Name: 2ⁿᵈ Exchange Meeting of SCOOP: International Network for Automated Text Recognition of Historical Sources
Start: 2026-09-07T08:00:00+02:00
End: 2026-09-09T19:00:00+02:00
Location: University of Vienna

2ⁿᵈ Exchange Meeting of SCOOP: International Network for Automated Text Recognition of Historical Sources

from Monday, September 7, 2026 (8:00 AM) to Wednesday, September 9, 2026 (7:00 PM)

Monday, September 7, 2026

9:00 AM Registration
Registration
9:00 AM - 10:00 AM

10:00 AM Plenary: Welcome
Welcome
10:00 AM - 10:15 AM
Room: Room 1
10:15 AM Keynote: Keynote
Keynote
10:15 AM - 11:30 AM
Room: Room 1
Contributions

10:15 AM The Transcription/Edition Distinction as a Foundation for Trustworthy Automatic Text Recognition - Thibault Clérice
11:30 AM Coffee break
Coffee break
11:30 AM - 12:00 PM
12:00 PM Working Group 1: WG1-1 - Technologies & Architectures
WG1-1 - Technologies & Architectures
12:00 PM - 1:30 PM
Room: Room 1
Contributions

12:00 PM Large Scale Approaches: Party - Benjamin Kiessling (ALMAnaCH, Inria)

12:20 PM VLM Input – Fine-tuning VLMS - William Mattingly

12:40 PM AnandaSky - Colin Brisson (EPHE Paris)

1:00 PM Metatools & Technological Agnosticism - Andy Stauder (READ COOP)
1:30 PM Lunch
Lunch
1:30 PM - 2:30 PM
2:30 PM Working Group 4: Language Challenges I
Language Challenges I
2:30 PM - 4:00 PM
Room: Room 3
Contributions

2:30 PM Four Scripts, Five Languages, One Digitalization Challenge - Ana Mihaljević (Institute for the Croatian language)

2:50 PM Matchbox: creating a combined recognition model for early medieval Celtic languages and Latin - Bernhard Bauer

3:10 PM Promising results for under-resourced languages : use cases on Arabic, Greek and Chinese - Baptiste Queuche

3:30 PM Using ATR of Yiddish to study language change - Seth Kulick
Working Group 1: Training as a continuous process
Training as a continuous process
2:30 PM - 4:00 PM
Room: Room 1
Contributions

2:30 PM Piloting HTR in the Library: Experiments and Groundwork - Doug Emery (UPenn)

2:50 PM Multi-Model OCR Arbitration: High-Precision OCR for 19th Century Administrative Mass Sources - Wolfgang Goederle (Graz/Passau)

3:10 PM From PDF to mARkdown: A Scalable Arabic OCR Pipeline for expanding the OpenITI Corpus - Alicia González Martínez (Universität Hamburg)

3:30 PM Anagnostes - Towards a Transformer-based OCR System for Ancient Greek Papyri - Anton Repushko Elena Chepel (University of Vienna)
Working Group 3: Transcription approaches I (Palaeography in focus)
Transcription approaches I (Palaeography in focus)
2:30 PM - 4:00 PM
Room: Room 2
Contributions

2:30 PM Computational Paleography through Automatic Text Recognition - Benjamin Kiessling (ALMAnaCH, Inria)

3:00 PM Towards Geometry-Based Scribal Hand Analysis: A Word-Level Graphometric Framework for Arabic Manuscripts - Sajjad Nikfahm-Khubravan (Roshan Institute for Persian Studies)

3:30 PM Leveraging HTR corpora for morphological and metrological paleographical analysis - Malamatenia Vlachou (IRHT/LIGM IPParis)
4:00 PM Coffee break
Coffee break
4:00 PM - 4:30 PM
4:30 PM Working Group 4: Language Challenges II
Language Challenges II
4:30 PM - 6:00 PM
Room: Room 3
Contributions

4:30 PM Dark Vellum, Dense Diacritics: Challenges in Training HTR Models for Medieval Icelandic - Katrín Lísa van der Linde Mikaelsdóttir

4:50 PM Impacts of Script Features on Text Recognition: Experiments with Greek and Arabic - Christine Roughan

5:10 PM Syriac Manuscripts That Can Talk: Giving Voice to Under-Resourced Scripts in HTR - Ephrem Ishac
Working Group 1: Experimental approaches
Experimental approaches
4:30 PM - 6:00 PM
Room: Room 1
Contributions

4:30 PM Utilization of the Open WebUI platform in Arkindex - Michal Racyn (Masaryk University)

4:50 PM Comparing HTR engines with Polyscriptor - Achim Rabus

5:10 PM Fichero and the Circuit Court Archive of Istmina: An AI Workflow App for Researchers - Daniel Tubb

5:30 PM Document Layout Analysis for Glossed Medieval Manuscripts: Comparing Kraken 6 and YOLO26 - Tristan Repolusk (University of Graz)
Working Group 3: Transcription approaches II (Transcription decisions, their effect, and related terminology)
Transcription approaches II (Transcription decisions, their effect, and related terminology)
4:30 PM - 6:00 PM
Room: Room 2
Contributions

4:30 PM Otto Dei gram, rogat vram Clam. From facsimile and descriptive transcriptions to “quasi-diplomatic” and interpretative approaches in ATR/HTR - Jan Odstrčilík (Institut für Mittelalterforschung, ÖAW)

