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

\harvarditem[Afzal et al.]{Afzal, Yan, Li and Vasarhelyi}{2026}{afzal2026}
{\bf Afzal, Muhammad~Talha, Jinqiu~(Claire) Yan, Huaxia Li, and Miklos
  Vasarhelyi}, ``Beyond the bottom line: using generative AI to extract
  narrative financial disclosures,'' {\it International Journal of Accounting
  Information Systems}, 2026, {\it 57}, 100777.

\harvarditem[Bellstam et al.]{Bellstam, Bhagat and Cookson}{2021}{bellstam2021}
{\bf Bellstam, Gustaf, Sanjai Bhagat, and J.~Anthony Cookson}, ``A Text-Based
  Analysis of Corporate Innovation,'' {\it Management Science}, 2021, {\it 67}
  (7), 4004--4031.

\harvarditem[Bettencourt et al.]{Bettencourt, Ding and
  Giesecke}{2026}{bettencourt2026}
{\bf Bettencourt, Nick, Xiaowei Ding, and Kay Giesecke}, ``The {Stanford}
  {EDGAR} Filings Dataset: Reconstructing U.S. Corporate and Financial
  Disclosures into Layout-Faithful and Token-Efficient Pretraining Data,''
  arXiv:2606.18192; also SSRN 7161699 (DOI 10.2139/ssrn.7161699) 2026.

\harvarditem[{BlackRock, Inc.}]{{BlackRock, Inc.}}{2026}{iwvholdings2026}
{\bf {BlackRock, Inc.}}, ``{iShares} {R}ussell 3000 {ETF} ({IWV}): Fund
  holdings file (\texttt{latest-holdings.csv}),''
  \url{https://www.ishares.com/us/products/239714/ishares-russell-3000-etf}
  2026.
\newblock Holdings as of October 23, 2026, downloaded October 27, 2026; subject
  to the iShares website terms of use; the downloaded file is not archived with
  the paper.

\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[Crane et al.]{Crane, Green, Harnish, McClennan, Soto, Vrankovich
  and Williams}{2024}{crane2024}
{\bf Crane, Leland~D., Emily Green, Molly Harnish, Will McClennan, Paul~E.
  Soto, Betsy Vrankovich, and Jacob Williams}, ``Tracking Real Time Layoffs
  with {SEC} Filings: A Preliminary Investigation,'' Finance and Economics
  Discussion Series 2024-020, Board of Governors of the Federal Reserve System
  2024.

\harvarditem[de~Kok]{de~Kok}{2025}{dekok2025}
{\bf de~Kok, Ties}, ``{ChatGPT} for Textual Analysis? How to Use Generative
  {LLMs} in Accounting Research,'' {\it Management Science}, 2025, {\it 71}
  (9), 7888--7906.

\harvarditem[Dolphin et al.]{Dolphin, Dursun, Blankenship, Adams and
  Pike}{2026}{dolphin2026}
{\bf Dolphin, Rian, Joe Dursun, Jarrett Blankenship, Katie Adams, and Quinton
  Pike}, ``Grounded Event Extraction from {SEC} {8-K} Filings with a
  Fine-Grained Taxonomy,'' arXiv:2607.08346; also SSRN 7087858 (DOI
  10.2139/ssrn.7087858) 2026.

\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}}{2026a}{ftserussell3000factsheet2026}
{\bf {FTSE Russell}}, ``Russell 3000 Index Factsheet,''
  \url{https://research.ftserussell.com/Analytics/FactSheets/Home/DownloadSingleIssue?issueName=US3000USD}
  2026.
\newblock Index characteristics as of September 30, 2026 (2,996 holdings);
  downloaded November 5, 2026.

\harvarditem[{FTSE Russell}]{{FTSE Russell}}{2026b}{ftserussell2026}
{\bf \bysame{}}, ``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[Gilardi et al.]{Gilardi, Alizadeh and Kubli}{2023}{gilardi2023}
{\bf Gilardi, Fabrizio, Meysam Alizadeh, and Maël Kubli}, ``{ChatGPT}
  outperforms crowd workers for text-annotation tasks,'' {\it Proceedings of
  the National Academy of Sciences}, 2023, {\it 120} (30), e2305016120.

\harvarditem[Greenstone et al.]{Greenstone, Hornbeck and
  Moretti}{2010}{greenstone2010}
{\bf Greenstone, Michael, Richard Hornbeck, and Enrico Moretti}, ``Identifying
  Agglomeration Spillovers: Evidence from Winners and Losers of Large Plant
  Openings,'' {\it Journal of Political Economy}, 2010, {\it 118} (3),
  536--598.

\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[Jha et al.]{Jha, Qian, Weber and Yang}{2024}{jha2024}
{\bf Jha, Manish, Jialin Qian, Michael Weber, and Baozhong Yang}, ``{ChatGPT}
  and Corporate Policies,'' NBER Working Paper 32161, National Bureau of
  Economic Research 2024.

