% Generated by code/make_tables.py from data/filings\_by\_form.csv, data/parse\_status.csv, data/stats.json, results/universe/filings\_status\_missing.csv. Do not edit by hand.
\begin{table}[H]
\centering\small
\caption{Filings in the corpus by form, 2010-01-04 to 2026-10-27}\label{tab:filings}
\begin{threeparttable}
\begin{tabular}{lrrrrrr}
\toprule
Form & Filings & First filing & Last filing & Raw HTML (GB) & Parser error & Missing on disk \\
\midrule
10-K & 31{,}775 & 2010-01-08 & 2026-10-27 & 88.6 & 2 & 1 \\
10-Q & 95{,}167 & 2010-01-05 & 2026-10-27 & 155.9 & 11 & 1 \\
8-K & 400{,}606 & 2010-01-04 & 2026-10-27 & 10.0 & 1 & 0 \\
\midrule
Total & 527{,}548 & 2010-01-04 & 2026-10-27 & 254.5 & 14 & 2 \\
\bottomrule
\end{tabular}
\begin{tablenotes}\footnotesize
\item Primary documents of Forms 10-K, 10-Q and 8-K retained from the SEC submissions index of every issuer of Table~\ref{tab:reconciliation}. ``Parser error'' counts documents whose primary document could not be cleaned; ``missing on disk'' counts documents logged as downloaded but not found at parse time. Raw HTML size is the sum of primary-document sizes recorded at download time. The 14 parser errors and 2 documents logged as downloaded but absent on disk are listed by accession number in \texttt{results/universe/filings\_status\_missing.csv} (parser errors: BJRI, NEWT, NNN, UNP; missing: XEL 10-K 2014, LNT 10-Q 2012).
\end{tablenotes}
\end{threeparttable}
\end{table}