Solver-aware training of a PBE decomposer with a frozen synthesizer's loss outperforms supervised imitation of ground-truth subgoals, solving tasks that a ground-truth decomposition oracle fails.
Synthesizing data structure transformations from input-output examples.ACM SIGPLAN Notices, 50(6):229–239, 2015
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.AI 1years
2026 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Solver-Aware Decompositions for Programming-by-Example: When Dividing Requires Knowing how to Conquer
Solver-aware training of a PBE decomposer with a frozen synthesizer's loss outperforms supervised imitation of ground-truth subgoals, solving tasks that a ground-truth decomposition oracle fails.