Accepted Papers
Long Papers
| Authors | Paper Title |
|---|---|
| Sebastien Fouss | Toward Pareto-Efficient Sovereign NER with Open-Weight LLMs: Cost, Latency, Quality, and Stability Trade-offs in a Structured Zero-shot Extraction Pipeline on Clean and OCR-Degraded Text |
| Stella Yin, Zhengyuan Liu, Dion Hoe-Lian Goh, Wenya Wang and Nancy F. Chen | InspAIre: Enhancing Research Thinking Skills Through Transparent-and-Interactive AI Reasoning |
| Jules Di Scala, Guillaume Cabanac, Ophélie Fraisier-Vannier, Gilles Hubert and Ronan Tournier | EditorCheck: Auditing editor–author conflicts of interests |
| Jim Hahn | Algorithmic BIBFRAME and Social Signaling |
| Claire Cate, Preston Clarke and Yiu-Kai Ng | Matching Hearts and Minds: Personalized STEM Book Recommendations for Adolescent through Emotional and Topical Alignment |
| Ying-Chen Lin, Zhiguang Liu and Yi Shang | NSTS: A Neuro-Symbolic System for Webpage Validity Timestamp Determination |
| Yijia Izzie He, Marco Martens, Erik J.A. Vos, Foekje Boersma and Victor de Boer | Metadata vs Arsenic: a Case Study of Digital Library for the Conservation of Physical Collections |
| Eryk Kulikowski | Same Problem, Different Field: Cross-Domain Solution Import via Domain-Stripped Computational Fingerprints |
| Hiroyuki Tsunoda, Yuan Sun, Masaki Nishizawa, Xiaomin Liu, Kou Amano and Shuntaro Kawamura | Research Data-Sharing Practices Through the Lens of Data Availability Statements |
| Cong Xu and Xinwei Gao | Making a Seven-Decade Policy Collection Navigable: Domain-Adapted Sentence Embeddings and a Coverage-Aware Topic-Alignment Protocol for Chinese Government Work Reports |
| Shirin Shujaa, Ginel Dorleon and Tri Dang Tran | ABSP: Attention-Based Semantic Preservation for Faithful Context Compression |
| Derek Denys, Angel Crawford and Yiu-Kai Ng | Contextual Document Discovery in Digital Libraries through Hybrid Summarization and LLM-Guided Query Decomposition |
| Yiyi Lu, Yilai Qian and Yucheng Jin | Visible but Not Yet Curatable: Characterizing the Curatability of Compact and Derived Open LLM Artifacts |
| Sonja Lachner and Andreas Henrich | What Makes Research Data Visible? Factors and Implications for Humanities Research Data Infrastructures |
| Rochana R. Obadage, Lamia Salsabil, Sawood Alam, William Ingram, Bipasha Banerjee, Edward Fox and Jian Wu | URL Extraction from Scholarly Documents: A Cross-Format Comparative Analysis |
| Caio Maia, André Maia and Pedro Corrêa | LLM-Based Semantic Metadata Enrichment for Findable Scientific Data Collections |
| Ahmed Hamdi, Jose G Moreno, Cécile Armand, Christian Henriot and Antoine Doucet | Adaptive LLM Selection for Question Answering over Historical Digital Libraries |
| Yue Zheng and Haiming Liu | Supporting Information-Need Expression with Icons and Text: An Exploratory Study with Adults with Learning Disabilities |
| Yuan Li | A Layered Content Delivery Model for Reframing Library Social Media as Service |
| Peter Organisciak, Maggie Ryan and Mina Ghobadi | Can LLMs Simulate Expert Panels? Evaluating CAT-Inspired Persona Prompting for Automated Creativity Scoring |
| Jingjia Ding, Qing Wang and Yuhan Kang | How Do Chinese Researchers Engage with GenAI: Perceptions, Usage, and Future Adoption |
| Jakub Dubec, Pavol Batalik, Michal Ries and Pavel Čičák | Remembering the Sentence: A Co-Curated Claim Graph for One Researcher’s Scholarly Record |
| Jiayu Yang, Durgesh Nandini, Frédérick Madore, Oliver Baumann, Neeraj Thandayan Viswajith and Mirco Schoenfeld | Beyond Keywords: Training-Free Entity Linking for Research Metadata via Cross-Lingual Retrieval Consensus |
| Aftab Anjum and Ralf Krestel | PReFER: A Multi-Proposer Refiner Framework for Named Entity Recognition |
| Juanita Gomez Romero, Emily Lovell, Stephanie Lieggi, James Davis and Alvaro Cardenas | Open Code, Hidden Collections: An Empirical Study of Academic Software Stewardship |
