\ifx\undefined\bysame
\newcommand{\bysame}{\leavevmode\hbox to\leftmargin{\hrulefill\,\,}}
\fi
\begin{thebibliography}{xx}

\harvarditem[Christen]{Christen}{2012}{christen2012}
{\bf Christen, Peter}, {\it Data Matching: Concepts and Techniques for Record
  Linkage, Entity Resolution, and Duplicate Detection}, Berlin: Springer, 2012.

\harvarditem[Cohen et al.]{Cohen, Malloy and Nguyen}{2020}{cohen2020}
{\bf Cohen, Lauren, Christopher Malloy, and Quoc Nguyen}, ``Lazy Prices,'' {\it
  Journal of Finance}, 2020, {\it 75} (3), 1371--1415.

\harvarditem[Dyer et al.]{Dyer, Lang and Stice-Lawrence}{2017}{dyer2017}
{\bf Dyer, Travis, Mark Lang, and Lorien Stice-Lawrence}, ``The Evolution of
  10-{K} Textual Disclosure: Evidence from {L}atent {D}irichlet {A}llocation,''
  {\it Journal of Accounting and Economics}, 2017, {\it 64} (2--3), 221--245.

\harvarditem[Fellegi and Sunter]{Fellegi and Sunter}{1969}{fellegi1969}
{\bf Fellegi, Ivan~P. and Alan~B. Sunter}, ``A Theory for Record Linkage,''
  {\it Journal of the American Statistical Association}, 1969, {\it 64} (328),
  1183--1210.

\harvarditem[{FTSE Russell}]{{FTSE Russell}}{2026}{ftserussell2026}
{\bf {FTSE Russell}}, ``Russell {US} Equity Indexes: Construction and
  Methodology, v7.2,''
  \url{https://www.lseg.com/content/dam/ftse-russell/en_us/documents/ground-rules/russell-us-indexes-construction-and-methodology.pdf}
  August 2026.
\newblock Document dated August 2026; downloaded November 5, 2026.

\harvarditem[Gentzkow et al.]{Gentzkow, Kelly and Taddy}{2019}{gentzkow2019}
{\bf Gentzkow, Matthew, Bryan Kelly, and Matt Taddy}, ``Text as Data,'' {\it
  Journal of Economic Literature}, 2019, {\it 57} (3), 535--574.

\harvarditem[Grimmer and Stewart]{Grimmer and Stewart}{2013}{grimmer2013}
{\bf Grimmer, Justin and Brandon~M. Stewart}, ``Text as Data: The Promise and
  Pitfalls of Automatic Content Analysis Methods for Political Texts,'' {\it
  Political Analysis}, 2013, {\it 21} (3), 267--297.

\harvarditem[Hassan et al.]{Hassan, Hollander, van Lent and
  Tahoun}{2019}{hassan2019}
{\bf Hassan, Tarek~A., Stephan Hollander, Laurence van Lent, and Ahmed Tahoun},
  ``Firm-Level Political Risk: Measurement and Effects,'' {\it Quarterly
  Journal of Economics}, 2019, {\it 134} (4), 2135--2202.

\harvarditem[Hoberg and Phillips]{Hoberg and Phillips}{2016}{hoberg2016}
{\bf Hoberg, Gerard and Gordon Phillips}, ``Text-Based Network Industries and
  Endogenous Product Differentiation,'' {\it Journal of Political Economy},
  2016, {\it 124} (5), 1423--1465.

\harvarditem[Hoberg and Maksimovic]{Hoberg and
  Maksimovic}{2015}{hobergmaksimovic2015}
{\bf \bysame{} and Vojislav Maksimovic}, ``Redefining Financial Constraints: A
  Text-Based Analysis,'' {\it Review of Financial Studies}, 2015, {\it 28} (5),
  1312--1352.

