E (exhibits): final build of main.pdf after the exhibit rebuild (84 pages, 0 errors, 0 undefined references, 0 overfull boxes > 5 pt, 0 bibtex warnings)
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
2 changed files +150 −3
modified
paper/main.bbl
+150 −3
@@ -3,6 +3,33 @@ | ||
| 3 | 3 | \fi |
| 4 | 4 | \begin{thebibliography}{xx} |
| 5 | 5 | |
| 6 | +\harvarditem[Afzal et al.]{Afzal, Yan, Li and Vasarhelyi}{2026}{afzal2026} | |
| 7 | +{\bf Afzal, Muhammad~Talha, Jinqiu~(Claire) Yan, Huaxia Li, and Miklos | |
| 8 | + Vasarhelyi}, ``Beyond the bottom line: using generative AI to extract | |
| 9 | + narrative financial disclosures,'' {\it International Journal of Accounting | |
| 10 | + Information Systems}, 2026, {\it 57}, 100777. | |
| 11 | + | |
| 12 | +\harvarditem[Bellstam et al.]{Bellstam, Bhagat and Cookson}{2021}{bellstam2021} | |
| 13 | +{\bf Bellstam, Gustaf, Sanjai Bhagat, and J.~Anthony Cookson}, ``A Text-Based | |
| 14 | + Analysis of Corporate Innovation,'' {\it Management Science}, 2021, {\it 67} | |
| 15 | + (7), 4004--4031. | |
| 16 | + | |
| 17 | +\harvarditem[Bettencourt et al.]{Bettencourt, Ding and | |
| 18 | + Giesecke}{2026}{bettencourt2026} | |
| 19 | +{\bf Bettencourt, Nick, Xiaowei Ding, and Kay Giesecke}, ``The {Stanford} | |
| 20 | + {EDGAR} Filings Dataset: Reconstructing U.S. Corporate and Financial | |
| 21 | + Disclosures into Layout-Faithful and Token-Efficient Pretraining Data,'' | |
| 22 | + arXiv:2606.18192; also SSRN 7161699 (DOI 10.2139/ssrn.7161699) 2026. | |
| 23 | + | |
| 24 | +\harvarditem[{BlackRock, Inc.}]{{BlackRock, Inc.}}{2026}{iwvholdings2026} | |
| 25 | +{\bf {BlackRock, Inc.}}, ``{iShares} {R}ussell 3000 {ETF} ({IWV}): Fund | |
| 26 | + 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; subject | |
| 30 | + to the iShares website terms of use; the downloaded file is not archived with | |
| 31 | + the paper. | |
| 32 | + | |
| 6 | 33 | \harvarditem[Christen]{Christen}{2012}{christen2012} |
| 7 | 34 | {\bf Christen, Peter}, {\it Data Matching: Concepts and Techniques for Record |
| 8 | 35 | Linkage, Entity Resolution, and Duplicate Detection}, Berlin: Springer, 2012. |
@@ -11,6 +38,26 @@ | ||
| 11 | 38 | {\bf Cohen, Lauren, Christopher Malloy, and Quoc Nguyen}, ``Lazy Prices,'' {\it |
| 12 | 39 | Journal of Finance}, 2020, {\it 75} (3), 1371--1415. |
| 13 | 40 | |
| 41 | +\harvarditem[Crane et al.]{Crane, Green, Harnish, McClennan, Soto, Vrankovich | |
| 42 | + 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 Layoffs | |
| 45 | + with {SEC} Filings: A Preliminary Investigation,'' Finance and Economics | |
| 46 | + Discussion Series 2024-020, Board of Governors of the Federal Reserve System | |
| 47 | + 2024. | |
| 48 | + | |
| 49 | +\harvarditem[de~Kok]{de~Kok}{2025}{dekok2025} | |
| 50 | +{\bf de~Kok, Ties}, ``{ChatGPT} for Textual Analysis? How to Use Generative | |
| 51 | + {LLMs} in Accounting Research,'' {\it Management Science}, 2025, {\it 71} | |
| 52 | + (9), 7888--7906. | |
| 53 | + | |
| 54 | +\harvarditem[Dolphin et al.]{Dolphin, Dursun, Blankenship, Adams and | |
| 55 | + Pike}{2026}{dolphin2026} | |
