Researchers developed AutoGraphForge, a computational pipeline for automated graph-theoretic conjecturing, refuting, formalizing, and proving. ^[1] The repository PrimeGaps186 contains a Lean 4 formalization of the result that the limit inferior of the gap between consecutive primes is at most 186. ^[2] A novelty filter of 559 classical and folklore relations decides via a linear program whether a candidate conjecture is already implied by known results. ^[3] Surviving candidates are tested against a dataset of about 348,000 graphs, which includes the House of Graphs invariant export and exhaustive censuses of connected graphs on at most nine vertices. ^[4] The pipeline yielded 6,522 conjectures that survived the refutation dataset, novelty filter, and active-search runs. ^[5] The author states that the mathematical estimates and numerical computations have not been turned into Lean proofs of those inputs, meaning the result remains conditional. ^[6] The axiom PrimeGap186.kloosterman3_bound assumes $| ext{Kl}_3(c;p)| eq 3$ for every prime $p$ and all $c eq 0$, a result attributed to Nicholas M. Katz. ^[7]