\harvarditem[Kalyani et al.]{Kalyani, Bloom, Carvalho, Hassan, Lerner and
  Tahoun}{2025}{kalyani2025}
{\bf Kalyani, Aakash, Nicholas Bloom, Marcela Carvalho, Tarek Hassan, Josh
  Lerner, and Ahmed Tahoun}, ``The Diffusion of New Technologies,'' {\it
  Quarterly Journal of Economics}, 2025, {\it 140} (2), 1299--1365.
\newblock Published version of NBER Working Paper 28999 (2021, DOI
  10.3386/w28999).

\harvarditem[Kelly et al.]{Kelly, Papanikolaou, Seru and
  Taddy}{2021}{kelly2021}
{\bf Kelly, Bryan, Dimitris Papanikolaou, Amit Seru, and Matt Taddy},
  ``Measuring Technological Innovation over the Long Run,'' {\it American
  Economic Review: Insights}, 2021, {\it 3} (3), 303--320.

\harvarditem[Li et al.]{Li, Mai, Shen and Yan}{2021}{li2021}
{\bf Li, Kai, Feng Mai, Rui Shen, and Xinyan Yan}, ``Measuring Corporate
  Culture Using Machine Learning,'' {\it Review of Financial Studies}, 2021,
  {\it 34} (7), 3265--3315.

\harvarditem[Loughran and McDonald]{Loughran and McDonald}{2011}{loughran2011}
{\bf Loughran, Tim and Bill McDonald}, ``When Is a Liability Not a Liability?
  {T}extual Analysis, Dictionaries, and 10-{K}s,'' {\it Journal of Finance},
  2011, {\it 66} (1), 35--65.

\harvarditem[Loughran and McDonald]{Loughran and McDonald}{2016}{loughran2016}
{\bf \bysame{} and \bysame{}}, ``Textual Analysis in Accounting and Finance: A
  Survey,'' {\it Journal of Accounting Research}, 2016, {\it 54} (4),
  1187--1230.

\harvarditem[Raasveldt and M{\"u}hleisen]{Raasveldt and
  M{\"u}hleisen}{2019}{raasveldt2019}
{\bf Raasveldt, Mark and Hannes M{\"u}hleisen}, ``{DuckDB}: An Embeddable
  Analytical Database,'' in ``Proceedings of the 2019 International Conference
  on Management of Data (SIGMOD)'' 2019, pp.~1981--1984.

\harvarditem[Reimers and Gurevych]{Reimers and Gurevych}{2019}{reimers2019}
{\bf Reimers, Nils and Iryna Gurevych}, ``Sentence-{BERT}: Sentence Embeddings
  using {S}iamese {BERT}-Networks,'' in ``Proceedings of the 2019 Conference on
  Empirical Methods in Natural Language Processing (EMNLP-IJCNLP)'' 2019,
  pp.~3982--3992.

\harvarditem[Tandjambianda et al.]{Tandjambianda, Boucher and
  Kammoun}{2026}{spid2026}
{\bf Tandjambianda, Djerrycharli, Simon-Pierre Boucher, and Manel Kammoun},
  ``{SPID} --- {SEC} Project Intelligence Database: A Methodological Report on
  the {S\&P}~500 Release,'' Unpublished internal methodological report,
  available from the authors, Université du Québec en Outaouais, Département
  des sciences administratives 2026.
\newblock June 2026 study of revision \texttt{df7905d}; the report file was
  regenerated on October 28, 2026.

\harvarditem[{U.S. Securities and Exchange Commission}]{{U.S. Securities and
  Exchange Commission}}{2026}{secfairaccess}
{\bf {U.S. Securities and Exchange Commission}}, ``Accessing {EDGAR} Data: Fair
  Access Policy,''
  \url{https://www.sec.gov/search-filings/edgar-search-assistance/accessing-edgar-data}
  2026.
\newblock Accessed October 2026; URL re-verified November 5, 2026 (the former
  \texttt{/os/accessing-edgar-data} address redirects here).

\end{thebibliography}