\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[Kammoun et al.]{Kammoun, Tandjambianda and
  Boucher}{2026}{kammoun2026ai}
{\bf Kammoun, Manel, Djerrycharli Tandjambianda, and Simon-Pierre Boucher},
  ``Does the Language of Artificial Intelligence Move Markets? {A} Semantic
  Analysis of {R}ussell~3000 {SEC} Filings and the Cross-Section of Stock
  Returns, 2010--2026,'' UQO Working Paper (FIRC) 0002, Université du Québec
  en Outaouais, Département des sciences administratives 2026.
\newblock Version 2.0, October 28, 2026.

\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[Kim et al.]{Kim, Muhn and Nikolaev}{2023}{kim2023}
{\bf Kim, Alex~G., Maximilian Muhn, and Valeri~V. Nikolaev}, ``From Transcripts
  to Insights: Uncovering Corporate Risks Using Generative AI,'' Working paper
  4593660, SSRN 2023.

\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[Li et al.]{Li, Li, Suhara, Doan and Tan}{2020}{li2020}
{\bf Li, Yuliang, Jinfeng Li, Yoshihiko Suhara, AnHai Doan, and Wang-Chiew
  Tan}, ``Deep entity matching with pre-trained language models,'' {\it
  Proceedings of the VLDB Endowment}, 2020, {\it 14} (1), 50--60.

\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[Loukas et al.]{Loukas, Fergadiotis, Androutsopoulos and
  Malakasiotis}{2021}{loukas2021}
{\bf Loukas, Lefteris, Manos Fergadiotis, Ion Androutsopoulos, and Prodromos
  Malakasiotis}, ``{EDGAR-CORPUS}: Billions of Tokens Make The World Go
  Round,'' in ``Proceedings of the Third Workshop on Economics and Natural
  Language Processing'' 2021, pp.~13--18.

\harvarditem[Ludwig et al.]{Ludwig, Mullainathan and
  Rambachan}{2026}{ludwig2025}
{\bf Ludwig, Jens, Sendhil Mullainathan, and Ashesh Rambachan}, ``Large
  Language Models: An Applied Econometric Framework,'' {\it Annual Review of
  Economics}, 2026, {\it 18} (1), 283--316.
\newblock Also NBER Working Paper 33344 (2025, DOI 10.3386/w33344).

\harvarditem[McConnell and Muscarella]{McConnell and
  Muscarella}{1985}{mcconnell1985}
{\bf McConnell, J and Chris~J. Muscarella}, ``Corporate capital expenditure
  decisions and the market value of the firm,'' {\it Journal of Financial
  Economics}, 1985, {\it 14} (3), 399--422.

\harvarditem[Peeters et al.]{Peeters, Steiner and Bizer}{2023}{peeters2023}
{\bf Peeters, Ralph, Aaron Steiner, and Christian Bizer}, ``Entity Matching
  using Large Language Models,'' arXiv:2310.11244 2023.

\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[Sautner et al.]{Sautner, van Lent, Vilkov and
  Zhang}{2023}{sautner2023}
{\bf Sautner, Zacharias, Laurence van Lent, Grigory Vilkov, and Ruishen Zhang},
  ``Firm-Level Climate Change Exposure,'' {\it Journal of Finance}, 2023, {\it
  78} (3), 1449--1498.

\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).

\harvarditem[{Wikipedia contributors}]{{Wikipedia
  contributors}}{2026}{wikipediasp500}
{\bf {Wikipedia contributors}}, ``List of {S\&P} 500 companies,''
  \url{https://en.wikipedia.org/wiki/List_of_S%26P_500_companies} 2026.
\newblock Table scraped May 25, 2026; text available under the Creative Commons
  Attribution-ShareAlike 4.0 licence.

\harvarditem[Yang et al.]{Yang, Tsai and Yamada}{2024}{yang2024}
{\bf Yang, Daniel, Yao-Hung~Hubert Tsai, and Makoto Yamada}, ``On Verbalized
  Confidence Scores for {LLMs},'' arXiv:2412.14737 2024.

\harvarditem[Ye et al.]{Ye, Yang, Pang, Wang, Wong, Yilmaz, Shi and
  Tu}{2024}{ye2024}
{\bf Ye, Fanghua, Mingming Yang, Jianhui Pang, Longyue Wang, Derek Wong, Emine
  Yilmaz, Shuming Shi, and Zhaopeng Tu}, ``Benchmarking {LLMs} via Uncertainty
  Quantification,'' in ``Advances in Neural Information Processing Systems 37
  (NeurIPS 2024)'' 2024, pp.~15356--15385.

\harvarditem[Zolas et al.]{Zolas, Kroff, Brynjolfsson, McElheran, Beede,
  Buffington, Goldschlag, Foster and Dinlersoz}{2020}{zolas2020}
{\bf Zolas, Nikolas, Zachary Kroff, Erik Brynjolfsson, Kristina McElheran,
  David Beede, Cathy Buffington, Nathan Goldschlag, Lucia Foster, and Emin
  Dinlersoz}, ``Advanced Technologies Adoption and Use by U.S. Firms: Evidence
  from the Annual Business Survey,'' NBER Working Paper 28290, National Bureau
  of Economic Research 2020.

\end{thebibliography}