spb/firc0001_uqo
Public
1@article{loughran2011,2 author = {Loughran, Tim and McDonald, Bill},3 title = {When Is a Liability Not a Liability? {T}extual Analysis, Dictionaries, and 10-{K}s},4 journal = {Journal of Finance},5 year = {2011}, volume = {66}, number = {1}, pages = {35--65},6 doi = {10.1111/j.1540-6261.2010.01625.x}7}8@article{loughran2016,9 author = {Loughran, Tim and McDonald, Bill},10 title = {Textual Analysis in Accounting and Finance: A Survey},11 journal = {Journal of Accounting Research},12 year = {2016}, volume = {54}, number = {4}, pages = {1187--1230},13 doi = {10.1111/1475-679X.12123}14}15@article{hoberg2016,16 author = {Hoberg, Gerard and Phillips, Gordon},17 title = {Text-Based Network Industries and Endogenous Product Differentiation},18 journal = {Journal of Political Economy},19 year = {2016}, volume = {124}, number = {5}, pages = {1423--1465},20 doi = {10.1086/688176}21}22@article{hobergmaksimovic2015,23 author = {Hoberg, Gerard and Maksimovic, Vojislav},24 title = {Redefining Financial Constraints: A Text-Based Analysis},25 journal = {Review of Financial Studies},26 year = {2015}, volume = {28}, number = {5}, pages = {1312--1352},27 doi = {10.1093/rfs/hhu089}28}29@article{gentzkow2019,30 author = {Gentzkow, Matthew and Kelly, Bryan and Taddy, Matt},31 title = {Text as Data},32 journal = {Journal of Economic Literature},33 year = {2019}, volume = {57}, number = {3}, pages = {535--574},34 doi = {10.1257/jel.20181020}35}36@article{hassan2019,37 author = {Hassan, Tarek A. and Hollander, Stephan and van Lent, Laurence and Tahoun, Ahmed},38 title = {Firm-Level Political Risk: Measurement and Effects},39 journal = {Quarterly Journal of Economics},40 year = {2019}, volume = {134}, number = {4}, pages = {2135--2202},41 doi = {10.1093/qje/qjz021}42}43@article{cohen2020,44 author = {Cohen, Lauren and Malloy, Christopher and Nguyen, Quoc},45 title = {Lazy Prices},46 journal = {Journal of Finance},47 year = {2020}, volume = {75}, number = {3}, pages = {1371--1415},48 doi = {10.1111/jofi.12885}49}50@article{kelly2021,51 author = {Kelly, Bryan and Papanikolaou, Dimitris and Seru, Amit and Taddy, Matt},52 title = {Measuring Technological Innovation over the Long Run},53 journal = {American Economic Review: Insights},54 year = {2021}, volume = {3}, number = {3}, pages = {303--320},55 doi = {10.1257/aeri.20190499}56}57@article{dyer2017,58 author = {Dyer, Travis and Lang, Mark and Stice-Lawrence, Lorien},59 title = {The Evolution of 10-{K} Textual Disclosure: Evidence from {L}atent {D}irichlet {A}llocation},60 journal = {Journal of Accounting and Economics},61 year = {2017}, volume = {64}, number = {2--3}, pages = {221--245},62 doi = {10.1016/j.jacceco.2017.07.002}63}64@article{li2021,65 author = {Li, Kai and Mai, Feng and Shen, Rui and Yan, Xinyan},66 title = {Measuring Corporate Culture Using Machine Learning},67 journal = {Review of Financial Studies},68 year = {2021}, volume = {34}, number = {7}, pages = {3265--3315},69 doi = {10.1093/rfs/hhaa079}70}71@article{grimmer2013,72 author = {Grimmer, Justin and Stewart, Brandon M.},73 title = {Text as Data: The Promise and Pitfalls of Automatic Content Analysis Methods for Political Texts},74 journal = {Political Analysis},75 year = {2013}, volume = {21}, number = {3}, pages = {267--297},76 doi = {10.1093/pan/mps028}77}78@article{fellegi1969,79 author = {Fellegi, Ivan P. and Sunter, Alan B.