UQO EDGAR Research DB: extension S&P 500 -> Russell 3000 (pipeline scalable, exécution distribuée MacLustr)

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

++{
++  "disabledMcpjsonServers": [
++    "cluster"
++  ]
++}

added .env.example +18 −0

++# EDGAR Research Database — Environment Configuration
++
++# SEC EDGAR requires a user-agent string with contact email
++SEC_USER_AGENT="UQO-Research simon-pierre.boucher@uqo.ca"
++
++# Project paths (defaults work for standard layout)
++# DATA_DIR=./data
++# DUCKDB_PATH=./data/duckdb/edgar_research.duckdb
++
++# Embedding API (optional — defaults to local sentence-transformers)
++# OPENAI_API_KEY=sk-...
++# OPENROUTER_API_KEY=sk-or-...
++# EMBEDDING_MODEL=all-MiniLM-L6-v2
++# EMBEDDING_BATCH_SIZE=256
++
++# Logging
++# LOG_LEVEL=INFO
++# LOG_FORMAT=json

added .gitignore +27 −0

++# data and secrets never enter git
++data/
++.venv/
++__pycache__/
++*.pyc
++.env
++project-db/.env
++project-db/data/
++project-db/logs/
++*.duckdb
++*.zip
++.DS_Store
++edgar_research_db.egg-info/
++analysis/data/
++outputs/
++UQ_WP_template/*.aux
++UQ_WP_template/*.log
++UQ_WP_template/*.fls
++UQ_WP_template/*.fdb_latexmk
++UQ_WP_template/*.out
++UQ_WP_template/*.synctex*
++project-db/docs/*.aux
++project-db/docs/*.log
++project-db/docs/*.fls
++project-db/docs/*.fdb_latexmk
++project-db/docs/*.out
++project-db/docs/*.toc

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

++{
++  "disabledMcpjsonServers": [
++    "cluster"
++  ]
++}

added UQ_WP_template/.latexmkrc +5 −0

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

added UQ_WP_template/Makefile +11 −0

++.PHONY: all clean distclean
++
++all:
++	latexmk
++
++clean:
++	latexmk -c
++
++distclean:
++	latexmk -C
++	rm -f *.synctex.gz *.run.xml *.bbl *.bcf

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

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

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

++% ============================================================================
++% Figure: Main Result
++% ============================================================================
++\begin{figure}[htbp]
++  \centering
++  % --- Replace placeholder with actual figure file ---
++  % \includegraphics[width=0.85\textwidth]{figures/main_result.pdf}
++  %
++  % Placeholder box (remove when replacing with actual figure)
++  \fbox{\parbox{0.85\textwidth}{\centering\vspace{4cm}
++    \textit{[Insert figure here: figures/main\_result.pdf]}
++  \vspace{4cm}}}
++  %
++  \caption{Main Result --- Effect of $X$ on $Y$ Over Time}
++  \label{fig:main_result}
++  \begin{minipage}{0.85\textwidth}
++    \vspace{0.3cm}
++    \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{}
++  \end{minipage}
++\end{figure}

