Binance USDT-MLABUSDT fell 53% on 6 September 2026
Picked after the fall, on one market.
What happened
Price opened the 02:00 hour at 0.07491 and reached a lowest trade of 0.035 in the 22:00 hour; the tested readings were taken at 01:00.
What stood out at 01:00
- Order book tilt-0.5682Tested: -0.56 or lower
- Order book lopsidedness0.07954Tested: 0.08 or lower
- Sweep + reclaim (15m)bearishTested: is bearish
01:00 always meets its own rules.
What the record says
Less often than any LAB minute, in this sample
Price at least 2% lower after 30 minutes
41 matches in 43,201 minutes checked.
Picked after the fall, on one market.
Evidence
No test to open
Multiple recorded sectors: sector_alpha, sector_crypto. Choose one explicitly.
Exactly what was counted3 conditions · 41 of 43,201 minutes · saved text
- Order book tilt -0.56 or lower. Size at the best bid against the best ask; above 0 means more bids, below 0 more asks.Book imbalance · top levels ≤ -0.56 · feature.book_imbalance
- Order book lopsidedness 0.08 or lower. How lopsided the sizes at the best bid and ask were, either way, against recent readings; low means unusually even.Book imbalance percentile ≤ 0.08 · feature.book_imbalance_pctrank
- Sweep + reclaim (15m) is bearish.Sweep + reclaim · 15m bearish · feature.candle_sweep_reclaim_15m
Read at 1 hour before the move.
Read at 01:00 UTC on 6 September, one hour before the selected 02:00 start.
LAB only, 12 August to 10 September 2026 (UTC, ending 11 September 00:00); all 3 readings had values on 43,201 of those minutes.
Reference: every LAB minute over the same dates, matches included; it is not a matched control group.
Outcome: the close exactly 30 minutes later, not the highest or lowest price along the way.
The 02:00 start was picked automatically after the move.
LABUSDT stored readings end 2026-09-11 00:00 UTC (exclusive). Prices and tick replay have separate coverage.
The feature manifest spans the lead-up. Individual minutes or inputs can still be unavailable.
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.
Saved study q#bfcf714b @ dataset d31fb5af, counted 12 Sep 2026 08:01 UTC.
Saved summary text, as written 12 Sep 2026
Written automatically when this study was saved and kept as written; where a line differs from the counts above, the counts govern.
Minutes like this appeared 41 times in the 43,201 minutes searched (<0.1%). What followed was close to a coin flip: 20 rose and 21 fell over the next 30 minutes (41 of the 41 matches have a complete 30 minutes forward).
After 30 minutes this setup fell 2% or more in 0 of 41 complete windows (0.0%), against 2.9% with no condition (1,251 of 43,171): 0.00x.
This reports the time frame with the biggest gap from any minute, chosen after counting. At least 3 of its 41 windows overlap the fall.
Best point inside 30 minutes reached +5% or more in 0 of 41 complete windows; worst point fell 5% or more in 0 of 41.
About 1.3 a day, on 21 of 31 days: spread through the record rather than one event.
It counts the single minute on 11 September as a day.
The other reading times, as written
From 1 minute before
Minutes like this appeared only 4 times in the 20,641 minutes searched. What followed was close to a coin flip: 2 rose and 2 fell over the next 30 minutes (4 of the 4 matches have a complete 30 minutes forward).
2 rose and 2 fell over 4 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.
About 0.1 a day, on 4 of 31 days: spread through the record rather than one event.
From 15 minutes before
Minutes like this are common here: 149 of the 20,641 minutes searched (0.7%), about 4.8 a day. What followed was close to a coin flip: 77 rose and 71 fell over the next 30 minutes (148 of the 149 matches have a complete 30 minutes forward).
After 7 days this setup rose 2% or more in 7 of 89 complete windows (7.9%), against 15.5% with no condition (5,145 of 33,121): 0.51x.
About 4.8 a day, on 12 of 31 days: spread through the record rather than one event.
Picked after the fall, on one market; the 41 matches came on 21 of 30 days, 3 during the fall.
When the matches happened21 of 30 days
- 12 Aug1 match
- 18 Aug1 match
- 19 Aug2 matches
- 20 Aug5 matches
- 21 Aug1 match
- 22 Aug2 matches
- 23 Aug1 match
- 24 Aug2 matches
- 26 Aug3 matches
- 27 Aug2 matches
- 29 Aug2 matches
- 30 Aug3 matches
- 1 Sep1 match
- 2 Sep1 match
- 3 Sep5 matches
- 4 Sep1 match
- 5 Sep3 matches
- 6 Sep2 matches
- 7 Sep1 match
- 8 Sep1 match
- 10 Sep1 match
No matches on the other 9 days.
Of the 41 matches, 37 came before the fall began, 3 during it and 1 after it.
Neighbouring minutes overlap, so these are not 41 separate trials.
Picked after the fall, on one market; the 41 matches came on 21 of 30 days, 3 during the fall.
