spb/uqo-research-db

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>

added .claude/settings.local.json +5 −0

		@@ -0,0 +1,5 @@
	1	+{
	2	+ "disabledMcpjsonServers": [
	3	+ "cluster"
	4	+ ]
	5	+}

added .env.example +18 −0

		@@ -0,0 +1,18 @@
	1	+# EDGAR Research Database — Environment Configuration
	2	+
	3	+# SEC EDGAR requires a user-agent string with contact email
	4	+SEC_USER_AGENT="UQO-Research simon-pierre.boucher@uqo.ca"
	5	+
	6	+# Project paths (defaults work for standard layout)
	7	+# DATA_DIR=./data
	8	+# DUCKDB_PATH=./data/duckdb/edgar_research.duckdb
	9	+
	10	+# Embedding API (optional — defaults to local sentence-transformers)
	11	+# OPENAI_API_KEY=sk-...
	12	+# OPENROUTER_API_KEY=sk-or-...
	13	+# EMBEDDING_MODEL=all-MiniLM-L6-v2
	14	+# EMBEDDING_BATCH_SIZE=256
	15	+
	16	+# Logging
	17	+# LOG_LEVEL=INFO
	18	+# LOG_FORMAT=json

added .gitignore +27 −0

		@@ -0,0 +1,27 @@
	1	+# data and secrets never enter git
	2	+data/
	3	+.venv/
	4	+__pycache__/
	5	+*.pyc
	6	+.env
	7	+project-db/.env
	8	+project-db/data/
	9	+project-db/logs/
	10	+*.duckdb
	11	+*.zip
	12	+.DS_Store
	13	+edgar_research_db.egg-info/
	14	+analysis/data/
	15	+outputs/
	16	+UQ_WP_template/*.aux
	17	+UQ_WP_template/*.log
	18	+UQ_WP_template/*.fls
	19	+UQ_WP_template/*.fdb_latexmk
	20	+UQ_WP_template/*.out
	21	+UQ_WP_template/*.synctex*
	22	+project-db/docs/*.aux
	23	+project-db/docs/*.log
	24	+project-db/docs/*.fls
	25	+project-db/docs/*.fdb_latexmk
	26	+project-db/docs/*.out
	27	+project-db/docs/*.toc

added UQ_WP_template/.claude/settings.local.json +5 −0

		@@ -0,0 +1,5 @@
	1	+{
	2	+ "disabledMcpjsonServers": [
	3	+ "cluster"
	4	+ ]
	5	+}

added UQ_WP_template/.latexmkrc +5 −0

		@@ -0,0 +1,5 @@
	1	+$pdf_mode = 1;
	2	+$pdflatex = 'pdflatex -interaction=nonstopmode -halt-on-error -synctex=1 %O %S';
	3	+$bibtex_use = 2;
	4	+$clean_ext = 'synctex.gz run.xml bbl bcf fdb_latexmk fls log aux out toc lof lot blg';
	5	+@default_files = ('main.tex');

added UQ_WP_template/Makefile +11 −0

		@@ -0,0 +1,11 @@
	1	+.PHONY: all clean distclean
	2	+
	3	+all:
	4	+ latexmk
	5	+
	6	+clean:
	7	+ latexmk -c
	8	+
	9	+distclean:
	10	+ latexmk -C
	11	+ rm -f *.synctex.gz *.run.xml *.bbl *.bcf

added UQ_WP_template/appendix/appendix.tex +53 −0

		@@ -0,0 +1,53 @@
	1	+% ============================================================================
	2	+% Appendix
	3	+% ============================================================================
	4	+\newpage
	5	+\begin{appendices}
	6	+
	7	+\renewcommand{\thetable}{A\arabic{table}}
	8	+\renewcommand{\thefigure}{A\arabic{figure}}
	9	+\setcounter{table}{0}
	10	+\setcounter{figure}{0}
	11	+
	12	+\section{Variable Definitions}
	13	+\label{app:variables}
	14	+
	15	+\begin{table}[htbp]
	16	+ \centering
	17	+ \caption{Variable Definitions}
	18	+ \label{tab:app_variables}
	19	+ \small
	20	+ \begin{tabular}{@{}p{4.2cm}p{10.5cm}@{}}
	21	+ \toprule
	22	+ Variable & Definition \\
	23	+ \midrule
	24	+ AI\,Adopt (\texttt{ai\_adoption\_wmean}) & Section-weighted mean cosine similarity of a firm's 10-K text chunks to the AI-internal-adoption anchor in fiscal year $Y$. \\[4pt]
	25	+ AI\,Infra (\texttt{ai\_infrastructure\_wmean}) & Section-weighted mean similarity to the AI-compute-infrastructure anchor. \\[4pt]
	26	+ AI\,Risk (\texttt{ai\_disruption\_risk\_wmean}) & Section-weighted mean similarity to the AI-product-disruption-risk anchor. \\[4pt]
	27	+ AI\,Compos & $\tfrac12[z(\text{AI\,Adopt})+z(\text{AI\,Infra})]$, with $z$ the within-year cross-sectional standardization. \\[4pt]
	28	+ Forward return & Buy-and-hold simple return from July of $Y{+}1$ to June of $Y{+}2$ (adjusted close, dividends reinvested). \\[4pt]
	29	+ Market-adjusted return & Forward return minus the contemporaneous SPY return. \\[4pt]
	30	+ Size & Natural logarithm of the market-cap proxy (latest shares outstanding $\times$ price) at formation. \\[4pt]
	31	+ Momentum & Own return over the 12 months ending at formation, skipping the last month. \\[4pt]
	32	+ Volatility & Annualized standard deviation of monthly returns over the trailing 12 months. \\[4pt]
	33	+ Post & Indicator equal to one for formation (fiscal) years $\ge 2022$. \\[4pt]
	34	+ CAR & Cumulative market-model abnormal return; market model estimated Jan--Oct 2022, event window Nov 2022--Jun 2024. \\
	35	+ \bottomrule
	36	+ \end{tabular}
	37	+\end{table}
	38	+
	39	+\section{Data Sources and Reproducibility}
	40	+\label{app:repro}
	41	+
	42	+Semantic factors are from the EDGAR Research Database (UQO), which embeds 10-K text with the
	43	+\texttt{all-MiniLM-L6-v2} sentence transformer and scores each chunk by cosine similarity to curated
	44	+anchor passages. Equity prices (monthly and daily) are from Yahoo Finance; the Fama--French five
	45	+factors, the momentum factor, and the risk-free rate are from the Kenneth R.\ French data library. All
	46	+return tests use look-ahead-free July-formation forward returns, with signals taken from the 10-K of
	47	+the preceding fiscal year. The analysis pipeline downloads prices, builds the merged firm-year panel,
	48	+runs the portfolio sorts, factor regressions, panel and Fama--MacBeth estimators, the
	49	+difference-in-differences specifications, and the market-model event study, and emits all figures and
	50	+tables programmatically; numerical results are serialized to machine-readable result files so that
	51	+every number reported in the paper is reproducible from source.
	52	+
	53	+\end{appendices}

added UQ_WP_template/figures/main_figure.tex +20 −0

		@@ -0,0 +1,20 @@
	1	+% ============================================================================
	2	+% Figure: Main Result
	3	+% ============================================================================
	4	+\begin{figure}[htbp]
	5	+ \centering
	6	+ % --- Replace placeholder with actual figure file ---
	7	+ % \includegraphics[width=0.85\textwidth]{figures/main_result.pdf}
	8	+ %
	9	+ % Placeholder box (remove when replacing with actual figure)
	10	+ \fbox{\parbox{0.85\textwidth}{\centering\vspace{4cm}
	11	+ \textit{[Insert figure here: figures/main\_result.pdf]}
	12	+ \vspace{4cm}}}
	13	+ %
	14	+ \caption{Main Result --- Effect of $X$ on $Y$ Over Time}
	15	+ \label{fig:main_result}
	16	+ \begin{minipage}{0.85\textwidth}
	17	+ \vspace{0.3cm}
	18	+ \footnotesize\textit{Notes:} This figure plots \ldots{} over the sample period January~1990 to December~2023. The solid line represents \ldots{} The shaded area indicates the 95\% confidence interval. The dashed vertical line marks \ldots{}
	19	+ \end{minipage}
	20	+\end{figure}

