---
res:
  bibo_abstract:
  - 'Adopting digital twin technologies in small andmedium-sized enterprises (SMEs)
    is often hinderedby heterogeneous, poorly documented productiondata. Current semantic
    type detection approachesrequire massive labeled datasets making themimpractical
    for resource-constrained SMEs. Wepropose a zero-shot hybrid framework combiningpattern-based
    classification with selective largelanguage model (LLM) reasoning formanufacturing-specific
    data types. The two-stagearchitecture uses rule-based patterns for high-confidence
    cases, forwarding ambiguous columnsto a multi-step LLM reasoner. Evaluation on
    fourmanufacturing datasets shows the hybrid approachachieves weighted F1 within
    7 24 percentagepoints of pure LLM classification performancewhile reducing LLM
    invocations by 39% onaverage. Processing time decreased by up to 2.8×.Our framework
    addresses a critical gap: automated,computationally efficient data type recognition
    formanufacturing SMEs without requiring trainingdata, contributing to automated
    simulation anddigital twin construction.@eng'
  bibo_authorlist:
  - foaf_Person:
      foaf_givenName: Lina
      foaf_name: Döring, Lina
      foaf_surname: Döring
      foaf_workInfoHomepage: http://www.librecat.org/personId=231689
    orcid: 0009-0000-3555-4183
    orcid_put_code_url: https://api.orcid.org/v2.0/0009-0000-3555-4183/work/221016189
  - foaf_Person:
      foaf_givenName: Sebastian
      foaf_name: Trojahn, Sebastian
      foaf_surname: Trojahn
  - foaf_Person:
      foaf_givenName: Pascal
      foaf_name: Reusch, Pascal
      foaf_surname: Reusch
      foaf_workInfoHomepage: http://www.librecat.org/personId=223271
  bibo_doi: 10.25673/123544
  dct_date: 2026^xs_gYear
  dct_language: eng
  dct_publisher: Otto von Guericke University Library, Magdeburg, Germany@
  dct_subject:
  - Semantic Data Type Detection
  - DigitalTwin
  - Manufacturing SMEs
  - Zero-shot Learning
  - Hybrid AI
  - LLM
  dct_title: 'Smart data adapter: A hybrid pattern-LLM approach@'
...