| Harish Varma Siravuri, Akhil Pandey Akella and Hamed Alhoori | Triaging Defects in Scholarly Result Graphs with Extraction, Evidence, and Consistency Signals |
| Satvik Chekuri and Edward Fox | Structured Knowledge Graph for Scholarly Exploration: IR and QA System for ETDs and their Elements |
| James Ecker, Jian Wu, B. Danette Allen and Michael L. Nelson | From Digital Library Records to Trust-Grounded Virtual Experts for Knowledge Retention |
| Bohan Jiang, Kyeongmin Rim, Kelley Lynch and James Pustejovsky | Segmentation-then-Summarization for Long-Form Audiovisual Archives: A Comparative Study of Three Pipelines |
| Hajra Klair, Amr Aboelnaga, Hoda Eldardiry and William A. Ingram | Old Stories, New Readers: Evaluating Retrieval and QA over Historical Newspapers under Diachronic Vocabulary Change |
| Lamia Salsabil, Rochana R. Obadage, Bipasha Banerjee, Sawood Alam, William Ingram, Edward Fox and Jian Wu | End-to-End Contextualized URL Extraction from Scholarly Papers |
| Kazuhiro Yamauchi and Marie Katsurai | Improving Cross-Lingual Transfer for Sequential Sentence Classification in Research Papers via Structural Similarity |
| William Ingram and Edward Fox | Beyond Topic Matching: Goal-Conditioned Evaluation of Research Contributions in ETD Collections |
| Sai Koneru, Jian Wu and Sarah Rajtmajer | Context Selection for Hypothesis and Statistical Evidence Extraction from Full-Text Scientific Articles |
| Akshay Kolgar Nayak, Sampath Jayarathna, Hae-Na Lee and Vikas Ashok | Assessing the Usability of Electronic Theses and Dissertations for Blind Users |
| Lakshmi Rajendram Bashyam | Reading the neighborhood: Text-Attentive Graph Reranking for Automated Subject Indexing |
| Amr Aboelnaga, Hajra Klair, Hoda Eldardiry and William A. Ingram | A Provenance-First Discovery Layer for Research Gaps, Limitations, and Future Directions in ETDs |
| Yurong Li, Fengchang Yu, Dehao Ying, Kunyao Bu, Yuan Wang, Haotan Liu and Wei Lu | Almost Correct Is Still Wrong: A Structure-Rich Benchmark for Evaluating Functional Correctness in Complex Scientific Table Recognition |
| Zhiyuan Lai, Xingkun Liang, Chenyang Jiang and Zhuoxi Li | Lives of the Infamous: Identity Linkage Potential and Everyday Information Practices among People Living with HIV |
Short Papers
| Authors | Paper Title |
|---|---|
| Qiuying Li | LLM-as-Judge for OCR Quality Assessment in Digital Libraries: A Reference-Free Approach |
| Linhan Wang, Meizi Song, Shengkun Wang, Chang-Tien Lu and Yinlin Chen | Learning Subject Tags from Incomplete Labels: A Recall-Oriented VLM Pipeline for Historical Photographs |
| Sang Min Lee and Thomas Kang | CoMuRAG: Condition-Mutated Hard Negatives for Safety-Sensitive Korean Building-Code Retrieval |
| You Peng, Gyuri Kang and Kahyun Choi | Poem Boundary Identification Without Full-Text Access: Five-Class Classification Using HathiTrust Extracted Features |
| Ming-Hsin Phoebe Chiu and Kai Li | Who Does Google Cite for Health? Auditing the Source Ecosystem of AI Overviews in Taiwan |
| Constantin Doru and Costel Bălcău | EvidenceCell-DL: Counterfactual Evidence Gates for Metadata Repair in Digital Libraries |
| Georgette Nicolosi and Hyerim Cho | Toward an Understanding of Digital Romance Media: A User-Centered Thematic Analysis of Love and Deepspace Discussions |
| Luyi Chen, Yumeng Hou and Xiaoyu Zhang | From Media Records to Knowledge Graph: Interoperable Ontology Modeling for a Multimodal Martial Arts Archive |
| Mario Morvan | Citation Location Needed: In-Source Locators and Wikipedia’s Growing Verification Cost |
| Rajesh Kumar Das and Gretchen R. Stahlman | Provenance-Aware Hybrid Search in AI-Mediated Digital Libraries |
| Xin Wei, Gayane Grigoryan, Alyssa Vargas, Sarah Rajtmajer and Jian Wu | Toward Explainable Replicability Assessment of Findings in the Social and Behavioral Sciences |