added UQ_WP_template/main.bbl +187 −0

++\ifx\undefined\bysame
++\newcommand{\bysame}{\leavevmode\hbox to\leftmargin{\hrulefill\,\,}}
++\fi
++\begin{thebibliography}{xx}
++
++\harvarditem[Acemoglu and Restrepo]{Acemoglu and
++  Restrepo}{2020}{acemoglu2020wrong}
++{\bf Acemoglu, Daron and Pascual Restrepo}, ``Robots and Jobs: Evidence from
++  {US} Labor Markets,'' {\it Journal of Political Economy}, 2020, {\it 128}
++  (6), 2188--2244.
++
++\harvarditem[Babina et al.]{Babina, Fedyk, He and
++  Hodson}{2024}{babina2024aiinvestment}
++{\bf Babina, Tania, Anastassia Fedyk, Alex He, and James Hodson}, ``Artificial
++  Intelligence, Firm Growth, and Product Innovation,'' {\it Journal of
++  Financial Economics}, 2024, {\it 151}, 103745.
++
++\harvarditem[Baker and Wurgler]{Baker and Wurgler}{2006}{bakerwurgler2006}
++{\bf Baker, Malcolm and Jeffrey Wurgler}, ``Investor Sentiment and the
++  Cross-Section of Stock Returns,'' {\it Journal of Finance}, 2006, {\it 61}
++  (4), 1645--1680.
++
++\harvarditem[Barber and Odean]{Barber and Odean}{2008}{barberodean2008}
++{\bf Barber, Brad~M. and Terrance Odean}, ``All That Glitters: The Effect of
++  Attention and News on the Buying Behavior of Individual and Institutional
++  Investors,'' {\it Review of Financial Studies}, 2008, {\it 21} (2), 785--818.
++
++\harvarditem[Bolton and Kacperczyk]{Bolton and
++  Kacperczyk}{2021}{bolton2021risk}
++{\bf Bolton, Patrick and Marcin Kacperczyk}, ``Do Investors Care about Carbon
++  Risk?,'' {\it Journal of Financial Economics}, 2021, {\it 142} (2), 517--549.
++
++\harvarditem[Bybee et al.]{Bybee, Kelly, Manela and
++  Xiu}{2024}{bybee2024narrative}
++{\bf Bybee, Leland, Bryan Kelly, Asaf Manela, and Dacheng Xiu}, ``Business News
++  and Business Cycles,'' {\it Journal of Finance}, 2024, {\it 79} (5),
++  3105--3147.
++
++\harvarditem[Cameron et al.]{Cameron, Gelbach and Miller}{2011}{cameron2011}
++{\bf Cameron, A.~Colin, Jonah~B. Gelbach, and Douglas~L. Miller}, ``Robust
++  Inference with Multiway Clustering,'' {\it Journal of Business \& Economic
++  Statistics}, 2011, {\it 29} (2), 238--249.
++
++\harvarditem[Cohen et al.]{Cohen, Malloy and Nguyen}{2020}{cohen2020lazy}
++{\bf Cohen, Lauren, Christopher Malloy, and Quoc Nguyen}, ``Lazy Prices,'' {\it
++  Journal of Finance}, 2020, {\it 75} (3), 1371--1415.
++
++\harvarditem[Cong et al.]{Cong, Liang and Zhang}{2022}{cong2022textfactor}
++{\bf Cong, Lin~William, Tengyuan Liang, and Xiao Zhang}, ``Textual Factors: A
++  Scalable, Interpretable, and Data-Driven Approach to Analyzing Unstructured
++  Information,'' Technical Report, Working Paper 2022.
++
++\harvarditem[Da et al.]{Da, Engelberg and Gao}{2011}{da2011}
++{\bf Da, Zhi, Joseph Engelberg, and Pengjie Gao}, ``In Search of Attention,''
++  {\it Journal of Finance}, 2011, {\it 66} (5), 1461--1499.
++
++\harvarditem[DellaVigna and Pollet]{DellaVigna and
++  Pollet}{2009}{dellavigna2009}
++{\bf DellaVigna, Stefano and Joshua~M. Pollet}, ``Investor Inattention and
++  {Friday} Earnings Announcements,'' {\it Journal of Finance}, 2009, {\it 64}
++  (2), 709--749.
++
++\harvarditem[Eisfeldt et al.]{Eisfeldt, Schubert and
++  Zhang}{2023}{eisfeldt2023generative}
++{\bf Eisfeldt, Andrea~L., Gregor Schubert, and Miao~Ben Zhang}, ``Generative
++  {AI} and Firm Values,'' NBER Working Paper 31222, National Bureau of Economic
++  Research 2023.
++
++\harvarditem[Fama and MacBeth]{Fama and MacBeth}{1973}{famamacbeth1973}
++{\bf Fama, Eugene~F. and James~D. MacBeth}, ``Risk, Return, and Equilibrium:
++  Empirical Tests,'' {\it Journal of Political Economy}, 1973, {\it 81} (3),
++  607--636.
++
++\harvarditem[Fama and French]{Fama and French}{2015}{famafrench2015}
++{\bf \bysame{} and Kenneth~R. French}, ``A Five-Factor Asset Pricing Model,''
++  {\it Journal of Financial Economics}, 2015, {\it 116} (1), 1--22.
++
++\harvarditem[Gentzkow et al.]{Gentzkow, Kelly and Taddy}{2019}{gentzkow2019}
++{\bf Gentzkow, Matthew, Bryan Kelly, and Matt Taddy}, ``Text as Data,'' {\it
++  Journal of Economic Literature}, 2019, {\it 57} (3), 535--574.
++
++\harvarditem[Hirshleifer et al.]{Hirshleifer, Hsu and
++  Li}{2013}{hirshleifer2013innovative}
++{\bf Hirshleifer, David, Po-Hsuan Hsu, and Dongmei Li}, ``Innovative Efficiency
++  and Stock Returns,'' {\it Journal of Financial Economics}, 2013, {\it 107}
++  (3), 632--654.
++
++\harvarditem[Hirshleifer et al.]{Hirshleifer, Lim and
++  Teoh}{2009}{hirshleifer2009driven}
++{\bf \bysame{}, Sonya~S. Lim, and Siew~Hong Teoh}, ``Driven to Distraction:
++  Extraneous Events and Underreaction to Earnings News,'' {\it Journal of
++  Finance}, 2009, {\it 64} (5), 2289--2325.
++
