% generated by tables/make_tables.py from ./results/bibliometrics/indexing_lag.csv
\begin{table}[htbp]\centering\caption{The OpenAlex \texttt{created\_date} relative to the publication date, by publication year.}\label{tab:indexing_lag}
\begin{threeparttable}\small
\begin{tabular}{lrrrrr}
\toprule
\textbf{Year} & \textbf{Works} & \textbf{Lag, Jan. (d)} & \textbf{Lag, June (d)} & \textbf{Within 90 d (\%)} & \textbf{After 180 d (\%)} \\
\midrule
2018 & 642{,}849 & 2839 & 2678 & 4.2 & 95.2 \\
2019 & 695{,}369 & 2474 & 2313 & 4.6 & 94.6 \\
2020 & 709{,}083 & 2109 & 1946 & 5.3 & 94.0 \\
2021 & 711{,}244 & 1743 & 1577 & 6.2 & 93.0 \\
2022 & 699{,}548 & 1378 & 1212 & 7.1 & 92.1 \\
2023 & 785{,}194 & 1013 & 847 & 6.7 & 92.7 \\
2024 & 901{,}654 & 648 & 480 & 6.0 & 93.4 \\
2025 & 1{,}065{,}828 & 282 & 121 & 36.4 & 41.0 \\
2026 & 901{,}651 & 112 & 2 & 80.5 & 9.0 \\
\bottomrule
\end{tabular}
\begin{tablenotes}\footnotesize\item Lag is created\_date minus publication date; the two lag columns give the median lag in days for works published in January and in June of the year; the last two columns give the shares of the year's works whose record was created within 90 days and after 180 days of publication. The near-constant decline of the median by one month per publication month in 2018--2024 identifies a single creation date for most records (a re-ingestion), not an indexing delay; see Part III.\end{tablenotes}
\end{threeparttable}\end{table}