August 17, 2026 Dataset Open Access

Lorenzo Valente; Thorsten Buss; Henry Day-Hall; Frank Gaede; Gregor Kasieczka; Katja Krüger; Peter McKeown

JSON Export

{"conceptdoi":"10.25592/uhhfdm.19102","conceptrecid":"19102","created":"2026-08-17T12:42:21.613069+00:00","doi":"10.25592/uhhfdm.19103","id":19103,"links":{"badge":"https://www.fdr.uni-hamburg.de/badge/doi/10.25592/uhhfdm.19103.svg","conceptbadge":"https://www.fdr.uni-hamburg.de/badge/doi/10.25592/uhhfdm.19102.svg","conceptdoi":"http://doi.org/10.25592/uhhfdm.19102","doi":"http://doi.org/10.25592/uhhfdm.19103"},"metadata":{"access_right":"open","access_right_category":"success","communities":[{"id":"uhh"}],"contributors":[{"affiliation":"University of Hamburg","name":"Lorenzo Valente","orcid":"0009-0007-0080-8738","type":"ContactPerson"}],"creators":[{"affiliation":"University of Hamburg","name":"Lorenzo Valente","orcid":"0009-0007-0080-8738"},{"affiliation":"University of Hamburg, DESY, RWTH Aachen University","name":"Thorsten Buss","orcid":"0000-0002-1717-2138"},{"affiliation":"DESY","name":"Henry Day-Hall","orcid":"0000-0002-7881-2506"},{"affiliation":"DESY","name":"Frank Gaede","orcid":"0000-0002-7055-9200"},{"affiliation":"University of Hamburg","name":"Gregor Kasieczka","orcid":"0000-0003-3457-2755"},{"affiliation":"DESY","name":"Katja Kr\u00fcger","orcid":"0000-0002-1956-6608"},{"affiliation":"CERN","name":"Peter McKeown","orcid":"0009-0006-9722-2233"}],"description":"<p>This record contains the simulated calorimeter shower datasets used in the study of &#39;<em>Transferable Fast Calorimeter Shower Generation via Multi-Geometry Pre-training&#39;</em>.</p>\n\n<p>All showers are photon-induced electromagnetic showers with incident energy uniformly distributed between 1 and 100 GeV, stored as HDF5 point clouds: each point carries the two transverse displacements with respect to the impact point, the longitudinal layer index, and the deposited energy. Deposits are clustered on a 1 mm &times; 1 mm transverse grid per layer, and cells below 10 keV are discarded. All detectors are described in DD4hep and simulated with Geant4 11.2.2 through the ddsim driver within the Key4hep stack.</p>\n\n<ul>\n\t<li><strong>SimpleBox</strong> is a synthetic family of ten thousand box-shaped tungsten-silicon sampling calorimeters spanning sampling fraction, longitudinal segmentation and incident angle, with four million showers in total, plus a one hundred thousand shower subsample, a test set of eight held-out configurations, and a held-out in-range configuration for zero-shot evaluation.</li>\n\t<li><strong>LEMURS</strong> is a point cloud re-simulation of five realistic barrel electromagnetic calorimeters (FCCee-CLD, the Open Data Detector calorimeter, Par04-SiW, Par04-SciPb and the noble-liquid FCCee-ALLEGRO), extracted on a fine transverse grid rather than the cell-aggregated representation of the original release. The first four provide one million training showers each and form the realistic pre-training pool.&nbsp;FCCee-ALLEGRO is the transfer target, with a one hundred thousand shower fine-tuning dataset. Every geometry also has an independent ten thousand shower test set, simulated with disjoint seeds.</li>\n</ul>\n\n<p>The structure is encoded in the file names.&nbsp;Per-file sizes, shower counts and MD5 checksums are in the included MANIFEST.json, and the full schema is documented in README.md.</p>","doi":"10.25592/uhhfdm.19103","keywords":["calorimeter simulation","fast simulation","generative models","point cloud","Geant4","machine learning","transfer learning","high energy physics"],"language":"eng","license":{"id":"CC-BY-4.0"},"publication_date":"2026-08-17","related_identifiers":[{"identifier":"https://arxiv.org/abs/2608.18233","relation":"isSupplementedBy","scheme":"url"},{"identifier":"10.57967/hf/10040","relation":"isSupplementTo","scheme":"doi"},{"identifier":"10.57967/hf/10041","relation":"isSupplementTo","scheme":"doi"},{"identifier":"https://github.com/FLC-QU-hep/AllShowers/tree/multi-geometry","relation":"isSupplementTo","scheme":"url"},{"identifier":"https://github.com/FLC-QU-hep/PointCountFM/tree/multi-geometry","relation":"isSupplementTo","scheme":"url"},{"identifier":"https://github.com/FLC-QU-hep/multi-calorimeter-dataset","relation":"isSupplementTo","scheme":"url"},{"identifier":"10.25592/uhhfdm.19102","relation":"isVersionOf","scheme":"doi"}],"relations":{"version":[{"count":1,"index":0,"is_last":true,"last_child":{"pid_type":"recid","pid_value":"19103"},"parent":{"pid_type":"recid","pid_value":"19102"}}]},"resource_type":{"title":"Dataset","type":"dataset"},"title":"Point cloud calorimeter shower datasets for multi-geometry pre-training: SimpleBox and LEMURS","version":"1.0.0"},"owners":[988],"revision":5,"updated":"2026-08-22T15:22:16.632879+00:00"}