added UQ_WP_template/main.bbl +187 −0

		@@ -0,0 +1,187 @@
	1	+\ifx\undefined\bysame
	2	+\newcommand{\bysame}{\leavevmode\hbox to\leftmargin{\hrulefill\,\,}}
	3	+\fi
	4	+\begin{thebibliography}{xx}
	5	+
	6	+\harvarditem[Acemoglu and Restrepo]{Acemoglu and
	7	+ Restrepo}{2020}{acemoglu2020wrong}
	8	+{\bf Acemoglu, Daron and Pascual Restrepo}, ``Robots and Jobs: Evidence from
	9	+ {US} Labor Markets,'' {\it Journal of Political Economy}, 2020, {\it 128}
	10	+ (6), 2188--2244.
	11	+
	12	+\harvarditem[Babina et al.]{Babina, Fedyk, He and
	13	+ Hodson}{2024}{babina2024aiinvestment}
	14	+{\bf Babina, Tania, Anastassia Fedyk, Alex He, and James Hodson}, ``Artificial
	15	+ Intelligence, Firm Growth, and Product Innovation,'' {\it Journal of
	16	+ Financial Economics}, 2024, {\it 151}, 103745.
	17	+
	18	+\harvarditem[Baker and Wurgler]{Baker and Wurgler}{2006}{bakerwurgler2006}
	19	+{\bf Baker, Malcolm and Jeffrey Wurgler}, ``Investor Sentiment and the
	20	+ Cross-Section of Stock Returns,'' {\it Journal of Finance}, 2006, {\it 61}
	21	+ (4), 1645--1680.
	22	+
	23	+\harvarditem[Barber and Odean]{Barber and Odean}{2008}{barberodean2008}
	24	+{\bf Barber, Brad~M. and Terrance Odean}, ``All That Glitters: The Effect of
	25	+ Attention and News on the Buying Behavior of Individual and Institutional
	26	+ Investors,'' {\it Review of Financial Studies}, 2008, {\it 21} (2), 785--818.
	27	+
	28	+\harvarditem[Bolton and Kacperczyk]{Bolton and
	29	+ Kacperczyk}{2021}{bolton2021risk}
	30	+{\bf Bolton, Patrick and Marcin Kacperczyk}, ``Do Investors Care about Carbon
	31	+ Risk?,'' {\it Journal of Financial Economics}, 2021, {\it 142} (2), 517--549.
	32	+
	33	+\harvarditem[Bybee et al.]{Bybee, Kelly, Manela and
	34	+ Xiu}{2024}{bybee2024narrative}
	35	+{\bf Bybee, Leland, Bryan Kelly, Asaf Manela, and Dacheng Xiu}, ``Business News
	36	+ and Business Cycles,'' {\it Journal of Finance}, 2024, {\it 79} (5),
	37	+ 3105--3147.
	38	+
	39	+\harvarditem[Cameron et al.]{Cameron, Gelbach and Miller}{2011}{cameron2011}
	40	+{\bf Cameron, A.~Colin, Jonah~B. Gelbach, and Douglas~L. Miller}, ``Robust
	41	+ Inference with Multiway Clustering,'' {\it Journal of Business \& Economic
	42	+ Statistics}, 2011, {\it 29} (2), 238--249.
	43	+
	44	+\harvarditem[Cohen et al.]{Cohen, Malloy and Nguyen}{2020}{cohen2020lazy}
	45	+{\bf Cohen, Lauren, Christopher Malloy, and Quoc Nguyen}, ``Lazy Prices,'' {\it
	46	+ Journal of Finance}, 2020, {\it 75} (3), 1371--1415.
	47	+
	48	+\harvarditem[Cong et al.]{Cong, Liang and Zhang}{2022}{cong2022textfactor}
	49	+{\bf Cong, Lin~William, Tengyuan Liang, and Xiao Zhang}, ``Textual Factors: A
	50	+ Scalable, Interpretable, and Data-Driven Approach to Analyzing Unstructured
	51	+ Information,'' Technical Report, Working Paper 2022.
	52	+
	53	+\harvarditem[Da et al.]{Da, Engelberg and Gao}{2011}{da2011}
	54	+{\bf Da, Zhi, Joseph Engelberg, and Pengjie Gao}, ``In Search of Attention,''
	55	+ {\it Journal of Finance}, 2011, {\it 66} (5), 1461--1499.
	56	+
	57	+\harvarditem[DellaVigna and Pollet]{DellaVigna and
	58	+ Pollet}{2009}{dellavigna2009}
	59	+{\bf DellaVigna, Stefano and Joshua~M. Pollet}, ``Investor Inattention and
	60	+ {Friday} Earnings Announcements,'' {\it Journal of Finance}, 2009, {\it 64}
	61	+ (2), 709--749.
	62	+
	63	+\harvarditem[Eisfeldt et al.]{Eisfeldt, Schubert and
	64	+ Zhang}{2023}{eisfeldt2023generative}
	65	+{\bf Eisfeldt, Andrea~L., Gregor Schubert, and Miao~Ben Zhang}, ``Generative
	66	+ {AI} and Firm Values,'' NBER Working Paper 31222, National Bureau of Economic
	67	+ Research 2023.
	68	+
	69	+\harvarditem[Fama and MacBeth]{Fama and MacBeth}{1973}{famamacbeth1973}
	70	+{\bf Fama, Eugene~F. and James~D. MacBeth}, ``Risk, Return, and Equilibrium:
	71	+ Empirical Tests,'' {\it Journal of Political Economy}, 1973, {\it 81} (3),
	72	+ 607--636.
	73	+
	74	+\harvarditem[Fama and French]{Fama and French}{2015}{famafrench2015}
	75	+{\bf \bysame{} and Kenneth~R. French}, ``A Five-Factor Asset Pricing Model,''
	76	+ {\it Journal of Financial Economics}, 2015, {\it 116} (1), 1--22.
	77	+
	78	+\harvarditem[Gentzkow et al.]{Gentzkow, Kelly and Taddy}{2019}{gentzkow2019}
	79	+{\bf Gentzkow, Matthew, Bryan Kelly, and Matt Taddy}, ``Text as Data,'' {\it
	80	+ Journal of Economic Literature}, 2019, {\it 57} (3), 535--574.
	81	+
	82	+\harvarditem[Hirshleifer et al.]{Hirshleifer, Hsu and
	83	+ Li}{2013}{hirshleifer2013innovative}
	84	+{\bf Hirshleifer, David, Po-Hsuan Hsu, and Dongmei Li}, ``Innovative Efficiency
	85	+ and Stock Returns,'' {\it Journal of Financial Economics}, 2013, {\it 107}
	86	+ (3), 632--654.
	87	+
	88	+\harvarditem[Hirshleifer et al.]{Hirshleifer, Lim and
	89	+ Teoh}{2009}{hirshleifer2009driven}
	90	+{\bf \bysame{}, Sonya~S. Lim, and Siew~Hong Teoh}, ``Driven to Distraction:
	91	+ Extraneous Events and Underreaction to Earnings News,'' {\it Journal of
	92	+ Finance}, 2009, {\it 64} (5), 2289--2325.
	93	+
	94	+\harvarditem[Hoberg and Phillips]{Hoberg and Phillips}{2010}{hoberg2010product}
	95	+{\bf Hoberg, Gerard and Gordon Phillips}, ``Product Market Synergies and
	96	+ Competition in Mergers and Acquisitions: A Text-Based Analysis,'' {\it Review
	97	+ of Financial Studies}, 2010, {\it 23} (10), 3773--3811.
	98	+
	99	+\harvarditem[Hoberg and Phillips]{Hoberg and
	100	+ Phillips}{2016}{hobergphillips2016}
	101	+{\bf \bysame{} and \bysame{}}, ``Text-Based Network Industries and Endogenous
	102	+ Product Differentiation,'' {\it Journal of Political Economy}, 2016, {\it
	103	+ 124} (5), 1423--1465.
	104	+
	105	+\harvarditem[Kelly et al.]{Kelly, Manela and
	106	+ Moreira}{2021}{kelly2019textregression}
	107	+{\bf Kelly, Bryan, Asaf Manela, and Alan Moreira}, ``Text Selection,'' {\it
	108	+ Journal of Business \& Economic Statistics}, 2021, {\it 39} (4), 859--879.
	109	+
	110	+\harvarditem[Kogan and Papanikolaou]{Kogan and
	111	+ Papanikolaou}{2014}{koganpapanikolaou2014}
	112	+{\bf Kogan, Leonid and Dimitris Papanikolaou}, ``Growth Opportunities,
	113	+ Technology Shocks, and Asset Prices,'' {\it Journal of Finance}, 2014, {\it
	114	+ 69} (2), 675--718.
	115	+
	116	+\harvarditem[Kogan et al.]{Kogan, Papanikolaou, Seru and
	117	+ Stoffman}{2017}{kogan2017technological}
	118	+{\bf \bysame{}, \bysame{}, Amit Seru, and Noah Stoffman}, ``Technological
	119	+ Innovation, Resource Allocation, and Growth,'' {\it Quarterly Journal of
	120	+ Economics}, 2017, {\it 132} (2), 665--712.
	121	+
	122	+\harvarditem[Lopez-Lira]{Lopez-Lira}{2023}{lopezlira2023risk}
	123	+{\bf Lopez-Lira, Alejandro}, ``Risk Factors That Matter: Textual Analysis of
	124	+ Risk Disclosures for the Cross-Section of Returns,'' Technical Report,
	125	+ Working Paper 2023.
	126	+
	127	+\harvarditem[Loughran and McDonald]{Loughran and McDonald}{2011}{lm2011}
	128	+{\bf Loughran, Tim and Bill McDonald}, ``When Is a Liability Not a Liability?
	129	+ Textual Analysis, Dictionaries, and 10-Ks,'' {\it Journal of Finance}, 2011,
	130	+ {\it 66} (1), 35--65.
	131	+
	132	+\harvarditem[Loughran and McDonald]{Loughran and McDonald}{2016}{lm2016}
	133	+{\bf \bysame{} and \bysame{}}, ``Textual Analysis in Accounting and Finance: A
	134	+ Survey,'' {\it Journal of Accounting Research}, 2016, {\it 54} (4),
	135	+ 1187--1230.
	136	+
	137	+\harvarditem[MacKinlay]{MacKinlay}{1997}{mackinlay1997}
	138	+{\bf MacKinlay, A.~Craig}, ``Event Studies in Economics and Finance,'' {\it
	139	+ Journal of Economic Literature}, 1997, {\it 35} (1), 13--39.
	140	+
	141	+\harvarditem[Newey and West]{Newey and West}{1987}{neweywest1987}
	142	+{\bf Newey, Whitney~K. and Kenneth~D. West}, ``A Simple, Positive
	143	+ Semi-Definite, Heteroskedasticity and Autocorrelation Consistent Covariance
	144	+ Matrix,'' {\it Econometrica}, 1987, {\it 55} (3), 703--708.
	145	+
	146	+\harvarditem[P{\'a}stor et al.]{P{\'a}stor, Stambaugh and
	147	+ Taylor}{2021}{pastor2021sustainable}
	148	+{\bf P{\'a}stor, {\v{L}}ubo{\v{s}}, Robert~F. Stambaugh, and Lucian~A. Taylor},
	149	+ ``Sustainable Investing in Equilibrium,'' {\it Journal of Financial
	150	+ Economics}, 2021, {\it 142} (2), 550--571.
	151	+
	152	+\harvarditem[P{\'a}stor et al.]{P{\'a}stor, Stambaugh and
	153	+ Taylor}{2022}{pastor2022dissecting}
	154	+{\bf \bysame{}, \bysame{}, and \bysame{}}, ``Dissecting Green Returns,'' {\it
	155	+ Journal of Financial Economics}, 2022, {\it 146} (2), 403--424.
	156	+
	157	+\harvarditem[Petersen]{Petersen}{2009}{petersen2009}
	158	+{\bf Petersen, Mitchell~A.}, ``Estimating Standard Errors in Finance Panel Data
	159	+ Sets: Comparing Approaches,'' {\it Review of Financial Studies}, 2009, {\it
	160	+ 22} (1), 435--480.
	161	+
	162	+\harvarditem[Reimers and Gurevych]{Reimers and
	163	+ Gurevych}{2019}{reimers2019sbert}
	164	+{\bf Reimers, Nils and Iryna Gurevych}, ``Sentence-{BERT}: Sentence Embeddings
	165	+ Using {Siamese} {BERT}-Networks,'' in ``Proceedings of the 2019 Conference on
	166	+ Empirical Methods in Natural Language Processing (EMNLP)'' 2019.
	167	+
	168	+\harvarditem[Shiller]{Shiller}{2017}{shiller2017narrative}
	169	+{\bf Shiller, Robert~J.}, ``Narrative Economics,'' {\it American Economic
	170	+ Review}, 2017, {\it 107} (4), 967--1004.
	171	+
	172	+\harvarditem[Tetlock]{Tetlock}{2007}{tetlock2007}
	173	+{\bf Tetlock, Paul~C.}, ``Giving Content to Investor Sentiment: The Role of
	174	+ Media in the Stock Market,'' {\it Journal of Finance}, 2007, {\it 62} (3),
	175	+ 1139--1168.
	176	+
	177	+\harvarditem[Tetlock et al.]{Tetlock, Saar-Tsechansky and
	178	+ Macskassy}{2008}{tetlock2008}
	179	+{\bf \bysame{}, Maytal Saar-Tsechansky, and Sofus Macskassy}, ``More Than
	180	+ Words: Quantifying Language to Measure Firms' Fundamentals,'' {\it Journal of
	181	+ Finance}, 2008, {\it 63} (3), 1437--1467.
	182	+
	183	+\harvarditem[Webb]{Webb}{2020}{webb2020}
	184	+{\bf Webb, Michael}, ``The Impact of Artificial Intelligence on the Labor
	185	+ Market,'' Technical Report, Stanford University Working Paper 2020.
	186	+
	187	+\end{thebibliography}

added UQ_WP_template/main.blg +48 −0

		@@ -0,0 +1,48 @@
	1	+This is BibTeX, Version 0.99e (TeX Live 2026)
	2	+Capacity: max_strings=200000, hash_size=200000, hash_prime=170003
	3	+The top-level auxiliary file: main.aux
	4	+The style file: aer.bst
	5	+Reallocated singl_function (elt_size=4) to 100 items from 50.
	6	+Reallocated singl_function (elt_size=4) to 100 items from 50.
	7	+Database file #1: references.bib
	8	+You've used 35 entries,
	9	+ 2984 wiz_defined-function locations,
	10	+ 847 strings with 8991 characters,
	11	+and the built_in function-call counts, 31924 in all, are:
	12	+= -- 5079
	13	+> -- 1808
	14	+< -- 516
	15	++ -- 580
	16	+- -- 328
	17	+* -- 2173
	18	+:= -- 7060
	19	+add.period$ -- 35
	20	+call.type$ -- 35
	21	+change.case$ -- 245
	22	+chr.to.int$ -- 35
	23	+cite$ -- 35
	24	+duplicate$ -- 385
	25	+empty$ -- 983
	26	+format.name$ -- 912
	27	+if$ -- 7891
	28	+int.to.chr$ -- 1
	29	+int.to.str$ -- 0
	30	+missing$ -- 31
	31	+newline$ -- 111
	32	+num.names$ -- 420
	33	+pop$ -- 527
	34	+preamble$ -- 1
	35	+purify$ -- 280
	36	+quote$ -- 0
	37	+skip$ -- 0
	38	+stack$ -- 0
	39	+substring$ -- 1182
	40	+swap$ -- 132
	41	+text.length$ -- 1
	42	+text.prefix$ -- 0
	43	+top$ -- 0
	44	+type$ -- 140
	45	+warning$ -- 0
	46	+while$ -- 409
	47	+width$ -- 0
	48	+write$ -- 589

added UQ_WP_template/main.pdf +0 −0

Binary file not shown.

added UQ_WP_template/main.tex +174 −0

		@@ -0,0 +1,174 @@
	1	+% ============================================================================
	2	+% UQO Working Paper Template — Economics / Finance
	3	+% ============================================================================
	4	+\documentclass[12pt,letterpaper]{article}
	5	+
	6	+% --- Encoding & Language ---
	7	+\usepackage[utf8]{inputenc}
	8	+\usepackage[T1]{fontenc}
	9	+\usepackage[english]{babel}
	10	+
	11	+% --- Page Layout ---
	12	+\usepackage[
	13	+ letterpaper,
	14	+ top=1in,
	15	+ bottom=1in,
	16	+ left=1in,
	17	+ right=1in
	18	+]{geometry}
	19	+
	20	+% --- Typography ---
	21	+\usepackage{mathptmx} % Times-like font (text + math)
	22	+\usepackage{microtype} % Improved typographic refinements
	23	+\usepackage{setspace}
	24	+\doublespacing % double line spacing (working-paper format)
	25	+
	26	+% --- Math ---
	27	+\usepackage{amsmath,amssymb,amsthm}
	28	+
	29	+% --- Tables ---
	30	+\usepackage{booktabs}
	31	+\usepackage{tabularx}
	32	+\usepackage{multirow}
	33	+\usepackage{threeparttable}
	34	+\usepackage{siunitx}
	35	+\sisetup{
	36	+ input-symbols = {()},
	37	+ table-format = -1.3,
	38	+ parse-numbers = false
	39	+}
	40	+
	41	+% --- Figures ---
	42	+\usepackage{graphicx}
	43	+\usepackage{subcaption}
	44	+\usepackage{float}
	45	+
	46	+% --- Colors & Links ---
	47	+\usepackage[dvipsnames]{xcolor}
	48	+\usepackage[
	49	+ colorlinks = true,
	50	+ linkcolor = NavyBlue,
	51	+ citecolor = NavyBlue,
	52	+ urlcolor = NavyBlue,
	53	+ breaklinks = true
	54	+]{hyperref}
	55	+
	56	+% --- Bibliography ---
	57	+\usepackage[authoryear,round,semicolon]{natbib}
	58	+\bibliographystyle{aer}
	59	+
	60	+% --- Captions ---
	61	+\usepackage[
	62	+ font = small,
	63	+ labelfont = bf,
	64	+ labelsep = period,
	65	+ justification = justified,
	66	+ singlelinecheck = false
	67	+]{caption}
	68	+
	69	+% --- Headers & Footers ---
	70	+\usepackage{fancyhdr}
	71	+\pagestyle{fancy}
	72	+\fancyhf{}
	73	+\renewcommand{\headrulewidth}{0pt}
	74	+\fancyfoot[C]{\thepage}
	75	+
	76	+% --- Section Formatting ---
	77	+\usepackage{titlesec}
	78	+\titleformat{\section}{\large\bfseries}{\thesection.}{0.5em}{}
	79	+\titleformat{\subsection}{\normalsize\bfseries}{\thesubsection.}{0.5em}{}
	80	+\titleformat{\subsubsection}{\normalsize\itshape}{\thesubsubsection.}{0.5em}{}
	81	+
	82	+% --- Appendix Support ---
	83	+\usepackage[toc,page]{appendix}
	84	+
	85	+% --- Misc ---
	86	+\usepackage{enumitem}
	87	+\setlist{nosep,leftmargin=*}
	88	+
	89	+% --- Project-specific additions ---
	90	+\graphicspath{{figures/}}
	91	+\newcommand{\tstat}[1]{{\footnotesize(\textit{t}=#1)}}
	92	+
	93	+% ============================================================================
	94	+% METADATA — Edit these fields for each working paper
	95	+% ============================================================================
	96	+\newcommand{\WPnumber}{2026-03}
	97	+\newcommand{\WPtitle}{Does the Language of Artificial Intelligence Move Markets?}
	98	+\newcommand{\WPsubtitle}{A Semantic Analysis of S\&P~500 SEC Filings and the Cross-Section of Stock Returns, 2010--2026}
	99	+\newcommand{\WPdate}{June 2026}
	100	+\newcommand{\WPversion}{1.0}
	101	+\newcommand{\WPabstract}{%
	102	+ We construct a \emph{semantic} measure of artificial-intelligence (AI) engagement for every
	103	+ S\&P~500 firm by embedding the text of its annual SEC filings (Form~10-K) with a sentence
	104	+ transformer and scoring each passage by cosine similarity to curated AI ``anchor'' concepts:
	105	+ internal AI adoption, AI infrastructure exposure, and AI product-disruption risk. Linking these
	106	+ scores to monthly equity prices from Yahoo Finance and to the Fama--French factor data, we
	107	+ assemble a panel of 7{,}869 firm-years (500 firms, fiscal years 2010--2026) and ask whether the
	108	+ intensity of AI language predicts the cross-section of subsequent returns. Our central result is
	109	+ \emph{conditional and economically large}: over the full sample the relation is positive but
	110	+ modest and only marginally significant, yet after the launch of ChatGPT (November~2022) it more
	111	+ than sextuples. The spread between the top and bottom quintile of AI disclosure rises from $+2.4$
	112	+ percentage points per year before 2022 to $+14.6$ points afterward, and the long--short Sharpe
	113	+ ratio rises from 0.15 to 1.33. The break survives section-weighting choices, alternative signal
	114	+ definitions and horizons, dimension reduction, and the exclusion of the ``Magnificent~7''
	115	+ mega-caps. Three identification tests sharpen the interpretation: (i)~a placebo across five
	116	+ non-AI semantic factors shows the post-2022 jump is specific to AI (ESG and climate disclosure
	117	+ earn \emph{negative} post-2022 spreads); (ii)~a market-model event study finds that firms with
	118	+ higher pre-event AI disclosure earned $+10.1\%$ higher cumulative abnormal returns over the year
	119	+ after ChatGPT ($t=1.97$); and (iii)~the effect is absorbed by firm fixed effects and roughly
	120	+ halved by sector fixed effects. We interpret the evidence as an attention- and narrative-driven
	121	+ \emph{re-rating}: the market repriced which firms and sectors are AI-exposed once AI became
	122	+ salient, rather than rewarding year-to-year changes in wording.%
	123	+}
	124	+\newcommand{\WPkeywords}{textual analysis, sentence embeddings, artificial intelligence, disclosure, cross-section of returns, investor attention, event study}
	125	+\newcommand{\WPjel}{G12, G14, G17, M41, O33}
	126	+
	127	+% --- Authors ---
	128	+\newcommand{\WPauthor}{%
	129	+ \begin{tabular}{c}
	130	+ {\large Manel Kammoun}\\[-0.05cm]
	131	+ {\small\href{mailto:manel.kammoun@uqo.ca}{manel.kammoun@uqo.ca}}\\[0.35cm]
	132	+ {\large Djerrycharli Tandjambianda}\\[-0.05cm]
	133	+ {\small\href{mailto:djerrycharli.tandjambianda@uqo.ca}{djerrycharli.tandjambianda@uqo.ca}}\\[0.35cm]
	134	+ {\large Simon-Pierre Boucher}\\[-0.05cm]
	135	+ {\small\href{mailto:simon-pierre.boucher@uqo.ca}{simon-pierre.boucher@uqo.ca}}
	136	+ \end{tabular}%
	137	+}
	138	+\newcommand{\WPaffiliation}{%
	139	+ Département des sciences administratives\\
	140	+ Université du Québec en Outaouais%
	141	+}
	142	+\newcommand{\WPemail}{}
	143	+\newcommand{\WPaddress}{%
	144	+ Gatineau -- Pavillon Alexandre-Taché\\
	145	+ 283, boulevard Alexandre-Taché\\
	146	+ Gatineau, Québec, Canada J9A 1L8%
	147	+}
	148	+
	149	+% ============================================================================
	150	+% DOCUMENT
	151	+% ============================================================================
	152	+\begin{document}
	153	+
	154	+% --- Title Page ---
	155	+\input{sections/titlepage}
	156	+
	157	+% --- Main Body ---
	158	+\input{sections/introduction}
	159	+\input{sections/literature}
	160	+\input{sections/data}
	161	+\input{sections/methodology}
	162	+\input{sections/results}
	163	+\input{sections/robustness}
	164	+\input{sections/discussion}
	165	+\input{sections/conclusion}
	166	+
	167	+% --- References ---
	168	+\newpage
	169	+\bibliography{references}
	170	+
	171	+% --- Appendix ---
	172	+\input{appendix/appendix}
	173	+
	174	+\end{document}

