Determinism in the Certification of UNSAT Proofs
This addresses trust issues in SAT solver verification for automated reasoning and formal methods, though it is incremental as it builds on existing certification approaches.
The paper tackled the problem of trustworthiness in SAT solver certification by proposing an extremely simplified certifier that eliminates the need for search, concluding that it can certify proofs of arbitrary size with restrictions on formats.
The search for increased trustworthiness of SAT solvers is very active and uses various methods. Some of these methods obtain a proof from the provers then check it, normally by replicating the search based on the proof's information. Because the certification process involves another nontrivial proof search, the trust we can place in it is decreased. Some attempts to amend this use certifiers which have been verified by proofs assistants such as Isabelle/HOL and Coq. Our approach is different because it is based on an extremely simplified certifier. This certifier enjoys a very high level of trust but is very inefficient. In this paper, we experiment with this approach and conclude that by placing some restrictions on the formats, one can mostly eliminate the need for search and in principle, can certify proofs of arbitrary size.