Research References

This appendix lists the research papers, datasets, and standards cited throughout the documentation.

Entity resolution

• Dasanaike, T., et al. (2026). EnsembleLink: Ensemble methods for scalable entity resolution. Preprint.
• Ornstein, J. (2025). fuzzylink: Probabilistic record linkage with large language models. Preprint.
• CE-RAG4EM (2026). Context-Enhanced Retrieval-Augmented Generation for Entity Matching. Preprint.
• Zeakis, A., et al. (2025). AvengER: Automated verification of entity resolution results. Preprint.

Election data sources

• MIT Election Data + Science Lab (MEDSL). U.S. Local Elections Dataset, 2018–2022. https://electionlab.mit.edu/data
• OpenElections Project. Certified election results by state. https://openelections.net
• North Carolina State Board of Elections (NC SBE). Official election results, 2004–present. https://www.ncsbe.gov/results-data
• Annual Local Government Election Dataset (ALGED). Municipal election returns for cities >50K population.
• Associated Press. AP Elections. Commercial license required.
• Voting and Election Science Team (VEST). Precinct-level election returns with shapefiles. https://dataverse.harvard.edu/dataverse/electionscience
• Federal Election Commission (FEC). Candidate master files. https://www.fec.gov/data/browse-data/
• U.S. Census Bureau. FIPS code reference and geographic hierarchies. https://www.census.gov/geographies

Standards

• National Institute of Standards and Technology. (2023). NIST SP 1500-100 v2: Election Results Common Data Format Specification. https://doi.org/10.6028/NIST.SP.1500-100r2

Architecture

• Databricks. Medallion Architecture: Bronze, Silver, Gold. https://www.databricks.com/glossary/medallion-architecture

Reports

• Union of Concerned Scientists. (2025). Election Data Report: The state of US election data infrastructure.