added UQ_WP_template/references.bib +340 −0

		@@ -0,0 +1,340 @@
	1	+% ============================================================================
	2	+% References — BibTeX Database
	3	+% "Does the Language of Artificial Intelligence Move Markets?"
	4	+% ============================================================================
	5	+
	6	+@article{acemoglu2020wrong,
	7	+ author = {Acemoglu, Daron and Restrepo, Pascual},
	8	+ title = {Robots and Jobs: Evidence from {US} Labor Markets},
	9	+ journal = {Journal of Political Economy},
	10	+ volume = {128},
	11	+ number = {6},
	12	+ pages = {2188--2244},
	13	+ year = {2020}
	14	+}
	15	+
	16	+@article{babina2024aiinvestment,
	17	+ author = {Babina, Tania and Fedyk, Anastassia and He, Alex and Hodson, James},
	18	+ title = {Artificial Intelligence, Firm Growth, and Product Innovation},
	19	+ journal = {Journal of Financial Economics},
	20	+ volume = {151},
	21	+ pages = {103745},
	22	+ year = {2024}
	23	+}
	24	+
	25	+@article{bakerwurgler2006,
	26	+ author = {Baker, Malcolm and Wurgler, Jeffrey},
	27	+ title = {Investor Sentiment and the Cross-Section of Stock Returns},
	28	+ journal = {Journal of Finance},
	29	+ volume = {61},
	30	+ number = {4},
	31	+ pages = {1645--1680},
	32	+ year = {2006}
	33	+}
	34	+
	35	+@article{barberodean2008,
	36	+ author = {Barber, Brad M. and Odean, Terrance},
	37	+ title = {All That Glitters: The Effect of Attention and News on the Buying Behavior of Individual and Institutional Investors},
	38	+ journal = {Review of Financial Studies},
	39	+ volume = {21},
	40	+ number = {2},
	41	+ pages = {785--818},
	42	+ year = {2008}
	43	+}
	44	+
	45	+@article{bolton2021risk,
	46	+ author = {Bolton, Patrick and Kacperczyk, Marcin},
	47	+ title = {Do Investors Care about Carbon Risk?},
	48	+ journal = {Journal of Financial Economics},
	49	+ volume = {142},
	50	+ number = {2},
	51	+ pages = {517--549},
	52	+ year = {2021}
	53	+}
	54	+
	55	+@article{bybee2024narrative,
	56	+ author = {Bybee, Leland and Kelly, Bryan and Manela, Asaf and Xiu, Dacheng},
	57	+ title = {Business News and Business Cycles},
	58	+ journal = {Journal of Finance},
	59	+ volume = {79},
	60	+ number = {5},
	61	+ pages = {3105--3147},
	62	+ year = {2024}
	63	+}
	64	+
	65	+@article{cameron2011,
	66	+ author = {Cameron, A. Colin and Gelbach, Jonah B. and Miller, Douglas L.},
	67	+ title = {Robust Inference with Multiway Clustering},
	68	+ journal = {Journal of Business \& Economic Statistics},
	69	+ volume = {29},
	70	+ number = {2},
	71	+ pages = {238--249},
	72	+ year = {2011}
	73	+}
	74	+
	75	+@article{cohen2020lazy,
	76	+ author = {Cohen, Lauren and Malloy, Christopher and Nguyen, Quoc},
	77	+ title = {Lazy Prices},
	78	+ journal = {Journal of Finance},
	79	+ volume = {75},
	80	+ number = {3},
	81	+ pages = {1371--1415},
	82	+ year = {2020}
	83	+}
	84	+
	85	+@techreport{cong2022textfactor,
	86	+ author = {Cong, Lin William and Liang, Tengyuan and Zhang, Xiao},
	87	+ title = {Textual Factors: A Scalable, Interpretable, and Data-Driven Approach to Analyzing Unstructured Information},
	88	+ institution = {Working Paper},
	89	+ year = {2022}
	90	+}
	91	+
	92	+@article{da2011,
	93	+ author = {Da, Zhi and Engelberg, Joseph and Gao, Pengjie},
	94	+ title = {In Search of Attention},
	95	+ journal = {Journal of Finance},
	96	+ volume = {66},
	97	+ number = {5},
	98	+ pages = {1461--1499},
	99	+ year = {2011}
	100	+}
	101	+
	102	+@article{dellavigna2009,
	103	+ author = {DellaVigna, Stefano and Pollet, Joshua M.},
	104	+ title = {Investor Inattention and {Friday} Earnings Announcements},
	105	+ journal = {Journal of Finance},
	106	+ volume = {64},
	107	+ number = {2},
	108	+ pages = {709--749},
	109	+ year = {2009}
	110	+}
	111	+
	112	+@techreport{eisfeldt2023generative,
	113	+ author = {Eisfeldt, Andrea L. and Schubert, Gregor and Zhang, Miao Ben},
	114	+ title = {Generative {AI} and Firm Values},
	115	+ institution = {National Bureau of Economic Research},
	116	+ type = {NBER Working Paper},
	117	+ number = {31222},
	118	+ year = {2023}
	119	+}
	120	+
	121	+@article{famafrench2015,
	122	+ author = {Fama, Eugene F. and French, Kenneth R.},
	123	+ title = {A Five-Factor Asset Pricing Model},
	124	+ journal = {Journal of Financial Economics},
	125	+ volume = {116},
	126	+ number = {1},
	127	+ pages = {1--22},
	128	+ year = {2015}
	129	+}
	130	+
	131	+@article{famamacbeth1973,
	132	+ author = {Fama, Eugene F. and MacBeth, James D.},
	133	+ title = {Risk, Return, and Equilibrium: Empirical Tests},
	134	+ journal = {Journal of Political Economy},
	135	+ volume = {81},
	136	+ number = {3},
	137	+ pages = {607--636},
	138	+ year = {1973}
	139	+}
	140	+
	141	+@article{gentzkow2019,
	142	+ author = {Gentzkow, Matthew and Kelly, Bryan and Taddy, Matt},
	143	+ title = {Text as Data},
	144	+ journal = {Journal of Economic Literature},
	145	+ volume = {57},
	146	+ number = {3},
	147	+ pages = {535--574},
	148	+ year = {2019}
	149	+}
	150	+
	151	+@article{hirshleifer2009driven,
	152	+ author = {Hirshleifer, David and Lim, Sonya S. and Teoh, Siew Hong},
	153	+ title = {Driven to Distraction: Extraneous Events and Underreaction to Earnings News},
	154	+ journal = {Journal of Finance},
	155	+ volume = {64},
	156	+ number = {5},
	157	+ pages = {2289--2325},
	158	+ year = {2009}
	159	+}
	160	+
	161	+@article{hirshleifer2013innovative,
	162	+ author = {Hirshleifer, David and Hsu, Po-Hsuan and Li, Dongmei},
	163	+ title = {Innovative Efficiency and Stock Returns},
	164	+ journal = {Journal of Financial Economics},
	165	+ volume = {107},
	166	+ number = {3},
	167	+ pages = {632--654},
	168	+ year = {2013}
	169	+}
	170	+
	171	+@article{hoberg2010product,
	172	+ author = {Hoberg, Gerard and Phillips, Gordon},
	173	+ title = {Product Market Synergies and Competition in Mergers and Acquisitions: A Text-Based Analysis},
	174	+ journal = {Review of Financial Studies},
	175	+ volume = {23},
	176	+ number = {10},
	177	+ pages = {3773--3811},
	178	+ year = {2010}
	179	+}
	180	+
	181	+@article{hobergphillips2016,
	182	+ author = {Hoberg, Gerard and Phillips, Gordon},
	183	+ title = {Text-Based Network Industries and Endogenous Product Differentiation},
	184	+ journal = {Journal of Political Economy},
	185	+ volume = {124},
	186	+ number = {5},
	187	+ pages = {1423--1465},
	188	+ year = {2016}
	189	+}
	190	+
	191	+@article{kelly2019textregression,
	192	+ author = {Kelly, Bryan and Manela, Asaf and Moreira, Alan},
	193	+ title = {Text Selection},
	194	+ journal = {Journal of Business \& Economic Statistics},
	195	+ volume = {39},
	196	+ number = {4},
	197	+ pages = {859--879},
	198	+ year = {2021}
	199	+}
	200	+
	201	+@article{kogan2017technological,
	202	+ author = {Kogan, Leonid and Papanikolaou, Dimitris and Seru, Amit and Stoffman, Noah},
	203	+ title = {Technological Innovation, Resource Allocation, and Growth},
	204	+ journal = {Quarterly Journal of Economics},
	205	+ volume = {132},
	206	+ number = {2},
	207	+ pages = {665--712},
	208	+ year = {2017}
	209	+}
	210	+
	211	+@article{koganpapanikolaou2014,
	212	+ author = {Kogan, Leonid and Papanikolaou, Dimitris},
	213	+ title = {Growth Opportunities, Technology Shocks, and Asset Prices},
	214	+ journal = {Journal of Finance},
	215	+ volume = {69},
	216	+ number = {2},
	217	+ pages = {675--718},
	218	+ year = {2014}
	219	+}
	220	+
	221	+@techreport{lopezlira2023risk,
	222	+ author = {Lopez-Lira, Alejandro},
	223	+ title = {Risk Factors That Matter: Textual Analysis of Risk Disclosures for the Cross-Section of Returns},
	224	+ institution = {Working Paper},
	225	+ year = {2023}
	226	+}
	227	+
	228	+@article{lm2011,
	229	+ author = {Loughran, Tim and McDonald, Bill},
	230	+ title = {When Is a Liability Not a Liability? Textual Analysis, Dictionaries, and 10-Ks},
	231	+ journal = {Journal of Finance},
	232	+ volume = {66},
	233	+ number = {1},
	234	+ pages = {35--65},
	235	+ year = {2011}
	236	+}
	237	+
	238	+@article{lm2016,
	239	+ author = {Loughran, Tim and McDonald, Bill},
	240	+ title = {Textual Analysis in Accounting and Finance: A Survey},
	241	+ journal = {Journal of Accounting Research},
	242	+ volume = {54},
	243	+ number = {4},
	244	+ pages = {1187--1230},
	245	+ year = {2016}
	246	+}
	247	+
	248	+@article{mackinlay1997,
	249	+ author = {MacKinlay, A. Craig},
	250	+ title = {Event Studies in Economics and Finance},
	251	+ journal = {Journal of Economic Literature},
	252	+ volume = {35},
	253	+ number = {1},
	254	+ pages = {13--39},
	255	+ year = {1997}
	256	+}
	257	+
	258	+@article{neweywest1987,
	259	+ author = {Newey, Whitney K. and West, Kenneth D.},
	260	+ title = {A Simple, Positive Semi-Definite, Heteroskedasticity and Autocorrelation Consistent Covariance Matrix},
	261	+ journal = {Econometrica},
	262	+ volume = {55},
	263	+ number = {3},
	264	+ pages = {703--708},
	265	+ year = {1987}
	266	+}
	267	+
	268	+@article{pastor2021sustainable,
	269	+ author = {P{\'a}stor, {\v{L}}ubo{\v{s}} and Stambaugh, Robert F. and Taylor, Lucian A.},
	270	+ title = {Sustainable Investing in Equilibrium},
	271	+ journal = {Journal of Financial Economics},
	272	+ volume = {142},
	273	+ number = {2},
	274	+ pages = {550--571},
	275	+ year = {2021}
	276	+}
	277	+
	278	+@article{pastor2022dissecting,
	279	+ author = {P{\'a}stor, {\v{L}}ubo{\v{s}} and Stambaugh, Robert F. and Taylor, Lucian A.},
	280	+ title = {Dissecting Green Returns},
	281	+ journal = {Journal of Financial Economics},
	282	+ volume = {146},
	283	+ number = {2},
	284	+ pages = {403--424},
	285	+ year = {2022}
	286	+}
	287	+
	288	+@article{petersen2009,
	289	+ author = {Petersen, Mitchell A.},
	290	+ title = {Estimating Standard Errors in Finance Panel Data Sets: Comparing Approaches},
	291	+ journal = {Review of Financial Studies},
	292	+ volume = {22},
	293	+ number = {1},
	294	+ pages = {435--480},
	295	+ year = {2009}
	296	+}
	297	+
	298	+@inproceedings{reimers2019sbert,
	299	+ author = {Reimers, Nils and Gurevych, Iryna},
	300	+ title = {Sentence-{BERT}: Sentence Embeddings Using {Siamese} {BERT}-Networks},
	301	+ booktitle = {Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing (EMNLP)},
	302	+ year = {2019}
	303	+}
	304	+
	305	+@article{shiller2017narrative,
	306	+ author = {Shiller, Robert J.},
	307	+ title = {Narrative Economics},
	308	+ journal = {American Economic Review},
	309	+ volume = {107},
	310	+ number = {4},
	311	+ pages = {967--1004},
	312	+ year = {2017}
	313	+}
	314	+
	315	+@article{tetlock2007,
	316	+ author = {Tetlock, Paul C.},
	317	+ title = {Giving Content to Investor Sentiment: The Role of Media in the Stock Market},
	318	+ journal = {Journal of Finance},
	319	+ volume = {62},
	320	+ number = {3},
	321	+ pages = {1139--1168},
	322	+ year = {2007}
	323	+}
	324	+
	325	+@article{tetlock2008,
	326	+ author = {Tetlock, Paul C. and Saar-Tsechansky, Maytal and Macskassy, Sofus},
	327	+ title = {More Than Words: Quantifying Language to Measure Firms' Fundamentals},
	328	+ journal = {Journal of Finance},
	329	+ volume = {63},
	330	+ number = {3},
	331	+ pages = {1437--1467},
	332	+ year = {2008}
	333	+}
	334	+
	335	+@techreport{webb2020,
	336	+ author = {Webb, Michael},
	337	+ title = {The Impact of Artificial Intelligence on the Labor Market},
	338	+ institution = {Stanford University Working Paper},
	339	+ year = {2020}
	340	+}

