This paper introduces a machine learning approach to reassemble fragmented oracle bones, which are important materials for understanding early Chinese history. Specifically, we propose a model based on the Diffusion Model, a generative deep learning framework that has demonstrated remarkable performance in computer vision tasks in recent years.

Research in mathematics, computational sciences, and archaeological theory has addressed the uncertainty in archaeological data and its links to annotator expertise/confidence. This study uses real data and three annotators with varying expertise to evaluate concordance metrics for fuzzy annotations, applying computational linguistics and vector distance methods within fuzzy data models.

The paper introduces RDFProxy, a Python library designed for building REST
APIs on top of Knowledge Graphs using Pydantic models.

RDFProxy is currently being developed at the Austrian Center for Digital Humanities and Cultural Heritage and will serve as the backend solution for the Releven project at University of Vienna.

This study examines the authorship of the Armenian geographical treatise Ashkharhatsuyts using stylometric methods. Results attribute the text to Anania Shirakatsi, aligning with prior hypotheses, while excluding Movses Khorenatsi. Uncertainty in early passages suggests potential compilations. Findings also question the authorship of Eghishe's Commentary on Genesis.

This paper addresses the lack of a coherent framework for understanding bias in digital humanities. Using colonial archives as case studies, it examines biases in archives, digitization, and AI. It proposes reframing bias as an analytical category and introduces a framework to dissect its interconnected dimensions.