond to develop data-driven, digital initiatives that highlight VR’s unique collections.

Inside the Digital Bootcamp

Throughout the course of the workshop in Athens, participants were taught the complete life cycle of a mapping project from idea to prototype, investigating best practices in digital mapping as well as digital project and data management generally. 

“We had hands-on sessions with each tool that could advance the project and shared alternative tools,” said Winston. “As we worked, we explored the features and limitations of each tool and how each decision during the project life cycle is contingent on the previous. Through this process, we communicated how to think critically about these tools and their outputs,” said Winston. “Humanists are well-trained in being critical of their sources, so the participants were very receptive to applying their discerning eye—a skill equally important as learning how to use the tool itself—to the tools we used.” Iteration was also important to the discussion on digital mapping. “By iterating over our data, and then different versions of our maps, we highlighted one of the major benefits of applying computational methods to your research,” said Winston. “We can identify unnoticed patterns and ask new questions of our research.”

“The clear and methodical approach made the material easy to digest and also provided a useful mental map for applying these methods in my own research,” said  Knortz. “One of the most valuable aspects of the workshop was discovering the sheer range of digital tools available to scholars. Being introduced to different options for collecting, cleaning, and manipulating data helped me understand how to prepare for each stage of a digital project.”

Using case studies of digital humanities projects focused on monuments and areas that are no longer accessible, the group explored tools like ESRI’s ArcGIS StoryMaps, LeafletJS, and others. Armed with this training, participants designed maps that spatialized the important resources created by Messinesi. 

Reviving a Lost Neighborhood, In Virtual Situ

Putting digital tools into practice, the group turned their focus on the Vrysaki neighborhood and Messinesi’s visual evidence of it. 

Facilitating this, a highlight of the workshop was the presentation and tour of the Athenian Agora by Sylvie Dumont, author of Vrysaki: A Neighborhood Lost in Search of the Athenian Agora. “Walking the site with her, amid fragments of stone and layers of urban memory, left a deep impact on me and sharpened my understanding of how loss, excavation, and narrative intersect in the Athenian landscape,” said Endres.

Participants grappled with the tension between the now visible Ancient Agora and the demolished neighborhood of Vrysaki. “The focus on mapping ‘lost’ urban spaces invited reflection on issues of historical memory, cultural preservation, and the ethical stakes of digital reconstruction,” said Endres. 

With a better sense of place, participants began constructing a dataset that could be mapped. They used OpenRefine to wrangle the descriptive data. “The biggest challenge was associating coordinates with photographs of buildings that no longer existed and had no corresponding street addresses,” explained Ermolaev. To proceed, participants learned about MapWarper, a geo-reference tool that allows you to render an image on a coordinate grid. After overlaying Messinesi’s hand drawn map over a modern map, participants were then able to associate coordinates with photograph markers. This made it possible to map the images and create a prototype reconstruction of Vrysaki. To complement the technical skills to make it possible to create a digital map, participants shared critical reflections about their data and the challenges of representing research spatially. Participants were also introduced to more advanced software and projects, such as 3D renderings of lost buildings and ways of fostering engagement with this cultural heritage. “In all, participants walked away with a usable dataset and a map prototype that fostered ideas for their own projects while also gaining a sense of what is possible for a larger scale project in the future,” said Winston.

“The program has significantly advanced my dissertation research, which focuses on theories of displacement, media, and memory—especially as exemplified by Sigmund Freud’s 1904 visit to Athens,” said Endres. “I was able to begin developing a spatial reconstruction of Freud’s journey through the city using georeferencing and map annotation via tools such as StoryMaps. This hands-on experience helped me prototype the integration of archival documents, correspondence, and visual reference points into a dynamic, research-driven digital map.” “I left the program not only with technical skills and scholarly momentum,” said Endres, “but also with a renewed sense of connection to the material I study.”

