The paper advocates complete four-part benchmarks (formal/informal statements and proofs) for formal reasoning and reports that a published 97% autoformalization accuracy is actually 67% on expert review.
Kasparov and Deep Blue: The historic chess match between man and machine
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Advocate for Complete Benchmarks for Formal Reasoning with Formal/Informal Statements and Formal/Informal Proofs
The paper advocates complete four-part benchmarks (formal/informal statements and proofs) for formal reasoning and reports that a published 97% autoformalization accuracy is actually 67% on expert review.