August 17, 2026 Dataset Open Access

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

DataCite XML Export

<?xml version='1.0' encoding='utf-8'?>
<resource xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns="http://datacite.org/schema/kernel-3" xsi:schemaLocation="http://datacite.org/schema/kernel-3 http://schema.datacite.org/meta/kernel-3/metadata.xsd">
  <identifier identifierType="DOI">10.25592/uhhfdm.19103</identifier>
  <creators>
    <creator>
      <creatorName>Lorenzo Valente</creatorName>
      <nameIdentifier nameIdentifierScheme="ORCID" schemeURI="http://orcid.org/">0009-0007-0080-8738</nameIdentifier>
      <affiliation>University of Hamburg</affiliation>
    </creator>
    <creator>
      <creatorName>Thorsten Buss</creatorName>
      <nameIdentifier nameIdentifierScheme="ORCID" schemeURI="http://orcid.org/">0000-0002-1717-2138</nameIdentifier>
      <affiliation>University of Hamburg, DESY, RWTH Aachen University</affiliation>
    </creator>
    <creator>
      <creatorName>Henry Day-Hall</creatorName>
      <nameIdentifier nameIdentifierScheme="ORCID" schemeURI="http://orcid.org/">0000-0002-7881-2506</nameIdentifier>
      <affiliation>DESY</affiliation>
    </creator>
    <creator>
      <creatorName>Frank Gaede</creatorName>
      <nameIdentifier nameIdentifierScheme="ORCID" schemeURI="http://orcid.org/">0000-0002-7055-9200</nameIdentifier>
      <affiliation>DESY</affiliation>
    </creator>
    <creator>
      <creatorName>Gregor Kasieczka</creatorName>
      <nameIdentifier nameIdentifierScheme="ORCID" schemeURI="http://orcid.org/">0000-0003-3457-2755</nameIdentifier>
      <affiliation>University of Hamburg</affiliation>
    </creator>
    <creator>
      <creatorName>Katja Krüger</creatorName>
      <nameIdentifier nameIdentifierScheme="ORCID" schemeURI="http://orcid.org/">0000-0002-1956-6608</nameIdentifier>
      <affiliation>DESY</affiliation>
    </creator>
    <creator>
      <creatorName>Peter McKeown</creatorName>
      <nameIdentifier nameIdentifierScheme="ORCID" schemeURI="http://orcid.org/">0009-0006-9722-2233</nameIdentifier>
      <affiliation>CERN</affiliation>
    </creator>
  </creators>
  <titles>
    <title>Point cloud calorimeter shower datasets for multi-geometry pre-training: SimpleBox and LEMURS</title>
  </titles>
  <publisher>Universität Hamburg</publisher>
  <publicationYear>2026</publicationYear>
  <subjects>
    <subject>calorimeter simulation</subject>
    <subject>fast simulation</subject>
    <subject>generative models</subject>
    <subject>point cloud</subject>
    <subject>Geant4</subject>
    <subject>machine learning</subject>
    <subject>transfer learning</subject>
    <subject>high energy physics</subject>
  </subjects>
  <contributors>
    <contributor contributorType="ContactPerson">
      <contributorName>Lorenzo Valente</contributorName>
      <nameIdentifier nameIdentifierScheme="ORCID" schemeURI="http://orcid.org/">0009-0007-0080-8738</nameIdentifier>
      <affiliation>University of Hamburg</affiliation>
    </contributor>
  </contributors>
  <dates>
    <date dateType="Issued">2026-08-17</date>
  </dates>
  <language>en</language>
  <resourceType resourceTypeGeneral="Dataset"/>
  <alternateIdentifiers>
    <alternateIdentifier alternateIdentifierType="url">https://www.fdr.uni-hamburg.de/record/19103</alternateIdentifier>
  </alternateIdentifiers>
  <relatedIdentifiers>
    <relatedIdentifier relatedIdentifierType="URL" relationType="IsSupplementedBy">https://arxiv.org/abs/2608.18233</relatedIdentifier>
    <relatedIdentifier relatedIdentifierType="DOI" relationType="IsSupplementTo">10.57967/hf/10040</relatedIdentifier>
    <relatedIdentifier relatedIdentifierType="DOI" relationType="IsSupplementTo">10.57967/hf/10041</relatedIdentifier>
    <relatedIdentifier relatedIdentifierType="URL" relationType="IsSupplementTo">https://github.com/FLC-QU-hep/AllShowers/tree/multi-geometry</relatedIdentifier>
    <relatedIdentifier relatedIdentifierType="URL" relationType="IsSupplementTo">https://github.com/FLC-QU-hep/PointCountFM/tree/multi-geometry</relatedIdentifier>
    <relatedIdentifier relatedIdentifierType="URL" relationType="IsSupplementTo">https://github.com/FLC-QU-hep/multi-calorimeter-dataset</relatedIdentifier>
    <relatedIdentifier relatedIdentifierType="DOI" relationType="IsPartOf">10.25592/uhhfdm.19102</relatedIdentifier>
  </relatedIdentifiers>
  <version>1.0.0</version>
  <rightsList>
    <rights rightsURI="https://creativecommons.org/licenses/by/4.0/legalcode">Creative Commons Attribution 4.0 International</rights>
    <rights rightsURI="info:eu-repo/semantics/openAccess">Open Access</rights>
  </rightsList>
  <descriptions>
    <description descriptionType="Abstract">&lt;p&gt;This record contains the simulated calorimeter shower datasets used in the study of &amp;#39;&lt;em&gt;Transferable Fast Calorimeter Shower Generation via Multi-Geometry Pre-training&amp;#39;&lt;/em&gt;.&lt;/p&gt;

&lt;p&gt;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 &amp;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.&lt;/p&gt;

&lt;ul&gt;
	&lt;li&gt;&lt;strong&gt;SimpleBox&lt;/strong&gt; 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.&lt;/li&gt;
	&lt;li&gt;&lt;strong&gt;LEMURS&lt;/strong&gt; 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.&amp;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.&lt;/li&gt;
&lt;/ul&gt;

&lt;p&gt;The structure is encoded in the file names.&amp;nbsp;Per-file sizes, shower counts and MD5 checksums are in the included MANIFEST.json, and the full schema is documented in README.md.&lt;/p&gt;</description>
  </descriptions>
</resource>