++\harvarditem[Hoberg and Phillips]{Hoberg and Phillips}{2010}{hoberg2010product}
++{\bf Hoberg, Gerard and Gordon Phillips}, ``Product Market Synergies and
++  Competition in Mergers and Acquisitions: A Text-Based Analysis,'' {\it Review
++  of Financial Studies}, 2010, {\it 23} (10), 3773--3811.
++
++\harvarditem[Hoberg and Phillips]{Hoberg and
++  Phillips}{2016}{hobergphillips2016}
++{\bf \bysame{} and \bysame{}}, ``Text-Based Network Industries and Endogenous
++  Product Differentiation,'' {\it Journal of Political Economy}, 2016, {\it
++  124} (5), 1423--1465.
++
++\harvarditem[Kelly et al.]{Kelly, Manela and
++  Moreira}{2021}{kelly2019textregression}
++{\bf Kelly, Bryan, Asaf Manela, and Alan Moreira}, ``Text Selection,'' {\it
++  Journal of Business \& Economic Statistics}, 2021, {\it 39} (4), 859--879.
++
++\harvarditem[Kogan and Papanikolaou]{Kogan and
++  Papanikolaou}{2014}{koganpapanikolaou2014}
++{\bf Kogan, Leonid and Dimitris Papanikolaou}, ``Growth Opportunities,
++  Technology Shocks, and Asset Prices,'' {\it Journal of Finance}, 2014, {\it
++  69} (2), 675--718.
++
++\harvarditem[Kogan et al.]{Kogan, Papanikolaou, Seru and
++  Stoffman}{2017}{kogan2017technological}
++{\bf \bysame{}, \bysame{}, Amit Seru, and Noah Stoffman}, ``Technological
++  Innovation, Resource Allocation, and Growth,'' {\it Quarterly Journal of
++  Economics}, 2017, {\it 132} (2), 665--712.
++
++\harvarditem[Lopez-Lira]{Lopez-Lira}{2023}{lopezlira2023risk}
++{\bf Lopez-Lira, Alejandro}, ``Risk Factors That Matter: Textual Analysis of
++  Risk Disclosures for the Cross-Section of Returns,'' Technical Report,
++  Working Paper 2023.
++
++\harvarditem[Loughran and McDonald]{Loughran and McDonald}{2011}{lm2011}
++{\bf Loughran, Tim and Bill McDonald}, ``When Is a Liability Not a Liability?
++  Textual Analysis, Dictionaries, and 10-Ks,'' {\it Journal of Finance}, 2011,
++  {\it 66} (1), 35--65.
++
++\harvarditem[Loughran and McDonald]{Loughran and McDonald}{2016}{lm2016}
++{\bf \bysame{} and \bysame{}}, ``Textual Analysis in Accounting and Finance: A
++  Survey,'' {\it Journal of Accounting Research}, 2016, {\it 54} (4),
++  1187--1230.
++
++\harvarditem[MacKinlay]{MacKinlay}{1997}{mackinlay1997}
++{\bf MacKinlay, A.~Craig}, ``Event Studies in Economics and Finance,'' {\it
++  Journal of Economic Literature}, 1997, {\it 35} (1), 13--39.
++
++\harvarditem[Newey and West]{Newey and West}{1987}{neweywest1987}
++{\bf Newey, Whitney~K. and Kenneth~D. West}, ``A Simple, Positive
++  Semi-Definite, Heteroskedasticity and Autocorrelation Consistent Covariance
++  Matrix,'' {\it Econometrica}, 1987, {\it 55} (3), 703--708.
++
++\harvarditem[P{\'a}stor et al.]{P{\'a}stor, Stambaugh and
++  Taylor}{2021}{pastor2021sustainable}
++{\bf P{\'a}stor, {\v{L}}ubo{\v{s}}, Robert~F. Stambaugh, and Lucian~A. Taylor},
++  ``Sustainable Investing in Equilibrium,'' {\it Journal of Financial
++  Economics}, 2021, {\it 142} (2), 550--571.
++
++\harvarditem[P{\'a}stor et al.]{P{\'a}stor, Stambaugh and
++  Taylor}{2022}{pastor2022dissecting}
++{\bf \bysame{}, \bysame{}, and \bysame{}}, ``Dissecting Green Returns,'' {\it
++  Journal of Financial Economics}, 2022, {\it 146} (2), 403--424.
++
++\harvarditem[Petersen]{Petersen}{2009}{petersen2009}
++{\bf Petersen, Mitchell~A.}, ``Estimating Standard Errors in Finance Panel Data
++  Sets: Comparing Approaches,'' {\it Review of Financial Studies}, 2009, {\it
++  22} (1), 435--480.
++
++\harvarditem[Reimers and Gurevych]{Reimers and
++  Gurevych}{2019}{reimers2019sbert}
++{\bf Reimers, Nils and Iryna Gurevych}, ``Sentence-{BERT}: Sentence Embeddings
++  Using {Siamese} {BERT}-Networks,'' in ``Proceedings of the 2019 Conference on
++  Empirical Methods in Natural Language Processing (EMNLP)'' 2019.
++
++\harvarditem[Shiller]{Shiller}{2017}{shiller2017narrative}
++{\bf Shiller, Robert~J.}, ``Narrative Economics,'' {\it American Economic
++  Review}, 2017, {\it 107} (4), 967--1004.
++
++\harvarditem[Tetlock]{Tetlock}{2007}{tetlock2007}
++{\bf Tetlock, Paul~C.}, ``Giving Content to Investor Sentiment: The Role of
++  Media in the Stock Market,'' {\it Journal of Finance}, 2007, {\it 62} (3),
++  1139--1168.
++
++\harvarditem[Tetlock et al.]{Tetlock, Saar-Tsechansky and
++  Macskassy}{2008}{tetlock2008}
++{\bf \bysame{}, Maytal Saar-Tsechansky, and Sofus Macskassy}, ``More Than
++  Words: Quantifying Language to Measure Firms' Fundamentals,'' {\it Journal of
++  Finance}, 2008, {\it 63} (3), 1437--1467.
++
++\harvarditem[Webb]{Webb}{2020}{webb2020}
++{\bf Webb, Michael}, ``The Impact of Artificial Intelligence on the Labor
++  Market,'' Technical Report, Stanford University Working Paper 2020.
++
++\end{thebibliography}

