Change market, time or detector

All times are UTC. Chart history only changes the display. Historical comparisons use the 30 days before the selected start and measure their own outcome horizon.

Move read

SOXSUSDT rose into Sep 15

+18%

Move window

Move window: 2026-09-13 05:00 to 2026-09-15 05:00 UTC.

48 hours. The automatic start is the last covered hourly candle touching the bottom 5% of the episode range (top 5% for a fall), measured using the eventual extreme. It is a hindsight anchor, not a detected causal onset. Change the start above to inspect a later acceleration. The end marks the hour containing the price extreme, not an exact tick.

Stored analytical feature coverage for SOXSUSDT ends 2026-09-20 00:00 UTC (exclusive). Price candles can continue beyond it; feature availability and tick replay are separate.

The feature manifest spans the lead-up. Individual minutes or inputs can still be unavailable.

34 historical matches for the proposed conditions. This is an exploratory investigation. The combined trendline, compression and microstructure hypothesis still needs validation.

> Full SOXSUSDT research page

Explore the move and its lead-up

Price history: lead-up and selected move

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: 2026-09-13 05:00 UTC. During the selected move: hindsight. Choose Read this minute to request it. Missing minutes remain unavailable.

Before the time above:

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

Geometry and microstructure, on the same clock

Read left to right: 24h → 4h → 1h → 15m → 1m before the selected start. These are five snapshots, not a continuous tape. Neutral readings stay visible; unavailable values are never zero.

Descending resistance

Reading	-24h	-4h	-1h	-15m	-1m
Time since resistance breakhours	Unavailable	Unavailable	Read failed	Unavailable	Unavailable
Resistance line spandays	Unavailable	Unavailable	Read failed	Unavailable	Unavailable
Resistance touchescount	Unavailable	Unavailable	Read failed	Unavailable	Unavailable
Touches before resistance breakcount	Unavailable	Unavailable	Read failed	Unavailable	Unavailable
Line ATR contractionmultiple	Unavailable	Unavailable	Read failed	Unavailable	Unavailable
Resistance line statelabel	Unavailable	Unavailable	Read failed	Unavailable	Unavailable
Distance to broken resistancemultiple	Unavailable	Unavailable	Read failed	Unavailable	Unavailable
Distance to resistancemultiple	Unavailable	Unavailable	Read failed	Unavailable	Unavailable
Support shapelabel	Unavailable	Unavailable	Read failed	Unavailable	Unavailable

Candle compression

Reading	-24h	-4h	-1h	-15m	-1m
last 15-minute candle range versus its baselinemultiple	0.6563	0.973	Read failed	0.6154	0.6154
last four-hour candle range versus its baselinemultiple · Highlight: ≤ 0.5 or ≥ 2	0.446	0.2016	Read failed	0.2347	0.2347
last one-hour candle range versus its baselinemultiple	0.3741	0.6769	Read failed	0.551	0.551

Order book

Reading	-24h	-4h	-1h	-15m	-1m
Order-book imbalanceratio · Highlight: ≤ -0.5 or ≥ 0.5	-0.9598	-0.333	Read failed	-0.3803	-0.6593
normalized spreadratio	0.04582	0.04515	Read failed	0.04509	0.04506
order-book imbalance rankpercentile	0.9796	0.3802	Read failed	0.9741	0.8131

Trade flow

Reading	-24h	-4h	-1h	-15m	-1m
Informed-trading pressureratio	0.1062	0.09777	Read failed	0.09331	0.09374
Net taker flow over the trailing four hoursratio	0.01996	0.02012	Read failed	-0.01992	-0.0167
Net taker flow over the trailing hourratio	-0.1352	0.2981	Read failed	0.1116	-0.02678
large-trade share of recent flowratio	0	0	Read failed	0	0
taker-buy share of recent flowratio	0.3675	0.5958	Read failed	0.05135	0.5447
VPIN regimelabel	normal	normal	Read failed	normal	normal
Turnover against its recent hoursratio	Unavailable	Unavailable	Read failed	Unavailable	Unavailable