| 56 | +{\bf Dolphin, Rian, Joe Dursun, Jarrett Blankenship, Katie Adams, and Quinton | |
| 57 | + Pike}, ``Grounded Event Extraction from {SEC} {8-K} Filings with a | |
| 58 | + Fine-Grained Taxonomy,'' arXiv:2607.08346; also SSRN 7087858 (DOI | |
| 59 | + 10.2139/ssrn.7087858) 2026. | |
| 60 | + | |
| 14 | 61 | \harvarditem[Dyer et al.]{Dyer, Lang and Stice-Lawrence}{2017}{dyer2017} |
| 15 | 62 | {\bf Dyer, Travis, Mark Lang, and Lorien Stice-Lawrence}, ``The Evolution of |
| 16 | 63 | 10-{K} Textual Disclosure: Evidence from {L}atent {D}irichlet {A}llocation,'' |
@@ -21,9 +68,17 @@ | ||
| 21 | 68 | {\it Journal of the American Statistical Association}, 1969, {\it 64} (328), |
| 22 | 69 | 1183--1210. |
| 23 | 70 | |
| 24 | −\harvarditem[{FTSE Russell}]{{FTSE Russell}}{2026}{ftserussell2026} | |
| 25 | −{\bf {FTSE Russell}}, ``Russell {US} Equity Indexes: Construction and | |
| 26 | − Methodology, v7.2,'' | |
| 71 | +\harvarditem[{FTSE Russell}]{{FTSE | |
| 72 | + 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. | |
| 78 | + | |
| 79 | +\harvarditem[{FTSE Russell}]{{FTSE Russell}}{2026b}{ftserussell2026} | |
| 80 | +{\bf \bysame{}}, ``Russell {US} Equity Indexes: Construction and Methodology, | |
| 81 | + v7.2,'' | |
| 27 | 82 | \url{https://www.lseg.com/content/dam/ftse-russell/en_us/documents/ground-rules/russell-us-indexes-construction-and-methodology.pdf} |
| 28 | 83 | August 2026. |
| 29 | 84 | \newblock Document dated August 2026; downloaded November 5, 2026. |
@@ -32,6 +87,18 @@ | ||
| 32 | 87 | {\bf Gentzkow, Matthew, Bryan Kelly, and Matt Taddy}, ``Text as Data,'' {\it |
| 33 | 88 | Journal of Economic Literature}, 2019, {\it 57} (3), 535--574. |
| 34 | 89 | |
| 90 | +\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 of | |
| 93 | + the National Academy of Sciences}, 2023, {\it 120} (30), e2305016120. | |
| 94 | + | |
| 95 | +\harvarditem[Greenstone et al.]{Greenstone, Hornbeck and | |
| 96 | + Moretti}{2010}{greenstone2010} | |
| 97 | +{\bf Greenstone, Michael, Richard Hornbeck, and Enrico Moretti}, ``Identifying | |
| 98 | + Agglomeration Spillovers: Evidence from Winners and Losers of Large Plant | |
| 99 | + Openings,'' {\it Journal of Political Economy}, 2010, {\it 118} (3), | |
| 100 | + 536--598. | |
| 101 | + | |
| 35 | 102 | \harvarditem[Grimmer and Stewart]{Grimmer and Stewart}{2013}{grimmer2013} |
| 36 | 103 | {\bf Grimmer, Justin and Brandon~M. Stewart}, ``Text as Data: The Promise and |
| 37 | 104 | Pitfalls of Automatic Content Analysis Methods for Political Texts,'' {\it |
@@ -54,6 +121,11 @@ | ||
| 54 | 121 | Text-Based Analysis,'' {\it Review of Financial Studies}, 2015, {\it 28} (5), |
| 55 | 122 | 1312--1352. |
| 56 | 123 | |
| 124 | +\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 of | |
| 127 | + Economic Research 2024. | |
| 128 | + | |
| 57 | 129 | \harvarditem[Kalyani et al.]{Kalyani, Bloom, Carvalho, Hassan, Lerner and |
| 58 | 130 | Tahoun}{2025}{kalyani2025} |
| 59 | 131 | {\bf Kalyani, Aakash, Nicholas Bloom, Marcela Carvalho, Tarek Hassan, Josh |
@@ -62,17 +134,36 @@ | ||
| 62 | 134 | \newblock Published version of NBER Working Paper 28999 (2021, DOI |