added UQ_WP_template/sections/conclusion.tex +30 −0

		@@ -0,0 +1,30 @@
	1	+% ============================================================================
	2	+\section{Conclusion}
	3	+\label{sec:conclusion}
	4	+% ============================================================================
	5	+
	6	+Using a semantic, embedding-based measure of artificial-intelligence language in the SEC filings of
	7	+S\&P~500 firms, linked to Yahoo Finance returns and standard factor data, we have shown that the
	8	+pricing of AI disclosure is a \emph{conditional, regime-dependent} phenomenon. For most of the 2010s,
	9	+how intensively a firm wrote about adopting, building, or being threatened by AI bore only a faint
	10	+relation to its subsequent returns, and a risk-adjusted long--short strategy earned no reliable
	11	+alpha. After the launch of ChatGPT in late 2022, the same disclosure became strongly priced: the
	12	+high-minus-low AI-disclosure return spread jumped from roughly $+2$ to roughly $+15$ percentage points
	13	+per year, and the long--short Sharpe ratio rose from 0.15 to 1.33.
	14	+
	15	+The break is robust to signal definition, horizon, dimension reduction, and the exclusion of mega-cap
	16	+winners; it is specific to AI-related language (ESG and climate disclosure, tested identically, were
	17	+\emph{penalized} in the same window); it is corroborated by a market-model event study in which
	18	+high-AI firms earned $+10$ points of additional abnormal return in the year after ChatGPT; and it
	19	+operates as a cross-sectional re-rating of persistent firm- and sector-level exposure rather than a
	20	+reward for year-to-year wording, fading under firm fixed effects.
	21	+
	22	+The economic message is that markets price the \emph{language} of AI---but only once AI commands their
	23	+attention. The methodological message is that embedding-based measurement of disclosure content opens
	24	+a productive avenue for asset pricing, capturing economically meaningful, multi-faceted exposures at
	25	+scale and revealing pricing dynamics that keyword counts and firm-differenced designs would miss. As
	26	+generative AI continues to reshape the corporate landscape, the semantic footprint it leaves in
	27	+mandatory disclosure offers a rich, and now demonstrably value-relevant, signal. Promising next steps
	28	+include extending the panel beyond the S\&P~500 to mid- and small-cap firms where attention frictions
	29	+are larger, incorporating earnings-call and patent text as complementary AI-exposure measures, and
	30	+tracking whether the post-2022 premium persists, decays, or reverses as the AI narrative matures.

added UQ_WP_template/sections/data.tex +135 −0

		@@ -0,0 +1,135 @@
	1	+% ============================================================================
	2	+\section{Data and Variable Construction}
	3	+\label{sec:data}
	4	+% ============================================================================
	5	+
	6	+\subsection{The semantic factor panel}
	7	+\label{subsec:semantic}
	8	+The backbone of our study is the EDGAR Research Database, an infrastructure that downloads, parses,
	9	+and semantically scores SEC filings for S\&P~500 firms. For each filing the pipeline (i)~extracts
	10	+the canonical sections (Risk Factors, MD\&A, legal proceedings, financial statements, and so on);
	11	+(ii)~splits each section into overlapping text chunks; (iii)~embeds every chunk into a
	12	+384-dimensional vector with the \texttt{all-MiniLM-L6-v2} sentence transformer; and (iv)~scores each
	13	+chunk by cosine similarity to a set of \emph{anchor} passages defining eight economic concepts. The
	14	+anchors are short, deliberately written paragraphs that articulate the concept in natural language;
	15	+for example, the AI-adoption anchor describes a firm ``internally using artificial intelligence,
	16	+machine learning, generative AI, large language models, automation, predictive analytics \dots\ to
	17	+improve productivity, operations, efficiency, decision-making.'' Cosine similarity to such an anchor
	18	+measures how closely a passage's \emph{meaning} matches the concept, regardless of the exact words
	19	+used---capturing paraphrase and context in a way keyword counts cannot.
	20	+
	21	+Chunk-level scores are aggregated to the filing level using section weights that emphasize the parts
	22	+of the document where the concept is most likely to be discussed substantively (e.g.\ MD\&A and Risk
	23	+Factors), and then to the firm-fiscal-year level. For each concept the database reports the mean,
	24	+maximum, standard deviation, top-5\% tail, and section-weighted mean (\texttt{wmean}) of chunk
	25	+similarities, along with first and second differences, percentage changes, and three-year rolling
	26	+statistics. The eight concepts comprise three AI facets---\emph{AI adoption}, \emph{AI
	27	+infrastructure}, \emph{AI disruption risk}---and five others used as placebos: \emph{ESG commitment},
	28	+\emph{climate risk}, \emph{cybersecurity}, \emph{automation/labor}, and \emph{macro risk}.
	29	+
	30	+The resulting panel covers all 500 current S\&P~500 members across fiscal years 2010--2026, a total
	31	+of 7{,}869 firm-years. We take the section-weighted mean (\texttt{wmean}) as our headline signal
	32	+because it up-weights the forward-looking, strategy-rich sections; we verify robustness to the
	33	+simple mean and the top-5\% tail in Section~\ref{sec:robustness}. Our three primary signals are
	34	+therefore \texttt{ai\_adoption\_wmean} (\textbf{AI\,Adopt}), \texttt{ai\_infrastructure\_wmean}
	35	+(\textbf{AI\,Infra}), and \texttt{ai\_disruption\_risk\_wmean} (\textbf{AI\,Risk}); we also form a
	36	+standardized opportunity composite, $\text{AI\,Compos}=\tfrac12[z(\text{AI\,Adopt})+z(\text{AI\,Infra})]$.
	37	+
	38	+\subsection{Price and factor data}
	39	+\label{subsec:price}
	40	+We download monthly adjusted-close prices for all 500 tickers from Yahoo Finance over 2009--2026
	41	+(handling share-class tickers such as BRK.B and BF.B), the SPDR S\&P~500 ETF (SPY) as the market
	42	+benchmark, and the Fama--French five factors \citep{famafrench2015}, the momentum factor, and the
	43	+risk-free rate from the Kenneth R.\ French data library. Monthly simple returns are computed from
	44	+adjusted prices, which incorporate dividends and splits. A market-capitalization proxy is formed as
	45	+shares outstanding (from Yahoo Finance) times the historical price; we use it for value-weighting and
	46	+as a size control, acknowledging the shares-held-constant approximation.
	47	+
	48	+\subsection{Timing and the construction of tradeable returns}
	49	+\label{subsec:timing}
	50	+The single most important design choice in a disclosure--return study is timing. A 10-K covering
	51	+fiscal year $Y$ becomes public only when filed, typically in February or March of year $Y{+}1$. To
	52	+guarantee that our signal is in the public information set before any return is measured, we follow
	53	+the Fama--French portfolio convention: signals from fiscal year $Y$ are used to form portfolios at
	54	+the end of June of $Y{+}1$, and we measure the forward twelve-month return from July of $Y{+}1$
	55	+through June of $Y{+}2$. The roughly three-month gap between the typical filing date and June~30
	56	+ensures no look-ahead bias even for late filers. After requiring a valid forward return with adequate
	57	+monthly coverage, we obtain 6{,}852 firm-years spanning formation years 2010--2024, with return
	58	+realizations extending through mid-2026.
	59	+
	60	+\subsection{Controls and standardization}
	61	+\label{subsec:controls}
	62	+For each formation year we compute cross-sectional $z$-scores of every signal, so that all
	63	+coefficients are expressed per cross-sectional standard deviation and the powerful secular rise in AI
	64	+language (documented below) is differenced out---in any given year we compare firms to their
	65	+contemporaneous peers. We control for the three workhorse return determinants: \emph{size} (log
	66	+market-cap proxy), \emph{momentum} (the firm's own return over the twelve months ending at formation,
	67	+skipping the last month), and \emph{idiosyncratic volatility} (the annualized standard deviation of
	68	+monthly returns over the trailing year). In regressions, returns and continuous controls are
	69	+winsorized at the 1st and 99th percentiles to limit the influence of outliers; in portfolio sorts we
	70	+use raw returns. Appendix~\ref{app:variables} gives precise definitions.
	71	+
	72	+\subsection{Summary statistics}
	73	+\label{subsec:summary}
	74	+Table~\ref{tab:summ} reports summary statistics for the estimation sample. The average forward
	75	+twelve-month return is 18.6\% (reflecting the strong 2011--2026 bull market for U.S.\ large caps),
	76	+with a wide cross-sectional dispersion (standard deviation 41.5\%). The AI signals are small in
	77	+level---cosine similarities of disclosure to narrow anchors---but exhibit meaningful cross-sectional
	78	+variation. Table~\ref{tab:corr} reports correlations. Two features stand out. First, the three AI
	79	+signals are highly collinear (pairwise $\rho$ between 0.75 and 0.86): firms that write more about
	80	+adopting AI also write more about AI infrastructure and AI risk. They are best understood as three
	81	+lenses on a single latent construct---\emph{AI salience}---a point we formalize with
	82	+principal-components analysis in Section~\ref{sec:robustness}. Second, the raw (unconditional)
	83	+correlation between each AI signal and the forward return is positive but small ($\approx 0.04$),
	84	+foreshadowing that the unconditional relation is weak and that the action lies in its time variation.
	85	+
	86	+\input{tables/tab_summary}
	87	+\input{tables/tab_corr}
	88	+
	89	+\subsection{The secular rise of AI language}
	90	+\label{subsec:trend}
	91	+Before turning to returns, Figure~\ref{fig:trend} documents the raw phenomenon that motivates our
	92	+within-year design. The cross-sectional mean similarity to all three AI concepts trended steadily
	93	+upward through the 2010s and inflected sharply after 2022; by 2025--2026 AI language saturates
	94	+S\&P~500 disclosure. This is precisely why our tests rely on within-year cross-sectional ranking: the
	95	+interesting question is not whether the index as a whole talks more about AI over time (it
	96	+emphatically does), but whether, \emph{in a given year}, firms that talk about AI more than their
	97	+peers subsequently earn different returns. Figure~\ref{fig:sectorbox} shows that AI disclosure is
	98	+also unevenly distributed across sectors, concentrated in Information Technology, Communication
	99	+Services, and Industrials---a fact that will matter for interpreting the sector channel.
	100	+
	101	+\begin{figure}[htbp]\centering
	102	+\includegraphics[width=0.9\textwidth]{fig4_ai_language_trend.png}
	103	+\caption{Cross-sectional mean of section-weighted cosine similarity to each AI anchor, by fiscal
	104	+year. All three measures trend upward and inflect after the 2022 launch of ChatGPT (dashed line).}
	105	+\label{fig:trend}
	106	+\end{figure}
	107	+
	108	+\begin{figure}[htbp]\centering
	109	+\includegraphics[width=0.9\textwidth]{fig12_sector_box.png}
	110	+\caption{Distribution of the AI-adoption score by GICS sector (box plots, outliers suppressed; red
	111	+line $=$ median). AI disclosure is concentrated in technology-intensive sectors.}
	112	+\label{fig:sectorbox}
	113	+\end{figure}
	114	+
	115	+\subsection{Which firms disclose the most AI? Descriptive evidence}
	116	+\label{subsec:topfirms}
	117	+Table~\ref{tab:topfirms} lists the ten most AI-intensive S\&P~500 firms by average AI-adoption score
	118	+over the full sample. The list is instructive in two ways. First, it has strong face validity: it
	119	+features enterprise-technology and software firms (Hewlett Packard Enterprise, Intel, IBM, Tyler
	120	+Technologies, Autodesk), an algorithm-centric platform (Uber), and data-intensive financials (BNY
	121	+Mellon, Berkshire Hathaway), exactly the kinds of firms one would expect to write substantively about
	122	+deploying AI. Second, the list is \emph{not} confined to the technology sector: industrials (Cummins)
	123	+and energy (EOG Resources) appear, confirming that intensive AI disclosure cuts across the GICS
	124	+taxonomy and that our continuous, text-based measure captures variation a sector dummy would miss.
	125	+
	126	+A further descriptive fact is central to our interpretation: the AI signal is highly
	127	+\emph{persistent}. The year-over-year cross-sectional rank autocorrelation of the AI composite is
	128	+0.88, and even at a five-year horizon it remains 0.73. Firms that are AI-intensive disclosers stay
	129	+AI-intensive; the measure captures a slow-moving structural characteristic of the firm rather than
	130	+transient wording. This persistence has two implications we exploit later: it explains why firm fixed
	131	+effects absorb most of the signal (there is little within-firm variation to identify), and it
	132	+underpins the difference-in-differences design, in which we fix each firm's exposure at its pre-event
	133	+level precisely because that level is stable.
	134	+
	135	+\input{tables/tab_topfirms}

