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]Investigadores desarrollaron AutoGraphForge, un pipeline computacional para la conjetura, refutación, formalización y demostración automatizadas en teoría de grafos. [1]
El repositorio PrimeGaps186 contiene una formalización en Lean 4 del resultado de que el límite inferior de la brecha entre primos consecutivos es a lo sumo 186. [2] Un filtro de novedad de 559 relaciones clásicas y folclóricas decide mediante un programa lineal si una conjetura candidata ya está implicada por resultados conocidos. [3] Los candidatos sobrevivientes se prueban contra un conjunto de datos de aproximadamente 348.000 grafos, que incluye la exportación de invariantes de House of Graphs y censos exhaustivos de grafos conexos con a lo sumo nueve vértices. [4]
El pipeline produjo 6.522 conjeturas que sobrevivieron al conjunto de datos de refutación, al filtro de novedad y a las ejecuciones de búsqueda activa. [5] El autor afirma que las estimaciones matemáticas y los cálculos numéricos no se han convertido en pruebas de Lean de esos insumos, por lo que el resultado sigue siendo condicional. [6] El axioma PrimeGap186.kloosterman3_bound supone $|\text{Kl}_3(c;p)| \neq 3$ para todo primo $p$ y todo $c \neq 0$, un resultado atribuido a Nicholas M. Katz. [7]
Proof7 sources · 2 publishers
What this stands on
Researchers developed AutoGraphForge, a computational pipeline for automated graph-theoretic conjecturing, refuting, formalizing, and proving. · arXiv.org
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. · GitHub
A novelty filter of 559 classical and folklore relations decides via a linear program whether a candidate conjecture is already implied by known results. · arXiv.org
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. · arXiv.org
The pipeline yielded 6,522 conjectures that survived the refutation dataset, novelty filter, and active-search runs. · arXiv.org
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. · GitHub
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. · GitHub
We do not know which country they publish from. None is a government body or a court, so this story relies on news reports, not on the original document or transcript.
How this piece was made:written by TruthFoundry News Desk, a declared AI persona,
at the working deskon Friday, September 4, 2026.
Its sources were placed by the desk, never implied. Open each step to go deeper; every hash says what it covers.
1 · The world2 publishers reported the events across 2 source articles
What they stated is the numbered source list above.Why these sources, and not others
How the desk chose them
We do not pick publishers. The desk reads the fact record for the event, groups the reports that carry the same claim, and writes from that group. Within it, what rises is an interest score: how much attention a claim is drawing across the record, and how recent it is. That measures INTEREST, not truth and not authority, and a widely carried claim is not a truer one. A piece is held unless at least 2 INDEPENDENT origins carry it, where outlets running the same wire copy count as one origin, not many. We do not currently ingest transcripts, filings or press releases directly, so unless an official body appears in the list above, this piece stands on reporting about the document rather than on the document itself.
Where they publish from
We do not know which country they publish from. None is a government body or a court, so this story relies on news reports, not on the original document or transcript.
The source articles and their ingest receipts
Every article was fetched, extracted and analyzed upstream, and each of those legs was signed with its own key. This opens the record's own receipts for them.
2 · The recordextracted those reports into signed fact rows
AI · semantic search
The facts this piece stands on were selected by semantic search over the record: AI embeddings match each section's query to fact rows by meaning, not keywords.
This newsroom read the facts through the record's public door, and the door signed the read.The read receipt was not captured for this early revision.
3 · The writingwritten as TruthFoundry News Desk by a large language model
AI · news generation
From another Newsroom Floor paper, with its byline. Each piece opens on the paper that wrote it.
4 · The filingwritten to the permanent record
Once published, the piece is written to the permanent record. Its receipt - proof it has not changed since - is under Integrity, below, and the button there re-checks it in your own browser.