added UQ_WP_template/main.blg +48 −0

++This is BibTeX, Version 0.99e (TeX Live 2026)
++Capacity: max_strings=200000, hash_size=200000, hash_prime=170003
++The top-level auxiliary file: main.aux
++The style file: aer.bst
++Reallocated singl_function (elt_size=4) to 100 items from 50.
++Reallocated singl_function (elt_size=4) to 100 items from 50.
++Database file #1: references.bib
++You've used 35 entries,
++            2984 wiz_defined-function locations,
++            847 strings with 8991 characters,
++and the built_in function-call counts, 31924 in all, are:
++= -- 5079
++> -- 1808
++< -- 516
+++ -- 580
++- -- 328
++* -- 2173
++:= -- 7060
++add.period$ -- 35
++call.type$ -- 35
++change.case$ -- 245
++chr.to.int$ -- 35
++cite$ -- 35
++duplicate$ -- 385
++empty$ -- 983
++format.name$ -- 912
++if$ -- 7891
++int.to.chr$ -- 1
++int.to.str$ -- 0
++missing$ -- 31
++newline$ -- 111
++num.names$ -- 420
++pop$ -- 527
++preamble$ -- 1
++purify$ -- 280
++quote$ -- 0
++skip$ -- 0
++stack$ -- 0
++substring$ -- 1182
++swap$ -- 132
++text.length$ -- 1
++text.prefix$ -- 0
++top$ -- 0
++type$ -- 140
++warning$ -- 0
++while$ -- 409
++width$ -- 0
++write$ -- 589

added UQ_WP_template/main.pdf +0 −0

Binary file not shown.

added UQ_WP_template/main.tex +174 −0

++% ============================================================================
++% UQO Working Paper Template — Economics / Finance
++% ============================================================================
++\documentclass[12pt,letterpaper]{article}
++
++% --- Encoding & Language ---
++\usepackage[utf8]{inputenc}
++\usepackage[T1]{fontenc}
++\usepackage[english]{babel}
++
++% --- Page Layout ---
++\usepackage[
++  letterpaper,
++  top=1in,
++  bottom=1in,
++  left=1in,
++  right=1in
++]{geometry}
++
++% --- Typography ---
++\usepackage{mathptmx}          % Times-like font (text + math)
++\usepackage{microtype}         % Improved typographic refinements
++\usepackage{setspace}
++\doublespacing                 % double line spacing (working-paper format)
++
++% --- Math ---
++\usepackage{amsmath,amssymb,amsthm}
++
++% --- Tables ---
++\usepackage{booktabs}
++\usepackage{tabularx}
++\usepackage{multirow}
++\usepackage{threeparttable}
++\usepackage{siunitx}
++\sisetup{
++  input-symbols = {()},
++  table-format  = -1.3,
++  parse-numbers = false
++}
++
++% --- Figures ---
++\usepackage{graphicx}
++\usepackage{subcaption}
++\usepackage{float}
++
++% --- Colors & Links ---
++\usepackage[dvipsnames]{xcolor}
++\usepackage[
++  colorlinks  = true,
++  linkcolor   = NavyBlue,
++  citecolor   = NavyBlue,
++  urlcolor    = NavyBlue,
++  breaklinks  = true
++]{hyperref}
++
++% --- Bibliography ---
++\usepackage[authoryear,round,semicolon]{natbib}
++\bibliographystyle{aer}
++
++% --- Captions ---
++\usepackage[
++  font       = small,
++  labelfont  = bf,
++  labelsep   = period,
++  justification = justified,
++  singlelinecheck = false
++]{caption}
++
++% --- Headers & Footers ---
++\usepackage{fancyhdr}
++\pagestyle{fancy}
++\fancyhf{}
++\renewcommand{\headrulewidth}{0pt}
++\fancyfoot[C]{\thepage}
++
++% --- Section Formatting ---
++\usepackage{titlesec}
++\titleformat{\section}{\large\bfseries}{\thesection.}{0.5em}{}
++\titleformat{\subsection}{\normalsize\bfseries}{\thesubsection.}{0.5em}{}
++\titleformat{\subsubsection}{\normalsize\itshape}{\thesubsubsection.}{0.5em}{}
++
++% --- Appendix Support ---
++\usepackage[toc,page]{appendix}
++
++% --- Misc ---
++\usepackage{enumitem}
++\setlist{nosep,leftmargin=*}
++
++% --- Project-specific additions ---
++\graphicspath{{figures/}}
++\newcommand{\tstat}[1]{{\footnotesize(\textit{t}=#1)}}
++
++% ============================================================================
++% METADATA — Edit these fields for each working paper
++% ============================================================================
++\newcommand{\WPnumber}{2026-03}
++\newcommand{\WPtitle}{Does the Language of Artificial Intelligence Move Markets?}
++\newcommand{\WPsubtitle}{A Semantic Analysis of S\&P~500 SEC Filings and the Cross-Section of Stock Returns, 2010--2026}
++\newcommand{\WPdate}{June 2026}
++\newcommand{\WPversion}{1.0}
++\newcommand{\WPabstract}{%
++  We construct a \emph{semantic} measure of artificial-intelligence (AI) engagement for every
++  S\&P~500 firm by embedding the text of its annual SEC filings (Form~10-K) with a sentence
++  transformer and scoring each passage by cosine similarity to curated AI ``anchor'' concepts:
++  internal AI adoption, AI infrastructure exposure, and AI product-disruption risk. Linking these
++  scores to monthly equity prices from Yahoo Finance and to the Fama--French factor data, we
++  assemble a panel of 7{,}869 firm-years (500 firms, fiscal years 2010--2026) and ask whether the
++  intensity of AI language predicts the cross-section of subsequent returns. Our central result is
++  \emph{conditional and economically large}: over the full sample the relation is positive but
++  modest and only marginally significant, yet after the launch of ChatGPT (November~2022) it more
++  than sextuples. The spread between the top and bottom quintile of AI disclosure rises from $+2.4$
++  percentage points per year before 2022 to $+14.6$ points afterward, and the long--short Sharpe
++  ratio rises from 0.15 to 1.33. The break survives section-weighting choices, alternative signal
++  definitions and horizons, dimension reduction, and the exclusion of the ``Magnificent~7''
++  mega-caps. Three identification tests sharpen the interpretation: (i)~a placebo across five
++  non-AI semantic factors shows the post-2022 jump is specific to AI (ESG and climate disclosure
++  earn \emph{negative} post-2022 spreads); (ii)~a market-model event study finds that firms with
++  higher pre-event AI disclosure earned $+10.1\%$ higher cumulative abnormal returns over the year
++  after ChatGPT ($t=1.97$); and (iii)~the effect is absorbed by firm fixed effects and roughly
++  halved by sector fixed effects. We interpret the evidence as an attention- and narrative-driven
++  \emph{re-rating}: the market repriced which firms and sectors are AI-exposed once AI became
++  salient, rather than rewarding year-to-year changes in wording.%
++}
++\newcommand{\WPkeywords}{textual analysis, sentence embeddings, artificial intelligence, disclosure, cross-section of returns, investor attention, event study}
++\newcommand{\WPjel}{G12, G14, G17, M41, O33}
++
++% --- Authors ---
++\newcommand{\WPauthor}{%
++  \begin{tabular}{c}
++    {\large Manel Kammoun}\\[-0.05cm]
++    {\small\href{mailto:manel.kammoun@uqo.ca}{manel.kammoun@uqo.ca}}\\[0.35cm]
++    {\large Djerrycharli Tandjambianda}\\[-0.05cm]
++    {\small\href{mailto:djerrycharli.tandjambianda@uqo.ca}{djerrycharli.tandjambianda@uqo.ca}}\\[0.35cm]
++    {\large Simon-Pierre Boucher}\\[-0.05cm]
++    {\small\href{mailto:simon-pierre.boucher@uqo.ca}{simon-pierre.boucher@uqo.ca}}
++  \end{tabular}%
++}
++\newcommand{\WPaffiliation}{%
++  Département des sciences administratives\\
++  Université du Québec en Outaouais%
++}
++\newcommand{\WPemail}{}
++\newcommand{\WPaddress}{%
++  Gatineau -- Pavillon Alexandre-Taché\\
++  283, boulevard Alexandre-Taché\\
++  Gatineau, Québec, Canada J9A 1L8%
++}
++
++% ============================================================================
++% DOCUMENT
++% ============================================================================
++\begin{document}
++
++% --- Title Page ---
++\input{sections/titlepage}
++
++% --- Main Body ---
++\input{sections/introduction}
++\input{sections/literature}
++\input{sections/data}
++\input{sections/methodology}
++\input{sections/results}
++\input{sections/robustness}
++\input{sections/discussion}
++\input{sections/conclusion}
++
++% --- References ---
++\newpage
++\bibliography{references}
++
++% --- Appendix ---
++\input{appendix/appendix}
++
++\end{document}