| 63 | 135 | 10.3386/w28999). |
| 64 | 136 | |
| 137 | +\harvarditem[Kammoun et al.]{Kammoun, Tandjambianda and | |
| 138 | + Boucher}{2026}{kammoun2026ai} | |
| 139 | +{\bf Kammoun, Manel, Djerrycharli Tandjambianda, and Simon-Pierre Boucher}, | |
| 140 | + ``Does the Language of Artificial Intelligence Move Markets? {A} Semantic | |
| 141 | + Analysis of {R}ussell~3000 {SEC} Filings and the Cross-Section of Stock | |
| 142 | + Returns, 2010--2026,'' UQO Working Paper (FIRC) 0002, Université du Québec | |
| 143 | + en Outaouais, Département des sciences administratives 2026. | |
| 144 | +\newblock Version 2.0, October 28, 2026. | |
| 145 | + | |
| 65 | 146 | \harvarditem[Kelly et al.]{Kelly, Papanikolaou, Seru and |
| 66 | 147 | Taddy}{2021}{kelly2021} |
| 67 | 148 | {\bf Kelly, Bryan, Dimitris Papanikolaou, Amit Seru, and Matt Taddy}, |
| 68 | 149 | ``Measuring Technological Innovation over the Long Run,'' {\it American |
| 69 | 150 | Economic Review: Insights}, 2021, {\it 3} (3), 303--320. |
| 70 | 151 | |
| 152 | +\harvarditem[Kim et al.]{Kim, Muhn and Nikolaev}{2023}{kim2023} | |
| 153 | +{\bf Kim, Alex~G., Maximilian Muhn, and Valeri~V. Nikolaev}, ``From Transcripts | |
| 154 | + to Insights: Uncovering Corporate Risks Using Generative AI,'' Working paper | |
| 155 | + 4593660, SSRN 2023. | |
| 156 | + | |
| 71 | 157 | \harvarditem[Li et al.]{Li, Mai, Shen and Yan}{2021}{li2021} |
| 72 | 158 | {\bf Li, Kai, Feng Mai, Rui Shen, and Xinyan Yan}, ``Measuring Corporate |
| 73 | 159 | Culture Using Machine Learning,'' {\it Review of Financial Studies}, 2021, |
| 74 | 160 | {\it 34} (7), 3265--3315. |
| 75 | 161 | |
| 162 | +\harvarditem[Li et al.]{Li, Li, Suhara, Doan and Tan}{2020}{li2020} | |
| 163 | +{\bf Li, Yuliang, Jinfeng Li, Yoshihiko Suhara, AnHai Doan, and Wang-Chiew | |
| 164 | + Tan}, ``Deep entity matching with pre-trained language models,'' {\it | |
| 165 | + Proceedings of the VLDB Endowment}, 2020, {\it 14} (1), 50--60. | |
| 166 | + | |
| 76 | 167 | \harvarditem[Loughran and McDonald]{Loughran and McDonald}{2011}{loughran2011} |
| 77 | 168 | {\bf Loughran, Tim and Bill McDonald}, ``When Is a Liability Not a Liability? |
| 78 | 169 | {T}extual Analysis, Dictionaries, and 10-{K}s,'' {\it Journal of Finance}, |
@@ -83,6 +174,30 @@ | ||
| 83 | 174 | Survey,'' {\it Journal of Accounting Research}, 2016, {\it 54} (4), |
| 84 | 175 | 1187--1230. |
| 85 | 176 | |
| 177 | +\harvarditem[Loukas et al.]{Loukas, Fergadiotis, Androutsopoulos and | |
| 178 | + Malakasiotis}{2021}{loukas2021} | |
| 179 | +{\bf Loukas, Lefteris, Manos Fergadiotis, Ion Androutsopoulos, and Prodromos | |
| 180 | + Malakasiotis}, ``{EDGAR-CORPUS}: Billions of Tokens Make The World Go | |
| 181 | + Round,'' in ``Proceedings of the Third Workshop on Economics and Natural | |
| 182 | + Language Processing'' 2021, pp.~13--18. | |
| 183 | + | |
| 184 | +\harvarditem[Ludwig et al.]{Ludwig, Mullainathan and | |
| 185 | + Rambachan}{2026}{ludwig2025} | |
| 186 | +{\bf Ludwig, Jens, Sendhil Mullainathan, and Ashesh Rambachan}, ``Large | |