},80 title = {A Theory for Record Linkage},81 journal = {Journal of the American Statistical Association},82 year = {1969}, volume = {64}, number = {328}, pages = {1183--1210},83 doi = {10.1080/01621459.1969.10501049}84}85@book{christen2012,86 author = {Christen, Peter},87 title = {Data Matching: Concepts and Techniques for Record Linkage, Entity Resolution, and Duplicate Detection},88 publisher = {Springer},89 address = {Berlin},90 year = {2012},91 doi = {10.1007/978-3-642-31164-2}92}93@inproceedings{reimers2019,94 author = {Reimers, Nils and Gurevych, Iryna},95 title = {Sentence-{BERT}: Sentence Embeddings using {S}iamese {BERT}-Networks},96 booktitle = {Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing (EMNLP-IJCNLP)},97 year = {2019}, pages = {3982--3992},98 doi = {10.18653/v1/D19-1410}99}100@inproceedings{raasveldt2019,101 author = {Raasveldt, Mark and M{\"u}hleisen, Hannes},102 title = {{DuckDB}: An Embeddable Analytical Database},103 booktitle = {Proceedings of the 2019 International Conference on Management of Data (SIGMOD)},104 year = {2019}, pages = {1981--1984},105 doi = {10.1145/3299869.3320212}106}107@misc{secfairaccess,108 author = {{U.S. Securities and Exchange Commission}},109 title = {Accessing {EDGAR} Data: Fair Access Policy},110 howpublished = {\url{https://www.sec.gov/search-filings/edgar-search-assistance/accessing-edgar-data}},111 year = {2026},112 note = {Accessed October 2026; URL re-verified November 5, 2026 (the former \texttt{/os/accessing-edgar-data} address redirects here)}113}114@misc{ftserussell2026,115 author = {{FTSE Russell}},116 title = {Russell {US} Equity Indexes: Construction and Methodology, v7.2},117 howpublished = {\url{https://www.lseg.com/content/dam/ftse-russell/en_us/documents/ground-rules/russell-us-indexes-construction-and-methodology.pdf}},118 year = {2026},119 month = {August},120 note = {Document dated August 2026; downloaded November 5, 2026}121}122@misc{ftserussell3000factsheet2026,123 author = {{FTSE Russell}},124 title = {Russell 3000 Index Factsheet},125 howpublished = {\url{https://research.ftserussell.com/Analytics/FactSheets/Home/DownloadSingleIssue?issueName=US3000USD}},126 year = {2026},127 note = {Index characteristics as of September 30, 2026 (2,996 holdings); downloaded November 5, 2026}128}129@techreport{spid2026,130 author = {Tandjambianda, Djerrycharli and Boucher, Simon-Pierre and Kammoun, Manel},131 title = {{SPID} --- {SEC} Project Intelligence Database: A Methodological Report on the {S\&P}~500 Release},132 institution = {Université du Québec en Outaouais, Département des sciences administratives},133 type = {Unpublished internal methodological report, available from the authors},134 year = {2026},135 note = {June 2026 study of revision \texttt{df7905d}; the report file was regenerated on October 28, 2026}136}137@techreport{kammoun2026ai,138 author = {Kammoun, Manel and Tandjambianda, Djerrycharli and Boucher, Simon-Pierre},139 title = {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},140 institution = {Université du Québec en Outaouais, Département des sciences administratives},141 type = {UQO Working Paper (FIRC)},142 number = {0002},143 year = {2026},144 note = {Version 2.0, October 28, 2026}145}146@misc{iwvholdings2026,147 author = {{BlackRock, Inc.