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.

Authors

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2026-10-29
DOI
https://doi.org/10.5281/zenodo.23769607
Primary Topic
Research Data Management Practices
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Intermediate report LUMEN Metasearch Design

Kévin Darty, Julien Homo
3 links
Zenodo (CERN European Organization for Nuclear Research)
Research Data Management Practices
article

Intermediate report LUMEN Metasearch Design

Kévin Darty, Julien Homo
article en

Abstract

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.

Zenodo (CERN European Organization for Nuclear Research)
Openalex Percentile: Top 6%
Research Data Management Practices
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon