spb/firc0001_uqo
Public
1% ============================================================================2% UQO Working Paper Template — Economics / Finance3% ============================================================================4\documentclass[12pt,letterpaper]{article}56% --- Encoding & Language ---7\usepackage[utf8]{inputenc}8\usepackage[T1]{fontenc}9\usepackage[english]{babel}1011% --- Page Layout ---12\usepackage[13 letterpaper,14 top=1in,15 bottom=1in,16 left=1in,17 right=1in18]{geometry}1920% --- Typography ---21\usepackage{mathptmx} % Times-like font (text + math)22\usepackage{microtype} % Improved typographic refinements23\usepackage{setspace}24\onehalfspacing % 1.5 line spacing2526% --- Math ---27\usepackage{amsmath,amssymb,amsthm}2829% --- Tables ---30\usepackage{booktabs}31\usepackage{tabularx}32\usepackage{multirow}33\usepackage{threeparttable}34\usepackage{siunitx}35\usepackage{makecell} % multi-line column headers of the generated tables (code/make_tables.py)36\sisetup{37 input-symbols = {()},38 table-format = -1.3,39 parse-numbers = false40}4142% --- Figures ---43\usepackage{graphicx}44\usepackage{subcaption}45\usepackage{float}4647% --- Colors & Links ---48\usepackage[dvipsnames]{xcolor}49\usepackage[50 colorlinks = true,51 linkcolor = NavyBlue,52 citecolor = NavyBlue,53 urlcolor = NavyBlue,54 breaklinks = true55]{hyperref}56\usepackage[capitalise,noabbrev]{cleveref} % \cref/\Cref in the Stage E prose (loaded after hyperref)5758% --- Bibliography ---59\usepackage[authoryear,round,semicolon]{natbib}60\bibliographystyle{aer}6162% --- Captions ---63\usepackage[64 font = small,65 labelfont = bf,66 labelsep = period,67 justification = justified,68 singlelinecheck = false69]{caption}7071% --- Headers & Footers ---72\usepackage{fancyhdr}73\pagestyle{fancy}74\fancyhf{}75\renewcommand{\headrulewidth}{0pt}76\fancyfoot[C]{\thepage}7778% --- Section Formatting ---79\usepackage{titlesec}80\titleformat{\section}{\large\bfseries}{\thesection.}{0.5em}{}81\titleformat{\subsection}{\normalsize\bfseries}{\thesubsection.}{0.5em}{}82\titleformat{\subsubsection}{\normalsize\itshape}{\thesubsubsection.}{0.5em}{}8384% --- Appendix Support ---85\usepackage[toc,page]{appendix}8687% --- Misc ---88\setlength{\emergencystretch}{3em}89\usepackage{enumitem}90\setlist{nosep,leftmargin=*}91\usepackage{longtable}92\usepackage{tikz}93\usetikzlibrary{positioning,arrows.meta,shapes.misc}94\usepackage{pdflscape}95\usepackage{adjustbox}96\usepackage{makecell} % multi-line column headers of the generated tables (code/make_tables.py)97\usepackage{upquote} % straight quotes in verbatim (extraction contract, gate regex)98\usepackage{listings} % \lstinputlisting (breaklines) of the inter-revision patches (Appendix, results/runs/*.patch)99\lstset{basicstyle=\ttfamily\scriptsize, breaklines=true, breakatwhitespace=false, columns=fullflexible, keepspaces=true, frame=none, xleftmargin=0pt}100% Notes under an adjustbox-scaled table: threeparttable measures the unscaled tabular, so its tablenotes overflow;101% widenotes sets the notes in a \textwidth minipage and accepts the \item of the generated *_note.tex fragments.102\newcommand{\widenotesitem}{\par}103\newenvironment{widenotes}{\par\vspace{3pt}\begin{minipage}{\textwidth}\footnotesize\setlength{\parindent}{0pt}\let\item\widenotesitem}{\end{minipage}}104\input{tables/numbers} % generated inline-number macros (code/make_tables.py); never edit by hand105\input{sections/numbers_pending} % PROVISIONAL \providecommand macros for Stage D audit numbers not yet emitted by the generator (Agent 10); each line names its results/ source106107% ============================================================================108% METADATA — Edit these fields for each working paper109% ============================================================================110\newcommand{\WPnumber}{0001}111\newcommand{\WPtitle}{From Corporate Disclosures to a Russell~3000 Strategic Project Database}112\newcommand{\WPsubtitle}{Identification, Measurement, Validation, and Research Applications}113% Stage E (2026-11-05), FIRC0001-THEO-18 / cluster I: the Chief Editor noted that "Identification" in the114% subtitle reads as econometric identification to a finance audience and that the estimand is a Russell 3000115% proxy (iShares IWV holdings). Proposed alternative, NOT imposed (author decision):116% \newcommand{\WPsubtitle}{Construction, Measurement, Validation Status, and Research Applications}117% The title is unchanged; the abstract and Section 3 state the proxy explicitly.118\newcommand{\WPdate}{November 2026}119\newcommand{\WPversion}{1.1 (revised after peer review; research database under validation)}120\newcommand{\WPfunding}{Research funded by the FIRC (Fonds institutionnel de recherche et de création), Université du Québec en Outaouais.}121\newcommand{\WPabstract}{%122 Can strategic projects be identified, classified, dated and linked across the SEC filings of a broad cross-section of U.S.-listed issuers? We document SPID, a project-level research database built for a Russell~3000 proxy (iShares IWV holdings, \SPIDrussellDistinctCiks\ of \SPIDrussellIndexConstituents\ index constituents) merged with the S\&P~500: \SPIDfilingsTotal\ Forms 10-K, 10-Q and 8-K of \SPIDuniverseN\ registrants filed since 2010, segmented into \SPIDsectionsTotal\ sections, of which \SPIDgatePassTotal\ reached a large-language-model extractor in JSON mode. The output is \SPIDmentions\ section-linked candidate mentions and \SPIDprojectCountCurrentKey\ candidate projects under the current resolution key (\SPIDprojectsKeyTypeDropped--\SPIDprojectsKeyStrict\ under alternative keys). Mechanical audits find \SPIDgroundAllPct\% of structured fields verbatim in the source section, a median \SPIDmdnaShownMedianPct\% of a 10-K MD\&A shown to the model, and \SPIDfinMentionsPct\% of mentions describing financing instruments. Precision and recall against human labels are not yet measured; the annotation frame is delivered. SPID is a research instrument under validation, not a census of projects.%123}124\newcommand{\WPkeywords}{SEC filings, text as data, corporate investment, strategic projects, information extraction, large language models, entity resolution, Russell 3000, measurement validation}125\newcommand{\WPjel}{C55, C81, G31, G38, M41, O33}126127% --- Authors (order, affiliations and contributions to be confirmed by the team; see docs/contributions.md) ---128\newcommand{\WPauthor}{Manel Kammoun \quad Djerrycharli Tandjambianda \quad Simon-Pierre Boucher}129\newcommand{\WPaffiliation}{%130 Département des sciences administratives\\131 Université du Québec en Outaouais%132}133\newcommand{\WPemail}{%134 \href{mailto:manel.kammoun@uqo.ca}{manel.kammoun@uqo.ca} \,\textperiodcentered\,135 \href{mailto:djerrycharli.tandjambianda@uqo.ca}{djerrycharli.tandjambianda@uqo.ca} \,\textperiodcentered\,136 \href{mailto:simon-pierre.boucher@uqo.ca}{simon-pierre.boucher@uqo.ca}%137}138\newcommand{\WPaddress}{%139 Gatineau -- Pavillon Alexandre-Taché\\140 283, boulevard Alexandre-Taché\\141 Gatineau, Québec, Canada J9A 1L8%142}143144% --- PDF metadata (Part X.3) ---145\hypersetup{146 pdftitle = {\WPtitle: \WPsubtitle},147 pdfauthor = {Manel Kammoun; Djerrycharli Tandjambianda; Simon-Pierre Boucher},148 pdfsubject = {UQO Working Paper No. \WPnumber, version \WPversion. JEL: \WPjel},149 pdfkeywords = {\WPkeywords}150}151152% ============================================================================153% DOCUMENT154% ============================================================================155\begin{document}156157% --- Title Page ---158\input{sections/titlepage}159160% --- Main Body ---161\input{sections/introduction}162\input{sections/literature}163\input{sections/data}164\input{sections/methodology}165\input{sections/construct}166\input{sections/resolution}167\input{sections/results}168\input{sections/validation}169\input{sections/applications}170\input{sections/conclusion}171172% --- References ---173\newpage174\bibliography{references}175176% --- Appendix ---177\input{appendix/appendix}178179\end{document}180