added UQ_WP_template/sections/discussion.tex +99 −0

		@@ -0,0 +1,99 @@
	1	+% ============================================================================
	2	+\section{Discussion: Mechanism and Interpretation}
	3	+\label{sec:discussion}
	4	+% ============================================================================
	5	+
	6	+What economic mechanism best fits this constellation of facts? We find an attention- and
	7	+narrative-driven repricing the most parsimonious explanation, and we read the evidence as follows.
	8	+
	9	+\paragraph{The information pre-existed; the attention did not.} Firms disclosed their AI engagement
	10	+for years before it was priced. The semantic content of those disclosures was, in cross-section, only
	11	+faintly related to returns through 2021. What changed in late 2022 was not the information but its
	12	+\emph{salience}: a consumer breakthrough (ChatGPT) made AI the dominant market narrative
	13	+\citep{shiller2017narrative}, drawing investor attention \citep{da2011,barberodean2008} to a body of
	14	+disclosure that had been hiding in plain sight. The abrupt, near-simultaneous repricing across the
	15	+cross-section---visible in the event study within months of the launch---is the signature of an
	16	+attention shock rather than the gradual accrual of a risk premium.
	17	+
	18	+\paragraph{It is a re-rating of levels, not of changes.} The disappearance of the effect under firm
	19	+fixed effects, the muted difference-in-differences estimates, and the event-time profile all point the
	20	+same way: the market repriced the persistent \emph{level} of a firm's AI exposure, not the
	21	+year-to-year change in its wording. This has a clear practical corollary---firms cannot mechanically
	22	+earn the premium by adding AI boilerplate to their filings (and our top-5\% and simple-mean
	23	+robustness suggests the measure is not easily gamed)---and a clear methodological one: studies that
	24	+difference out firm effects will understate the cross-sectional importance of disclosure content.
	25	+
	26	+\paragraph{It operates substantially, but not entirely, through sectors.} The sector-neutral and
	27	+sector-fixed-effects results show that much of the AI premium reflects the re-rating of AI-exposed
	28	+\emph{sectors}---technology, communication services, and the industrial firms supplying the AI
	29	+build-out---relative to the rest of the index. This is economically sensible: the generative-AI boom
	30	+was, to first order, a sectoral reallocation of expected cash flows and valuations. Yet a positive
	31	+within-sector residual remains in the event study, indicating that the firm's own disclosure carried
	32	+incremental information even among industry peers.
	33	+
	34	+\paragraph{The thematic asymmetry is telling.} Perhaps the most revealing single fact is the placebo:
	35	+in the very same post-2022 window, high-AI firms were rewarded while high-ESG and high-climate firms
	36	+were penalized. Markets did not simply reward verbose or virtuous-sounding disclosure; they rotated
	37	+toward one theme (AI) and away from another (sustainability). This is difficult to reconcile with a
	38	+purely mechanical or risk-based account and natural under a narrative-rotation view of investor
	39	+attention.
	40	+
	41	+\paragraph{Relation to the AI-asset-pricing literature.} Our findings complement
	42	+\citet{eisfeldt2023generative}, who show that an occupation-task measure of generative-AI exposure was
	43	+priced around ChatGPT. We reach a convergent conclusion from an entirely different measurement---firms'
	44	+own disclosure language---and extend it along the time dimension, showing that the same exposure was
	45	+\emph{un}priced for a decade beforehand. The agreement of two independent measures on the timing and
	46	+sign of the effect strengthens confidence that a real AI repricing occurred.
	47	+
	48	+\subsection{Implications}
	49	+Our findings carry distinct implications for three audiences. \emph{For investors and quantitative
	50	+strategists}, the results are a caution as much as an opportunity. The AI-disclosure signal delivered
	51	+a striking post-2022 Sharpe ratio, but the same signal was nearly inert for the preceding decade, and
	52	+the effect is absorbed by firm fixed effects---so a strategy that traded on year-to-year changes in AI
	53	+verbosity would have captured little. The tradeable content lies in the persistent cross-sectional
	54	+\emph{level} of AI exposure, and even that is partly a sector bet whose durability is unproven. The
	55	+honest reading is that disclosure-based AI signals are best viewed as a lens on a regime-dependent
	56	+theme rather than as a stable alpha source. \emph{For corporate managers and disclosure policy}, the
	57	+asymmetry between AI (rewarded) and ESG/climate (penalized) after 2022 illustrates how powerfully the
	58	+prevailing market narrative conditions the valuation consequences of what firms choose to emphasize.
	59	+Because the premium attaches to persistent, hard-to-fake exposure rather than to boilerplate, the
	60	+result does not invite cheap disclosure manipulation; but it does suggest that the market reads
	61	+filings for genuine strategic content and reprices it when attention turns. \emph{For researchers},
	62	+the study demonstrates that embedding-based semantic measurement uncovers pricing dynamics invisible
	63	+to both keyword counts (which cannot distinguish meaning) and firm-differenced panels (which discard
	64	+the persistent cross-sectional variation that turns out to matter).
	65	+
	66	+\subsection{Summary of the evidence across designs}
	67	+It is worth stepping back to see how the designs corroborate one another, since each has different
	68	+weaknesses. The portfolio sorts establish the raw magnitude and its post-2022 timing but are
	69	+model-free and could in principle reflect risk; the factor-model spanning regressions show the
	70	+unconditional spread is not explained by standard factors yet is statistically weak over the full
	71	+sample; the sub-period and interaction tests localize the effect to the post-ChatGPT regime; the
	72	+placebo rules out a mechanical or generic-disclosure explanation by showing the opposite sign for ESG
	73	+and climate; the event study, using daily abnormal returns purged of beta, provides cleanly-timed,
	74	+cross-sectional confirmation within months of the catalyst; and the fixed-effects and
	75	+difference-in-differences estimates pin down that the priced object is persistent firm- and
	76	+sector-level exposure, not incremental wording. No single design is decisive, but their
	77	+convergence---on the same sign, the same timing, and a consistent economic story---is what gives us
	78	+confidence in the conclusion.
	79	+
	80	+\subsection{Limitations}
	81	+\label{subsec:limits}
	82	+Several caveats temper our conclusions. \emph{First}, the post-2022 window contains only three
	83	+formation cohorts, and the size-controlled premium is concentrated in the most recent (2024) cohort,
	84	+which captures the 2024--2025 AI-infrastructure capital-expenditure boom. The regime result is
	85	+economically large and consistent across designs, but its post-period rests on a short sample and
	86	+could in principle reflect a single extraordinary episode rather than a durable new regime; only
	87	+future data can settle this. \emph{Second}, our universe is current S\&P~500 membership, which
	88	+introduces survivorship and look-ahead-at-the-index-level bias. This biases the level of returns
	89	+upward but is less likely to drive the \emph{cross-sectional} AI--return relation that is our focus.
	90	+\emph{Third}, the market-capitalization proxy holds shares outstanding at their latest value,
	91	+approximating historical size with error. \emph{Fourth}, the semantic anchors, though carefully
	92	+written, embed the authors' definitional choices; different anchor wording would yield somewhat
	93	+different scores, although the robustness to mean/tail aggregations and to PCA mitigates this concern.
	94	+\emph{Fifth}, disclosure intensity is correlated with sector, and while our within-year, size-,
	95	+momentum-, and volatility-controlled tests and the sector-FE event study address this, we cannot fully
	96	+separate ``AI exposure'' from ``technology sector'' as the priced characteristic. \emph{Finally}, our
	97	+designs establish a robust association and an event-study-based timing argument, but not strict
	98	+causality; the attention-repricing interpretation is the most consistent with the evidence rather than
	99	+the only logically possible one.

added UQ_WP_template/sections/introduction.tex +101 −0

		@@ -0,0 +1,101 @@
	1	+% ============================================================================
	2	+\section{Introduction}
	3	+\label{sec:introduction}
	4	+% ============================================================================
	5	+
	6	+The arrival of generative artificial intelligence has been the defining corporate-narrative shift
	7	+of the 2020s. Between the public launch of ChatGPT in late 2022 and 2025, the market
	8	+capitalization of AI-linked firms swelled by trillions of dollars, ``AI'' became the most
	9	+frequently invoked theme on earnings calls, and the language of corporate disclosure filled with
	10	+references to large language models, generative tools, intelligent automation, and the compute
	11	+infrastructure that powers them. This paper asks a deceptively simple question: did the
	12	+\emph{language} of AI in firms' mandatory disclosures carry information about their subsequent
	13	+stock returns---and if so, when and through what channel?
	14	+
	15	+Answering this question well requires three ingredients that have only recently become jointly
	16	+feasible: a large, machine-readable corpus of corporate disclosure; a measurement technology that
	17	+captures the \emph{meaning} of text rather than the mere frequency of keywords; and a clean mapping
	18	+from disclosure to tradeable returns. We bring all three to bear. Our laboratory is the universe of
	19	+S\&P~500 constituents over fiscal years 2010--2026. Our raw material is the full text of their
	20	+annual reports (Form~10-K), parsed section by section. Our measurement engine is the EDGAR Research
	21	+Database, which embeds every text chunk with the \texttt{all-MiniLM-L6-v2} sentence transformer and
	22	+scores it by cosine similarity to a set of carefully written ``anchor'' passages that define eight
	23	+economic concepts. Three of these anchors isolate distinct facets of AI engagement: \emph{internal
	24	+AI adoption} (using AI to run the business), \emph{AI infrastructure exposure} (capital tied to AI
	25	+compute), and \emph{AI product-disruption risk} (the danger that AI commoditizes the firm's
	26	+offerings). The result is a continuous, comparable, firm-year measure of how intensively---and in
	27	+what sense---each firm engages with AI in its own words.
	28	+
	29	+We pair these semantic scores with monthly adjusted prices for all 500 tickers from Yahoo Finance
	30	+and with the Fama--French five factors plus momentum. To avoid look-ahead bias we adopt the
	31	+standard portfolio-formation convention: because a 10-K covering fiscal year $Y$ is public by early
	32	+in year $Y{+}1$, we form signals at the end of June of $Y{+}1$ and measure the forward twelve-month
	33	+return from July of $Y{+}1$ to June of $Y{+}2$. The signal is therefore always known before the
	34	+holding period begins. This yields 6{,}852 firm-years with a strictly tradeable forward return,
	35	+spanning formation years 2010 through 2024.
	36	+
	37	+Our headline finding is that the pricing of AI language is \emph{not} a stable factor premium but a
	38	+regime-dependent re-rating that switched on with the generative-AI boom. For most of the 2010s,
	39	+sorting S\&P~500 firms on the intensity of their AI disclosure produced only a faint return
	40	+pattern: the equal-weighted spread between the highest and lowest quintiles averaged about $+2.4$
	41	+percentage points per year, and a risk-adjusted long--short portfolio earned an economically small
	42	+and statistically insignificant alpha. After the launch of ChatGPT in November 2022, the same sort
	43	+produced a spread of $+14.6$ percentage points per year. The cross-sectional re-rating is visible
	44	+in every post-2022 formation cohort, in a cumulative long--short wealth curve that inflects sharply
	45	+upward at the end of 2022, and in a year-by-year Fama--MacBeth slope that jumps from near zero to
	46	+large and positive.
	47	+
	48	+A natural worry is that this pattern simply reflects the well-known rally of a handful of
	49	+technology mega-caps. We address this concern head-on and reject it. The post-2022 spread is
	50	+$+14.1$ percentage points \tstat{1.9} when the ``Magnificent~7'' are excluded and $+14.5$ points
	51	+when the ten largest firms by market capitalization are dropped---the effect is broad-based across
	52	+the index, not an artifact of Nvidia, Microsoft, or their peers. It is robust to using the simple
	53	+mean, the section-weighted mean, or the top-5\% tail of similarity scores; to six-, twelve-, and
	54	+twenty-four-month horizons; and to replacing the three AI signals with their first principal
	55	+component, which alone explains 87\% of their common variation.
	56	+
	57	+We then deploy three complementary tests to pin down what the result is---and is not. First, a
	58	+\emph{placebo} exercise re-runs the entire design on the five non-AI semantic factors in the
	59	+database (ESG, climate, cybersecurity, automation/labor, and macro risk). If the post-2022 jump
	60	+merely reflected a generic ``more disclosure earns more'' phenomenon, or a mechanical artifact of
	61	+our pipeline, every factor should display it. They do not. The post-2022 spread is large and
	62	+positive for the AI factors, essentially zero for macro-risk language, and \emph{negative} for ESG
	63	+and climate disclosure---high-ESG firms \emph{underperformed} after 2022. The post-ChatGPT
	64	+re-rating is specific to AI-related content. Second, we run a market-model \emph{event study} around
	65	+the 30~November 2022 ChatGPT launch. Firms in the top tercile of pre-event AI disclosure (measured
	66	+from their FY2021 10-K, the last report filed before the event) earned cumulative abnormal returns
	67	+$+10.1$ percentage points higher than the bottom tercile over the following year \tstat{1.97} and
	68	+$+14.6$ points higher over eighteen months. Because abnormal returns are purged of market-beta
	69	+exposure, this is a clean cross-sectional response to an unanticipated narrative shock. Third, we
	70	+use two-way fixed effects and difference-in-differences to localize the mechanism. The premium is
	71	+absorbed by firm fixed effects and roughly halved by sector fixed effects, telling us that the
	72	+durable signal is the persistent \emph{level} of a firm's (and its sector's) AI exposure relative
	73	+to peers, not the year-to-year wiggle in its wording.
	74	+
	75	+Taken together, the evidence supports an attention- and narrative-driven repricing interpretation.
	76	+The textual evidence of firms' AI engagement accumulated quietly for a decade and was barely priced.
	77	+A salient catalyst---the consumer breakthrough of generative AI---then drew investor attention to
	78	+that pre-existing information, and capital flowed toward the firms and sectors whose disclosures
	79	+revealed the greatest AI exposure. This is the asset-pricing signature of limited attention and
	80	+narrative economics, observed not through a sentiment proxy but directly in the semantic content of
	81	+mandatory disclosure.
	82	+
	83	+\paragraph{Contribution.} We make four contributions. \emph{First}, methodologically, we
	84	+demonstrate the value of embedding-based semantic measurement of disclosure for asset pricing: a
	85	+cosine-similarity-to-anchor design captures economically meaningful, multi-faceted exposure
	86	+(adoption vs.\ infrastructure vs.\ risk) that keyword counts cannot, and it does so at scale across
	87	+the entire S\&P~500 and a decade and a half of filings. \emph{Second}, substantively, we provide
	88	+text-based, look-ahead-free evidence that the cross-sectional pricing of AI exposure is a post-2022
	89	+regime phenomenon rather than a long-standing premium. \emph{Third}, we discipline the finding with
	90	+a placebo across non-AI factors and an event study, distinguishing a genuine AI-specific repricing
	91	+from a mechanical or market-wide artifact. \emph{Fourth}, we document the \emph{anatomy} of the
	92	+effect---its concentration in smaller firms, its operation substantially through a sector channel,
	93	+and its disappearance under firm fixed effects---which sharpens the economic interpretation and
	94	+warns against naive trading strategies.
	95	+
	96	+The remainder of the paper is organized as follows. Section~\ref{sec:literature} situates the study
	97	+in five literatures and states our hypotheses. Section~\ref{sec:data} describes the data and the
	98	+construction of the semantic measures. Section~\ref{sec:methodology} lays out the empirical
	99	+methodology. Section~\ref{sec:results} presents the main results, and Section~\ref{sec:robustness}
	100	+the robustness and identification tests. Section~\ref{sec:discussion} discusses mechanisms and
	101	+limitations, and Section~\ref{sec:conclusion} concludes.

