Intermediate report LUMEN Metasearch Design

This report presents the LUMEN Metasearch, the cross-domain knowledge discovery service of the LUMEN Common Discovery Infrastructure. It lets researchers query and discover metadata exposed by LUMEN communities through governed Data Products across scientific domains, without storing the underlying resources, addressing an interdisciplinary EOSC use case. The report consolidates the design set out in Deliverable 4.1 and Deliverable 4.2, describes the underlying method, and gives a first characterization of the system’s outputs. Resources are embedded in a shared semantic vector space so that discovery works across community vocabularies, combined with contract-aware filtering for access conditions, provenance and licensing. The Metasearch also detects “bridges”, credible links between data products from different communities, scored transparently across methodology, amplitude, location and period. It accompanies the June 2026 alpha release, tested by LUMEN communities at the Consortium Meeting in Paris. It serves as T6.1’s intermediate input to D6.2 and informs MS6.2. Current limitations and next steps, including expert validation and a labelled benchmark, are discussed.