SCOOP: Source Codes of the Past

Training as a continuous process

• Doug Emery ・ University of Pennsylvania LibrariesPiloting HTR in the Library: Experiments and Groundwork
• Wolfgang Göderle & David Fleischhacker ・ University of Graz | University of Passau | MPI GEAMulti-Model OCR Arbitration: High-Precision OCR for 19th Century Administrative Mass Sources
• Alicia González Martínez ・ Hamburg UniversityFrom PDF to mARkdown: A Scalable Arabic OCR Pipeline for expanding the OpenITI Corpus
• Elena Chepel & Anton Repushko ・ University of ViennaAnagnostes - Towards a Transformer-based OCR System for Ancient Greek Papyri

Transcription approaches I (Palaeography in focus)

• Benjamin Kiessling ・ ALMAnaCH, Inria ParisComputational Paleography through Automatic Text Recognition
• Sajjad Nikfahm-Khubravan ・ Roshan Institute for Persian Studies, University of MarylandTowards Geometry-Based Scribal Hand Analysis: A Word-Level Graphometric Framework for Arabic Manuscripts
• Malamatenia Vlachou ・ IRHT/CNRS-ENPCLeveraging HTR for Script Characterization: Toward a Unified Computational Framework for Palaeographical Analysis
• Dominique Stutzmann ・ IRHT-CNRS / HU BerlinWorkflows and granularities: text, image, and what remains

Language Challenges I

• Ana Mihaljević ・ Institute for the Croatian languageFour Scripts, Five Languages, One Digitalization Challenge
• Bernhard Bauer ・ University of GrazMatchbox: Creating a Combined Recognition Model for Early Medieval Celtic Languages and Latin
• Baptiste Queuche ・ CalfaHow hybrid HTR+VLM approaches are unlocking the processing of under-resourced, non-western languages
• Seth Kulick ・ Linguistic Data Consortium, University of PennsylvaniaUsing OCR to expand historical treebanks
• Andrew Janco ・ Princeton UniversityWhich Languages Are In-Vocabulary?
• Isabelle Marthot-Santaniello ・ University of BaselThe language of Greek papyri? One millennium of writing and its complexity

Experimental approaches

• Michal Racyn ・ Masaryk UniversityUtilization of the Open WebUI platform in Arkindex
• Tristan Repolusk ・ Department of Digital Humanities, University of GrazDocument Layout Analysis for Glossed Medieval Manuscripts: Comparing Kraken 6 and YOLO26
• Elise Wang ・ California State University, FullertonFinding our way through the National Archives: HTR for indexing a large corpus
• Tobias Hodel ・ University of BernInsights from an Unsound Experiment: Testing Kraken, TrOCR, and VLMs with an LLM Judge

Transcription approaches II (Transcription decisions, their effect, and related terminology)

• Jan Odstrčilík ・ Institute for Medieval Research, Austrian Academy of SciencesOtto Dei gram, rogat vram Clam. From facsimile and descriptive transcriptions to “quasi-diplomatic” and interpretative approaches in ATR/HTR
• Anna Michalcová ・ Czech Language Institute, Czech Academy of Sciences; Institute for Medieval Research, Austrian Academy of SciencesLost in Transcription? Reconciling HTR Output with Old Czech Editorial Standards
• Ana Mihaljević ・ Institute for the Croatian languageReading Glagolitic in the Twenty-First Century: Between Philology, HTR, and AI
• Paweł Figurski ・ Polish Academy of SciencesHTR of Normalized Latin Texts: Insights from Liturgical Manuscripts

Language Challenges II

• Katrín Lísa van der Linde Mikaelsdóttir ・ University of IcelandDark Vellum, Dense Diacritics: Challenges in Training HTR Models for Medieval Icelandic
• Christine Roughan ・ Princeton UniversityImpacts of Script Features on Text Recognition: Experiments with Greek and Arabic
• Ephrem Aboud Ishac ・ Institute for Medieval Research, Austrian Academy of SciencesSyriac Manuscripts That Can Talk: Giving Voice to Under-Resourced Scripts in HTR

Roundtable

Handwriting Classification I

• Asimina Paparrigopoulou & Paraskevi Platanou ・ Democritus University of ThraceFrom Handwriting Classification Errors to Paleographic Evidence: Graphic Compensation in Ancient Greek Documentary Hands
• Tara Andrews ・ University of ViennaClassification of Armenian manuscripts without OCR/HTR preprocessing
• Serena Ammirati & Paolo Merialdo ・ Università degli Studi Roma TreBeyond the Heatmap: What Faithful Explanations Can Do for Handwriting Identification

Leveraging Outputs: Text Reuse, NLP, and More (talks)

• Alexander O'Neill ・ Musashino UniversityTesting the Reuse Value of Pracalit Ground Truth for Bhujimol Manuscripts
• Nikola Krisztian Czindrity ・ University of ViennaFrom Old Icelandic HTR Outputs to Normalised Texts through Seq2Seq Transformers
• Seth Kulick ・ Linguistic Data Consortium, University of PennsylvaniaUsing OCR to expand a treebank of historical Yiddish: A Progress Report

Handwriting Classification II

• Aaron Hershkowitz ・ The Institute for Advanced StudyClassifying Squeezes Again: Initial Results from an ICDAR Contest
• Sebastian Sobecki & Sam Grieggs ・ University of TorontoCommunities of Practice: Capturing the Aspect of Late Medieval Handwriting
• Giuseppe De Gregorio ・ Computer Vision Center - CVC - BarcelonaScript classification and alphabet identification

Roundtable 🎤 - Language Challenges

Leveraging Outputs: Text Reuse, NLP, and More (demos)

• Wayne de Fremery ・ Dominican University of CaliforniaNew Ways to Transform and Explore Older Korean Texts: From ATR to Reading Texts to Agentic Retrieval in Mo文oNExplorer
• Andrew Janco ・ Princeton UniversityFrom Document Images to Research Catalogue
• Daniel Tubb ・ Anthropology, University of New Brunswick, CanadaFichero and the Circuit Court Archive of Istmina: An AI Workflow App for Researchers
• Martin Roček ・ Institute for Medieval Research, Austrian Academy of Sciences and Faculty of Arts, Charles UniversityIntertextuality as a Retrieval Task: Benchmarking Text Reuse in Classical and Medieval Latin

Building ATR/HTR pipelines

• Michael Schonhardt ・ TU Darmstadt / Akademie der Wissenschaften und der Literatur | MainzThe Pragmatics of ATR Pipelines: Structural Dilemmas in Designing Workflows for Historical Corpora
• Olaf Berg ・ Ruhr-Universität BochumBuilding an ATR pipeline for tabular data and script translation
• Osama Eshera ・ University of MarylandIterative HTR: A new pipeline for automatic text recognition of Arabic-script
• Johannes Knüchel ・ Austrian National LibraryBuilding an OCR Pipeline at the Austrian National Library

Datasets and Institutions

• Jessie Dummer ・ University of Pennsylvania LibrariesIntegrating HTR into Digital Library Workflows
• Michael Lužný ・ National Library of the Czech RepublicManuscriptorium Full-Text Module: Building a Digital-Edition Infrastructure
• Tim Geelhaar ・ Goethe Universität Frankfurt am MainReviving the Legacy: How to Adapt the Latin Text Archive for the Age of AI
• Ursula Stampfer ・ Bayerische StaatsbibliothekHTR in the German Manuscript Centres: Current Status, Challenges, and Perspectives

Unconference