Descriptive record — not a forecast. This page records what our liquidation map showed before this cascade (snapshot timestamps shown), what then happened on our multi-venue tape, and the model's measured historical record as it stood before the event. Every accuracy figure carries its sample size and a Wilson 95% lower bound. It does not predict future price moves and does not claim the model forecasts when a cascade will start.
Cascade Autopsy: XAU — 2026-07-10
2026-07-10T01:44:15Z → 01:53:56Z UTC · generated 2026-07-20T19:39:01Z · artifact 2026-07-10T0144-XAU
What happened
Venues
binance, bitmex, bybit, hyperliquid, kraken_fut, okx
Direction
predominantly LONG liquidations (66% of events) — price fell
| Symbol | Liquidated | Events | Share |
|---|
| XAUUSDT | $370.6M | 1 | 93.1% |
| BTCUSDT | $13.2M | 386 | 3.3% |
| ETHUSDT | $4.9M | 215 | 1.2% |
| ZECUSDT | $3.6M | 23 | 0.9% |
| TAOUSDT | $2.9M | 12 | 0.7% |
Timeline (UTC, minute by minute)
| Minute | Events | Liquidated | Top symbol | Venues |
|---|
| 01:44 | 1 | $14 | XLMUSDT | binance |
| 01:45 | 1 | $136 | XAUUSDT | binance |
| 01:47 | 3 | $297 | XRPUSDT | binance, okx |
| 01:48 | 819 | $21.8M | BTCUSDT | binance, bitmex, bybit, kraken_fut, okx |
| 01:49 | 92 | $1.8M | ETHUSDT | binance, bybit, okx |
| 01:50 | 4 | $6,453 | ETHUSDT | binance, bybit |
| 01:51 | 126 | $374.2M | XAUUSDT | binance, bitmex, bybit, hyperliquid, kraken_fut, okx |
| 01:52 | 11 | $35,118 | ETHUSDT | binance, bybit, okx |
| 01:53 | 20 | $184,175 | ETHUSDT | binance, bybit, okx |
| 01:54 | 4 | $7,838 | ETHUSDT | binance |
Venue breakdown
| Venue | Liquidated | Events |
|---|
| okx | $378.0M | 129 |
| binance | $11.2M | 264 |
| bybit | $7.8M | 660 |
| bitmex | $1.0M | 8 |
| kraken_fut | $47,582 | 15 |
| hyperliquid | $5,464 | 1 |
Independent re-read of our own captured tape (verify: PASS). Cross-venue capture is the product moat.
What the map showed BEFORE the cascade
No pre-cascade map snapshot exists for this symbol (level capture not active for it at that time, or outside the retention window). We do not reconstruct or backfill a before-map — that would be look-ahead.
The measured record, as it stood before this cascade
As of 2026-07-10 00:43 UTC (the last calibration record before this cascade, n=None day-clusters), the model's walk-forward calibration was below its own validation gate (the Wilson 95% lower bound on out-of-sample precision@N did not clear the published target). Per our honesty rules we do not quote the figure itself while it sits below gate — only the status. The level-by-level record above stands on its own as the descriptive evidence for this event.