added UQ_WP_template/references.bib +340 −0

++% ============================================================================
++% References — BibTeX Database
++% "Does the Language of Artificial Intelligence Move Markets?"
++% ============================================================================
++
++@article{acemoglu2020wrong,
++  author  = {Acemoglu, Daron and Restrepo, Pascual},
++  title   = {Robots and Jobs: Evidence from {US} Labor Markets},
++  journal = {Journal of Political Economy},
++  volume  = {128},
++  number  = {6},
++  pages   = {2188--2244},
++  year    = {2020}
++}
++
++@article{babina2024aiinvestment,
++  author  = {Babina, Tania and Fedyk, Anastassia and He, Alex and Hodson, James},
++  title   = {Artificial Intelligence, Firm Growth, and Product Innovation},
++  journal = {Journal of Financial Economics},
++  volume  = {151},
++  pages   = {103745},
++  year    = {2024}
++}
++
++@article{bakerwurgler2006,
++  author  = {Baker, Malcolm and Wurgler, Jeffrey},
++  title   = {Investor Sentiment and the Cross-Section of Stock Returns},
++  journal = {Journal of Finance},
++  volume  = {61},
++  number  = {4},
++  pages   = {1645--1680},
++  year    = {2006}
++}
++
++@article{barberodean2008,
++  author  = {Barber, Brad M. and Odean, Terrance},
++  title   = {All That Glitters: The Effect of Attention and News on the Buying Behavior of Individual and Institutional Investors},
++  journal = {Review of Financial Studies},
++  volume  = {21},
++  number  = {2},
++  pages   = {785--818},
++  year    = {2008}
++}
++
++@article{bolton2021risk,
++  author  = {Bolton, Patrick and Kacperczyk, Marcin},
++  title   = {Do Investors Care about Carbon Risk?},
++  journal = {Journal of Financial Economics},
++  volume  = {142},
++  number  = {2},
++  pages   = {517--549},
++  year    = {2021}
++}
++
++@article{bybee2024narrative,
++  author  = {Bybee, Leland and Kelly, Bryan and Manela, Asaf and Xiu, Dacheng},
++  title   = {Business News and Business Cycles},
++  journal = {Journal of Finance},
++  volume  = {79},
++  number  = {5},
++  pages   = {3105--3147},
++  year    = {2024}
++}
++
++@article{cameron2011,
++  author  = {Cameron, A. Colin and Gelbach, Jonah B. and Miller, Douglas L.},
++  title   = {Robust Inference with Multiway Clustering},
++  journal = {Journal of Business \& Economic Statistics},
++  volume  = {29},
++  number  = {2},
++  pages   = {238--249},
++  year    = {2011}
++}
++
++@article{cohen2020lazy,
++  author  = {Cohen, Lauren and Malloy, Christopher and Nguyen, Quoc},
++  title   = {Lazy Prices},
++  journal = {Journal of Finance},
++  volume  = {75},
++  number  = {3},
++  pages   = {1371--1415},
++  year    = {2020}
++}
++
++@techreport{cong2022textfactor,
++  author      = {Cong, Lin William and Liang, Tengyuan and Zhang, Xiao},
++  title       = {Textual Factors: A Scalable, Interpretable, and Data-Driven Approach to Analyzing Unstructured Information},
++  institution = {Working Paper},
++  year        = {2022}
++}
++
++@article{da2011,
++  author  = {Da, Zhi and Engelberg, Joseph and Gao, Pengjie},
++  title   = {In Search of Attention},
++  journal = {Journal of Finance},
++  volume  = {66},
++  number  = {5},
++  pages   = {1461--1499},
++  year    = {2011}
++}
++
++@article{dellavigna2009,
++  author  = {DellaVigna, Stefano and Pollet, Joshua M.},
++  title   = {Investor Inattention and {Friday} Earnings Announcements},
++  journal = {Journal of Finance},
++  volume  = {64},
++  number  = {2},
++  pages   = {709--749},
++  year    = {2009}
++}
++
++@techreport{eisfeldt2023generative,
++  author      = {Eisfeldt, Andrea L. and Schubert, Gregor and Zhang, Miao Ben},
++  title       = {Generative {AI} and Firm Values},
++  institution = {National Bureau of Economic Research},
++  type        = {NBER Working Paper},
++  number      = {31222},
++  year        = {2023}
++}
++
++@article{famafrench2015,
++  author  = {Fama, Eugene F. and French, Kenneth R.},
++  title   = {A Five-Factor Asset Pricing Model},
++  journal = {Journal of Financial Economics},
++  volume  = {116},
++  number  = {1},
++  pages   = {1--22},
++  year    = {2015}
++}
++
++@article{famamacbeth1973,
++  author  = {Fama, Eugene F. and MacBeth, James D.},
++  title   = {Risk, Return, and Equilibrium: Empirical Tests},
++  journal = {Journal of Political Economy},
++  volume  = {81},
++  number  = {3},
++  pages   = {607--636},
++  year    = {1973}
++}
++
++@article{gentzkow2019,
++  author  = {Gentzkow, Matthew and Kelly, Bryan and Taddy, Matt},
++  title   = {Text as Data},
++  journal = {Journal of Economic Literature},
++  volume  = {57},
++  number  = {3},
++  pages   = {535--574},
++  year    = {2019}
++}
++
++@article{hirshleifer2009driven,
++  author  = {Hirshleifer, David and Lim, Sonya S. and Teoh, Siew Hong},
++  title   = {Driven to Distraction: Extraneous Events and Underreaction to Earnings News},
++  journal = {Journal of Finance},
++  volume  = {64},
++  number  = {5},
++  pages   = {2289--2325},
++  year    = {2009}
++}
++
++@article{hirshleifer2013innovative,
++  author  = {Hirshleifer, David and Hsu, Po-Hsuan and Li, Dongmei},
++  title   = {Innovative Efficiency and Stock Returns},
++  journal = {Journal of Financial Economics},
++  volume  = {107},
++  number  = {3},
++  pages   = {632--654},
