spb/firc0001_uqo

1% Generated by code/make_tables.py from results/resolver/spec\_curve.csv, composition.json, ties\_idempotence.json, top\_name\_tokens.csv. Do not edit by hand.2\begin{table}[H]3\centering\scriptsize4\setlength{\tabcolsep}{3pt}5\caption{Specification curve of the project count over alternative resolution keys and confidence thresholds}\label{tab:spec_curve}6\begin{threeparttable}7\begin{adjustbox}{max width=\textwidth}8\begin{tabular}{lrrrrrr}9\toprule10Resolution key & \multicolumn{1}{c}{\makecell{Projects\\($\geq 0.45$)}} & \multicolumn{1}{c}{\makecell{Single-mention\\projects (\%)}} & \multicolumn{1}{c}{\makecell{Projects with\\$> 10$ mentions (\%)}} & \multicolumn{1}{c}{\makecell{Mentions\\per project}} & \multicolumn{1}{c}{\makecell{Cheniere\\cluster size}} & \multicolumn{1}{c}{\makecell{Projects\\($\geq 0.9$)}} \\11\midrule12Issuer $\times$ type (no location, no name) & 21{,}027 & 20.7 & 29.8 & 14.65 & 176 & 16{,}562 \\13Current key without the type & 96{,}749 & 52.6 & 5.0 & 3.18 & 11 & 70{,}174 \\14Issuer $\times$ type $\times$ name token (location ignored) & 114{,}244 & 56.4 & 3.7 & 2.70 & 40 & 78{,}834 \\15Current key (location, else name token) $\dagger$ & 121{,}099 & 60.2 & 3.1 & 2.54 & 8 & 83{,}483 \\16Current key, city-normalised locations & 123{,}246 & 56.8 & 2.8 & 2.50 & 8 & 86{,}347 \\17Current key, extended stop-word list & 130{,}101 & 59.1 & 2.5 & 2.37 & 8 & 91{,}918 \\18Issuer $\times$ type $\times$ two name tokens & 145{,}697 & 63.0 & 1.7 & 2.11 & 8 & 100{,}490 \\19Strict: full normalised name + location & 198{,}488 & 75.8 & 0.5 & 1.55 & 1 & 135{,}411 \\20No resolution (one project per mention) & 308{,}065 & 100.0 & 0.0 & 1.00 & 1 & 207{,}150 \\21\bottomrule22\end{tabular}23\end{adjustbox}24\begin{tablenotes}\footnotesize25\item Every key is applied to the same 308{,}065 stored mentions, rebuilt from \texttt{resolve.py} in a temporary table on the master node; $\dagger$ marks the key of the released \texttt{projects} table, whose identifier set is reproduced exactly. ``Cheniere cluster size'' is the number of projects formed by the mentions of the Table~\ref{tab:provenance} example. Thresholds drop mentions below the stated confidence before resolution. The project count is therefore a property of the key: 21{,}027--308{,}065 at the release threshold, and the single-mention share and projects-per-issuer statistics move with it. Under the current key 66{,}405 projects (54.8\%) are keyed on a name token because the mention has no location, 54{,}658 on a location and 286 on the fallback ``general''; the single token ``acquisition'' absorbs 40{,}407 mentions into 2{,}256 projects (Table~\ref{tab:top_name_tokens}). The stored table is not exactly reproducible: 33{,}820 projects have several mentions at the maximum confidence (\texttt{arg\_max} ties), and re-running the authors' SQL changes 394 representative names and 600 descriptions while reproducing every project identifier.26\end{tablenotes}27\end{threeparttable}28\end{table}29