spb/firc0001_uqo
Public
1\ifx\undefined\bysame2\newcommand{\bysame}{\leavevmode\hbox to\leftmargin{\hrulefill\,\,}}3\fi4\begin{thebibliography}{xx}56\harvarditem[Afzal et al.]{Afzal, Yan, Li and Vasarhelyi}{2026}{afzal2026}7{\bf Afzal, Muhammad~Talha, Jinqiu~(Claire) Yan, Huaxia Li, and Miklos8 Vasarhelyi}, ``Beyond the bottom line: using generative AI to extract9 narrative financial disclosures,'' {\it International Journal of Accounting10 Information Systems}, 2026, {\it 57}, 100777.1112\harvarditem[Bellstam et al.]{Bellstam, Bhagat and Cookson}{2021}{bellstam2021}13{\bf Bellstam, Gustaf, Sanjai Bhagat, and J.~Anthony Cookson}, ``A Text-Based14 Analysis of Corporate Innovation,'' {\it Management Science}, 2021, {\it 67}15 (7), 4004--4031.1617\harvarditem[Bettencourt et al.]{Bettencourt, Ding and18 Giesecke}{2026}{bettencourt2026}19{\bf Bettencourt, Nick, Xiaowei Ding, and Kay Giesecke}, ``The {Stanford}20 {EDGAR} Filings Dataset: Reconstructing U.S. Corporate and Financial21 Disclosures into Layout-Faithful and Token-Efficient Pretraining Data,''22 arXiv:2606.18192; also SSRN 7161699 (DOI 10.2139/ssrn.7161699) 2026.2324\harvarditem[{BlackRock, Inc.}]{{BlackRock, Inc.}}{2026}{iwvholdings2026}25{\bf {BlackRock, Inc.}}, ``{iShares} {R}ussell 3000 {ETF} ({IWV}): Fund26 holdings file (\texttt{latest-holdings.csv}),''27 \url{https://www.ishares.com/us/products/239714/ishares-russell-3000-etf}28 2026.29\newblock Holdings as of October 23, 2026, downloaded October 27, 2026; subject30 to the iShares website terms of use; the downloaded file is not archived with31 the paper.3233\harvarditem[Christen]{Christen}{2012}{christen2012}34{\bf Christen, Peter}, {\it Data Matching: Concepts and Techniques for Record35 Linkage, Entity Resolution, and Duplicate Detection}, Berlin: Springer, 2012.3637\harvarditem[Cohen et al.]{Cohen, Malloy and Nguyen}{2020}{cohen2020}38{\bf Cohen, Lauren, Christopher Malloy, and Quoc Nguyen}, ``Lazy Prices,'' {\it39 Journal of Finance}, 2020, {\it 75} (3), 1371--1415.4041\harvarditem[Crane et al.]{Crane, Green, Harnish, McClennan, Soto, Vrankovich42 and Williams}{2024}{crane2024}43{\bf Crane, Leland~D., Emily Green, Molly Harnish, Will McClennan, Paul~E.44 Soto, Betsy Vrankovich, and Jacob Williams}, ``Tracking Real Time Layoffs45 with {SEC} Filings: A Preliminary Investigation,'' Finance and Economics46 Discussion Series 2024-020, Board of Governors of the Federal Reserve System47 2024.4849\harvarditem[de~Kok]{de~Kok}{2025}{dekok2025}50{\bf de~Kok, Ties}, ``{ChatGPT} for Textual Analysis? How to Use Generative51 {LLMs} in Accounting Research,'' {\it Management Science}, 2025, {\it 71}52 (9), 7888--7906.5354\harvarditem[Dolphin et al.]{Dolphin, Dursun, Blankenship, Adams and55 Pike}{2026}{dolphin2026}56{\bf Dolphin, Rian, Joe Dursun, Jarrett Blankenship, Katie Adams, and Quinton57 Pike}, ``Grounded Event Extraction from {SEC} {8-K} Filings with a58 Fine-Grained Taxonomy,'' arXiv:2607.08346; also SSRN 7087858 (DOI59 10.2139/ssrn.7087858) 2026.6061\harvarditem[Dyer et al.]