}},148 title = {{iShares} {R}ussell 3000 {ETF} ({IWV}): Fund holdings file (\texttt{latest-holdings.csv})},149 howpublished = {\url{https://www.ishares.com/us/products/239714/ishares-russell-3000-etf}},150 year = {2026},151 note = {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}152}153@misc{wikipediasp500,154 author = {{Wikipedia contributors}},155 title = {List of {S\&P} 500 companies},156 howpublished = {\url{https://en.wikipedia.org/wiki/List_of_S%26P_500_companies}},157 year = {2026},158 note = {Table scraped May 25, 2026; text available under the Creative Commons Attribution-ShareAlike 4.0 licence}159}160@article{kalyani2025,161 author = {Kalyani, Aakash and Bloom, Nicholas and Carvalho, Marcela and Hassan, Tarek and Lerner, Josh and Tahoun, Ahmed},162 title = {The Diffusion of New Technologies},163 journal = {Quarterly Journal of Economics},164 year = {2025}, volume = {140}, number = {2}, pages = {1299--1365},165 doi = {10.1093/qje/qjaf002},166 note = {Published version of NBER Working Paper 28999 (2021, DOI 10.3386/w28999)}167}168@techreport{jha2024,169 author = {Jha, Manish and Qian, Jialin and Weber, Michael and Yang, Baozhong},170 title = {{ChatGPT} and Corporate Policies},171 institution = {National Bureau of Economic Research}, type = {NBER Working Paper}, number = {32161},172 year = {2024}, doi = {10.3386/w32161}173}174@article{ludwig2025,175 author = {Ludwig, Jens and Mullainathan, Sendhil and Rambachan, Ashesh},176 title = {Large Language Models: An Applied Econometric Framework},177 journal = {Annual Review of Economics},178 year = {2026}, volume = {18}, number = {1}, pages = {283--316},179 doi = {10.1146/annurev-economics-120925-105620},180 note = {Also NBER Working Paper 33344 (2025, DOI 10.3386/w33344)}181}182@article{gilardi2023,183 author = {Gilardi, Fabrizio and Alizadeh, Meysam and Kubli, Maël},184 title = {{ChatGPT} outperforms crowd workers for text-annotation tasks},185 journal = {Proceedings of the National Academy of Sciences},186 year = {2023}, volume = {120}, number = {30}, pages = {e2305016120},187 doi = {10.1073/pnas.2305016120}188}189@article{dekok2025,190 author = {de Kok, Ties},191 title = {{ChatGPT} for Textual Analysis? How to Use Generative {LLMs} in Accounting Research},192 journal = {Management Science},193 year = {2025}, volume = {71}, number = {9}, pages = {7888--7906},194 doi = {10.1287/mnsc.2023.03253}195}196@techreport{kim2023,197 author = {Kim, Alex G. and Muhn, Maximilian and Nikolaev, Valeri V.},198 title = {From Transcripts to Insights: Uncovering Corporate Risks Using Generative AI},199 institution = {SSRN}, type = {Working paper}, number = {4593660},200 year = {2023}, doi = {10.2139/ssrn.4593660}201}202@misc{dolphin2026,203 author = {Dolphin, Rian and Dursun, Joe and Blankenship, Jarrett and Adams, Katie and Pike, Quinton},204 title = {Grounded Event Extraction from {SEC} {8-K} Filings with a Fine-Grained Taxonomy},205 howpublished = {arXiv:2607.08346; also SSRN 7087858 (DOI 10.2139/ssrn.7087858)},206 year = {2026}, doi = {10.48550/arXiv.2607.08346}207}208@techreport{crane2024,209 author = {Crane, Leland D. and Green, Emily and Harnish, Molly and McClennan, Will and Soto, Paul E. and Vrankovich, Betsy and Williams, Jacob},210 title = {Tracking Real Time Layoffs with {SEC} Filings: A Preliminary Investigation},211 institution = {Board of Governors of the Federal Reserve System}, type = {Finance and Economics Discussion Series}, number = {2024-020},212 year = {2024}, doi = {10.17016/feds.2024.020}213}214@inproceedings{loukas2021,215 author = {Loukas, Lefteris and Fergadiotis, Manos and Androutsopoulos, Ion and Malakasiotis, Prodromos},216 title = {{EDGAR-CORPUS}: Billions of Tokens Make The World Go Round},217 booktitle = {Proceedings of the Third Workshop on Economics and Natural Language Processing},218 year = {2021}, pages = {13--18},219 doi = {10.18653/v1/2021.econlp-1.2}220}221@misc{bettencourt2026,222 author = {Bettencourt, Nick and Ding, Xiaowei and Giesecke, Kay},223 title = {The {Stanford} {EDGAR} Filings Dataset: Reconstructing U.S. Corporate and Financial