Methods · free, forever, no email wall
Everything we know, published.
Democratized intelligence should mean democratized methods. Every gate, prompt, protocol, and agent architecture we use is public. You can run our entire loop without us, and we would rather you did.
The loop
What we actually do
Label every claim PROVED, VERIFIED, OPEN, CORRECTED, or REFUTED. Exact arithmetic. Errata filed the day an error is found. Nothing ships untagged.
Independent checkers with uncorrelated failure modes. A chain is only as calibrated as its weakest link; correlated checkers do not add up. Twelve families at ρ ≈ 0.2 behave like about four independent ones — we design for that, and we say so.
Attack the argument until it breaks or survives. Treat a surviving claim as evidence, not proof, and name what would falsify it.
Publish the entries that went against you. A method that only reports successes is a method for producing successes, not truths. Ours is here.
When you cannot evaluate the content, evaluate the process. Gates, track records, calibration, audit trails — and the theorems governing when a chain of deference is rational at all.
All of the above, wired together and downloadable. Take one.
Our moat isn’t secrecy. It’s a public track record of being right, and of saying so when we weren’t.
Calibration
The Solonic Scale (0–10)
A calibrated scale for academic quality. Not a grade — a location on a distribution.
Grad student work — competent but unpublishable. Demonstrates understanding without advancing knowledge.
Barely publishable in conference proceedings. A real contribution, but incremental and narrowly scoped.
Good collection — publishable in a decent journal. Solid work that moves the conversation forward.
Mean for a good peer-reviewed journal. Genuine contribution to the literature, well-executed.
Mean for the best journals — Nature, Science, Annals of Mathematics. Outstanding work that shapes a field.
Nobel / Fields / Pulitzer level contribution. Transformative, once-in-a-generation work.
The scale is deliberately sparse between anchor points. There are no 8.5s — you jump from the best journals to world-changing.
Five Dimensions
Every Jürge review scores these five dimensions independently.
Are the claims true? Are the proofs valid? Are the data real? This is the gate — everything else is downstream.
Is this new? Does it advance the field? Incremental extension of known results scores low; genuine new technique scores high.
Can a competent reader follow the argument? Notation defined before use. Logical flow without gaps. Readable prose.
Does this matter? To whom? A correct, novel result that no one cares about scores high on the first two and low here.
Could someone replicate this work? Data available, code linked, experimental conditions specified, proofs complete.
If you’d rather be taught
Classes
We teach the whole loop — generation, gates, ledger discipline, errata practice — to teams who want to run it themselves. Cohorts are small and scheduled by demand. Write to us and say what you work on.