Funding and positioning

Reading	-24h	-4h	-1h	-15m	-1m
Funding minus premium indexsigned_fraction	0.0007072	0.0000632	Read failed	-0.00002616	-0.0003872
Minutes until funding settlesminutes	180	420	Read failed	195	181
Premium index change over 1hsigned_fraction	-0.0009843	0.0003352	Read failed	0.0005762	-0.000373
Premium index rank over 30dpercentile	0.09653	0.3007	Read failed	0.5347	0.7083
Published premium indexsigned_fraction	-0.0008367	-0.00006178	Read failed	0.00002758	0.0003886
funding raterate	-0.0001295	0.00000142	Read failed	0.00000142	0.00000142
global long ratioratio	0.5688	0.6401	Read failed	0.6318	0.6302
hourly change in open contractssigned_fraction	-0.0009477	-0.0002024	Read failed	0.001046	0.0008476
normalized funding rateratio	0.04315	0.0004733	Read failed	0.0004733	0.0004733
open-interest velocity rankpercentile	0.2314	0.6886	Read failed	0.1978	0.8903
top-trader long ratioratio	0.4192	0.4186	Read failed	0.4199	0.4204
top-versus-crowd long skewratio_difference	-0.1496	-0.2215	Read failed	-0.2119	-0.2098

Liquidations

Reading	-24h	-4h	-1h	-15m	-1m
Cascade clusteringratio · Highlight: ≥ 0.5	0.6301	0.6287	Read failed	0.624	0.624
Liquidation intensityratio	0	0	Read failed	0	0
Liquidations in the trailing hourusd	0	0	Read failed	0	0
Longs liquidated in the trailing hourusd	0	0	Read failed	0	0
Shorts liquidated in the trailing hourusd	0	0	Read failed	0	0
Which side the trailing hour of liquidations fell onratio	Unavailable	Unavailable	Read failed	Unavailable	Unavailable

Highlighted cells meet the printed fixed rule. This does not establish rarity, statistical significance or a cause of the move. Book readings describe the best quotes, not full-depth liquidity; liquidation readings describe what the venue reported.

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.

Could not read 1 hour before the move. The engine did not answer for those minutes, so nothing is claimed about them. Reload to try again.

-24h2026-09-12 05:00 UTC

At 24 hours before the move, 7 of the 65 readings met a highlight rule.

Book imbalance · top levels ≤ -0.95Book imbalance percentile ≥ 0.97Compression · 1h ≤ 0.38Compression · 4h ≤ 0.45Cascade clustering ≥ 0.63how many times the broken short descending resistance had been tested ≥ 3how long ago the short descending resistance broke 12 to 720

Show the full readings

READING	BEFORE THE MOVE	SEARCHES FOR
Book imbalance · top levels feature.book_imbalance	-0.9598	≤ -0.95
Book imbalance percentile feature.book_imbalance_pctrank	0.9796	≥ 0.97
Compression · 1h feature.candle_compression_1h	0.3741	≤ 0.38
Compression · 4h feature.candle_compression_4h	0.446	≤ 0.45
Cascade clustering feature.cascade_clustering_index	0.6301	≥ 0.63
how many times the broken short descending resistance had been tested feature.desc_resistance_short_broken_touches	3	≥ 3
how long ago the short descending resistance broke feature.desc_resistance_short_hours_since_break	349	12 to 720

-4h2026-09-13 01:00 UTC

At 4 hours before the move, 4 of the 65 readings met a highlight rule.

Compression · 4h ≤ 0.21Cascade clustering ≥ 0.62how many times the broken short descending resistance had been tested ≥ 3how long ago the short descending resistance broke 12 to 720

Show the full readings

READING	BEFORE THE MOVE	SEARCHES FOR
Compression · 4h feature.candle_compression_4h	0.2016	≤ 0.21
Cascade clustering feature.cascade_clustering_index	0.6287	≥ 0.62
how many times the broken short descending resistance had been tested feature.desc_resistance_short_broken_touches	3	≥ 3
how long ago the short descending resistance broke feature.desc_resistance_short_hours_since_break	369	12 to 720

-15m2026-09-13 04:45 UTC

At 15 minutes before the move, 6 of the 65 readings met a highlight rule.

