Pay-per-call adjudication for trading research. No account, no
API key, no subscription — USDC on Base, priced per request.
What we do not sell. Money Mind has no proven trading edge and its own
realised P&L is negative. So we sell no signals, no forecasts, no market
analysis and no data. We sell the thing that killed our own ideas: a judge
that tells you whether a number is real. If that is not what you need, close
this page — we would rather lose the sale than the argument.
Why this judge is worth renting
0.020 vs 0.464Median |open−close|/range on the same FX pairs: a free feed against a real broker. Free feeds synthesise the bar's open instead of observing it, so anything that depends on the open was tested on a market that never existed.
39% vs 10%Real false-discovery rate of a strategy search in this repo, against the 10% it advertised — measured by shifting signals against price so the answer was known in advance.
1.9xHow much every t-statistic here was inflated by treating clustered signals as independent daily draws.
35Concepts this judge has killed, including every one we wanted to keep. The gates were built by losing, which is why they are worth renting.
Products
/referee
$5.00
11-gate adjudication of a trading signal series.
Use when you have OHLC bars and a -1/0/1 signal series and need to know whether a backtest result is real or an artefact. Applies 11 gates most backtests fail: matched random-entry drift control, date-clustered standard errors, entry at the next bar's open, events-not-fills, absolute (not just excess) return, slippage stress, walk-forward, overlap correction, financing, and a block bootstrap that must agree on both excess and absolute return. Returns CANDIDATE or REFUTED plus every blocking reason.
Is your OHLC real, or an indicative feed pretending to be.
FREE, no payment or account needed. Use BEFORE trusting any backtest, to check whether the price data itself is real. Free and indicative feeds frequently synthesise the bar's open instead of observing it, which pins |open-close|/range near zero; measured on the same FX pairs, a free feed reads 0.020 against a real broker's 0.464. Any result that depends on the open — gap trades, overnight holds, next-bar entries — is invalid on such data. Also reports frozen (zero-range) bars, duplicate and out-of-order timestamps, and bars whose high/low do not bracket open/close. Returns BROKER-GRADE, SUSPECT or INDICATIVE.
You tested N strategies and kept the best; is it noise.
Use when you searched many strategies or parameter sets and kept the best one. Quoting that winner's solo p-value is the most common way a backtest lies. Give the number of things you tested and the winner's t-statistic; returns the family-wise p-value, the t you actually needed, and the t that pure noise would be expected to hand you from a search that size.
Your t-stat assumes independence; your trades cluster.
Use when your trades are not independent — several in the same day, the same regime, or a correlated basket. A t-stat computed as if every trade were an independent draw is inflated; in this repo the factor was about 1.9x. Give per-trade returns and their dates; returns the naive t, the date-clustered t, the inflation factor, and how many genuinely independent days you actually have.
You tried N prompts/models/configs and kept the best; how much of that is selection.
FREE, no payment or account. Use when you picked the best of several prompts, models, configs or hyperparameters from an eval. Keeping the top scorer out of N is SELECTION, and the winner's score is inflated by having looked N times — every eval harness and prompt optimiser does this and reports the winning score as though one experiment were run. Give the score each variant achieved; returns how much of the winner's margin is explained by the search itself, the margin pure noise would have handed you, and whether the excess is real. Supply n_per_variant to also check whether your variants can be ranked apart at all.
The same pairs, the same hours, two feeds. On one, the bar's open sits where a real trade happened. On the other it is manufactured from the close — and the ratio that exposes it is one line of code.
Prompt optimisation has a selection problem nobody corrects for, and it is the same error that kills trading backtests. Here is how much of your winner's margin the search itself explains.
Two independent ways a backtest overstates itself, both invisible from inside the backtest, both measured here on our own research.
Buy with a card
Data Reality Check
$19
Is your price data real, or an indicative feed pretending to be? The cheapest question to answer and the one that invalidates everything else if you get it wrong.
One strategy, fully adjudicated — the data-quality audit, the multiple-testing correction, the clustering correction and all eleven gates, returned as one report.
For teams whose numbers must stay true, not just be true once. Unlimited data-quality and selection checks, plus 40 full 11-gate adjudications a month. Built for marketplaces verifying sellers, AI teams correcting best-of-N in weekly evals, and funds re-validating a book as data arrives.
For traders about to risk real capital. Everything in the audit, across up to 12 instruments — a verdict per instrument and the exact reason for every gate that blocks it, before you fund anything.
You are redirected straight to your report page after paying. Submit your data there and the report is stored against your purchase, so you can come back to it any time.
Pay per call (developers & agents)
Every endpoint speaks x402 — call
it, get HTTP 402 with the payment requirements, sign a USDC authorization,
call again. Any x402 client works. A GET is free and returns the
full spec, so you can see exactly what you get before paying anything.
# see what it does — free
curl https://money-mind-e3yv.onrender.com/dataquality
# call it — returns 402 with payment requirements
curl -X POST https://money-mind-e3yv.onrender.com/dataquality \
-H 'Content-Type: application/json' \
-d '{"bars": {"EURUSD": [ ...your OHLC... ]}}'