{Dyer, Lang and Stice-Lawrence}{2017}{dyer2017}62{\bf Dyer, Travis, Mark Lang, and Lorien Stice-Lawrence}, ``The Evolution of63 10-{K} Textual Disclosure: Evidence from {L}atent {D}irichlet {A}llocation,''64 {\it Journal of Accounting and Economics}, 2017, {\it 64} (2--3), 221--245.6566\harvarditem[Fellegi and Sunter]{Fellegi and Sunter}{1969}{fellegi1969}67{\bf Fellegi, Ivan~P. and Alan~B. Sunter}, ``A Theory for Record Linkage,''68 {\it Journal of the American Statistical Association}, 1969, {\it 64} (328),69 1183--1210.7071\harvarditem[{FTSE Russell}]{{FTSE72 Russell}}{2026a}{ftserussell3000factsheet2026}73{\bf {FTSE Russell}}, ``Russell 3000 Index Factsheet,''74 \url{https://research.ftserussell.com/Analytics/FactSheets/Home/DownloadSingleIssue?issueName=US3000USD}75 2026.76\newblock Index characteristics as of September 30, 2026 (2,996 holdings);77 downloaded November 5, 2026.7879\harvarditem[{FTSE Russell}]{{FTSE Russell}}{2026b}{ftserussell2026}80{\bf \bysame{}}, ``Russell {US} Equity Indexes: Construction and Methodology,81 v7.2,''82 \url{https://www.lseg.com/content/dam/ftse-russell/en_us/documents/ground-rules/russell-us-indexes-construction-and-methodology.pdf}83 August 2026.84\newblock Document dated August 2026; downloaded November 5, 2026.8586\harvarditem[Gentzkow et al.]{Gentzkow, Kelly and Taddy}{2019}{gentzkow2019}87{\bf Gentzkow, Matthew, Bryan Kelly, and Matt Taddy}, ``Text as Data,'' {\it88 Journal of Economic Literature}, 2019, {\it 57} (3), 535--574.8990\harvarditem[Gilardi et al.]{Gilardi, Alizadeh and Kubli}{2023}{gilardi2023}91{\bf Gilardi, Fabrizio, Meysam Alizadeh, and Maël Kubli}, ``{ChatGPT}92 outperforms crowd workers for text-annotation tasks,'' {\it Proceedings of93 the National Academy of Sciences}, 2023, {\it 120} (30), e2305016120.9495\harvarditem[Greenstone et al.]{Greenstone, Hornbeck and96 Moretti}{2010}{greenstone2010}97{\bf Greenstone, Michael, Richard Hornbeck, and Enrico Moretti}, ``Identifying98 Agglomeration Spillovers: Evidence from Winners and Losers of Large Plant99 Openings,'' {\it Journal of Political Economy}, 2010, {\it 118} (3),100 536--598.101102\harvarditem[Grimmer and Stewart]{Grimmer and Stewart}{2013}{grimmer2013}103{\bf Grimmer, Justin and Brandon~M. Stewart}, ``Text as Data: The Promise and104 Pitfalls of Automatic Content Analysis Methods for Political Texts,'' {\it105 Political Analysis}, 2013, {\it 21} (3), 267--297.106107\harvarditem[Hassan et al.]{Hassan, Hollander, van Lent and108 Tahoun}{2019}{hassan2019}109{\bf Hassan, Tarek~A., Stephan Hollander, Laurence van Lent, and Ahmed Tahoun},110 ``Firm-Level Political Risk: Measurement and Effects,'' {\it Quarterly111 Journal of Economics}, 2019, {\it 134} (4), 2135--2202.112113\harvarditem[Hoberg and Phillips]{Hoberg and Phillips}{2016}{hoberg2016}114{\bf Hoberg, Gerard and Gordon Phillips}, ``Text-Based Network Industries and115 Endogenous Product Differentiation,'' {\it Journal of Political Economy},116 2016, {\it 124} (5), 1423--1465.117118\harvarditem[Hoberg and Maksimovic]{Hoberg and119 Maksimovic}{2015}{hobergmaksimovic2015}120{\bf \bysame{} and Vojislav Maksimovic}, ``Redefining Financial Constraints: A121 Text-Based Analysis,'' {\it Review of Financial Studies}, 2015, {\it 28} (5),122 1312--1352.123124\harvarditem[Jha et al.]{Jha, Qian, Weber and Yang}{2024}{jha2024}125{\bf Jha, Manish, Jialin Qian, Michael Weber, and Baozhong Yang}, ``{ChatGPT}126 and Corporate Policies,'' NBER Working Paper 32161, National Bureau of127 Economic Research 2024.128129\harvarditem[Kalyani et al.]{Kalyani, Bloom, Carvalho, Hassan, Lerner and130 Tahoun}{2025}{kalyani2025}131{\bf Kalyani, Aakash, Nicholas Bloom, Marcela Carvalho, Tarek Hassan, Josh132 Lerner, and Ahmed Tahoun}, ``The Diffusion of New Technologies,'' {\it133 Quarterly Journal of Economics}, 2025, {\it 140} (2), 1299--1365.134\newblock Published version of NBER Working Paper 28999 (2021, DOI135 10.3386/w28999).136137\harvarditem[Kammoun et al.]