Reference Extraction at the Intersection of AI Research and the Digital Humanities: Validation, Interoperability and Collaboration

Tuesday Nov 4, 2025, 9:00 AM → 10:00 PM Europe/Berlin

Z01 (Max Planck Institute for Legal History and Legal Theory)

Andreas Wagner (Max Planck Institute for Legal History and Legal Theory, Frankfurt/Main, Germany), Christian Boulanger (Max Planck Institute for Legal History and Legal Theory, Frankfurt/Main, Germany)

One-Day Workshop at the Max Planck Institute for Legal History and Legal Theory (hybrid)

 We are delighted to invite you to the second workshop in the "New Approaches for the Extraction of Heterogeneous Reference Data" series at mpilhlt.

This informal meeting is meant mainly to foster collaboration and knowledge exchange between researchers and practitioners working at the intersection of data extraction, artificial intelligence, and the digital humanities. While it continues activities started in 2023, we are eager to welcome new collaborators.

20251024_RefExtract_2025_Programme.pdf

Workshop Series Homepage

9:00 AM → 9:45 AM I. ONBOARDING

9:00 AM Arrival/Registration

9:15 AM Welcome

Speakers: Dr Christian Boulanger (Max Planck Institute for Legal History and Legal Theory, Franfurt/Main, Germany), Andreas Wagner (MFER)

9:20 AM Upshot from RefExtract2023, State of the Discussion

Speakers: Dr Christian Boulanger (Max Planck Institute for Legal History and Legal Theory, Franfurt/Main, Germany), Andreas Wagner (MFER)

9:45 AM → 10:00 AM Coffee Break

10:00 AM → 12:30 PM II. RESEARCH

10:00 AM In-depth Research Impact Summarization through Fine-Grained Temporal Citation Analysis

Speaker: Hiba Arnaout (TU Darmstadt)

10:30 AM Benchmarking Large Language Models on Reference Extraction and Parsing in the Social Sciences and Humanities

Speakers: Yurui Zhu (Odoma), Matteo Romanello (Odoma)

11:00 AM How Scientific Ideas Evolve

Speaker: Sofía Aguilar Valdez (Saarland University)

11:30 AM Open Discussion and Ad-Hoc Presentation of Research

12:30 PM → 1:30 PM Lunch Break

1:30 PM → 3:30 PM III. DATASETS, INFRASTRUCTURE AND INTEROPERABILITY

1:30 PM OpenCitations Project

Speakers: Angelo Di Iorio (University of Bologna), Ivan Heibi (University of Bologna), Lorenzo Paolini (University of Bologna), Marta Soricetti (University of Bologna), Matteo Guenci (University of Bologna), Silvio Peroni (University of Bologna)

2:00 PM Open Citation Data for Educational Research

Speakers: Ahsan Shahid (GESIS – Leibniz Institute for the Social Sciences (Cologne)), Christoph Schindler (DIPF | Leibniz Institute for Research and Information in Education), Philipp Mayr (GESIS – Leibniz Institute for the Social Sciences (Cologne)), Tamara Heck (DIPF | Leibniz Institute for Research and Information in Education), Verena Weimer (DIPF | Leibniz Institute for Research and Information in Education)

2:30 PM Datasets in the Legal Theory Knowledge Graph Project

Speakers: Andreas Wagner (MFER), Dr Christian Boulanger (Max Planck Institute for Legal History and Legal Theory, Franfurt/Main, Germany)

3:00 PM Interoperability Roundtable: Open Discussion on Data Models and Data Formats

3:30 PM → 4:00 PM Coffee Break

4:00 PM → 5:30 PM IV. TOOLS, WORKFLOWS AND PIPELINES

4:00 PM LLM-Based Knowledge Graph Extraction Pipeline

Speakers: Aleksandta Kaye (MPI of Geoanthropology), Malte Vogl (MPI of Geoanthropology), Raphael Schlattmann (TU Berlin)

4:30 PM Training the Grobid Reference Extraction Models

Speaker: Luca Foppiano (ScienciaLAB)

5:00 PM Annotation Tools for Machine Learning: PDF-TEI Editor (for LLamore & Grobid), Prodigy, TEI-Publisher

Speakers: Andreas Wagner (MFER), Dr Christian Boulanger (Max Planck Institute for Legal History and Legal Theory, Franfurt/Main, Germany)

5:30 PM → 6:30 PM Takeaways, Way Forward, Closing

5:30 PM Takeaways, Way Forward, Closing

7:00 PM → 10:00 PM Dinner (Self-Paid)