SparseBank: Sparse Measurement for Fixed Workflow Banks

SparseBank studies sparse measurement for selecting a fixed workflow bank and routing queries within it. On the Automated Programming Progress Standard (APPS), support-aware $G$-opt lowers routed regret against Uniform without replacement at 200 and 280 unique edges. The gain persists after matching unique counts and reflects support and weights jointly. Prospective CodeContests supports the preregistered primary $90/10$ $G$-opt–Uniform mixture against Uniform. The unchanged sampler is a secondary replication arm and performs better than the mixture. HumanEval+ marks a boundary: ordinary least squares (OLS) shows no stable acquisition advantage and loses to a development-set predictor. Supporting theory bounds completion error and its transfer to bank and routed regret for realizable linear models with fresh independent noise. A realized-design corollary covers outcome-independent acquisition with full rank. The real-task evidence concerns frozen observed tables; it does not certify expected fresh-execution utility.