Disclosures into Layout-Faithful and Token-Efficient Pretraining Data},224 howpublished = {arXiv:2606.18192; also SSRN 7161699 (DOI 10.2139/ssrn.7161699)},225 year = {2026}, doi = {10.48550/arXiv.2606.18192}226}227@article{greenstone2010,228 author = {Greenstone, Michael and Hornbeck, Richard and Moretti, Enrico},229 title = {Identifying Agglomeration Spillovers: Evidence from Winners and Losers of Large Plant Openings},230 journal = {Journal of Political Economy},231 year = {2010}, volume = {118}, number = {3}, pages = {536--598},232 doi = {10.1086/653714}233}234@article{mcconnell1985,235 author = {McConnell, J and Muscarella, Chris J.},236 title = {Corporate capital expenditure decisions and the market value of the firm},237 journal = {Journal of Financial Economics},238 year = {1985}, volume = {14}, number = {3}, pages = {399--422},239 doi = {10.1016/0304-405X(85)90006-6}240}241@misc{yang2024,242 author = {Yang, Daniel and Tsai, Yao-Hung Hubert and Yamada, Makoto},243 title = {On Verbalized Confidence Scores for {LLMs}},244 howpublished = {arXiv:2412.14737},245 year = {2024}, doi = {10.48550/arXiv.2412.14737}246}247@inproceedings{ye2024,248 author = {Ye, Fanghua and Yang, Mingming and Pang, Jianhui and Wang, Longyue and Wong, Derek and Yilmaz, Emine and Shi, Shuming and Tu, Zhaopeng},249 title = {Benchmarking {LLMs} via Uncertainty Quantification},250 booktitle = {Advances in Neural Information Processing Systems 37 (NeurIPS 2024)},251 year = {2024}, pages = {15356--15385},252 doi = {10.52202/079017-0491}253}254@article{li2020,255 author = {Li, Yuliang and Li, Jinfeng and Suhara, Yoshihiko and Doan, AnHai and Tan, Wang-Chiew},256 title = {Deep entity matching with pre-trained language models},257 journal = {Proceedings of the VLDB Endowment},258 year = {2020}, volume = {14}, number = {1}, pages = {50--60},259 doi = {10.14778/3421424.3421431}260}261@misc{peeters2023,262 author = {Peeters, Ralph and Steiner, Aaron and Bizer, Christian},263 title = {Entity Matching using Large Language Models},264 howpublished = {arXiv:2310.11244},265 year = {2023}, doi = {10.48550/arXiv.2310.11244}266}267@article{bellstam2021,268 author = {Bellstam, Gustaf and Bhagat, Sanjai and Cookson, J. Anthony},269 title = {A Text-Based Analysis of Corporate Innovation},270 journal = {Management Science},271 year = {2021}, volume = {67}, number = {7}, pages = {4004--4031},272 doi = {10.1287/mnsc.2020.3682}273}274@article{sautner2023,275 author = {Sautner, Zacharias and van Lent, Laurence and Vilkov, Grigory and Zhang, Ruishen},276 title = {Firm-Level Climate Change Exposure},277 journal = {Journal of Finance},278 year = {2023}, volume = {78}, number = {3}, pages = {1449--1498},279 doi = {10.1111/jofi.13219}280}281@article{afzal2026,282 author = {Afzal, Muhammad Talha and Yan, Jinqiu (Claire) and Li, Huaxia and Vasarhelyi, Miklos},283 title = {Beyond the bottom line: using generative AI to extract narrative financial disclosures},284 journal = {International Journal of Accounting Information Systems},285 year = {2026}, volume = {57}, pages = {100777},286 doi = {10.1016/j.accinf.2026.100777}287}288@techreport{zolas2020,289 author = {Zolas, Nikolas and Kroff, Zachary and Brynjolfsson, Erik and McElheran, Kristina and Beede, David and Buffington, Cathy and Goldschlag, Nathan and Foster, Lucia and Dinlersoz, Emin},290 title = {Advanced Technologies Adoption and Use by U.S. Firms: Evidence from the Annual Business Survey},291 institution = {National Bureau of Economic Research}, type = {NBER Working Paper}, number = {28290},292 year = {2020}, doi = {10.3386/w28290}293}294