Introduces LP-anchored attribution for neural CO policies with CSP-certified counterfactuals and Bonferroni-PAC sufficient subsets, showing higher agreement with certified signals than gradient proxies on CVRPTW and OP.
The CP-SAT-LP Solver , booktitle =
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
LLM-generated combinatorial solvers achieve highest correctness when the model formalizes problems for verified backends rather than attempting to optimize search, which often causes regressions.
citing papers explorer
-
Constraint-Anchored Attribution: Feasibility-Certified Counterfactuals and Bonferroni-PAC Sufficient Subsets for Neural CO Policies
Introduces LP-anchored attribution for neural CO policies with CSP-certified counterfactuals and Bonferroni-PAC sufficient subsets, showing higher agreement with certified signals than gradient proxies on CVRPTW and OP.
-
Formalize, Don't Optimize: The Heuristic Trap in LLM-Generated Combinatorial Solvers
LLM-generated combinatorial solvers achieve highest correctness when the model formalizes problems for verified backends rather than attempting to optimize search, which often causes regressions.