● the trust layer

Don't trust us. Verify us.

Every public claim AtlasVector makes seals to one tamper-evident audit chain — the head-to-head benchmark, the long-horizon agent leaderboard, and the self-falsified house verdicts all re-derive from a single sha256 root. Re-walk the chain yourself.

✓ Audit chain intact
4,474 sealed events re-walked · 0 hash breaks
raw JSON →
Three public proofs · one chain
Do the model's stated odds match reality?

The reliability diagram — predicted vs realized hit probability. We bin every served prediction by the probability the model assigned it, then plot that bin's mean predicted probability against how often the call actually landed. A well-calibrated model's predicted probabilities match realized frequencies, so its dots sit on the diagonal. Overconfidence shows as dots below the line; underconfidence, above it.

0%25%50%75%100%0%25%50%75%100%perfect calibrationpredicted probabilityrealized frequency
Accumulating — not enough graded predictions yet
A calibration curve is only meaningful over enough matured, graded predictions. We draw no curve until the model has served at least 100.
0 / 100 graded predictions
raw JSON →
We grade our own risk model

The VaR backtest — Basel's traffic-light test applied to our own engine. Every day the risk desk makes a 99% one-day Value-at-Risk forecast; the next day the book realizes a P&L. An exception is a realized loss worse than the forecast. Over a rolling 250-day window you expect ~2.5 exceptions: ≤4 green, 5–9 yellow, ≥10 red. Kupiec (coverage) and Christoffersen (independence) tests back the light. This is glass-box applied to our own risk numbers — we grade ourselves in public.

Accumulating — not enough real forecast/outcome pairs yet
A Basel traffic-light zone is only meaningful over a full 250-day window of real (VaR forecast, realized next-day P&L) pairs. The engine has only just begun logging daily forecasts, so we draw no zone yet. Nothing — not an exception, not a zone — is fabricated in the meantime.
0 / 250 settled days · 0 exceptions so far (running tally, not yet a Basel verdict)
raw JSON →
Why this can't be faked

One root, not three claims

Benchmark, leaderboard, and verdicts share one chain. You can't fabricate a track record retroactively without breaking every downstream hash.

It attacks itself

The agent runs a RED-TEAM desk and a self-falsification gate on its own conclusions, and we publish the catch-rate.

Independently verifiable by any party

Every proof surface ships a /verify endpoint. The numbers aren't "trust the vendor" — they're recompute-and-check.

Data provenance

Market data is real-time for stocks, ETFs, indices and crypto; illustrative figures are labeled as such. The reasoning structure and the cryptographic seal are always real.