Visual Resources Research Award

To encourage use of VR’s rich collections, A&A has established the Visual Resources Research Award to support a short-term residency allowing scholars to work with materials in person.  VR’s collections include archival material from various archaeological expeditions undertaken by members of the department in Sardis (Turkey), Antioch-on-the-Orontes (Turkey), Morgantina (Sicily), Polis (Cyprus), and Syria. These also include faculty photograph collections such as the A. Sheldon Pennoyer Collection featuring Italian monuments in the aftermath of World War II, the records of Byzantinist Kurt Weitzmann, and documentation of the restoration of Hilandar Monastery in Mount Athos by Slobodan Nenadović, to name just a few.

Visual Resources is currently accepting applications for the 2026 Research Award. Applicants should submit their C.V. and a letter of interest to visres@princeton.edu by November 1, 2025. 

Forging the future of text recognition for research focused on historical manuscripts, the Source Codes of the Past (SCOOP) conference connected an international network of experts at the Institute for Advanced Studies (IAS) in Princeton in June 2025. 

Collaborative in every regard, the conference was organized by Professor of History Helmut Reimitz, Center for Digital Humanities (CDH) Postdoctoral Research Associate Christine Roughan, and History Ph.D. candidate Lucia Waldschuetz, along with Professor of Medieval Studies at the IAS Suzanne Akbari and CDH Executive Director Natalia Ermolaev.  The launch of this network was a joint venture of the IAS, Princeton Humanities Initiative (PHI), the CDH, the Manuscript, Rare Book, and Archival Studies Initiative (MARBAS) and the Institute for Medieval Research at the Austrian Academy of Sciences. Along with the organizers, the Center for Collaborative History, Department of Classics, the Seeger Center for Hellenic Studies, the Program in Medieval Studies and the Committee for the Study of Late Antiquity also joined in sponsoring the workshop. 

“Fostering collaboration is a major goal of the Princeton Humanities Initiative, and SCOOP brings together teams that are working across institutions, disciplines, and countries to advance our ability to learn about the past and inform our future.” 
— John Paul Christy, Executive Director, Princeton Humanities Initiative

Humanities and social science scholars, software engineers, and machine learning researchers—some wearing several hats—pooled their expertise, mutually informing one another’s understanding of automatic text recognition (ATR) and handwritten text recognition (HTR) technologies. This intensive think tank centered the challenge of adapting existing technologies for diverse scripts, textual traditions, and manuscript structures, especially for understudied languages and materials. Given the long-running separate streams of time and resource investment devoted to developing these projects, the convening of project leaders to share successes and challenges represents an efficiency windfall.

“AI and machine learning tools for text recognition are transformative—not only for deciphering individual manuscript traditions, but for enabling large-scale, comparative research that brings diverse cultural histories into meaningful conversation with one another,” said Ermolaev. “As these technologies become more sophisticated, it is essential that humanists are at the table, helping shape how these tools are designed and deployed. Scholars of historical languages and cultures bring deep knowledge that is critical to developing more accurate, ethical, and inclusive AI systems. The long-standing collaboration between humanists and technologists in digital humanities is more urgent than ever, as we work together to ensure that the cultural data of the past informs the technological futures we’re building today.”

“The long-standing collaboration between humanists and technologists in digital humanities is more urgent than ever, as we work together to ensure that the cultural data of the past informs the technological futures we’re building today.” 
— Natalia Ermolaev, Executive Director, CDH

Presenter Tobias Hodel (University of Bern) underscored the importance of leaning into the ATR/HTR community of stakeholders and experts.  Having bested the tech hurdle, he said, the critical question “what’s next?” requires a collaborative answer.  Achim Rabus (University of Freiburg) agreed that discussion between parties is imperative, as is sufficient training.  He noted the debilitating gap between those with technological and humanistic expertise, underscoring the importance of elevating training for both to arrive at maximum usability. Evaluating output anomalies of a program, for example, requires a collaborative examination when faced with the recurring problem: “We don’t know if it’s a bug or a feature.” Among definitive features, Achim pointed to strides and further opportunities in smart transcription, which automatically interprets and expands abbreviations in original text. 

