MARSCOINUSDT rose into Sep 5
+335%
Counted on 2026-09-07, against a record covering to 2026-09-07 00:00 UTC. These numbers are frozen: this page will always say what it said the day it was written.
This move is in the event archive as a volatility spike on 2026-09-04. Open the archived event
Exact setup countedCascade clustering ≥ 0.53 and Return · 15m ≤ -0.016 and Return · 1h ≤ -0.055 · Read at 1 hour before the move.
After 1 hour this setup fell 2% or more in 8 of 30 complete windows (26.7%), against 32.8% with no condition (2,623 of 7,995): 0.81x.
Best point inside 1 hour reached +5% or more in 12 of 30 complete windows; worst point fell 5% or more in 12 of 30.
Counts above cover this market only. Suggested starting scope: 10 large cap markets. Sector counts have not been computed here. This market only · Every recorded market
Watch the ignition replay Free replay covers the latest fully archived UTC day on 6 major markets. Pro reaches 90 days; Research reaches the whole recorded order book, which begins 15 May 2026. Earlier days are searchable but hold no book, so they cannot be replayed. Access is checked when you open a replay.
Evidence and counting
Read at 1 hour before the move.
Of the 30 fires, 6 came before the move began and 16 happened while it was already under way. A fire during the move sees it; it does not telegraph it.
About 1 a day, on 6 of 31 days: spread through the record rather than one event.
This is not a similarity search. Each count matches the exact readings above and nothing else.
Picked in hindsight: the counts include every other time these readings appeared, not just this move.
Fires often arrive as clusters of consecutive minutes, and forward windows overlap. A cluster is one episode, not many independent trials.
If these counts read weaker than the move suggested, that is the tool working: the lead-up of a picked move always looks special until it is counted everywhere else.
Explore the move and its lead-up
Hourly candles. The marked lines are the minutes the readings came from: 1 minute, 15 minutes, 1 hour, 4 hours and 24 hours before the selected start. These five samples test the lead-up only, not the full move. Use the minute inspector to explore during or after the move.
Explore historical state
Current-minute reads are free after sign-in. Pro and Research include historical-minute inspection and comparison with an hour earlier.
Past readings use stored inputs where available. Recent minutes may use the live buffer and are labelled unpinned. Missing minutes remain visible.
Read the available analytical inputs at one minute, including measurements over the preceding windows. Compare with an hour earlier, then take a reading into Research to test it. Dates are UTC.
These additional reads are separate from the five pre-start samples. Observations during or after the selected move describe what had already happened; they are not advance evidence.
Selected time: 2026-09-03 02:00 UTC. During the selected move: hindsight. Choose Read this minute to request it. Missing minutes remain unavailable.
Follow positioning and flow through the move
Read 21 sampled minutes from the selected start through one hour after the selected end. The peak hour has extra 15-minute samples. The end marks the peak hour, not the exact peak tick. These are separate snapshots, not a continuous tape or an advance-warning test.
Historical access applies. Reads preserve each source revision; missing values stay unavailable. Contract OI, turnover and direct spot basis are not supplied by this table. Published premium is a different measure from direct basis.
No additional reads have run.
The OI score measures absolute USD-notional change, not signed contract growth. Zero 15-second liquidation intensity can coexist with substantial hourly liquidations. Binance liquidation amounts are observed publications, not complete venue totals.
Pre-start evidence: five separate snapshots
Highlighted readings and exact search conditions
Highlighted readings meet fixed rules, not a statistical-significance test. The observed value and proposed search condition are different: a condition rounds a value or selects an interval for a repeatable search.
- -24h2026-09-02 02:00 UTC
At 24 hours before the move, 6 of the 58 readings met a highlight rule.
Book imbalance · top levels ≥ 0.5Compression · 15m ≥ 2.2Cascade clustering ≥ 0.58Return · 15m ≤ -0.069Return · 1h ≤ -0.095VWAP distance · day ≤ -0.059Show the full readings
READING BEFORE THE MOVE SEARCHES FOR Book imbalance · top levels feature.book_imbalance 0.5013 ≥ 0.5 Compression · 15m feature.candle_compression_15m 2.261 ≥ 2.2 Cascade clustering feature.cascade_clustering_index 0.5836 ≥ 0.58 Return · 15m feature.ret_15m -0.06955 ≤ -0.069 Return · 1h feature.ret_1h -0.09563 ≤ -0.095 VWAP distance · day feature.vwap_dist -0.05951 ≤ -0.059 - -4h2026-09-02 22:00 UTC
At 4 hours before the move, 3 of the 58 readings met a highlight rule.
