SEPIA: Search for Proofs Using Inferred Automata

Abstract

This paper describes SEPIA, a tool for automated proof generation in Coq. SEPIA combines model inference with interactive theorem proving. Existing proof corpora are modelled using state-based models inferred from tactic sequences. These can then be traversed automatically to identify proofs. The SEPIA system is described and its performance evaluated on three Coq datasets. Our results show that SEPIA provides a useful complement to existing automated tactics in Coq.

To appear at 25th International Conference on Automated Deduction

References in corpus (1)

• Mining State-Based Models from Proof Corpora

Cited by in corpus (2)

• Proof Mining with Dependent Types
• ENIGMA: Efficient Learning-based Inference Guiding Machine