Benjamin Kiessling (Paris Sciences et Lettres University) campaigned for new text reader models to resolve the lingering problem that bespoke models cater to niche research questions. What’s needed, he said, is a way to align output with research questions and allow models to become more interchangeable or generalized. With this goal in mind, Kiessling has developed PARTY, or Page-wise Recognition of Text. 

The workshop illustrated that when stakeholders work together across functions and areas of expertise, the boon for scholarship can be exponential. Using technology to make manuscripts accessible to scholars in languages unfamiliar to them allows for connections heretofore left on the table. This democratization of knowledge, said Achim, is game-changing. 

Launching a Graduate Student Text Recognition Technology Boot Camp

The conference included a comprehensive three-day ATR/HTR Training Workshop designed to train graduate students and scholars with various experience levels and backgrounds in text recognition technology. Led by instructors Helmut Reimitz, Christine Roughan, Anna Michalcová, Martin Roček, and Jan Odstrčilík, the workshop provided a structured progression from technical fundamentals to practical application. 

“We took care to structure the workshop so that it would offer training relevant to researchers working in any historical written tradition, because the underlying methods of ATR are not limited by language or discipline,” shared Roughan. “We were pleased to be joined by participants from history to NES, from art & archaeology to music as a result.”

The first day covered introductory concepts, including how HTR/ATR works technically, available ATR tools, and the basics of key platforms such as Transkribus and eScriptorium. The second day delved into the practicalities of using such platforms, covering topics such as layout and model training, data formats, and methodological considerations for both Latin and non-Latin scripts. The last day of the training workshop turned to the practicalities of using text recognition tools and outputs in research: HTR model evaluation, data sharing through platforms such as Zenodo and GitHub, and techniques for developing custom models using existing published models. Supervised hands-on practice sessions were conducted throughout to reinforce learning objectives.

“Knowing how to use the tools is just step one,” said Roughan. “The scholarly community continues to publish a wealth of data and models – knowing how to interact with and build upon that foundation empowers people to get the most out of research using text recognition methodologies.”

“Knowing how to use the tools is just step one. The scholarly community continues to publish a wealth of data and models – knowing how to interact with and build upon that foundation empowers people to get the most out of research using text recognition methodologies.” 
— Christine Roughan, Postdoctoral Research Associate, CDH

SCOOP 2.0

By all accounts, the conference exceeded its goals. “It was an amazing and extremely encouraging start for the network,” said Reimitz. “Everyone agreed that a platform for exchanging ideas between AI experts, computer scientists, and humanities scholars is urgently needed in order to take the application of HTR in the humanities to the next level.”

Paving the way to that next level, a second SCOOP workshop is already in the making. Hosted by the Austrian Academy of Sciences, SCOOP will reconvene in Vienna in summer 2026.

In the meantime, members of the SCOOP network are working to establish a digital communication platform to evolve conversations on the implementation of text recognition tools in diverse projects involving various languages, scripts, layouts, and visualizations in original manuscripts and documents.  Furthermore, the forum facilitates shared experimentation and modeling. “As an important focus, we agreed in Princeton on the question of interoperability issues and experiences with large established engines and smaller research groups working on under-resourced scripts and languages,” said Reimitz.

SCOOP partners, the Princeton Humanities Initiative, Center for Digital Humanities, Institute for Advanced Study at Princeton, and the Austrian Academy, are committed to carrying forward the momentum of this inaugural SCOOP conference.  “Fostering collaboration is a major goal of the Initiative,” said Christy, “and SCOOP brings together teams that are working across institutions, disciplines, and countries to advance our ability to learn about the past and inform our future.”

“It was an amazing and extremely encouraging start for the network. Everyone agreed that a platform for exchanging ideas between AI experts, computer scientists, and humanities scholars is urgently needed in order to take the application of HTR in the humanities to the next level.”
— Helmut Reimitz, Professor of History

To join the SCOOP network or learn more: scoop@oeaw.ac.at, croughan@princeton.edu, anna.michalcova@oeaw.ac.at.