Other time frames30 minutes to 7 days
The answer uses 30 minutes, the time frame this study counted by default. Each row counts the same matches at a later close, in both directions. The bars show how often price was 2% or more lower at each time frame: first the matches, then any LAB minute.
- 30 minutes
3 of 41 (7.3%) were 2% or more higher; any LAB minute 1,286 of 43,171 (3.0%).
Every match has a 30-minute close.
At least 3 of these windows overlap the fall.
- 1 hour
6 of 41 (14.6%) were 2% or more higher; any LAB minute 2,515 of 43,141 (5.8%).
Every match has a 1-hour close.
At least 3 of these windows overlap the fall.
- 4 hours
7 of 41 (17.1%) were 2% or more higher; any LAB minute 6,627 of 42,961 (15.4%).
Every match has a 4-hour close.
At least 3 of these windows overlap the fall.
- 24 hours
11 of 40 (27.5%) were 2% or more higher; any LAB minute 9,811 of 41,761 (23.5%).
1 without a 24-hour close yet, left out.
At least 3 of these windows overlap the fall.
- 72 hours
8 of 39 (20.5%) were 2% or more higher; any LAB minute 11,585 of 38,881 (29.8%).
2 without a 72-hour close yet, left out.
At least 4 of these windows overlap the fall.
- 7 days
4 of 32 (12.5%) were 2% or more higher; any LAB minute 5,145 of 33,121 (15.5%).
9 without a 7-day close yet, left out.
At least 7 of these windows overlap the fall.
The saved summary picked, after counting, the time frame with the biggest gap from any minute: 30 minutes.
After 30 minutes this setup fell 2% or more in 0 of 41 complete windows (0.0%), against 2.9% with no condition (1,251 of 43,171): 0.00x.
At least 3 of those windows ran through the fall itself, so it partly counts the fall as an outcome.
Along the way (the highest and lowest price inside 30 minutes, not the close):
Best point inside 30 minutes reached +5% or more in 0 of 41 complete windows; worst point fell 5% or more in 0 of 41.
Picked after the fall, on one market; the 41 matches came on 21 of 30 days, 3 during the fall.
Readings at five times before the fall24 hours to 1 minute before · 2 other times tried
Highlights follow fixed rules, not significance tests. Proposed conditions round values or use ranges; inspect them before running.
24 hours before · 5 Sep 02:00 UTC · 9 of 63 stood out
Order book tilt -0.99 or lowerEngulfing (1h) is bearishSweep + reclaim (15m) is bullishSweep + reclaim (1h) is bearishLiquidation bunching 0.54 or higherHow many times the broken descending resistance had been tested 3 or higherHow long ago the descending resistance broke between 12 and 720Touches on the broken resistance 3 or moreTime since the resistance broke between 12 and 720 hoursShow the full readings
Reading Value at that minute Stored rule Book imbalance · top levels feature.book_imbalance -0.9903 ≤ -0.99 Engulfing · 1h feature.candle_engulfing_1h bearish bearish Sweep + reclaim · 15m feature.candle_sweep_reclaim_15m bullish bullish Sweep + reclaim · 1h feature.candle_sweep_reclaim_1h bearish bearish Cascade clustering feature.cascade_clustering_index 0.5474 ≥ 0.54 how many times the broken descending resistance had been tested feature.desc_resistance_broken_touches 4 ≥ 3 how long ago the descending resistance broke feature.desc_resistance_hours_since_break 35 12 to 720 how many times the broken short descending resistance had been tested feature.desc_resistance_short_broken_touches 7 ≥ 3 how long ago the short descending resistance broke feature.desc_resistance_short_hours_since_break 346 12 to 720 4 hours before · 5 Sep 22:00 UTC · 6 of 63 stood out
4-hour range against usual 0.46 or lowerLiquidation bunching 0.52 or higherHow many times the broken descending resistance had been tested 3 or higherHow long ago the descending resistance broke between 12 and 720Touches on the broken resistance 3 or moreTime since the resistance broke between 12 and 720 hoursShow the full readings
Reading Value at that minute Stored rule the last four-hour candle range versus its baseline feature.candle_compression_4h 0.4558 ≤ 0.46 Cascade clustering feature.cascade_clustering_index 0.5245 ≥ 0.52 how many times the broken descending resistance had been tested feature.desc_resistance_broken_touches 4 ≥ 3 how long ago the descending resistance broke feature.desc_resistance_hours_since_break 55 12 to 720 how many times the broken short descending resistance had been tested feature.desc_resistance_short_broken_touches 7 ≥ 3 how long ago the short descending resistance broke feature.desc_resistance_short_hours_since_break 366 12 to 720 1 hour before · 6 Sep 01:00 UTC · 9 of 63 stood out
Order book tilt -0.56 or lowerOrder book lopsidedness 0.08 or lowerSweep + reclaim (15m) is bearishLiquidation bunching 0.52 or higherHow many times the broken descending resistance had been tested 3 or higherHow long ago the descending resistance broke between 12 and 720Touches on the broken resistance 3 or moreTime since the resistance broke between 12 and 720 hoursTaker buy share (15m) 0.65 or higherShow the full readings