Cascade clustering ≥ 0.52Return · 15m ≤ -0.011Return · 1h ≤ -0.051Show the full readings
READING BEFORE THE MOVE SEARCHES FOR Cascade clustering feature.cascade_clustering_index 0.523 ≥ 0.52 Return · 15m feature.ret_15m -0.01136 ≤ -0.011 Return · 1h feature.ret_1h -0.05118 ≤ -0.051 - -1h2026-09-03 01:00 UTC
At 1 hour before the move, 3 of the 58 readings met a highlight rule.
Cascade clustering ≥ 0.53Return · 15m ≤ -0.016Return · 1h ≤ -0.055Show the full readings
READING BEFORE THE MOVE SEARCHES FOR Cascade clustering feature.cascade_clustering_index 0.5311 ≥ 0.53 Return · 15m feature.ret_15m -0.01626 ≤ -0.016 Return · 1h feature.ret_1h -0.05505 ≤ -0.055 - -15m2026-09-03 01:45 UTC
At 15 minutes before the move, 5 of the 58 readings met a highlight rule.
Book imbalance · top levels ≥ 0.71Compression · 15m ≥ 2Cascade clustering ≥ 0.53Return · 15m ≥ 0.028Return · 1h ≥ 0.021Show the full readings
READING BEFORE THE MOVE SEARCHES FOR Book imbalance · top levels feature.book_imbalance 0.7147 ≥ 0.71 Compression · 15m feature.candle_compression_15m 2.037 ≥ 2 Cascade clustering feature.cascade_clustering_index 0.5399 ≥ 0.53 Return · 15m feature.ret_15m 0.02827 ≥ 0.028 Return · 1h feature.ret_1h 0.02135 ≥ 0.021 - -1m2026-09-03 01:59 UTC
At 1 minute before the move, 5 of the 58 readings met a highlight rule.
Book imbalance · top levels ≤ -0.79Compression · 15m ≥ 2Cascade clustering ≥ 0.53Return · 15m ≤ -0.011Return · 1h ≥ 0.032Show the full readings
READING BEFORE THE MOVE SEARCHES FOR Book imbalance · top levels feature.book_imbalance -0.7926 ≤ -0.79 Compression · 15m feature.candle_compression_15m 2.037 ≥ 2 Cascade clustering feature.cascade_clustering_index 0.5399 ≥ 0.53 Return · 15m feature.ret_15m -0.01118 ≤ -0.011 Return · 1h feature.ret_1h 0.03253 ≥ 0.032
Also counted
Book imbalance · top levels ≤ -0.79 and Compression · 15m ≥ 2 and Cascade clustering ≥ 0.5318 matches, 12 rose, 5 fell
Read at 1 minute before the move.
12 rose and 5 fell over 17 complete 30m windows. Too few completed windows for a directional generalization. No horizon cleared the floor of 30 complete windows on both the setup and the reference, so no lift is claimed.
Of the 18 fires, 4 came before the move began and 10 happened while it was already under way. A fire during the move sees it; it does not telegraph it.
About 0.6 a day, on 5 of 31 days: spread through the record rather than one event.
Book imbalance · top levels ≥ 0.71 and Compression · 15m ≥ 2 and Cascade clustering ≥ 0.5317 matches, 9 rose, 7 fell
Read at 15 minutes before the move.
9 rose and 7 fell over 16 complete 30m windows. Too few completed windows for a directional generalization. No horizon cleared the floor of 30 complete windows on both the setup and the reference, so no lift is claimed.
Of the 17 fires, 3 came before the move began and 10 happened while it was already under way. A fire during the move sees it; it does not telegraph it.
About 0.5 a day, on 5 of 31 days: spread through the record rather than one event.
Every night the record counts what fired and what usually followed: the daily brief.
No account? Replay a real move tick by tick, free: TUT short squeeze · 9 Aug 2026.