TSTUSDT rose 132% into Aug 10. The record covers the whole lead-up.
Move window: 2026-08-07 08:00 to 2026-08-10 10:00 UTC. The record for TSTUSDT currently ends 2026-08-14 00:00 UTC.
Containment · 15m inside and Cascade clustering ≥ 0.54 and Taker buy share · 15m ≥ 0.68
feature.candle_containment_15m + feature.cascade_clustering_index + feature.taker_buy_ratio_15m
Read at 1 hour before the move.
Minutes like this appeared 90 times in the 43,201 minutes searched (0.2%). What followed leaned up: 47 of the 85 matches with a complete 30 minutes forward rose (55%).
Of the 90 fires, 88 came before the move began; none were during it.
About 2.9 a day, on 21 of 31 days: spread through the record rather than one event.
q#0ab78d62 @ dataset de1f6756
Best supported: Containment · 15m inside and Cascade clustering ≥ 0.54 and Taker buy share · 15m ≥ 0.68, the combination with the most fires before the move began.
Opens this exact search in the research tool. Nothing runs until you confirm it there, and arming it as an alert sends a message when it next becomes true.
No account? Replay a real move tick by tick, free: TUT short squeeze · 9 Aug 2026.
Picked in hindsight: the counts include every other time these readings appeared, not just this move.
Also counted
This is not a similarity search. Each count matches the exact readings above and nothing else.
Book imbalance percentile ≥ 0.94 and Cascade clustering ≥ 0.54 and Minutes to funding ≤ 1
feature.book_imbalance_pctrank + feature.cascade_clustering_index + feature.mins_to_funding
Read at 1 minute before the move.
Minutes like this appeared only 7 times in the 43,201 minutes searched. What followed leaned up: 6 of the 7 matches with a complete 30 minutes forward rose (86%).
Of the 7 fires, 6 came before the move began and 1 happened while it was already under way. A fire during the move sees it; it does not telegraph it.
About 0.2 a day, on 7 of 31 days: spread through the record rather than one event.
q#77105dd0 @ dataset de1f6756
Cascade clustering ≥ 0.54 and Minutes to funding ≤ 15 and Return · 1h ≥ 0.025
feature.cascade_clustering_index + feature.mins_to_funding + feature.ret_1h
Read at 15 minutes before the move.
Minutes like this appeared only 10 times in the 43,201 minutes searched. What followed leaned up: 7 of the 10 matches with a complete 30 minutes forward rose (70%).
Of the 10 fires, 6 came before the move began and 4 happened while it was already under way. A fire during the move sees it; it does not telegraph it.
About 0.3 a day, on 8 of 31 days: spread through the record rather than one event.
q#37e4ea0e @ dataset de1f6756
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.
Every night the record counts what fired and what usually followed: the daily brief.