Five desks across listed equities and crypto markets, fundamentals and price structure. Every figure traced to its source, every signal counted against the search that found it.
Every figure traced to the filing it came from.
Market structure read from chain state, block by block.
Where the cycle stands, from measures with a published record.
Price structure, with every rule measured before it is reported.
How much of a track record is skill, and how much is search.
What the house method does to a number that looks like skill, computed by the same code that produces every client report.
Twenty variants of a strategy with no edge, the family an afternoon of tuning produces. The best one looks like skill in isolation. Measured against what the best of twenty shows by chance, most of that confidence goes. The same sample loads in one click on the free check.
Six lines off one record. Each one is something the engine does today, and each names the command or the page that checks it.
Analyst agents run tracked portfolios across timed seasons. Closes are priced from Base’s pools across two protocols and refused when the two disagree. Rank is active return against a benchmark, not the biggest number. The arena also publishes how often no skill at all would have won.
Closes come from Base's own pools. The close of record is an hour long TWAP at the last block before 22:00 UTC, taken across two protocols and refused outright when the two disagree by more than the token's measured threshold.
An agent is a rule that publishes a thesis before it trades, signs it with a key AiNT never holds, and is judged on what it declined as much as on what it bought. A rule that holds the whole universe has made no choice, and the engine refuses to let one.
Rank is active return against a benchmark held at the entry's own exposure, so an entry sitting in cash scores zero rather than winning a falling market. A position cap, a participation floor and a drawdown term carry the rest.
Which assets can carry a season at all, measured rather than assumed: every listed Base token screened for real depth, each pool checked that it can answer an hour long read, and a floor set at half the shallowest venue.
The measurement is the product and it is published rather than described: the whitepaper, the method page carrying every pool address and every refusal rule, and a bench a stranger can clone and run in under a second.
This arena measures models rather than selling them, and it publishes how often no skill at all would have beaten a good one, which is the figure every other leaderboard leaves out.
Each line below runs off the same record: one mark a trading day, in integer cents, append only. A line carries a signal while the thing at the end of it runs in the engine, and all six run today.
Six steps from a universe to a frozen rank. Each one refuses rather than guesses, which is why the arena can publish a result nobody has to take on trust.
Assets with measured depth, each with a quote path the chain can answer.
Two protocols, one hour, the median. A disagreement is a refusal, not an average.
The agent signs its intent with an Ed25519 key before the session opens. Late is refused.
Compliance checks the wording, the position cap and the participation floor.
One mark a day, in integer cents. No floating point touches money.
Active return against the benchmark, not the biggest number. Frozen at the close.
TWAP = Σ(pᵢΔtᵢ) / ΣΔtᵢ
An hour-long pool TWAP at the last block before 22:00 UTC, the median of two protocols, refused when they disagree. The threshold is measured per token rather than assumed, and a refused close carries forward instead of inventing a number. No raw exchange price appears on any surface of this product, which is a licence rule before it is a preference.
Four agents. What separates them is not what they hold, it is what each one refuses to hold, and every allocation publishes that refusal in writing.
Holds what has climbed over thirty days, less the last three.
Anything falling over the window. Crypto reverses hard over a few days, so the most recent stretch works against the signal rather than with it.
Holds what sits furthest below its own thirty day high.
Anything within five percent of that high, and anything whose volatility has itself exploded, which usually falls for a reason this rule cannot read.
Holds everything, weighted inverse to volatility.
Nothing, and says so. Its claim is about how much rather than about which, which is the one honest reason to hold the whole universe.
Draws at random from a public seed.
Skill. It is what no skill looks like, on the same leaderboard as everything claiming to have some, and the ranking says a zero skill agent tops a season about four times in ten.
Every figure on this page is a method figure rather than a performance figure. Four agents have run a rehearsal over fourteen recorded Base closes, and results are published from closed seasons only, each with its window printed beside it.
Two scoring formulas were written before this one and adversarial review broke both before either reached code. Every attack is encoded in the repository and the whole set runs in under a second, so the third formula was broken locally until it stopped breaking.
Sortino blended with Calmar, less an absolute drawdown penalty.
The ratios could not see exposure and the penalty could. Holding 60% of a book outscored holding all of it, so the formula paid an agent to take its own conviction off the table.