| 187 | + Language Models: An Applied Econometric Framework,'' {\it Annual Review of | |
| 188 | + Economics}, 2026, {\it 18} (1), 283--316. | |
| 189 | +\newblock Also NBER Working Paper 33344 (2025, DOI 10.3386/w33344). | |
| 190 | + | |
| 191 | +\harvarditem[McConnell and Muscarella]{McConnell and | |
| 192 | + Muscarella}{1985}{mcconnell1985} | |
| 193 | +{\bf McConnell, J and Chris~J. Muscarella}, ``Corporate capital expenditure | |
| 194 | + decisions and the market value of the firm,'' {\it Journal of Financial | |
| 195 | + Economics}, 1985, {\it 14} (3), 399--422. | |
| 196 | + | |
| 197 | +\harvarditem[Peeters et al.]{Peeters, Steiner and Bizer}{2023}{peeters2023} | |
| 198 | +{\bf Peeters, Ralph, Aaron Steiner, and Christian Bizer}, ``Entity Matching | |
| 199 | + using Large Language Models,'' arXiv:2310.11244 2023. | |
| 200 | + | |
| 86 | 201 | \harvarditem[Raasveldt and M{\"u}hleisen]{Raasveldt and |
| 87 | 202 | M{\"u}hleisen}{2019}{raasveldt2019} |
| 88 | 203 | {\bf Raasveldt, Mark and Hannes M{\"u}hleisen}, ``{DuckDB}: An Embeddable |
@@ -95,6 +210,12 @@ | ||
| 95 | 210 | Empirical Methods in Natural Language Processing (EMNLP-IJCNLP)'' 2019, |
| 96 | 211 | pp.~3982--3992. |
| 97 | 212 | |
| 213 | +\harvarditem[Sautner et al.]{Sautner, van Lent, Vilkov and | |
| 214 | + 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, {\it | |
| 217 | + 78} (3), 1449--1498. | |
| 218 | + | |
| 98 | 219 | \harvarditem[Tandjambianda et al.]{Tandjambianda, Boucher and |
| 99 | 220 | Kammoun}{2026}{spid2026} |
| 100 | 221 | {\bf Tandjambianda, Djerrycharli, Simon-Pierre Boucher, and Manel Kammoun}, |
@@ -114,4 +235,30 @@ | ||
| 114 | 235 | \newblock Accessed October 2026; URL re-verified November 5, 2026 (the former |
| 115 | 236 | \texttt{/os/accessing-edgar-data} address redirects here). |
| 116 | 237 | |
| 238 | +\harvarditem[{Wikipedia contributors}]{{Wikipedia | |
| 239 | + 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 Commons | |
| 243 | + Attribution-ShareAlike 4.0 licence. | |
| 244 | + | |
| 245 | +\harvarditem[Yang et al.]{Yang, Tsai and Yamada}{2024}{yang2024} | |
| 246 | +{\bf Yang, Daniel, Yao-Hung~Hubert Tsai, and Makoto Yamada}, ``On Verbalized | |
| 247 | + Confidence Scores for {LLMs},'' arXiv:2412.14737 2024. | |
| 248 | + | |
| 249 | +\harvarditem[Ye et al.]{Ye, Yang, Pang, Wang, Wong, Yilmaz, Shi and | |
| 250 | + Tu}{2024}{ye2024} | |
| 251 | +{\bf Ye, Fanghua, Mingming Yang, Jianhui Pang, Longyue Wang, Derek Wong, Emine | |
| 252 | + Yilmaz, Shuming Shi, and Zhaopeng Tu}, ``Benchmarking {LLMs} via Uncertainty | |
| 253 | + Quantification,'' in ``Advances in Neural Information Processing Systems 37 | |
| 254 | + (NeurIPS 2024)'' 2024, pp.~15356--15385. | |
| 255 | + | |
| 256 | +\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 Emin | |
| 260 | + Dinlersoz}, ``Advanced Technologies Adoption and Use by U.S. Firms: Evidence | |
| 261 | + from the Annual Business Survey,'' NBER Working Paper 28290, National Bureau | |
| 262 | + of Economic Research 2020. | |
| 263 | + | |
| 117 | 264 | \end{thebibliography} |
modified
paper/main.pdf
+0 −0
Binary file not shown.