| Mary Ann Tan, Genet-Asefa Gesese and Harald Sack | BibNER-Werk: Bibliographic NER for Historical German Catalogs |
| Maria Elpiniki Zafeiraki, Jos Beerens and Houda Lamqaddam | This Artwork Image Couldn’t Be Found: Human-AI Semantic Tagging of Artwork from Titles |
| Huaqing Xu and Dan Wu | From AI Capability to Service Accountability: A Warrant-Based Framework for Smart Libraries |
| Isham Kalappurackal Mansoor, Jian Wu and Kehinde Ajayi | A Dual-Expert Routing Framework for Structured Data Extraction from Scientific Tables |
| Katrina Fenlon, Nikki Wise, Ximeng Deng and Amanda Sorensen | Community-institutional partnerships in digital cultural heritage: A state-of-the-art review |
| Malik Oyewale Salami, Liri Fang and Vetle I. Torvik | Can LLMs Identify Advisor-Advisee Relationships in Coauthorship Network Based on Publication Metadata? |
| Ibrahim Al Azhar, Zhishuai Guo and Hamed Alhoori | LimAgents: Multi-Agent LLMs for Generating Research Limitations |
Undergraduate Research Symposium
| Authors | Paper Title |
|---|---|
| Peishan Zhong, Shuya Liu, Xiaoju Dong and Tingting Yu | CARES: Citation-Aware Representative Work Evaluation System |
| Brian Han | From Fragmented Literature to Reusable Knowledge: Concept-Conditioned Information Integration through LLMs |
| Brian Li and Yunhe Feng | Same Passages, Different Readings: Comparing Complete Human and LLM Interpretations of a Story |
| Tevin Billingsley, Mingchen Li and Yunhe Feng | Examining Dermatology Image Generation Capabilities of Generative AI Across Skin Tones |
| Sawyer Alston, Yashaswini Sreenivasa Shetty, Sreeja Kanuganti, Anirban Saha Anik, Xiaoying Song and Lingzi Hong | Can LLMs Reason Over Where and When? Benchmarking Spatiotemporal Synthesis in Crisis Response |
| Sriprajnav Koduri, Dawei Gao, Huaxiao Yang and Yunhe Feng | Making Cardiac-Organoid Literature Comparable: An Arm-Level Framework and Source-Linked Resource |
| Pranav Verma, Noah Dengler, Angela Lyons and Deepika Pingali | Beyond Gravity Models: Predicting Human Migration with Spatial Gates and Graph Neural Networks |
| Landen Summers, Haeseon Yoon, Weijian Zheng and Yunhe Feng | Exploring the Abstention Ability of LLMs using Scientific Reasoning in Critical Fields |
| Anish Sandaka, Jessica Craig, Chad Trulson and Yunhe Feng | Explaining the Performance Plateau in Machine Learning-based Juvenile Recidivism Prediction on PACT dataset |
| Samantha Gallardo, Omieibi Pollyn, Zexuan Meng, Kewei Sha and Clifford Whitworth | Vulnerabilities of ROS 2 Communication in Autonomous Vehicle Systems |
Posters, Demos
| Authors | Paper Title |
|---|---|
| Ran Elgedawy, Sanjay Das, Ethan Seefried, Gavin Wiggins, Ryan Burchfield, Kimberly Jeskie, Susan Fiscor, Subhamay Pramanik, Billey Thomas, Chrissi Schnell, Todd Thomas, Sudarshan Srinivasan and Tirthankar Ghosal | ChemSafe: Hybrid Retrieval-Augmented Decision Support for Laboratory Chemical Hazard Assessment |
| Rachel Dubose and Dakeya Chambers | Approaches to Supporting and Teaching Quantum Computing |
| Owen Leitzell, Logan Simba, Alex Sharon, Ella Hawkins and Behrooz Mansouri | Unified Speech-to-LaTeX Models for Spoken Mathematical Expressions |
| Shuhei Kobayashi and Keishi Tajima | Estimating Name Recognition of Public Figures from the Web |
| Aislin Davis, Ella Hawkins, Adah Holt and Behrooz Mansouri | MathDisAm: Towards Math Query Disambiguation |
| Swati Rajwal, Ran Elgedawy, Hugo Bouteiller, Hsin Wang, Brad Johnson and Tirthankar Ghosal | SCATTER: Skutterudite Comprehensive Answering Tool for Thermoelectric Research |
| Camila da Silva, Artur Rozestraten and Jiangping Chen | GLOBAL ARCHIGRAPHY: A Collaborative Digital Platform for Lusophone and Anglophone Architectural Photographs |
| Daniel Alemneh, Mark Phillips and Tushar Shrivastava | Beyond DOI Assignment: Integrating Electronic Theses and Dissertations into the Global Scholarly Citation Infrastructure |