{Kammoun, Tandjambianda and138 Boucher}{2026}{kammoun2026ai}139{\bf Kammoun, Manel, Djerrycharli Tandjambianda, and Simon-Pierre Boucher},140 ``Does the Language of Artificial Intelligence Move Markets? {A} Semantic141 Analysis of {R}ussell~3000 {SEC} Filings and the Cross-Section of Stock142 Returns, 2010--2026,'' UQO Working Paper (FIRC) 0002, Université du Québec143 en Outaouais, Département des sciences administratives 2026.144\newblock Version 2.0, October 28, 2026.145146\harvarditem[Kelly et al.]{Kelly, Papanikolaou, Seru and147 Taddy}{2021}{kelly2021}148{\bf Kelly, Bryan, Dimitris Papanikolaou, Amit Seru, and Matt Taddy},149 ``Measuring Technological Innovation over the Long Run,'' {\it American150 Economic Review: Insights}, 2021, {\it 3} (3), 303--320.151152\harvarditem[Kim et al.]{Kim, Muhn and Nikolaev}{2023}{kim2023}153{\bf Kim, Alex~G., Maximilian Muhn, and Valeri~V. Nikolaev}, ``From Transcripts154 to Insights: Uncovering Corporate Risks Using Generative AI,'' Working paper155 4593660, SSRN 2023.156157\harvarditem[Li et al.]{Li, Mai, Shen and Yan}{2021}{li2021}158{\bf Li, Kai, Feng Mai, Rui Shen, and Xinyan Yan}, ``Measuring Corporate159 Culture Using Machine Learning,'' {\it Review of Financial Studies}, 2021,160 {\it 34} (7), 3265--3315.161162\harvarditem[Li et al.]{Li, Li, Suhara, Doan and Tan}{2020}{li2020}163{\bf Li, Yuliang, Jinfeng Li, Yoshihiko Suhara, AnHai Doan, and Wang-Chiew164 Tan}, ``Deep entity matching with pre-trained language models,'' {\it165 Proceedings of the VLDB Endowment}, 2020, {\it 14} (1), 50--60.166167\harvarditem[Loughran and McDonald]{Loughran and McDonald}{2011}{loughran2011}168{\bf Loughran, Tim and Bill McDonald}, ``When Is a Liability Not a Liability?169 {T}extual Analysis, Dictionaries, and 10-{K}s,'' {\it Journal of Finance},170 2011, {\it 66} (1), 35--65.171172\harvarditem[Loughran and McDonald]{Loughran and McDonald}{2016}{loughran2016}173{\bf \bysame{} and \bysame{}}, ``Textual Analysis in Accounting and Finance: A174 Survey,'' {\it Journal of Accounting Research}, 2016, {\it 54} (4),175 1187--1230.176177\harvarditem[Loukas et al.]{Loukas, Fergadiotis, Androutsopoulos and178 Malakasiotis}{2021}{loukas2021}179{\bf Loukas, Lefteris, Manos Fergadiotis, Ion Androutsopoulos, and Prodromos180 Malakasiotis}, ``{EDGAR-CORPUS}: Billions of Tokens Make The World Go181 Round,'' in ``Proceedings of the Third Workshop on Economics and Natural182 Language Processing'' 2021, pp.~13--18.183184\harvarditem[Ludwig et al.]{Ludwig, Mullainathan and185 Rambachan}{2026}{ludwig2025}186{\bf Ludwig, Jens, Sendhil Mullainathan, and Ashesh Rambachan}, ``Large187 Language Models: An Applied Econometric Framework,'' {\it Annual Review of188 Economics}, 2026, {\it 18} (1), 283--316.189\newblock Also NBER Working Paper 33344 (2025, DOI 10.3386/w33344).190191\harvarditem[McConnell and Muscarella]{McConnell and192 Muscarella}{1985}{mcconnell1985}193{\bf McConnell, J and Chris~J. Muscarella}, ``Corporate capital expenditure194 decisions and the market value of the firm,'' {\it Journal of Financial195 Economics}, 1985, {\it 14} (3), 399--422.196197\harvarditem[Peeters et al.]