April 1, 2026 Bachelor Thesis Open Access

Großmann, Daniel Micha

MARC21 XML Export

<?xml version='1.0' encoding='UTF-8'?>
<record xmlns="http://www.loc.gov/MARC21/slim">
  <leader>00000nam##2200000uu#4500</leader>
  <controlfield tag="001">22427</controlfield>
  <datafield tag="100" ind1=" " ind2=" ">
    <subfield code="a">Großmann, Daniel Micha</subfield>
    <subfield code="u">KIT/ETP</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="a">Ferber, Torben</subfield>
    <subfield code="u">KIT/ETP</subfield>
    <subfield code="4">ths</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="a">Streit, Achim</subfield>
    <subfield code="u">KIT/SCC</subfield>
    <subfield code="4">ths</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="a">Reuter, Lea</subfield>
    <subfield code="u">KIT/ETP</subfield>
    <subfield code="4">ths</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">13289988</subfield>
    <subfield code="u">https://publish.etp.kit.edu/record/22427/files/Thesis.pdf</subfield>
    <subfield code="z">md5:8d14deb0c7c520f458bc528848315dd5</subfield>
  </datafield>
  <controlfield tag="005">20260529074937.0</controlfield>
  <datafield tag="542" ind1=" " ind2=" ">
    <subfield code="l">open</subfield>
  </datafield>
  <datafield tag="041" ind1=" " ind2=" ">
    <subfield code="a">eng</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">user-belle2</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">user-computing</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">user-etp</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">thesis</subfield>
    <subfield code="b">bachelor-thesis</subfield>
  </datafield>
  <datafield tag="245" ind1=" " ind2=" ">
    <subfield code="a">One-Shot Neural Inference for Latent Space Clustering in GNN-Based Track Finding at Belle II</subfield>
  </datafield>
  <datafield tag="260" ind1=" " ind2=" ">
    <subfield code="c">2026-04-01</subfield>
  </datafield>
  <datafield tag="909" ind1="C" ind2="O">
    <subfield code="o">oai:publish.etp.kit.edu:22427</subfield>
    <subfield code="p">user-belle2</subfield>
    <subfield code="p">user-computing</subfield>
    <subfield code="p">user-etp</subfield>
  </datafield>
  <datafield tag="520" ind1=" " ind2=" ">
    <subfield code="a">&lt;p&gt;This thesis proposes a one-shot neural clustering algorithm for object condensation pipelines. The algorithm groups an unordered input point cloud of variable count with latent space representations of the input hits into a variable number of clusters and differentiates between signal and noise. Implementation and evaluation is done in the graph neural network based track-finding pipeline for the Belle II central drift chamber. In a first&lt;br&gt;
step, the clustering pipeline and machine learning architecture are presented, combining key solutions from different computer vision pipelines. Next, the required hyperparameters are fitted using simulated detector samples, showing a good generalization across vastly differing event topologies. Then, the clustering is evaluated on a diverse set of&lt;br&gt;
challenging events, leveraging a realistic detector simulation combined with high levels of detector noise measured in actual collisions. Additional validation is performed directly on measured collision data with high levels of detector noise, showing real-world applicability and robustness. The evaluation shows a significant improvement in track charge efficiency&lt;br&gt;
and clone rate, while retaining a similar fake rate. When benchmarked against state of the art classical clustering algorithms, the one-shot neural inference provides a significant speedup without sacrificing clustering quality.&lt;/p&gt;</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">machine learning</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">tracking</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">pointcloud</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">clustering</subfield>
  </datafield>
</record>