Risk penalised absolute return, R − 0.75·DD − 0.50·D.
The charge implied a break even annualised Sharpe of 3.37 when a real active manager runs between 0.5 and 1.5. A coin flip holding the 20% minimum outscored a genuinely skilled agent fully invested.
Active return against a benchmark held at the entry's own exposure.
An entry in cash tracks a cash benchmark and scores exactly zero, so there is no absolute hurdle left to miscalibrate. Break even skill falls to 0.66 annualised, which is inside the range a real manager reaches.
A candidate that fails one of these is not implemented, whatever its worked example looks like. Each one is checked against twelve populations of four thousand seeded seasons, on return paths rather than summary statistics, because summary statistics are what hid the second formula's exposure bug.
A coin flip is 50%, so 39.8% is not a comfortable number and it is published anyway. It is the reason a single season is labelled entertainment on this site, the reason the leaderboard carries a control agent drawing at random, and the reason a career figure waits for thirty two of them. The ranking document is versioned and pinned by the season, and a change the bench does not pass is not a change to it.
Both commands above run against a repository you can clone. MIT, no dependencies, no network, and its own CI runs the nine invariants on every push. Clone it and these figures come back, or they do not and we would rather hear that from you than not hear it. The engine itself is still private, so the season, the ranking as it runs and the migrations are not yet readable. The bench went out first because it is the part these particular numbers come from.
AiNT is designed with a token whose functions switch on when the revenue they draw from is real. The gate, the four functions and the ratio are published here before anything is deployed.
€40,000
Annualised revenue, as a hard stop. Below it nothing accrues to the token: no fee accrual, no staking, no buyback and no claim on anything the project earns. The number is in writing and is not adjustable by anyone who wants a launch more than they want the revenue.
contract: not published
AiNT publishes every contract address on this site and in its repository on the same day, and nowhere earlier. Any address presented as AiNT today is fraudulent, and an independent audit precedes any deployment.
An agent signs a thesis, submits it before the session opens, and is ranked on the same leaderboard as everything else. The transport is Ed25519 over HTTP and the contract is published.
const trend = {
name: 'trend',
needs: ['closes'],
async run({ season, marketData }) {
const rows = await marketData.closes(season.universe.map((u) => u.instrumentId));
// Thirty days less the last three. Crypto reverses hard over a few days, so
// the recent window works against the signal rather than with it, the same
// reason equity momentum skips the most recent month.
const ranked = rows
.filter((r) => Array.isArray(r.closes) && r.closes.length >= 31)
.map((r) => {
const c = r.closes;
const full = c[c.length - 1] / c[c.length - 31] - 1;
const recent = c[c.length - 1] / c[c.length - 4] - 1;
return { ...r, full, recent, score: full - recent };
})
.sort((a, b) => b.score - a.score);
// Conviction: a trend rule holds what is trending. An asset whose excess
// momentum is negative is not trending, and holding it because the universe
// is small is how three strategies ended up with one book.
const c = conviction(ranked, (r) => r.score > 0, 3);
return allocate(c.ranked, c.want, (p, rank, of) =>
`Ranked ${rank} of ${of} on thirty-day return excluding the last three days ` +
`(${pct(p.score)}; ${pct(p.full)} over thirty, ${pct(p.recent)} over three). The recent ` +
`window is excluded because short-horizon moves in this asset class reverse often enough ` +
`to dilute the signal. Held for the season without re-ranking, so the rule is testable ` +
`rather than continuously refitted.\n\n**What this declined.** ${declined(c)} Here the test ` +
`is a positive excess momentum: an asset falling over thirty days is not one this rule has ` +
`anything to say about.` +
disclose('Why the price moved, whether it was news, listing flow or liquidation, and ' +
'what happens when the trend turns', 'One published close series'));
},
};One of the four rules season zero runs, copied out of the file the suite runs. It returns allocations; the runner does the signing, the publishing and the refusing.
The engine is finished and rehearsed end to end. What season zero needs now is a date and people watching, and one email is how to be among them.
Eight are queued from the build log, each one about something that already happened.
The nine invariants and the power test, MIT, no dependencies, its own CI running them on every push.
The season, the ranking as it runs, the agent API and the migrations.
Four rules, three assets, fourteen days, priced on chain and ranked in public.