added UQ_WP_template/sections/literature.tex +98 −0

		@@ -0,0 +1,98 @@
	1	+% ============================================================================
	2	+\section{Related Literature and Hypotheses}
	3	+\label{sec:literature}
	4	+% ============================================================================
	5	+
	6	+Our study sits at the intersection of five strands of research: textual analysis in finance, the
	7	+pricing of corporate disclosure, technology and innovation in asset pricing, investor attention and
	8	+narrative economics, and the nascent literature on the economics of artificial intelligence.
	9	+
	10	+\subsection{Textual analysis and natural language processing in finance}
	11	+A now-large literature extracts economic signals from financial text. The foundational work of
	12	+\citet{tetlock2007} showed that the tone of a \textit{Wall Street Journal} column forecasts
	13	+aggregate returns, and \citet{tetlock2008} extended this to firm-level news. \citet{lm2011}
	14	+demonstrated that finance-specific sentiment dictionaries materially outperform general-purpose word
	15	+lists in 10-K analysis, launching a wave of dictionary-based studies and the widely used
	16	+Loughran--McDonald word lists; \citet{lm2016} survey this field. A second generation moved from
	17	+counting words to modeling them: \citet{gentzkow2019} review text-as-data methods in economics,
	18	+while \citet{kelly2019textregression} and \citet{bybee2024narrative} use machine-learning
	19	+representations of news to construct interpretable factors and a ``state of the economy'' from text.
	20	+Our paper belongs to the most recent, embedding-based generation. Rather than counting AI
	21	+keywords---which conflate ``we use no AI'' with ``we are an AI leader'' and miss paraphrase---we
	22	+measure the \emph{semantic similarity} of disclosure to anchor concepts using a sentence transformer
	23	+\citep{reimers2019sbert}. This follows a growing practice of using contextual embeddings to quantify
	24	+disclosure content \citep{cong2022textfactor}, and is closest in spirit to similarity-to-concept
	25	+designs that score documents against reference passages.
	26	+
	27	+\subsection{The pricing of corporate disclosure}
	28	+A parallel literature asks whether the \emph{content} and \emph{changes} of mandatory disclosure
	29	+predict returns. \citet{cohen2020lazy} show that firms that change the language of their 10-K
	30	+relative to the prior year (``lazy prices'' when they do not) experience predictable future returns
	31	+and operating outcomes. \citet{hoberg2010product} and \citet{hobergphillips2016} use 10-K product
	32	+descriptions to build text-based industry classifications and measures of product-market fluidity
	33	+that carry asset-pricing content. \citet{lopezlira2023risk} extracts risk exposures from 10-K
	34	+risk-factor sections. The general lesson is that the qualitative portions of filings contain
	35	+value-relevant information that markets process incompletely and with delay. We contribute a
	36	+focused, concept-level measure---AI engagement---and show that its pricing is strongly
	37	+state-dependent, a dimension the disclosure-pricing literature has largely left implicit.
	38	+
	39	+\subsection{Technology, innovation, and the cross-section of returns}
	40	+Asset pricing has long sought to connect technological change to risk and return.
	41	+\citet{hirshleifer2013innovative} show that innovative efficiency predicts returns;
	42	+\citet{kogan2017technological} build market-based measures of innovation from patents and link them
	43	+to growth and reallocation; \citet{koganpapanikolaou2014} show that investment-specific technology
	44	+shocks shape the cross-section. A more recent literature studies AI exposure directly:
	45	+\citet{babina2024aiinvestment} measure firm-level AI investment from job-posting and resume data and
	46	+document faster growth among AI-adopting firms; \citet{eisfeldt2023generative} construct a
	47	+firm-level measure of \emph{generative}-AI exposure from the task content of occupations and show
	48	+that a generative-AI factor was priced precisely in the weeks around ChatGPT's release.
	49	+\citet{acemoglu2020wrong} and \citet{webb2020} study the labor-market exposure of firms to AI and
	50	+automation. Our contribution relative to this work is to measure AI exposure from the firm's
	51	+\emph{own disclosure}---a self-reported, narrative signal available for the entire index at annual
	52	+frequency---and to characterize the full time profile of its pricing across a decade and a half, not
	53	+only the event window. Where \citet{eisfeldt2023generative} use occupation-task exposure, we use the
	54	+language firms choose, providing a complementary and highly granular measure.
	55	+
	56	+\subsection{Investor attention, salience, and narrative economics}
	57	+Why might value-relevant disclosure be priced only after a catalyst? The behavioral literature
	58	+offers a clear mechanism: limited investor attention. \citet{barberodean2008} show that retail
	59	+investors are drawn to attention-grabbing stocks; \citet{da2011} construct a direct attention proxy
	60	+from Google search and link it to prices; \citet{dellavigna2009} document under-reaction to
	61	+information released when attention is low; and \citet{hirshleifer2009driven} show that earnings news
	62	+is underweighted when investors are distracted. \citet{shiller2017narrative} argues that contagious
	63	+narratives drive major asset-price movements, and \citet{bakerwurgler2006} show that sentiment
	64	+differentially affects hard-to-value, speculative stocks. Our results provide a sharp illustration:
	65	+the information about firms' AI engagement existed in filings for years but was repriced abruptly
	66	+when a salient consumer event---ChatGPT---focused investor attention on AI. The asymmetry we document
	67	+(AI rewarded, ESG penalized after 2022) is itself consistent with a shift in the prevailing market
	68	+narrative.
	69	+
	70	+\subsection{ESG and climate disclosure as a comparison case}
	71	+Finally, our placebo design connects to the literature on the pricing of ESG and climate disclosure.
	72	+\citet{pastor2021sustainable} model how sustainability preferences depress the expected returns of
	73	+green assets in equilibrium, and \citet{pastor2022dissecting} show that green stocks' strong
	74	+\emph{realized} returns through 2021 reflected unexpected increases in climate concern rather than
	75	+high expected returns. \citet{bolton2021risk} document a carbon premium. Consistent with the
	76	+post-2021 reversal in this literature, we find that high-ESG and high-climate disclosure earned
	77	+\emph{negative} spreads after 2022, exactly when AI disclosure began to earn large positive
	78	+ones---underscoring that the post-2022 re-rating reflects a thematic rotation toward AI rather than a
	79	+generic disclosure effect.
	80	+
	81	+\subsection{Hypotheses}
	82	+\label{subsec:hypotheses}
	83	+Our analysis is organized around four hypotheses.
	84	+\begin{description}[leftmargin=2.4em,style=nextline]
	85	+\item[H1 (Unconditional pricing).] If AI exposure carries a stable risk premium or persistent
	86	+mispricing, then sorting on AI-disclosure intensity yields a positive and significant risk-adjusted
	87	+return spread over the full 2010--2026 sample.
	88	+\item[H2 (Regime dependence).] If instead AI exposure is repriced only once AI becomes salient, the
	89	+return spread is small before and large after the late-2022 generative-AI catalyst, with a
	90	+detectable structural break.
	91	+\item[H3 (AI-specificity).] If the post-2022 spread reflects a genuine AI repricing rather than a
	92	+mechanical or market-wide artifact, it appears for AI-related semantic factors but not for unrelated
	93	+factors (e.g.\ ESG, climate, macro risk).
	94	+\item[H4 (Cross-sectional, not within-firm).] If the market repriced \emph{which} firms are
	95	+AI-exposed rather than rewarding incremental wording, the effect is concentrated in the
	96	+cross-section and attenuates under firm and sector fixed effects.
	97	+\end{description}
	98	+\noindent The data, as we show, decisively favor H2--H4 over H1.

added UQ_WP_template/sections/methodology.tex +64 −0

		@@ -0,0 +1,64 @@
	1	+% ============================================================================
	2	+\section{Methodology}
	3	+\label{sec:methodology}
	4	+% ============================================================================
	5	+
	6	+We bring six complementary research designs to bear, ranging from simple portfolio sorts to a
	7	+market-model event study. Using multiple designs with different identifying assumptions guards
	8	+against any single method's weaknesses and lets us triangulate the economic interpretation.
	9	+
	10	+\subsection{Portfolio sorts}
	11	+Each formation year we sort firms into quintiles on a given (within-year standardized) AI signal and
	12	+compute the equal-weighted (EW) and value-weighted (VW) forward return of each quintile, plus the
	13	+high-minus-low (Q5$-$Q1) spread. We report the time-series average of the annual spreads and test its
	14	+significance with Newey--West \citep{neweywest1987} standard errors (three lags) to account for any
	15	+serial correlation in the overlapping return windows. Sorts are model-free and transparent, and the
	16	+EW--VW comparison reveals whether an effect is concentrated in larger or smaller firms.
	17	+
	18	+\subsection{Factor-model spanning of a long--short portfolio}
	19	+To ask whether the AI spread survives risk adjustment, we build an annually rebalanced, equal-weighted,
	20	+self-financing long--short portfolio (top minus bottom quintile), record its monthly return, and
	21	+regress it on (i)~the CAPM market factor and (ii)~the Fama--French five factors plus momentum (FF6).
	22	+The intercept (alpha) measures the average return unexplained by known risk factors; we use
	23	+heteroskedasticity- and autocorrelation-consistent (HAC) standard errors. A significant alpha would
	24	+indicate pricing beyond standard exposures.
	25	+
	26	+\subsection{Two-way fixed-effects panel regressions}
	27	+We estimate
	28	+\begin{equation}
	29	+ r_{i,t\to t+12} = \beta\, \text{AI}_{i,t} + \gamma' X_{i,t} + \alpha_i + \delta_t + \varepsilon_{i,t},
	30	+ \label{eq:panel}
	31	+\end{equation}
	32	+where $r$ is the winsorized forward return, $\text{AI}_{i,t}$ the standardized signal, $X$ the
	33	+controls, and $\alpha_i,\delta_t$ firm and year fixed effects. Standard errors are double-clustered by
	34	+firm and year \citep{petersen2009,cameron2011}. Firm fixed effects absorb all time-invariant
	35	+cross-firm differences, so $\beta$ identifies whether \emph{within-firm} changes in AI language
	36	+predict returns; year fixed effects absorb common shocks. Contrasting this estimate with the
	37	+cross-sectional ones isolates whether the signal lives across or within firms (H4).
	38	+
	39	+\subsection{Fama--MacBeth regressions}
	40	+We also run annual cross-sectional regressions of the forward return on the AI signal and controls and
	41	+average the slopes following \citet{famamacbeth1973}, with Newey--West errors on the time series of
	42	+coefficients. This estimator weights each year equally and yields an interpretable
	43	+per-standard-deviation premium; plotting the annual slopes reveals the time profile of the premium
	44	+directly.
	45	+
	46	+\subsection{Structural-break and difference-in-differences designs}
	47	+To test regime dependence (H2) we split the sample at the 30~November 2022 ChatGPT launch and compare
	48	+sub-period spreads, and we estimate pooled interaction models of the form
	49	+$r = \beta_1 \text{AI} + \beta_2 (\text{AI}\times \text{Post}) + \gamma' X + \varepsilon$, where
	50	+$\text{Post}=\mathbb{1}[\text{formation year}\ge 2022]$ and $\beta_2$ captures the change in the
	51	+premium. We complement this with a difference-in-differences design in which treatment is the firm's
	52	+\emph{pre-determined} AI exposure---fixed at its 2019--2021 average so it cannot respond to the
	53	+event---interacted with Post, within firm and year fixed effects. An event-time version interacts
	54	+pre-determined exposure with each year dummy (relative to 2021) to trace the dynamic response.
	55	+
	56	+\subsection{Market-model event study}
	57	+Finally, we run a classic event study \citep{mackinlay1997} around the ChatGPT launch. For each stock
	58	+we estimate a market model ($r_{i,d}=a_i+b_i r^{m}_{d}+e_{i,d}$) over the estimation window
	59	+January--October 2022 and compute daily abnormal returns $\text{AR}_{i,d}=r_{i,d}-(\hat a_i+\hat b_i
	60	+r^m_d)$ over the event window November 2022--June 2024. Cumulative abnormal returns (CAR) are compared
	61	+across terciles of \emph{pre-event} AI disclosure (from the FY2021 10-K), and we regress firm-level
	62	+CAR on pre-event exposure with size, beta, and sector controls. Because abnormal returns net out
	63	+market-beta exposure, the event study isolates the cross-sectional response to the AI-narrative shock
	64	+from the contemporaneous (and initially negative) market drift of 2022--2023.

