Generating Correctness Proofs with Neural Networks · HackerPapers discussions

Generating Correctness Proofs with Neural Networks — mentioned by aSanchezStern

Fri, 27 Oct 2023 18:52:58 GMT

Sounds like you've stumbled into the wonderful world of machine-learning guided proof synthesis! While I don't think the full system you're describing has been built yet, many similar systems and pieces have. In terms of the initial phase of supervised learning on existing proofs to prove new ones, there's TacticToe (https://arxiv.org/abs/1804.00596), Tactician (https://arxiv.org/pdf/2008.00120.pdf), CoqGym/ASTactic (https://arxiv.org/abs/1905.09381), Proverbot9001 (https://arxiv.org/abs/1907.07794), and Diva (https://dl.acm.org/doi/10.1145/3510003.3510138#sec-terms), among others. Most of…

Paper and discussion history. A mention is not an endorsement.

Generating Correctness Proofs with Neural Networks — mentioned by xvilka

Thu, 31 Oct 2019 17:26:12 GMT

Yes, it's already possible[1] with Coq. There are two strategies for that - lowering the CIC (Calculus of Inductive Constructions) to SMT[2] and employ SMT solvers like Z3, and employing Deep Learning[3][4]. For the Lean part, compared to Coq - there is an interesting discussion[5] why Lean might be not as good as they claim. [1] https://coq.discourse.group/t/machine-learning-and-hammers-f... [2] https://github.com/lukaszcz/coqhammer [3] https://arxiv.org/abs/1907.07794 [4] https://github.com/UCSD-PL/proverbot9001 [5] https://github.com/coq/coq/issues/10871

Paper and discussion history. A mention is not an endorsement.

Generating Correctness Proofs with Neural Networks — mentioned by nickpsecurity

Sat, 24 Aug 2019 18:20:42 GMT

Two more: https://arxiv.org/abs/1907.07794 https://arxiv.org/pdf/1904.03241.pdf

Paper and discussion history. A mention is not an endorsement.

Generating Correctness Proofs with Neural Networks — HN submission

Fri, 19 Jul 2019 15:28:28 GMT

Generating Correctness Proofs with Neural Networks

1 point; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.