Krzysztof Kutt

Archives, libraries, and museums at universities typically operate with separate cataloguing workflows, metadata standards, and information systems, which makes it difficult to trace people, places, objects, and documents across institutional boundaries and over long historical periods. At the Jagiellonian University, cultural heritage data are distributed across the Jagiellonian Library, the University Archives, and the University Museum, each preserving different types of materials and serving distinct scholarly and public audiences. This paper introduces CHExGraph, a cultural heritage knowledge graph that integrates metadata from these three units within a shared linked data environment. CHExGraph focuses on the early history of the university (1364–1780) and unifies person-centric biographical records, bibliographic records, and object-centred descriptions. The graph adopts CIDOC-CRM as its core conceptual model and extends it to represent academic trajectories, institutional affiliations, and object-related roles. The resulting data set comprising 862,877 RDF triples was evaluated over selected competency questions. The evaluation shows that CHExGraph enables unified querying and analysis of Jagiellonian University’s distributed cultural heritage resources. CHExGraph is released with in a Zenodo repository https://zenodo.org/records/21705767. It is accompanied with documentation intended to facilitate reuse and adaptation in other digital library and cultural heritage projects.

The growing volume of digital cultural heritage resources highlights the need for advanced recommendation methods capable of interpreting semantic relationships between heterogeneous data entities. This paper presents a complete methodology for implementing a hybrid recommendation pipeline integrating knowledge-graph embeddings, approximate nearest-neighbour search, and SPARQL-driven semantic filtering. The work is evaluated on the JUHMP (Jagiellonian University Heritage Metadata Portal) knowledge graph developed within the CHExRISH project, which at the time of experimentation contained ${\approx}3.2$M RDF triples describing people, events, objects, and historical relations affiliated with the Jagiellonian University (Kraków, PL). We evaluate four embedding families (TransE, ComplEx, ConvE, CompGCN) and perform hyperparameter selection for ComplEx and HNSW. Then, we present and evaluate the final three-stage neuro-symbolic recommender. Despite sparse and heterogeneous metadata, the approach produces useful and explainable recommendations, which were also proven with expert evaluation.

We present a proof-of-concept system that automates iconographic classification and content-based recommendation of digitized artworks using the Iconclass vocabulary and selected artificial intelligence methods. The prototype implements a four-stage workflow for classification and recommendation, which integrates YOLOv8 object detection with algorithmic mappings to Iconclass codes, rule-based inference for abstract meanings, and three complementary recommenders (hierarchical proximity, IDF-weighted overlap, and Jaccard similarity). Although more engineering is still needed, the evaluation demonstrates the potential of this solution: Iconclass-aware computer vision and recommendation methods can accelerate cataloging and enhance navigation in large heritage repositories. The key insight is to let computer vision propose visible elements and to use symbolic structures (Iconclass hierarchy) to reach meaning.

We developed a proof-of-concept method for the automatic analysis of the structure and content of incunabula pages. A custom dataset comprising 500 annotated pages from five different incunabula was created using resources from the Jagiellonian Digital Library. Each page was manually labeled with five predefined classes: Text, Title, Picture, Table, and Handwriting. Additionally, the publicly available DocLayNet dataset was utilized as supplementary training data. To perform object detection, YOLO11n and YOLO11s models were employed and trained using two strategies: a combined dataset (DocLayNet and the custom dataset) and the custom dataset alone. The highest performance (F1 = 0.94) was achieved by the YOLO11n model trained exclusively on the custom data. Optical character recognition was then conducted on regions classified as Text, using both Tesseract and Kraken OCR, with Tesseract demonstrating superior results. Subsequently, image classification was applied to the Picture class using a ResNet18 model, achieving an accuracy of 98.7% across five subclasses: Decorative_letter, Illustration, Other, Stamp, and Wrong_detection. Furthermore, the CLIP model was utilized to generate semantic descriptions of illustrations. The results confirm the potential of machine learning in the analysis of early printed books, while emphasizing the need for further advancements in OCR performance and visual content interpretation.