added UQ_WP_template/sections/results.tex +144 −0

		@@ -0,0 +1,144 @@
	1	+% ============================================================================
	2	+\section{Results}
	3	+\label{sec:results}
	4	+% ============================================================================
	5	+
	6	+\subsection{Portfolio sorts: a weak unconditional relation}
	7	+Table~\ref{tab:sorts} reports the quintile sorts over the full sample. The relation between AI
	8	+disclosure and future returns is positive and broadly monotone but economically modest. The
	9	+equal-weighted Q5$-$Q1 spread is $+4.6$ percentage points per year for AI adoption \tstat{1.83},
	10	+$+3.9$ for AI infrastructure \tstat{1.58}, $+5.3$ for AI disruption risk \tstat{2.27}, and $+4.9$ for
	11	+the composite \tstat{1.88}. Value-weighting attenuates the adoption and composite spreads, indicating
	12	+the effect is stronger among smaller index members. The left panel of Figure~\ref{fig:quint} displays
	13	+the full-sample pattern: returns rise gently from the lowest to the highest AI quintile. On its own,
	14	+this is suggestive but far from decisive evidence---and, as we now show, it averages over two very
	15	+different regimes.
	16	+
	17	+\input{tables/tab_sorts}
	18	+
	19	+\subsection{Does AI disclosure earn risk-adjusted alpha unconditionally? (H1)}
	20	+Table~\ref{tab:alpha} reports CAPM and FF6 alphas of the long--short portfolios. The AI-opportunity
	21	+composite earns a raw spread of about $+2.3\%$ per year, of which the FF6 alpha is $+1.9\%$---but
	22	+statistically insignificant \tstat{1.24}. The AI-adoption and AI-infrastructure long--shorts are
	23	+similarly insignificant after risk adjustment. The one exception is the AI-disruption-risk spread,
	24	+whose FF6 alpha of $+2.8\%$ per year is marginally significant \tstat{2.10}, hinting at a small risk
	25	+premium for firms that flag AI as a competitive threat. The factor loadings (not the focus here) show
	26	+the AI long--short is roughly market-neutral with modest negative profitability (RMW) and investment
	27	+(CMA) tilts, consistent with a growth-oriented long leg. The verdict on H1 is clear:
	28	+\textbf{unconditionally, AI disclosure is at best weakly priced.} This is not the end of the story but
	29	+the beginning of it.
	30	+
	31	+\input{tables/tab_alpha}
	32	+
	33	+\subsection{Panel and Fama--MacBeth estimates}
	34	+Table~\ref{tab:panel} juxtaposes the two-way fixed-effects panel with the Fama--MacBeth estimator. The
	35	+contrast is instructive. In the Fama--MacBeth (cross-sectional) regressions, the AI-adoption and
	36	+AI-infrastructure premia are positive---$+1.3$ and $+1.6$ percentage points per standard
	37	+deviation---with \textit{t}-statistics near 1.6--1.7, indicating a weak but positive cross-sectional
	38	+premium on average. In the two-way fixed-effects panel, however, every AI coefficient collapses to
	39	+essentially zero. Because firm fixed effects remove all permanent cross-firm differences, this tells
	40	+us the signal lives \emph{across} firms, not \emph{within} them: a given firm writing relatively more
	41	+about AI from one year to the next does not predict its own subsequent return (anticipating H4).
	42	+Throughout, size carries the familiar negative premium ($t\approx-8$) and volatility a positive one,
	43	+consistent with the broader cross-sectional literature in this large-cap universe.
	44	+
	45	+\input{tables/tab_panel}
	46	+
	47	+\subsection{The structural break: AI pricing switched on after ChatGPT (H2)}
	48	+The full-sample averages mask a sharp regime change that is the paper's central result. Splitting the
	49	+sample at the November 2022 ChatGPT launch, the center and right panels of Figure~\ref{fig:quint}
	50	+reveal a striking transformation: the quintile pattern is nearly flat before 2022 and steeply
	51	+increasing afterward. The high-minus-low composite spread is $+2.4$ percentage points per year
	52	+pre-ChatGPT but $+14.6$ points per year post-ChatGPT---a more than sixfold increase.
	53	+
	54	+\begin{figure}[htbp]\centering
	55	+\includegraphics[width=\textwidth]{fig1_quintile_returns.png}
	56	+\caption{Mean forward twelve-month return by AI-disclosure composite quintile, full sample and by
	57	+sub-period. The high-minus-low spread is $+2.4$ percentage points before ChatGPT and $+14.6$ points
	58	+after.}\label{fig:quint}
	59	+\end{figure}
	60	+
	61	+Table~\ref{tab:break} quantifies the break two ways. In sub-period sorts, the AI-adoption Q5$-$Q1
	62	+spread rises from $+2.2\%$ per year \tstat{2.04} pre-2022 to $+14.3\%$ \tstat{2.15} post-2022; the
	63	+composite rises from $+2.5\%$ to $+14.6\%$; AI infrastructure from $+1.4\%$ to $+13.6\%$. In the
	64	+pooled interaction regressions, the post-2022 incremental slope is positive for all three signals and
	65	+statistically significant for AI infrastructure \tstat{2.63}---the facet most directly tied to the
	66	+chip, cloud, data-center, and power firms that led the 2023--2025 rally. Figure~\ref{fig:spread} shows
	67	+the annual spreads: small and mixed-sign through 2021, uniformly large and positive for every
	68	+post-2022 cohort.
	69	+
	70	+\input{tables/tab_break}
	71	+
	72	+\begin{figure}[htbp]\centering
	73	+\includegraphics[width=0.9\textwidth]{fig3_annual_spread.png}
	74	+\caption{Annual high-minus-low (Q5$-$Q1) forward-return spread on the AI-disclosure composite, by
	75	+10-K fiscal year. Post-ChatGPT cohorts (red) are uniformly and substantially positive.}
	76	+\label{fig:spread}
	77	+\end{figure}
	78	+
	79	+The same regime change is visible in two further lenses. Figure~\ref{fig:cum} plots the cumulative
	80	+value of one dollar invested in the equal-weighted, annually rebalanced, self-financing
	81	+high-minus-low portfolio: it drifts sideways-to-up for a decade and then inflects upward after the
	82	+dashed ChatGPT line. Figure~\ref{fig:fmyear} plots the year-by-year Fama--MacBeth slope on the AI
	83	+composite (with controls): it hovers near zero for the entire 2010s and then turns sharply positive,
	84	+peaking in the 2024 cohort. The latter figure also delivers an important nuance: the size-controlled
	85	+premium is largest in the most recent cohort, consistent with the AI \emph{infrastructure}
	86	+super-cycle of 2024--2025 (the build-out of data centers and accelerated compute). We return to this
	87	+concentration when discussing limitations.
	88	+
	89	+\begin{figure}[htbp]\centering
	90	+\includegraphics[width=0.86\textwidth]{fig2_cumulative_ls.png}
	91	+\caption{Cumulative value of \$1 invested in the equal-weighted, annually rebalanced, self-financing
	92	+high-minus-low AI-disclosure portfolio (AI opportunity composite and AI disruption-risk).}
	93	+\label{fig:cum}
	94	+\end{figure}
	95	+
	96	+\begin{figure}[htbp]\centering
	97	+\includegraphics[width=0.9\textwidth]{fig6_fm_byyear.png}
	98	+\caption{Year-by-year Fama--MacBeth slope on the AI-disclosure composite (forward return per
	99	+cross-sectional standard deviation), controlling for size, momentum, and volatility. Bars are $\pm1$
	100	+standard error.}\label{fig:fmyear}
	101	+\end{figure}
	102	+
	103	+Finally, Figure~\ref{fig:bin} confirms the pattern is not an artifact of a few influential
	104	+observations: the binned relation between the AI composite and forward returns is essentially flat in
	105	+the pre-ChatGPT sub-period and distinctly upward-sloping afterward, across the entire distribution of
	106	+AI disclosure rather than only at the extreme quintiles.
	107	+
	108	+\begin{figure}[htbp]\centering
	109	+\includegraphics[width=\textwidth]{fig5_binscatter.png}
	110	+\caption{Binned scatter of forward twelve-month return against the AI-disclosure composite, by
	111	+sub-period. Each point is a portfolio of firms in a bin of the AI signal; the line is an OLS fit. The
	112	+conditional slope steepens markedly after ChatGPT.}\label{fig:bin}
	113	+\end{figure}
	114	+
	115	+\subsection{The anatomy of the premium: size and sector}
	116	+Where in the cross-section does the post-2022 premium concentrate? Table~\ref{tab:doublesort} and
	117	+Figure~\ref{fig:double} report an AI~$\times$~size double sort. Before 2022 the AI gradient is flat
	118	+within both size halves. After 2022 it is steep, and dramatically so among smaller firms: small,
	119	+high-AI firms earned a mean forward return of 34.6\%, versus 19.5\% for small, low-AI firms---a
	120	+15-point gap---while the corresponding gap among large firms is 7 points. The premium is thus
	121	+\emph{not} merely a mega-cap phenomenon (a point we reinforce in Section~\ref{sec:robustness}); if
	122	+anything it is strongest among the smaller, less-followed names, consistent with an attention-based
	123	+mechanism in which information diffuses more slowly into smaller stocks.
	124	+
	125	+\input{tables/tab_doublesort}
	126	+
	127	+\begin{figure}[htbp]\centering
	128	+\includegraphics[width=\textwidth]{fig9_double_sort.png}
	129	+\caption{AI-disclosure $\times$ firm-size double sort: mean forward twelve-month return by AI tercile
	130	+within small and large firms, pre- and post-ChatGPT.}\label{fig:double}
	131	+\end{figure}
	132	+
	133	+\subsection{Economic significance}
	134	+The statistical break is matched by an economic one. The Sharpe ratio of the equal-weighted
	135	+AI-composite long--short portfolio---a direct gauge of risk-adjusted attractiveness---rises from 0.15
	136	+in the pre-ChatGPT decade to 1.33 afterward; for the AI-disruption-risk spread it rises from 0.33 to
	137	+1.15. A Sharpe ratio above one is exceptional for a single-characteristic, self-financing equity
	138	+strategy, and its emergence precisely at the ChatGPT boundary is hard to reconcile with a constant
	139	+risk premium. The point estimates in the quintile sorts are equally vivid: a 14-point annual spread
	140	+between the top and bottom AI quintiles is roughly three times the unconditional equity risk premium
	141	+and an order of magnitude larger than the pre-2022 spread. Even acknowledging that a portion of this
	142	+reflects the higher realized volatility of AI-exposed firms (documented in Section~\ref{sec:robustness})
	143	+and the broad technology rally, the magnitude of the post-2022 re-rating is among the largest
	144	+single-theme cross-sectional effects in the recent asset-pricing record.

added UQ_WP_template/sections/robustness.tex +114 −0

Large diff (114 lines) is not loaded by default to keep the page fast.Load diff

added UQ_WP_template/sections/titlepage.tex +77 −0

Large diff (77 lines) is not loaded by default to keep the page fast.Load diff

added UQ_WP_template/tables/regression.tex +37 −0

Large diff (37 lines) is not loaded by default to keep the page fast.Load diff

added UQ_WP_template/tables/summary_stats.tex +29 −0

Large diff (29 lines) is not loaded by default to keep the page fast.Load diff

added UQ_WP_template/tables/tab_alpha.tex +11 −0

Large diff (12 lines) is not loaded by default to keep the page fast.Load diff

added UQ_WP_template/tables/tab_break.tex +11 −0

Large diff (12 lines) is not loaded by default to keep the page fast.Load diff

added UQ_WP_template/tables/tab_corr.tex +12 −0

Large diff (13 lines) is not loaded by default to keep the page fast.Load diff

added UQ_WP_template/tables/tab_did.tex +10 −0

Large diff (11 lines) is not loaded by default to keep the page fast.Load diff

added UQ_WP_template/tables/tab_doublesort.tex +13 −0

Large diff (14 lines) is not loaded by default to keep the page fast.Load diff

added UQ_WP_template/tables/tab_event.tex +14 −0

Large diff (15 lines) is not loaded by default to keep the page fast.Load diff

added UQ_WP_template/tables/tab_panel.tex +16 −0

Large diff (17 lines) is not loaded by default to keep the page fast.Load diff

added UQ_WP_template/tables/tab_placebo.tex +15 −0

Large diff (16 lines) is not loaded by default to keep the page fast.Load diff

added UQ_WP_template/tables/tab_robust.tex +18 −0

Large diff (19 lines) is not loaded by default to keep the page fast.Load diff

added UQ_WP_template/tables/tab_sorts.tex +15 −0

Large diff (16 lines) is not loaded by default to keep the page fast.Load diff

added UQ_WP_template/tables/tab_summary.tex +14 −0

Large diff (15 lines) is not loaded by default to keep the page fast.Load diff

added UQ_WP_template/tables/tab_topfirms.tex +16 −0

Large diff (17 lines) is not loaded by default to keep the page fast.Load diff

added analysis/01_download_prices.py +85 −0

Large diff (85 lines) is not loaded by default to keep the page fast.Load diff

added analysis/02_build_panel.py +88 −0

Large diff (88 lines) is not loaded by default to keep the page fast.Load diff

added analysis/03_analysis.py +277 −0

Large diff (277 lines) is not loaded by default to keep the page fast.Load diff

added analysis/04_figures.py +106 −0

Large diff (106 lines) is not loaded by default to keep the page fast.Load diff

added analysis/05_make_tables.py +102 −0

Large diff (102 lines) is not loaded by default to keep the page fast.Load diff

added analysis/06_extended.py +274 −0

Large diff (274 lines) is not loaded by default to keep the page fast.Load diff

added analysis/07_event_study.py +132 −0

Large diff (132 lines) is not loaded by default to keep the page fast.Load diff

added analysis/08_figures_ext.py +121 −0

Large diff (121 lines) is not loaded by default to keep the page fast.Load diff

added analysis/09_make_tables_ext.py +110 −0

Large diff (110 lines) is not loaded by default to keep the page fast.Load diff

added analysis/README.md +43 −0

Large diff (43 lines) is not loaded by default to keep the page fast.Load diff

added analysis/report/ai_disclosure_returns.tex +269 −0

Large diff (269 lines) is not loaded by default to keep the page fast.Load diff

added analysis/report/ai_disclosure_returns_full.tex +909 −0

Large diff (909 lines) is not loaded by default to keep the page fast.Load diff

added analysis/report/tab_alpha.tex +11 −0

Large diff (12 lines) is not loaded by default to keep the page fast.Load diff

added analysis/report/tab_break.tex +11 −0

Large diff (12 lines) is not loaded by default to keep the page fast.Load diff

added analysis/report/tab_corr.tex +12 −0

Large diff (13 lines) is not loaded by default to keep the page fast.Load diff

added analysis/report/tab_did.tex +10 −0

Large diff (11 lines) is not loaded by default to keep the page fast.Load diff

added analysis/report/tab_doublesort.tex +13 −0

Large diff (14 lines) is not loaded by default to keep the page fast.Load diff

added analysis/report/tab_event.tex +14 −0

Large diff (15 lines) is not loaded by default to keep the page fast.Load diff

added analysis/report/tab_panel.tex +16 −0

Large diff (17 lines) is not loaded by default to keep the page fast.Load diff

added analysis/report/tab_placebo.tex +15 −0

Large diff (16 lines) is not loaded by default to keep the page fast.Load diff

added analysis/report/tab_robust.tex +18 −0

Large diff (19 lines) is not loaded by default to keep the page fast.Load diff

added analysis/report/tab_sorts.tex +15 −0

Large diff (16 lines) is not loaded by default to keep the page fast.Load diff

added analysis/report/tab_summary.tex +14 −0

Large diff (15 lines) is not loaded by default to keep the page fast.Load diff

added analysis/report/tab_topfirms.tex +16 −0

Large diff (17 lines) is not loaded by default to keep the page fast.Load diff

added analysis/tables/results.json +465 −0

Large diff (466 lines) is not loaded by default to keep the page fast.Load diff

added analysis/tables/results2.json +445 −0

Large diff (446 lines) is not loaded by default to keep the page fast.Load diff

added analysis/tables/results_event.json +45 −0

Large diff (46 lines) is not loaded by default to keep the page fast.Load diff

added analysis/tables/results_extra.json +23 −0

Large diff (24 lines) is not loaded by default to keep the page fast.Load diff

added analysis/tables/t1_summary_stats.csv +9 −0

Large diff (9 lines) is not loaded by default to keep the page fast.Load diff

added analysis/tables/t1b_correlations.csv +7 −0

Large diff (7 lines) is not loaded by default to keep the page fast.Load diff

added analysis/tables/t2_portfolio_sorts.csv +13 −0

Large diff (13 lines) is not loaded by default to keep the page fast.Load diff

added analysis/tables/t6_did_eventtime.csv +11 −0

Large diff (11 lines) is not loaded by default to keep the page fast.Load diff

added analysis/tables/t6_double_sort_post.csv +3 −0

Large diff (3 lines) is not loaded by default to keep the page fast.Load diff

added analysis/tables/t6_double_sort_pre.csv +3 −0

Large diff (3 lines) is not loaded by default to keep the page fast.Load diff

added analysis/tables/t6_fm_byyear.csv +16 −0

Large diff (16 lines) is not loaded by default to keep the page fast.Load diff

added analysis/tables/t6_sector_aieffect_post.csv +12 −0

Large diff (12 lines) is not loaded by default to keep the page fast.Load diff

added config/database.yaml +22 −0

Large diff (22 lines) is not loaded by default to keep the page fast.Load diff

added config/embeddings.yaml +40 −0

Large diff (40 lines) is not loaded by default to keep the page fast.Load diff

added config/factors.yaml +51 −0

Large diff (51 lines) is not loaded by default to keep the page fast.Load diff

added config/parsing.yaml +93 −0

Large diff (93 lines) is not loaded by default to keep the page fast.Load diff

added config/sec.yaml +31 −0

Large diff (31 lines) is not loaded by default to keep the page fast.Load diff

added docs/RUSSELL3000-EXTENSION.md +59 −0

Large diff (59 lines) is not loaded by default to keep the page fast.Load diff

added notebooks/.ipynb_checkpoints/01_database_overview-checkpoint.ipynb +833 −0

Large diff (833 lines) is not loaded by default to keep the page fast.Load diff

added notebooks/.ipynb_checkpoints/03_ai_deep_dive-checkpoint.ipynb +933 −0

Large diff (933 lines) is not loaded by default to keep the page fast.Load diff

added notebooks/.ipynb_checkpoints/05_panel_econometrics-checkpoint.ipynb +1376 −0

