@article{loughran2011,
  author  = {Loughran, Tim and McDonald, Bill},
  title   = {When Is a Liability Not a Liability? {T}extual Analysis, Dictionaries, and 10-{K}s},
  journal = {Journal of Finance},
  year    = {2011}, volume = {66}, number = {1}, pages = {35--65},
  doi     = {10.1111/j.1540-6261.2010.01625.x}
}
@article{loughran2016,
  author  = {Loughran, Tim and McDonald, Bill},
  title   = {Textual Analysis in Accounting and Finance: A Survey},
  journal = {Journal of Accounting Research},
  year    = {2016}, volume = {54}, number = {4}, pages = {1187--1230},
  doi     = {10.1111/1475-679X.12123}
}
@article{hoberg2016,
  author  = {Hoberg, Gerard and Phillips, Gordon},
  title   = {Text-Based Network Industries and Endogenous Product Differentiation},
  journal = {Journal of Political Economy},
  year    = {2016}, volume = {124}, number = {5}, pages = {1423--1465},
  doi     = {10.1086/688176}
}
@article{hobergmaksimovic2015,
  author  = {Hoberg, Gerard and Maksimovic, Vojislav},
  title   = {Redefining Financial Constraints: A Text-Based Analysis},
  journal = {Review of Financial Studies},
  year    = {2015}, volume = {28}, number = {5}, pages = {1312--1352},
  doi     = {10.1093/rfs/hhu089}
}
@article{gentzkow2019,
  author  = {Gentzkow, Matthew and Kelly, Bryan and Taddy, Matt},
  title   = {Text as Data},
  journal = {Journal of Economic Literature},
  year    = {2019}, volume = {57}, number = {3}, pages = {535--574},
  doi     = {10.1257/jel.20181020}
}
@article{hassan2019,
  author  = {Hassan, Tarek A. and Hollander, Stephan and van Lent, Laurence and Tahoun, Ahmed},
  title   = {Firm-Level Political Risk: Measurement and Effects},
  journal = {Quarterly Journal of Economics},
  year    = {2019}, volume = {134}, number = {4}, pages = {2135--2202},
  doi     = {10.1093/qje/qjz021}
}
@article{cohen2020,
  author  = {Cohen, Lauren and Malloy, Christopher and Nguyen, Quoc},
  title   = {Lazy Prices},
  journal = {Journal of Finance},
  year    = {2020}, volume = {75}, number = {3}, pages = {1371--1415},
  doi     = {10.1111/jofi.12885}
}
@article{kelly2021,
  author  = {Kelly, Bryan and Papanikolaou, Dimitris and Seru, Amit and Taddy, Matt},
  title   = {Measuring Technological Innovation over the Long Run},
  journal = {American Economic Review: Insights},
  year    = {2021}, volume = {3}, number = {3}, pages = {303--320},
  doi     = {10.1257/aeri.20190499}
}
@techreport{bloom2021,
  author      = {Bloom, Nicholas and Hassan, Tarek A. and Kalyani, Aakash and Lerner, Josh and Tahoun, Ahmed},
  title       = {The Diffusion of Disruptive Technologies},
  institution = {National Bureau of Economic Research},
  type        = {NBER Working Paper},
  number      = {28999},
  year        = {2021},
  doi         = {10.3386/w28999}
}
@article{dyer2017,
  author  = {Dyer, Travis and Lang, Mark and Stice-Lawrence, Lorien},
  title   = {The Evolution of 10-{K} Textual Disclosure: Evidence from {L}atent {D}irichlet {A}llocation},
  journal = {Journal of Accounting and Economics},
  year    = {2017}, volume = {64}, number = {2--3}, pages = {221--245},
  doi     = {10.1016/j.jacceco.2017.07.002}
}
@article{li2021,
  author  = {Li, Kai and Mai, Feng and Shen, Rui and Yan, Xinyan},
  title   = {Measuring Corporate Culture Using Machine Learning},
  journal = {Review of Financial Studies},
  year    = {2021}, volume = {34}, number = {7}, pages = {3265--3315},
  doi     = {10.1093/rfs/hhaa079}
}
@article{grimmer2013,
  author  = {Grimmer, Justin and Stewart, Brandon M.},
  title   = {Text as Data: The Promise and Pitfalls of Automatic Content Analysis Methods for Political Texts},
  journal = {Political Analysis},
  year    = {2013}, volume = {21}, number = {3}, pages = {267--297},
  doi     = {10.1093/pan/mps028}
}
@article{fellegi1969,
  author  = {Fellegi, Ivan P. and Sunter, Alan B.},
  title   = {A Theory for Record Linkage},
  journal = {Journal of the American Statistical Association},
  year    = {1969}, volume = {64}, number = {328}, pages = {1183--1210},
  doi     = {10.1080/01621459.1969.10501049}
}
@book{christen2012,
  author    = {Christen, Peter},
  title     = {Data Matching: Concepts and Techniques for Record Linkage, Entity Resolution, and Duplicate Detection},
  publisher = {Springer},
  address   = {Berlin},
  year      = {2012},
  doi       = {10.1007/978-3-642-31164-2}
}
@inproceedings{reimers2019,
  author    = {Reimers, Nils and Gurevych, Iryna},
  title     = {Sentence-{BERT}: Sentence Embeddings using {S}iamese {BERT}-Networks},
  booktitle = {Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing (EMNLP-IJCNLP)},
  year      = {2019}, pages = {3982--3992},
  doi       = {10.18653/v1/D19-1410}
}
@inproceedings{raasveldt2019,
  author    = {Raasveldt, Mark and M{\"u}hleisen, Hannes},
  title     = {{DuckDB}: An Embeddable Analytical Database},
  booktitle = {Proceedings of the 2019 International Conference on Management of Data (SIGMOD)},
  year      = {2019}, pages = {1981--1984},
  doi       = {10.1145/3299869.3320212}
}
@misc{secfairaccess,
  author       = {{U.S. Securities and Exchange Commission}},
  title        = {Accessing {EDGAR} Data: Fair Access Policy},
  howpublished = {\url{https://www.sec.gov/os/accessing-edgar-data}},
  year         = {2024},
  note         = {Accessed October 2026}
}
@misc{ftserussell2026,
  author       = {{FTSE Russell}},
  title        = {Russell {US} Equity Indexes: Construction and Methodology},
  howpublished = {\url{https://www.lseg.com/en/ftse-russell/indices/russell-us}},
  year         = {2026},
  note         = {Accessed October 2026}
}
@techreport{spid2026,
  author      = {Tandjambianda, Djerrycharli and Boucher, Simon-Pierre and Kammoun, Manel},
  title       = {{SPID} --- {SEC} Project Intelligence Database: A Methodological Report on the {S\&P}~500 Release},
  institution = {Université du Québec en Outaouais, Département des sciences administratives},
  type        = {Internal methodological report},
  year        = {2026},
  note        = {Revision df7905d; October 28, 2026}
}