1\section{Results}2\label{sec:results}3\input{tables/numbers}4All numbers in this section are computed from the released per-attempt records by \texttt{src/wp30/analysis/analyze.py}; every table5cell and plotted point resolves to run identifiers through \texttt{results/provenance.json}. Quality is accuracy for the synthetic and6executable families and LongBench F1 for the public subsets; intervals are 95\,\% document-level cluster-bootstrap intervals; test7statistics follow the registered plan (Section~\ref{sec:protocol}). Scheduled core trials: \nCoreTrials.89\input{sections/results_frontier}10\input{sections/results_transfer}11\input{sections/results_handoffs}12\input{sections/results_fanin}13\input{sections/results_network}14\input{sections/results_hosted}15