% Generated by code/make_tables.py from data/sections\_by\_form.csv, ledger\_by\_form.csv, mentions\_by\_form.csv, results/ledger/table3\_ledger\_vs\_stored.csv, ledger\_collisions.csv. Do not edit by hand.
\begin{table}[H]
\centering\scriptsize
\setlength{\tabcolsep}{3pt}
\caption{Parsed sections, extraction ledger, gate-passing calls and mentions, by form}\label{tab:sections}
\begin{threeparttable}
\begin{adjustbox}{max width=\textwidth}
\begin{tabular}{lrrrrrrrr}
\toprule
Form & \multicolumn{1}{c}{\makecell{Parsed\\sections}} & \multicolumn{1}{c}{\makecell{Median\\words}} & \multicolumn{1}{c}{\makecell{Ledgered rows\\($\geq 30$ words)}} & \multicolumn{1}{c}{\makecell{Gate-passing\\calls}} & \multicolumn{1}{c}{\makecell{Sections with\\$\geq 1$ mention}} & \multicolumn{1}{c}{\makecell{Mentions returned\\(ledger, before de-dup.)}} & \multicolumn{1}{c}{\makecell{Mentions\\stored}} & \multicolumn{1}{c}{\makecell{Issuers\\ledgered}} \\
\midrule
10-K & 341{,}207 & 875 & 143{,}704 & 135{,}310 & 30{,}877 & 81{,}622 & 81{,}495 & 2{,}464 \\
10-Q & 600{,}471 & 500 & 578{,}793 & 363{,}973 & 75{,}705 & 152{,}261 & 152{,}004 & 2{,}494 \\
8-K & 400{,}605 & 575 & 400{,}601 & 204{,}442 & 61{,}648 & 74{,}594 & 74{,}566 & 2{,}499 \\
\midrule
Total & 1{,}342{,}283 & & 1{,}123{,}098 & 703{,}725 & 168{,}230 & 308{,}477 & 308{,}065 & 2{,}499$^{\dagger}$ \\
\bottomrule
\end{tabular}
\end{adjustbox}
\begin{tablenotes}\footnotesize
\item ``Ledgered rows'' counts rows of the \texttt{extracted\_sections} ledger (parsed sections with at least 30 words; for 10-Ks restricted to the items of Table~\ref{tab:items}); the ledger records neither whether the candidate gate passed nor whether the API call succeeded, so it is not a count of calls. ``Gate-passing calls'' recomputes the candidate gate of Appendix~\ref{app:prompt} over the ledgered text: 703{,}725 sections reached the model and 419{,}361 were ledgered with zero mentions without a call (Table~\ref{tab:ledger_calls} splits them by run). ``Mentions returned'' is $\sum$\texttt{n\_mentions} over the ledger (308{,}477); ``Mentions stored'' is the row count of \texttt{project\_mentions} (308{,}065). The difference of 412 (10-K 127, 10-Q 257, 8-K 28), spread over 304 sections, is the number of mentions overwritten before storage because the mention identifier hashes the type and the first 40 characters of the project name (Section~\ref{sec:construct}); every count in the text uses the stored basis unless labelled ``ledger''. $^{\dagger}$Issuers with at least one filing of any form, not a column sum.
\end{tablenotes}
\end{threeparttable}
\end{table}