4:50 PM Lost in Transcription? Reconciling HTR Output with Old Czech Editorial Standards - Anna Michalcová (Czech Academy of Sciences / IMAFO, ÖAW)

5:10 PM HTR of Normalized Latin Texts: Insights from Liturgical Manuscripts - Paweł Figurski (Polish Academy of Sciences)

5:30 PM Reading Glagolitic in the Twenty-First Century: Between Philology, HTR, and AI - Ana Mihaljević (Institute for the Croatian language)
6:00 PM Break
Break
6:00 PM - 6:15 PM
6:15 PM Keynote
6:15 PM - 7:30 PM
Room: Room 1
Contributions

6:15 PM New Epistemic Frontiers: LLMs for Linking Transcription, Editing, and Interpretation - Anna Dolganov David Smith (Northwestern)
7:30 PM Reception
Reception
7:30 PM - 9:00 PM
Tuesday, September 8, 2026
10:00 AM Working Group 5: Datasets and Institutions
Datasets and Institutions
10:00 AM - 11:30 AM
Room: Room 2
Contributions

10:00 AM Pipelines and Workflows - Jessie Dummer

10:20 AM Manuscriptorium Full-Text Module – The newest component of the Manuscriptorium digital library - Michael Lužný

10:40 AM How do you revive a legacy dataset? - Tim Geelhaar

11:00 AM The current status of the field of HTR within the German manuscript centres - Ursula Stampfer
Working Group 6: Leveraging Outputs: Text Reuse, NLP, and More (talks)
Leveraging Outputs: Text Reuse, NLP, and More (talks)
10:00 AM - 11:30 AM
Room: Room 3
Contributions

10:00 AM Testing the Reuse Value of Pracalit Ground Truth for Bhujimol Manuscripts - Alexander O'Neill

10:30 AM From Old Icelandic HTR Outputs to Normalised Texts through Seq2Seq Transformers - Nikola Krisztian Czindrity

11:00 AM New Ways to Transform and Explore Older Korean Texts: From ATR to Reading Texts to Agentic Retrieval in Mo文oNExplorer - Seth Kulick
Working Group 1: Roundtable
Roundtable
10:00 AM - 11:30 AM
Room: Room 1

11:30 AM Coffee Break
Coffee Break
11:30 AM - 12:00 PM

12:00 PM Working Group 4: Roundtable 🎤 - Language Challenges
Roundtable 🎤 - Language Challenges
12:00 PM - 1:30 PM
Room: Room 2
Working Group 6: Leveraging Outputs: Text Reuse, NLP, and More (demos)
Leveraging Outputs: Text Reuse, NLP, and More (demos)
12:00 PM - 1:30 PM
Room: Room 3
Contributions

12:00 PM New Ways to Transform and Explore Older Korean Texts: From ATR to Reading Texts to Agentic Retrieval in Mo文oNExplorer - Wayne de Fremery

12:30 PM From Document Images to Research Catalogue - Andrew Janco

1:00 PM TBD - Martin Roček
Working Group 2: Handwriting Classification I
Handwriting Classification I
12:00 PM - 1:30 PM
Room: Room 1
Contributions

12:00 PM Classifying Squeezes Again: Initial Results from an ICDAR Contest - Aaron Hershkowitz

12:30 PM Communities of Practice: Capturing the Aspect of Late Medieval Handwriting - Sam Grieggs Sebastian Sobecki

1:00 PM Script classification and alphabet identification - Giuseppe de Gregorio
1:30 PM Lunch
Lunch
1:30 PM - 2:30 PM

2:30 PM Working Group 6: Unconference
Unconference
2:30 PM - 4:00 PM
Room: Room 3
Working Group 2: Handwriting Classification II
Handwriting Classification II
2:30 PM - 4:00 PM
Room: Room 1
Contributions

2:30 PM [TBD - Handwriting classification] - Asimina Paparrigopoulou Paraskevi (Vivian) Platanou

3:00 PM Classification of Armenian manuscripts without OCR/HTR preprocessing - Tara Andrews

3:30 PM [TBD - Explainability] - Serena Ammirati
Working Group 3: Building ATR/HTR pipelines
Building ATR/HTR pipelines
2:30 PM - 4:00 PM
Room: Room 2
Contributions

2:30 PM The Pragmatics of ATR Pipelines: Structural Dilemmas in Designing Workflows for Historical Corpora - Michael Schonhardt (Univ. Freiburg)

2:50 PM Building an ATR pipeline for tabular data and script translation - Olaf Berg (Ruhr-Universität Bochum, AI:RUB, ERC-LOOP)

3:10 PM Iterative HTR: A new pipeline for automatic text recognition of Arabic-script - Osama Eshera (University of Maryland)

3:30 PM Developing a pipeline for OCR at the Austrian National Library - Johannes Knüchel (Austrian National Library)
4:00 PM Coffee Break
Coffee Break
4:00 PM - 4:30 PM

4:30 PM Working Groups working on conclusions
Working Groups working on conclusions
4:30 PM - 6:00 PM

6:00 PM Short Break
Short Break
6:00 PM - 6:15 PM

6:15 PM Final Roundtable - Open data, open code, open minds in AI
Final Roundtable - Open data, open code, open minds in AI
6:15 PM - 7:45 PM

7:45 PM Conclusion of the public part
Conclusion of the public part
7:45 PM - 8:00 PM
Wednesday, September 9, 2026

10:00 AM Internal meeting of SCOOP
Internal meeting of SCOOP
10:00 AM - 6:05 PM