SCOOP (Source Codes of the Past) is an international network dedicated to the automatic transcription and analysis of handwritten historical sources. It brings together people from very different corners of the scholarly world: historians, philologists, and palaeographers, archivists and librarians; computer scientists and machine learning researchers; software engineers asf. What unites them is a shared challenge: how to use automatic/handwritten text recognition (ATR/HTR) to unlock the vast written heritage of the past, and how to do it well.
Recent years have brought remarkable progress in text recognition technologies, but much work remains in adapting them to the diversity of historical materials, ranging from different scripts and writing systems, varied textual traditions and manuscript structures, to low-resource languages for which training data and tools are scarce. At the same time, ATR is increasingly interwoven with other methodologies, from dataset curation and text reuse analysis to the automation of editorial workflows. These developments are transforming how researchers engage with manuscript sources, and they raise questions that no single discipline can answer alone.
SCOOP exists to bring these conversations together. Technological development, methodological reflection, and the practical needs of editors, cataloguers, and collecting institutions too often happen in separate communities; the network's aim is to let technological and humanistic expertise inform one another directly, across the boundaries of disciplines, languages, and scripts.