++  year    = {2013}
++}
++
++@article{hoberg2010product,
++  author  = {Hoberg, Gerard and Phillips, Gordon},
++  title   = {Product Market Synergies and Competition in Mergers and Acquisitions: A Text-Based Analysis},
++  journal = {Review of Financial Studies},
++  volume  = {23},
++  number  = {10},
++  pages   = {3773--3811},
++  year    = {2010}
++}
++
++@article{hobergphillips2016,
++  author  = {Hoberg, Gerard and Phillips, Gordon},
++  title   = {Text-Based Network Industries and Endogenous Product Differentiation},
++  journal = {Journal of Political Economy},
++  volume  = {124},
++  number  = {5},
++  pages   = {1423--1465},
++  year    = {2016}
++}
++
++@article{kelly2019textregression,
++  author  = {Kelly, Bryan and Manela, Asaf and Moreira, Alan},
++  title   = {Text Selection},
++  journal = {Journal of Business \& Economic Statistics},
++  volume  = {39},
++  number  = {4},
++  pages   = {859--879},
++  year    = {2021}
++}
++
++@article{kogan2017technological,
++  author  = {Kogan, Leonid and Papanikolaou, Dimitris and Seru, Amit and Stoffman, Noah},
++  title   = {Technological Innovation, Resource Allocation, and Growth},
++  journal = {Quarterly Journal of Economics},
++  volume  = {132},
++  number  = {2},
++  pages   = {665--712},
++  year    = {2017}
++}
++
++@article{koganpapanikolaou2014,
++  author  = {Kogan, Leonid and Papanikolaou, Dimitris},
++  title   = {Growth Opportunities, Technology Shocks, and Asset Prices},
++  journal = {Journal of Finance},
++  volume  = {69},
++  number  = {2},
++  pages   = {675--718},
++  year    = {2014}
++}
++
++@techreport{lopezlira2023risk,
++  author      = {Lopez-Lira, Alejandro},
++  title       = {Risk Factors That Matter: Textual Analysis of Risk Disclosures for the Cross-Section of Returns},
++  institution = {Working Paper},
++  year        = {2023}
++}
++
++@article{lm2011,
++  author  = {Loughran, Tim and McDonald, Bill},
++  title   = {When Is a Liability Not a Liability? Textual Analysis, Dictionaries, and 10-Ks},
++  journal = {Journal of Finance},
++  volume  = {66},
++  number  = {1},
++  pages   = {35--65},
++  year    = {2011}
++}
++
++@article{lm2016,
++  author  = {Loughran, Tim and McDonald, Bill},
++  title   = {Textual Analysis in Accounting and Finance: A Survey},
++  journal = {Journal of Accounting Research},
++  volume  = {54},
++  number  = {4},
++  pages   = {1187--1230},
++  year    = {2016}
++}
++
++@article{mackinlay1997,
++  author  = {MacKinlay, A. Craig},
++  title   = {Event Studies in Economics and Finance},
++  journal = {Journal of Economic Literature},
++  volume  = {35},
++  number  = {1},
++  pages   = {13--39},
++  year    = {1997}
++}
++
++@article{neweywest1987,
++  author  = {Newey, Whitney K. and West, Kenneth D.},
++  title   = {A Simple, Positive Semi-Definite, Heteroskedasticity and Autocorrelation Consistent Covariance Matrix},
++  journal = {Econometrica},
++  volume  = {55},
++  number  = {3},
++  pages   = {703--708},
++  year    = {1987}
++}
++
++@article{pastor2021sustainable,
++  author  = {P{\'a}stor, {\v{L}}ubo{\v{s}} and Stambaugh, Robert F. and Taylor, Lucian A.},
++  title   = {Sustainable Investing in Equilibrium},
++  journal = {Journal of Financial Economics},
++  volume  = {142},
++  number  = {2},
++  pages   = {550--571},
++  year    = {2021}
++}
++
++@article{pastor2022dissecting,
++  author  = {P{\'a}stor, {\v{L}}ubo{\v{s}} and Stambaugh, Robert F. and Taylor, Lucian A.},
++  title   = {Dissecting Green Returns},
++  journal = {Journal of Financial Economics},
++  volume  = {146},
++  number  = {2},
++  pages   = {403--424},
++  year    = {2022}
++}
++
++@article{petersen2009,
++  author  = {Petersen, Mitchell A.},
++  title   = {Estimating Standard Errors in Finance Panel Data Sets: Comparing Approaches},
++  journal = {Review of Financial Studies},
++  volume  = {22},
++  number  = {1},
++  pages   = {435--480},
++  year    = {2009}
++}
++
++@inproceedings{reimers2019sbert,
++  author    = {Reimers, Nils and Gurevych, Iryna},
++  title     = {Sentence-{BERT}: Sentence Embeddings Using {Siamese} {BERT}-Networks},
++  booktitle = {Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing (EMNLP)},
++  year      = {2019}
++}
++
++@article{shiller2017narrative,
++  author  = {Shiller, Robert J.},
++  title   = {Narrative Economics},
++  journal = {American Economic Review},
++  volume  = {107},
++  number  = {4},
++  pages   = {967--1004},
++  year    = {2017}
++}
++
++@article{tetlock2007,
++  author  = {Tetlock, Paul C.},
++  title   = {Giving Content to Investor Sentiment: The Role of Media in the Stock Market},
++  journal = {Journal of Finance},
++  volume  = {62},
++  number  = {3},
++  pages   = {1139--1168},
++  year    = {2007}
++}
++
++@article{tetlock2008,
++  author  = {Tetlock, Paul C. and Saar-Tsechansky, Maytal and Macskassy, Sofus},
++  title   = {More Than Words: Quantifying Language to Measure Firms' Fundamentals},
++  journal = {Journal of Finance},
++  volume  = {63},
++  number  = {3},
++  pages   = {1437--1467},
++  year    = {2008}
++}
++
++@techreport{webb2020,
++  author      = {Webb, Michael},
++  title       = {The Impact of Artificial Intelligence on the Labor Market},
++  institution = {Stanford University Working Paper},
++  year        = {2020}
++}