Reading Value at that minute Stored rule Book imbalance · top levels feature.book_imbalance -0.5682 ≤ -0.56 Book imbalance percentile feature.book_imbalance_pctrank 0.07954 ≤ 0.08 Sweep + reclaim · 15m feature.candle_sweep_reclaim_15m bearish bearish Cascade clustering feature.cascade_clustering_index 0.5233 ≥ 0.52 how many times the broken descending resistance had been tested feature.desc_resistance_broken_touches 4 ≥ 3 how long ago the descending resistance broke feature.desc_resistance_hours_since_break 58 12 to 720 how many times the broken short descending resistance had been tested feature.desc_resistance_short_broken_touches 7 ≥ 3 how long ago the short descending resistance broke feature.desc_resistance_short_hours_since_break 369 12 to 720 Taker buy share · 15m feature.taker_buy_ratio_15m 0.6587 ≥ 0.65 15 minutes before · 6 Sep 01:45 UTC · 6 of 63 stood out
Order book tilt 0.93 or higherLiquidation bunching 0.51 or higherHow many times the broken descending resistance had been tested 3 or higherHow long ago the descending resistance broke between 12 and 720Touches on the broken resistance 3 or moreTime since the resistance broke between 12 and 720 hoursShow the full readings
Reading Value at that minute Stored rule Book imbalance · top levels feature.book_imbalance 0.9326 ≥ 0.93 Cascade clustering feature.cascade_clustering_index 0.5197 ≥ 0.51 how many times the broken descending resistance had been tested feature.desc_resistance_broken_touches 4 ≥ 3 how long ago the descending resistance broke feature.desc_resistance_hours_since_break 58.75 12 to 720 how many times the broken short descending resistance had been tested feature.desc_resistance_short_broken_touches 7 ≥ 3 how long ago the short descending resistance broke feature.desc_resistance_short_hours_since_break 369.8 12 to 720 1 minute before · 6 Sep 01:59 UTC · 5 of 63 stood out
Liquidation bunching 0.51 or higherHow many times the broken descending resistance had been tested 3 or higherHow long ago the descending resistance broke between 12 and 720Touches on the broken resistance 3 or moreTime since the resistance broke between 12 and 720 hoursShow the full readings
Reading Value at that minute Stored rule Cascade clustering feature.cascade_clustering_index 0.5197 ≥ 0.51 how many times the broken descending resistance had been tested feature.desc_resistance_broken_touches 4 ≥ 3 how long ago the descending resistance broke feature.desc_resistance_hours_since_break 58.98 12 to 720 how many times the broken short descending resistance had been tested feature.desc_resistance_short_broken_touches 7 ≥ 3 how long ago the short descending resistance broke feature.desc_resistance_short_hours_since_break 370 12 to 720
Two other reading times we tried 4 and 149 matches
1 minute before (01:59): liquidation bunching 0.51 or higher, how many times the broken descending resistance had been tested 3 or higher, how long ago the descending resistance broke between 12 and 720.
Cascade clustering ≥ 0.51 and how many times the broken descending resistance had been tested ≥ 3 and how long ago the descending resistance broke 12 to 720
4 matches: price was 2% or more lower after 30 minutes in 0 of 4, and 2% or more higher in 1 of 4.
Of the 4 matches, 3 came before the fall began, 0 during it and 1 after it.
15 minutes before (01:45): order book tilt 0.93 or higher, liquidation bunching 0.51 or higher, how many times the broken descending resistance had been tested 3 or higher.
Book imbalance · top levels ≥ 0.93 and Cascade clustering ≥ 0.51 and how many times the broken descending resistance had been tested ≥ 3
149 matches: price was 2% or more lower after 30 minutes in 6 of 148 (4.1%), and 2% or more higher in 5 of 148 (3.4%).
Of the 149 matches, 126 came before the fall began, 3 during it and 20 after it.
Rows with fewer than 30 results print counts only.
The saved study leads with 01:00: the narrowest set with at least 30 matches before the fall.
Picked after the fall, on one market; the 41 matches came on 21 of 30 days, 3 during the fall.
Hourly candles around the fallfull context, lead-up, move
The 02:00 start was picked after the move, and the hour before was already falling.
Hourly candles, UTC. 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.
Other ways to test itsame dates
Multiple recorded sectors: sector_alpha, sector_crypto. Choose one explicitly.
Each opens Review the test; nothing runs until you press Run.
Running needs a free account and uses your allowance; you see the cost first.
Starting defaults and coverage
Starting defaults: 2026-08-12 to 2026-09-11 UTC; finishes down 2% or more after 1 hour. Review or change the markets, dates, conditions and outcome before running. Current recorded classification and sector tags, not point-in-time membership. Historical membership may differ. Instrument history does not guarantee every setup input or outcome is present; actual study exclusions remain authoritative.