| Krzysztof Kutt, Elżbieta Sroka, Luiz Do Valle Miranda, Joanna Ślaga, Jacek Partyka, Tomasz Zacharski, Przemysław Żukowski and Grzegorz J. Nalepa | Exploring University Heritage as Linked Data: A Demonstration of the Jagiellonian University Heritage Metadata Portal |
| Jiebei Luo and Kyong Eun Oh | Mapping Evidence Work in Academic Libraries: Preliminary Findings from an Ongoing Content Analysis |
| Jian Yang, Haishen Yu and An Tao | Making Music Performance Research Cumulative: Vmus.net V3 as a Digital Library for Versioned, Attributable Annotations |
| Sanjay Das, Ryan Burchfield, Gavin Wiggins, Alan Guy and Tirthankar Ghosal | SafeLens: AI-Augmented Exploratory Analysis over Organizational Safety Records for Actionable Insights Generation |
| Anji Sakamoto, Tokinori Suzuki, Takashi Inui, Keizo Oyama and Ken’Ichi Kansaku | Which Text Normalization Methods Matter for Example-Based Retrieval of OCR-Generated Japanese Classical Texts? |
| Ximeng Deng and Wei Ai | Creating Linked Provenance Data for Chinese Art in US Museums: An LLM-in-the-Loop Workflow |
| Robert B. Allen | Highly Structured Discourse Statements for Scientific Research Reports |
| Aubin Mugisha and Behrooz Mansouri | Strong Solvers, Leaky Tutors: Evaluating Answer Leakage in LLM Math Tutors |
| Sarah Griebel, Glen Layne-Worthey and John Stephen Downie | Identifying English-Language Translations in a Large Digital Library |
| Jose G Moreno, Ahmed Hamdi, Cécile Armand, Christian Henriot and Antoine Doucet | An Interactive Tool for Exploring Multi-LLM Correctness on Bilingual Historical Digitised Documents |
| Adrián Carrascosa, Mariona Coll Ardanuy, Laura Servat, Alexandra Málaga, Ramon Sarobe, Coral Cuadrada and Mercè Crosas | scalable-htr: A Framework for Scalable and Reproducible Handwritten Text Recognition on Historical Documents |
| Rei Miyata | Can Large Language Models Identify Technical Terms in Documents Like Human Annotators? |
| Chengxi Chu and Yi-Shuai Xu | Robust Cross-Modal Alignment for Reliable Multimodal Video Information Access under Noisy Textual Descriptions |
| Mikaela Ballmer, Benjamin Charles Germain Lee, Trevor Owens and Rowan Tabor | The Wikipedia Edit-a-thon Companion App: A Crowdsourcing Tool for Reparative Description with Oral History Transcripts |
| Koshi Motegi, Koichiro Ito and Shigeki Matsubara | Cross-Format Citation Classification: Examining the Effects of Combining Bibliographic and URL Citations |
| Tomas Blazauskas, Rytis Maskeliūnas and Jakub Swacha | Experimenting with Snowball Sampling of Research Papers using Large Language Models |
| Erica Shusas | Who Labels Matters: Differences in Responses to Content Label Sources Among Young Adult Marginalized Demographic Groups |
| Adam Amin | TURATH: An AI Platform for Transcribing, Translating, and Indexing Historical Handwritten Archives |
| Jewoong Moon and Yong Ju Jung | SpeakWise: Real-time AI-mediated Oral Assessment for Educational Settings |
| Mahdieh Nazari | Extending Search Habits: Unfolding Novice User Experience with Conversational AI through Information Retrieval Tasks |
| Meng-Han Lee | Journal Atlas: Venue Fit Scoring Under Incomplete Evidence, and the Corpus Method It Requires |
| Han Zhang | Traceable Literature-to-Data Workflows: EcoEvidence, a Human-in-the-Loop Evidence Workbench |
| Sergiu Gordea and George Christian Cotea | HEXER: An Online Tool for Building, Validating and Exploring Knowledge Graphs from Historical Documents |
| Hadi Ghaemi, Zakieh Alizadehsani and Markus Stocker | SciClaim2Explore: Claim-Guided Exploration of Scientific Data Evidence |
| Saber Zahhar, Christophe Rodrigues, Nédra Mellouli and Nicolas Travers | KPViz: A Framework for Keyphrase Prediction Experiments |
| Gaozheng Liu, Jill Naiman and J. Stephen Downie | Accessibility Annotations as OCR Ground Truth: A Large-Scale Corpus of Long, Visually Complex Documents |