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

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

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

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

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

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

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

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

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

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

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

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

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

++% ============================================================================
++\section{Results}
++\label{sec:results}
++% ============================================================================
++
++\subsection{Portfolio sorts: a weak unconditional relation}
++Table~\ref{tab:sorts} reports the quintile sorts over the full sample. The relation between AI
++disclosure and future returns is positive and broadly monotone but economically modest. The
++equal-weighted Q5$-$Q1 spread is $+4.6$ percentage points per year for AI adoption \tstat{1.83},
++$+3.9$ for AI infrastructure \tstat{1.58}, $+5.3$ for AI disruption risk \tstat{2.27}, and $+4.9$ for
++the composite \tstat{1.88}. Value-weighting attenuates the adoption and composite spreads, indicating
++the effect is stronger among smaller index members. The left panel of Figure~\ref{fig:quint} displays
++the full-sample pattern: returns rise gently from the lowest to the highest AI quintile. On its own,
++this is suggestive but far from decisive evidence---and, as we now show, it averages over two very
++different regimes.
++
++\input{tables/tab_sorts}
++
++\subsection{Does AI disclosure earn risk-adjusted alpha unconditionally? (H1)}
++Table~\ref{tab:alpha} reports CAPM and FF6 alphas of the long--short portfolios. The AI-opportunity
++composite earns a raw spread of about $+2.3\%$ per year, of which the FF6 alpha is $+1.9\%$---but
++statistically insignificant \tstat{1.24}. The AI-adoption and AI-infrastructure long--shorts are
++similarly insignificant after risk adjustment. The one exception is the AI-disruption-risk spread,
++whose FF6 alpha of $+2.8\%$ per year is marginally significant \tstat{2.10}, hinting at a small risk
++premium for firms that flag AI as a competitive threat. The factor loadings (not the focus here) show
++the AI long--short is roughly market-neutral with modest negative profitability (RMW) and investment
++(CMA) tilts, consistent with a growth-oriented long leg. The verdict on H1 is clear:
++\textbf{unconditionally, AI disclosure is at best weakly priced.} This is not the end of the story but
++the beginning of it.
++
++\input{tables/tab_alpha}
++
++\subsection{Panel and Fama--MacBeth estimates}
++Table~\ref{tab:panel} juxtaposes the two-way fixed-effects panel with the Fama--MacBeth estimator. The
++contrast is instructive. In the Fama--MacBeth (cross-sectional) regressions, the AI-adoption and
++AI-infrastructure premia are positive---$+1.3$ and $+1.6$ percentage points per standard
++deviation---with \textit{t}-statistics near 1.6--1.7, indicating a weak but positive cross-sectional
++premium on average. In the two-way fixed-effects panel, however, every AI coefficient collapses to
++essentially zero. Because firm fixed effects remove all permanent cross-firm differences, this tells
++us the signal lives \emph{across} firms, not \emph{within} them: a given firm writing relatively more
++about AI from one year to the next does not predict its own subsequent return (anticipating H4).
++Throughout, size carries the familiar negative premium ($t\approx-8$) and volatility a positive one,
++consistent with the broader cross-sectional literature in this large-cap universe.
++
++\input{tables/tab_panel}
++
++\subsection{The structural break: AI pricing switched on after ChatGPT (H2)}
++The full-sample averages mask a sharp regime change that is the paper's central result. Splitting the
++sample at the November 2022 ChatGPT launch, the center and right panels of Figure~\ref{fig:quint}
++reveal a striking transformation: the quintile pattern is nearly flat before 2022 and steeply
++increasing afterward. The high-minus-low composite spread is $+2.4$ percentage points per year
++pre-ChatGPT but $+14.6$ points per year post-ChatGPT---a more than sixfold increase.
++
++\begin{figure}[htbp]\centering
++\includegraphics[width=\textwidth]{fig1_quintile_returns.png}
++\caption{Mean forward twelve-month return by AI-disclosure composite quintile, full sample and by
++sub-period. The high-minus-low spread is $+2.4$ percentage points before ChatGPT and $+14.6$ points
++after.}\label{fig:quint}
++\end{figure}
++
++Table~\ref{tab:break} quantifies the break two ways. In sub-period sorts, the AI-adoption Q5$-$Q1
++spread rises from $+2.2\%$ per year \tstat{2.04} pre-2022 to $+14.3\%$ \tstat{2.15} post-2022; the
++composite rises from $+2.5\%$ to $+14.6\%$; AI infrastructure from $+1.4\%$ to $+13.6\%$. In the
++pooled interaction regressions, the post-2022 incremental slope is positive for all three signals and
++statistically significant for AI infrastructure \tstat{2.63}---the facet most directly tied to the
++chip, cloud, data-center, and power firms that led the 2023--2025 rally. Figure~\ref{fig:spread} shows
++the annual spreads: small and mixed-sign through 2021, uniformly large and positive for every
++post-2022 cohort.
++
++\input{tables/tab_break}
++
++\begin{figure}[htbp]\centering
++\includegraphics[width=0.9\textwidth]{fig3_annual_spread.png}
++\caption{Annual high-minus-low (Q5$-$Q1) forward-return spread on the AI-disclosure composite, by
++10-K fiscal year. Post-ChatGPT cohorts (red) are uniformly and substantially positive.}
++\label{fig:spread}
++\end{figure}
++
++The same regime change is visible in two further lenses. Figure~\ref{fig:cum} plots the cumulative
++value of one dollar invested in the equal-weighted, annually rebalanced, self-financing
++high-minus-low portfolio: it drifts sideways-to-up for a decade and then inflects upward after the
++dashed ChatGPT line. Figure~\ref{fig:fmyear} plots the year-by-year Fama--MacBeth slope on the AI
++composite (with controls): it hovers near zero for the entire 2010s and then turns sharply positive,
++peaking in the 2024 cohort. The latter figure also delivers an important nuance: the size-controlled
++premium is largest in the most recent cohort, consistent with the AI \emph{infrastructure}
++super-cycle of 2024--2025 (the build-out of data centers and accelerated compute). We return to this
++concentration when discussing limitations.
++
++\begin{figure}[htbp]\centering
++\includegraphics[width=0.86\textwidth]{fig2_cumulative_ls.png}
++\caption{Cumulative value of \$1 invested in the equal-weighted, annually rebalanced, self-financing
++high-minus-low AI-disclosure portfolio (AI opportunity composite and AI disruption-risk).}
++\label{fig:cum}
++\end{figure}
++
++\begin{figure}[htbp]\centering
++\includegraphics[width=0.9\textwidth]{fig6_fm_byyear.png}
++\caption{Year-by-year Fama--MacBeth slope on the AI-disclosure composite (forward return per
++cross-sectional standard deviation), controlling for size, momentum, and volatility. Bars are $\pm1$
++standard error.}\label{fig:fmyear}
++\end{figure}
++
++Finally, Figure~\ref{fig:bin} confirms the pattern is not an artifact of a few influential
++observations: the binned relation between the AI composite and forward returns is essentially flat in
++the pre-ChatGPT sub-period and distinctly upward-sloping afterward, across the entire distribution of
++AI disclosure rather than only at the extreme quintiles.
++
++\begin{figure}[htbp]\centering
++\includegraphics[width=\textwidth]{fig5_binscatter.png}
++\caption{Binned scatter of forward twelve-month return against the AI-disclosure composite, by
++sub-period. Each point is a portfolio of firms in a bin of the AI signal; the line is an OLS fit. The
++conditional slope steepens markedly after ChatGPT.}\label{fig:bin}
++\end{figure}
++
++\subsection{The anatomy of the premium: size and sector}
++Where in the cross-section does the post-2022 premium concentrate? Table~\ref{tab:doublesort} and
++Figure~\ref{fig:double} report an AI~$\times$~size double sort. Before 2022 the AI gradient is flat
++within both size halves. After 2022 it is steep, and dramatically so among smaller firms: small,
++high-AI firms earned a mean forward return of 34.6\%, versus 19.5\% for small, low-AI firms---a
++15-point gap---while the corresponding gap among large firms is 7 points. The premium is thus
++\emph{not} merely a mega-cap phenomenon (a point we reinforce in Section~\ref{sec:robustness}); if
++anything it is strongest among the smaller, less-followed names, consistent with an attention-based
++mechanism in which information diffuses more slowly into smaller stocks.
++
++\input{tables/tab_doublesort}
++
++\begin{figure}[htbp]\centering
++\includegraphics[width=\textwidth]{fig9_double_sort.png}
++\caption{AI-disclosure $\times$ firm-size double sort: mean forward twelve-month return by AI tercile
++within small and large firms, pre- and post-ChatGPT.}\label{fig:double}
++\end{figure}
++
++\subsection{Economic significance}
++The statistical break is matched by an economic one. The Sharpe ratio of the equal-weighted
++AI-composite long--short portfolio---a direct gauge of risk-adjusted attractiveness---rises from 0.15
++in the pre-ChatGPT decade to 1.33 afterward; for the AI-disruption-risk spread it rises from 0.33 to
++1.15. A Sharpe ratio above one is exceptional for a single-characteristic, self-financing equity
++strategy, and its emergence precisely at the ChatGPT boundary is hard to reconcile with a constant
++risk premium. The point estimates in the quintile sorts are equally vivid: a 14-point annual spread
++between the top and bottom AI quintiles is roughly three times the unconditional equity risk premium
++and an order of magnitude larger than the pre-2022 spread. Even acknowledging that a portion of this
++reflects the higher realized volatility of AI-exposed firms (documented in Section~\ref{sec:robustness})
++and the broad technology rally, the magnitude of the post-2022 re-rating is among the largest
++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.

spb/uqo-research-db

Theme