{Peeters, Steiner and Bizer}{2023}{peeters2023}198{\bf Peeters, Ralph, Aaron Steiner, and Christian Bizer}, ``Entity Matching199 using Large Language Models,'' arXiv:2310.11244 2023.200201\harvarditem[Raasveldt and M{\"u}hleisen]{Raasveldt and202 M{\"u}hleisen}{2019}{raasveldt2019}203{\bf Raasveldt, Mark and Hannes M{\"u}hleisen}, ``{DuckDB}: An Embeddable204 Analytical Database,'' in ``Proceedings of the 2019 International Conference205 on Management of Data (SIGMOD)'' 2019, pp.~1981--1984.206207\harvarditem[Reimers and Gurevych]{Reimers and Gurevych}{2019}{reimers2019}208{\bf Reimers, Nils and Iryna Gurevych}, ``Sentence-{BERT}: Sentence Embeddings209 using {S}iamese {BERT}-Networks,'' in ``Proceedings of the 2019 Conference on210 Empirical Methods in Natural Language Processing (EMNLP-IJCNLP)'' 2019,211 pp.~3982--3992.212213\harvarditem[Sautner et al.]{Sautner, van Lent, Vilkov and214 Zhang}{2023}{sautner2023}215{\bf Sautner, Zacharias, Laurence van Lent, Grigory Vilkov, and Ruishen Zhang},216 ``Firm-Level Climate Change Exposure,'' {\it Journal of Finance}, 2023, {\it217 78} (3), 1449--1498.218219\harvarditem[Tandjambianda et al.]{Tandjambianda, Boucher and220 Kammoun}{2026}{spid2026}221{\bf Tandjambianda, Djerrycharli, Simon-Pierre Boucher, and Manel Kammoun},222 ``{SPID} --- {SEC} Project Intelligence Database: A Methodological Report on223 the {S\&P}~500 Release,'' Unpublished internal methodological report,224 available from the authors, Université du Québec en Outaouais, Département225 des sciences administratives 2026.226\newblock June 2026 study of revision \texttt{df7905d}; the report file was227 regenerated on October 28, 2026.228229\harvarditem[{U.S. Securities and Exchange Commission}]{{U.S. Securities and230 Exchange Commission}}{2026}{secfairaccess}231{\bf {U.S. Securities and Exchange Commission}}, ``Accessing {EDGAR} Data: Fair232 Access Policy,''233 \url{https://www.sec.gov/search-filings/edgar-search-assistance/accessing-edgar-data}234 2026.235\newblock Accessed October 2026; URL re-verified November 5, 2026 (the former236 \texttt{/os/accessing-edgar-data} address redirects here).237238\harvarditem[{Wikipedia contributors}]{{Wikipedia239 contributors}}{2026}{wikipediasp500}240{\bf {Wikipedia contributors}}, ``List of {S\&P} 500 companies,''241 \url{https://en.wikipedia.org/wiki/List_of_S%26P_500_companies} 2026.242\newblock Table scraped May 25, 2026; text available under the Creative Commons243 Attribution-ShareAlike 4.0 licence.244245\harvarditem[Yang et al.]{Yang, Tsai and Yamada}{2024}{yang2024}246{\bf Yang, Daniel, Yao-Hung~Hubert Tsai, and Makoto Yamada}, ``On Verbalized247 Confidence Scores for {LLMs},'' arXiv:2412.14737 2024.248249\harvarditem[Ye et al.]{Ye, Yang, Pang, Wang, Wong, Yilmaz, Shi and250 Tu}{2024}{ye2024}251{\bf Ye, Fanghua, Mingming Yang, Jianhui Pang, Longyue Wang, Derek Wong, Emine252 Yilmaz, Shuming Shi, and Zhaopeng Tu}, ``Benchmarking {LLMs} via Uncertainty253 Quantification,'' in ``Advances in Neural Information Processing Systems 37254 (NeurIPS 2024)'' 2024, pp.~15356--15385.255256\harvarditem[Zolas et al.]{Zolas, Kroff, Brynjolfsson, McElheran, Beede,257 Buffington, Goldschlag, Foster and Dinlersoz}{2020}{zolas2020}258{\bf Zolas, Nikolas, Zachary Kroff, Erik Brynjolfsson, Kristina McElheran,259 David Beede, Cathy Buffington, Nathan Goldschlag, Lucia Foster, and Emin260 Dinlersoz}, ``Advanced Technologies Adoption and Use by U.S. Firms: Evidence261 from the Annual Business Survey,'' NBER Working Paper 28290, National Bureau262 of Economic Research 2020.263264\end{thebibliography}265