Articles

Hallucination Rates Across Domain-Specific LLM Fine-Tuning: A Systematic Evaluation

Mehmet Yilmaz*, Preethi Rajagopalan, Anton Ivashkin
Open Access PDF

1-4

DOI: https://doi.org/10.63646/

Benchmarking Real Trade and Multi-Regional Input–Output Databases for Applied Analytical Workflows: An Empirical Comparison of Coverage, Policy Readiness, and Use-Case Fit

Wei Zhang, Lin Chen*, Mingyu Zhao
Open Access PDF

5-21

DOI: https://doi.org/10.63646/datamind.2025.030102

Database-Oriented AI Safety: Storing, Indexing, and Mining Chain-of-Thought Traces for Deception Detection

Rui Wang, Lin Zhao*, Hao Chen
Open Access PDF

22-39

DOI: https://doi.org/10.63646/datamind.2025.030103

A Benchmark Data Governance Framework for Federated Urban Trajectory Mining under Privacy Constraints

Ahmad Faizal Noor, Mei Lin Tan*, Prakash Nair
Open Access PDF

40-59

DOI: https://doi.org/10.63646/datamind.2025.030104

Learning Analytics Databases for Early Warning of Student Dropout

Felipe Augusto Rodrigues, Mariana Conceição Ferreira*, Thiago Henrique Braga
Open Access PDF

60-75

DOI: https://doi.org/10.63646/datamind.2025.030105

A Data-Driven Computational Pipeline for Multi-Class Network Behavior Recognition Using Hybrid Feature Transformation and Distributed Verification Mechanisms

Haoran Wei, Daniela M. Santos*, Junfeng Li, Aravind R. Nair
Open Access PDF

76-95

DOI: https://doi.org/10.63646/datamind.2025.030106

DataQualityOps: Continuous Data Quality Observability for AI-Critical Databases

Elena Petrova, Yuki Tanaka, Marcus Adebayo*
Open Access PDF

96-107

DOI: https://doi.org/10.63646/datamind.2025.030107