Not correct. Checkable.

Take a numerical claim someone already believes — from a language model, from a published paper, or from my own draft — and either produce an interval that provably contains the true answer, together with the program that produced it, or report that the method did not reach one and stop there.

Much of the recent work is verification of machine-generated mathematics: AI-claimed results re-checked in independent arithmetic, each check first shown to fail on a deliberately broken copy of itself. The tools are interval arithmetic with outward rounding, exact rational arithmetic — BigInt on one side, standard-library fractions on the other — Sturm chains, and contraction arguments of the Krawczyk kind.

I work alone, from Brazil.

• The program, not a description of it. Every page is generated from the records it cites, and the repository — engine, instruments, certificates, corpus — is public under MIT with no dependencies. The detached verifiers run in the Python standard library: the next person to extend one needs neither my permission nor my machine.
• Proof that the check can fail. A check that has never gone red is decorative — consistent with the code being right, and equally consistent with the check testing nothing. So every battery carries red controls, deliberate forgeries that must be caught, and every instrument is calibrated against a case with a known answer before it decides anything new.
• The errors, dated, in public. Refuted claims are published with their generating mechanism named, and the machine’s own defects are recorded the same way. Every real bug this project has found was caught by a control, a calibration, or an impossible number — none by reading code.

Everything here is self-published and self-checked, so the honest question is what happens when it leaves. The record, with the status words meant exactly:

• Submitted, awaiting moderation. A correction to a GPT-published constant on Erdős #852 — refuted at its 12th significant digit, certified replacement attached — posted to the problem’s discussion thread on erdosproblems.com.
• Filed, 5 August 2026 — no reply yet. An independent confirmation of the computational appendix of a claimed proof of Erdős #1038, filed as an issue on the claiming authors’ own repository: all 30 printed decimals verified by a different route — Krawczyk rather than bisection.
• Posted, 4 August 2026 — no reply yet. An evaluation note on Anthropic’s public automated-alignment sandbox, posted as an issue on the repository whose authors invited stress-testing.
• Submitted, awaiting moderation. A note on Erdős #290 to erdosproblems.com; the constant’s decimal expansion is also an OEIS submission, posted 4 August 2026, unanswered.

Filed is not accepted; posted is not replied. No result on this site has yet been reproduced by anyone else, and none has been peer-reviewed. That is the plain state of it, and it is why the pages ship their own falsifiers rather than asking for trust.

No employment history, no degrees, no years-of-experience figure, no self-rated skills. Each of those is a claim a reader would have to take on trust, and putting them beside claims that can be re-run devalues the second kind. If a process needs a conventional CV, ask and you will get one.

The mathematics, the design of every check, and the decision about what may be claimed are mine. The writing and much of the implementation are done with AI assistance, under the discipline this site describes: a screen may only prune, a gate counts only once it has been shown to go red on a broken copy, and every page recomputes its numbers from the records at build time — a build that drifts refuses to ship. The output rate is a consequence of that arrangement, and saying so seems better than letting a reader wonder.

The code and the checks on it share one author, so they rule out slips but not a shared misconception. An independent recomputation of any result here — in whatever you already trust — is the thing this site most wants, and a refutation gets published like any other result, with the name of whoever found it if they want it there.

carlos@carlostoledo.co — corrections, questions about a step, collaboration. A message that names the page and the one step it doubts can be answered properly; a general introduction usually cannot.