Large diff (1,376 lines) is not loaded by default to keep the page fast.Load diff

added notebooks/01_database_overview.ipynb +832 −0

Large diff (832 lines) is not loaded by default to keep the page fast.Load diff

added notebooks/02_factor_scores_analysis.ipynb +794 −0

Large diff (794 lines) is not loaded by default to keep the page fast.Load diff

added notebooks/03_ai_deep_dive.ipynb +933 −0

Large diff (933 lines) is not loaded by default to keep the page fast.Load diff

added notebooks/04_esg_risk_analysis.ipynb +1099 −0

Large diff (1,099 lines) is not loaded by default to keep the page fast.Load diff

added notebooks/05_panel_econometrics.ipynb +1376 −0

Large diff (1,376 lines) is not loaded by default to keep the page fast.Load diff

added project-db/.claude/settings.local.json +5 −0

Large diff (5 lines) is not loaded by default to keep the page fast.Load diff

added project-db/.env.example +20 −0

Large diff (20 lines) is not loaded by default to keep the page fast.Load diff

added project-db/.gitignore +11 −0

Large diff (11 lines) is not loaded by default to keep the page fast.Load diff

added project-db/README.md +182 −0

Large diff (182 lines) is not loaded by default to keep the page fast.Load diff

added project-db/docs/figures/fig_degree_dist.pdf +0 −0

Binary file not shown.

added project-db/docs/figures/fig_embedding_tsne.pdf +0 −0

Binary file not shown.

added project-db/docs/figures/fig_mentions_by_year.pdf +0 −0

Binary file not shown.

added project-db/docs/figures/fig_sector_type_heatmap.pdf +0 −0

Binary file not shown.

added project-db/docs/figures/fig_tech_network.pdf +0 −0

Binary file not shown.

added project-db/docs/figures/fig_type_distribution.pdf +0 −0

Binary file not shown.

added project-db/docs/make_figures.py +271 −0

Large diff (271 lines) is not loaded by default to keep the page fast.Load diff

added project-db/docs/rapport_uqo/figures/fig_cycle.pdf +0 −0

Binary file not shown.

added project-db/docs/rapport_uqo/figures/fig_cycle.png +0 −0

Binary file not shown.

added project-db/docs/rapport_uqo/figures/fig_dynamique.pdf +0 −0

Binary file not shown.

added project-db/docs/rapport_uqo/figures/fig_dynamique.png +0 −0

Binary file not shown.

added project-db/docs/rapport_uqo/figures/fig_entonnoir.pdf +0 −0

Binary file not shown.

added project-db/docs/rapport_uqo/figures/fig_entonnoir.png +0 −0

Binary file not shown.

added project-db/docs/rapport_uqo/figures/fig_entreprises.pdf +0 −0

Binary file not shown.

added project-db/docs/rapport_uqo/figures/fig_entreprises.png +0 −0

Binary file not shown.

added project-db/docs/rapport_uqo/figures/fig_graphe.pdf +0 −0

Binary file not shown.

added project-db/docs/rapport_uqo/figures/fig_graphe.png +0 −0

Binary file not shown.

added project-db/docs/rapport_uqo/figures/fig_heatmap_secteur_type.pdf +0 −0

Binary file not shown.

added project-db/docs/rapport_uqo/figures/fig_heatmap_secteur_type.png +0 −0

Binary file not shown.

added project-db/docs/rapport_uqo/figures/fig_mentions_annee.pdf +0 −0

Binary file not shown.

added project-db/docs/rapport_uqo/figures/fig_mentions_annee.png +0 −0

Binary file not shown.

added project-db/docs/rapport_uqo/figures/fig_montants.pdf +0 −0

Binary file not shown.

added project-db/docs/rapport_uqo/figures/fig_montants.png +0 −0

Binary file not shown.

added project-db/docs/rapport_uqo/figures/fig_secteurs.pdf +0 −0

Binary file not shown.

added project-db/docs/rapport_uqo/figures/fig_secteurs.png +0 −0

Binary file not shown.

added project-db/docs/rapport_uqo/figures/fig_sections_10k.pdf +0 −0

Binary file not shown.

added project-db/docs/rapport_uqo/figures/fig_sections_10k.png +0 −0

Binary file not shown.

added project-db/docs/rapport_uqo/figures/fig_statut.pdf +0 −0

Binary file not shown.

added project-db/docs/rapport_uqo/figures/fig_statut.png +0 −0

Binary file not shown.

added project-db/docs/rapport_uqo/figures/fig_tech_localisations.pdf +0 −0

Binary file not shown.

added project-db/docs/rapport_uqo/figures/fig_tech_localisations.png +0 −0

Binary file not shown.

added project-db/docs/rapport_uqo/figures/fig_types.pdf +0 −0

Binary file not shown.

added project-db/docs/rapport_uqo/figures/fig_types.png +0 −0

Binary file not shown.

added project-db/docs/rapport_uqo/make_figures.py +462 −0

Large diff (462 lines) is not loaded by default to keep the page fast.Load diff

added project-db/docs/rapport_uqo/rapport_spid.bbl +0 −0

Large diff (0 lines) is not loaded by default to keep the page fast.Load diff

added project-db/docs/rapport_uqo/rapport_spid.pdf +0 −0

Binary file not shown.

added project-db/docs/rapport_uqo/rapport_spid.synctex(busy) +0 −0

Large diff (0 lines) is not loaded by default to keep the page fast.Load diff

added project-db/docs/rapport_uqo/rapport_spid.tex +712 −0

Large diff (712 lines) is not loaded by default to keep the page fast.Load diff

added project-db/docs/rapport_uqo/stats.json +67 −0

Large diff (68 lines) is not loaded by default to keep the page fast.Load diff

added project-db/docs/rapport_uqo/tables/macros.tex +30 −0

Large diff (30 lines) is not loaded by default to keep the page fast.Load diff

added project-db/docs/rapport_uqo/tables/tab_entreprises.tex +15 −0

Large diff (15 lines) is not loaded by default to keep the page fast.Load diff

added project-db/docs/rapport_uqo/tables/tab_exemples.tex +6 −0

Large diff (6 lines) is not loaded by default to keep the page fast.Load diff

added project-db/docs/rapport_uqo/tables/tab_plus_suivis.tex +10 −0

Large diff (10 lines) is not loaded by default to keep the page fast.Load diff

added project-db/docs/rapport_uqo/tables/tab_secteurs.tex +11 −0

Large diff (11 lines) is not loaded by default to keep the page fast.Load diff

added project-db/docs/rapport_uqo/tables/tab_sections.tex +6 −0

Large diff (6 lines) is not loaded by default to keep the page fast.Load diff

added project-db/docs/rapport_uqo/tables/tab_top_projets.tex +15 −0

Large diff (15 lines) is not loaded by default to keep the page fast.Load diff

added project-db/docs/rapport_uqo/tables/tab_types.tex +21 −0

Large diff (21 lines) is not loaded by default to keep the page fast.Load diff

added project-db/docs/rapport_uqo/uqo-logo.png +0 −0

Binary file not shown.

added project-db/docs/spid_database.tex +608 −0

Large diff (608 lines) is not loaded by default to keep the page fast.Load diff

added project-db/docs/spid_potential.tex +245 −0

Large diff (245 lines) is not loaded by default to keep the page fast.Load diff

added project-db/docs/tables/stats.tex +8 −0

Large diff (9 lines) is not loaded by default to keep the page fast.Load diff

added project-db/docs/tables/top_companies.tex +18 −0

Large diff (19 lines) is not loaded by default to keep the page fast.Load diff

added project-db/docs/tables/top_ma.tex +16 −0

Large diff (17 lines) is not loaded by default to keep the page fast.Load diff

added project-db/requirements.txt +17 −0

Large diff (17 lines) is not loaded by default to keep the page fast.Load diff

added project-db/research/README.md +51 −0

Large diff (51 lines) is not loaded by default to keep the page fast.Load diff

added project-db/research/code/01_build_datasets.py +158 −0

Large diff (158 lines) is not loaded by default to keep the page fast.Load diff

added project-db/research/code/02_descriptives.py +152 −0

Large diff (152 lines) is not loaded by default to keep the page fast.Load diff

added project-db/research/code/03_count_models.py +111 −0

Large diff (111 lines) is not loaded by default to keep the page fast.Load diff

added project-db/research/code/04_amount_models.py +107 −0

Large diff (107 lines) is not loaded by default to keep the page fast.Load diff

added project-db/research/code/05_diffusion.py +97 −0

Large diff (97 lines) is not loaded by default to keep the page fast.Load diff

added project-db/research/code/06_did_event_study.py +98 −0

Large diff (98 lines) is not loaded by default to keep the page fast.Load diff

added project-db/research/code/07_survival.py +88 −0

Large diff (88 lines) is not loaded by default to keep the page fast.Load diff

added project-db/research/code/08_network.py +105 −0

Large diff (105 lines) is not loaded by default to keep the page fast.Load diff

added project-db/research/code/09_embeddings.py +117 −0

Large diff (117 lines) is not loaded by default to keep the page fast.Load diff

added project-db/research/code/10_ml_prediction.py +87 −0

Large diff (87 lines) is not loaded by default to keep the page fast.Load diff

added project-db/research/code/common.py +73 −0

Large diff (73 lines) is not loaded by default to keep the page fast.Load diff

added project-db/research/figures/fig_ai_diffusion.pdf +0 −0

Binary file not shown.

added project-db/research/figures/fig_ai_diffusion.png +0 −0

Binary file not shown.

added project-db/research/figures/fig_amount_coef.pdf +0 −0

Binary file not shown.

added project-db/research/figures/fig_amount_coef.png +0 −0

Binary file not shown.

added project-db/research/figures/fig_capex_by_year.pdf +0 −0

Binary file not shown.

added project-db/research/figures/fig_capex_by_year.png +0 −0

Binary file not shown.

added project-db/research/figures/fig_count_coef.pdf +0 −0

Binary file not shown.

added project-db/research/figures/fig_count_coef.png +0 −0

Binary file not shown.

added project-db/research/figures/fig_degree_dist.pdf +0 −0

Binary file not shown.

added project-db/research/figures/fig_degree_dist.png +0 −0

Binary file not shown.

added project-db/research/figures/fig_did_event.pdf +0 −0

Binary file not shown.

added project-db/research/figures/fig_did_event.png +0 −0

Binary file not shown.

added project-db/research/figures/fig_embedding_tsne.pdf +0 −0

Binary file not shown.

added project-db/research/figures/fig_embedding_tsne.png +0 −0

Binary file not shown.

added project-db/research/figures/fig_mentions_by_year.pdf +0 −0

Binary file not shown.

added project-db/research/figures/fig_mentions_by_year.png +0 −0

Binary file not shown.

added project-db/research/figures/fig_ml_roc.pdf +0 −0

Binary file not shown.

added project-db/research/figures/fig_ml_roc.png +0 −0

Binary file not shown.

added project-db/research/figures/fig_sector_type_heatmap.pdf +0 −0

Binary file not shown.

added project-db/research/figures/fig_sector_type_heatmap.png +0 −0

Binary file not shown.

added project-db/research/figures/fig_silhouette.pdf +0 −0

Binary file not shown.

added project-db/research/figures/fig_silhouette.png +0 −0

Binary file not shown.

added project-db/research/figures/fig_survival_km.pdf +0 −0

Binary file not shown.

added project-db/research/figures/fig_survival_km.png +0 −0

Binary file not shown.

added project-db/research/figures/fig_tech_network.pdf +0 −0

Binary file not shown.

added project-db/research/figures/fig_tech_network.png +0 −0

Binary file not shown.

added project-db/research/figures/fig_top_locations.pdf +0 −0

Binary file not shown.

added project-db/research/figures/fig_top_locations.png +0 −0

Binary file not shown.

added project-db/research/figures/fig_type_distribution.pdf +0 −0

Binary file not shown.

added project-db/research/figures/fig_type_distribution.png +0 −0

Binary file not shown.

added project-db/research/paper/build.log +295 −0

Large diff (295 lines) is not loaded by default to keep the page fast.Load diff

added project-db/research/paper/main.aux +157 −0

Large diff (157 lines) is not loaded by default to keep the page fast.Load diff

added project-db/research/paper/main.fdb_latexmk +180 −0

Large diff (180 lines) is not loaded by default to keep the page fast.Load diff

added project-db/research/paper/main.fls +383 −0

Large diff (383 lines) is not loaded by default to keep the page fast.Load diff

added project-db/research/paper/main.log +758 −0

Large diff (758 lines) is not loaded by default to keep the page fast.Load diff

added project-db/research/paper/main.out +25 −0

Large diff (25 lines) is not loaded by default to keep the page fast.Load diff

added project-db/research/paper/main.pdf +0 −0

Binary file not shown.

added project-db/research/paper/main.synctex.gz +0 −0

Binary file not shown.

added project-db/research/paper/main.tex +12 −0

Large diff (12 lines) is not loaded by default to keep the page fast.Load diff

Diff truncated — file too large.