NOVA models the generate-verify-accumulate-retrain loop as adaptive sampling and proves that cumulative generation cost to obtain D genuine discoveries scales as Theta(c_gen D^alpha) under a Zipf tail-equivalence assumption with alpha greater than 1.
A language modelM t generates candidate proofs in a formal lan- guage (e.g., Lean 4)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
NOVA: Fundamental Limits of Knowledge Discovery Through AI
NOVA models the generate-verify-accumulate-retrain loop as adaptive sampling and proves that cumulative generation cost to obtain D genuine discoveries scales as Theta(c_gen D^alpha) under a Zipf tail-equivalence assumption with alpha greater than 1.