Book imbalance percentile ≥ 0.97Compression · 4h ≤ 0.24Cascade clustering ≥ 0.62how many times the broken short descending resistance had been tested ≥ 3how long ago the short descending resistance broke 12 to 720Taker buy share · 15m ≤ 0.052

Show the full readings

READING	BEFORE THE MOVE	SEARCHES FOR
Book imbalance percentile feature.book_imbalance_pctrank	0.9741	≥ 0.97
Compression · 4h feature.candle_compression_4h	0.2347	≤ 0.24
Cascade clustering feature.cascade_clustering_index	0.624	≥ 0.62
how many times the broken short descending resistance had been tested feature.desc_resistance_short_broken_touches	3	≥ 3
how long ago the short descending resistance broke feature.desc_resistance_short_hours_since_break	372.8	12 to 720
Taker buy share · 15m feature.taker_buy_ratio_15m	0.05135	≤ 0.052

-1m2026-09-13 04:59 UTC

At 1 minute before the move, 5 of the 65 readings met a highlight rule.

Book imbalance · top levels ≤ -0.65Compression · 4h ≤ 0.24Cascade clustering ≥ 0.62how many times the broken short descending resistance had been tested ≥ 3how long ago the short descending resistance broke 12 to 720

Show the full readings

READING	BEFORE THE MOVE	SEARCHES FOR
Book imbalance · top levels feature.book_imbalance	-0.6593	≤ -0.65
Compression · 4h feature.candle_compression_4h	0.2347	≤ 0.24
Cascade clustering feature.cascade_clustering_index	0.624	≥ 0.62
how many times the broken short descending resistance had been tested feature.desc_resistance_short_broken_touches	3	≥ 3
how long ago the short descending resistance broke feature.desc_resistance_short_hours_since_break	373	12 to 720

Point the research surface at any past minute yourself PRO

Historical comparison

Exact setup countedBook imbalance percentile ≥ 0.97 and Compression · 4h ≤ 0.24 and Cascade clustering ≥ 0.62 · Read at 15 minutes before the move.These are the printed conditions only. The selected detector family does not change this automatically proposed combination. Edit it before testing the full recipe.

What the record says

Measure after

The selected move lasts 48 hours. This comparison measures 72 hours after each historical match. Changing it uses the existing result.

Descriptive comparison; an edge has not been established.

Outcome	Matching setup	Same-market reference	Difference
Finished at least 2% higher	16 / 33 (48.5%)1 unavailable	17,147 / 37,994 (45.1%)5207 unavailable	+3.4 pp
Finished at least 2% lower	16 / 33 (48.5%)1 unavailable	13,815 / 37,994 (36.4%)5207 unavailable	+12.1 pp
Reached +5% at any point	17 / 33 (51.5%)1 unavailable	24,153 / 38,458 (62.8%)4743 unavailable	-11.3 pp
Reached -5% at any point	16 / 33 (48.5%)1 unavailable	17,802 / 38,458 (46.3%)4743 unavailable	+2.2 pp

Reference: eligible minutes in the same market and scan period, without the proposed conditions. The 30-window reporting floor is not a significance test. Overlapping windows and shared market events can reduce independent evidence. Conditions were selected after seeing this move; confirmation needs unseen data.

Does this setup hold across its sector?

Open the proposed study with starting defaults. Review the evidence, refine the idea, then save it or monitor it if useful.

What Research includes

Choose a recorded Binance crypto perpetual market with confirmed instrument classification.

Starting defaults and coverage

Starting defaults: 2026-08-21 to 2026-09-20 UTC; finishes up 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.

Choose the study population explicitly: All recorded crypto perpetuals

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

feature.book_imbalance_pctrank + feature.candle_compression_4h + feature.cascade_clustering_index

Read at 15 minutes before the move.

Of the 34 fires, 33 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 1.1 a day over 31 days, but 2026-09-05 alone holds 41% of them: this is close to a single episode.

q#aa3d72ef @ dataset fbafe5a9

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.

Also counted

Book imbalance · top levels ≤ -0.65 and Compression · 4h ≤ 0.24 and Cascade clustering ≥ 0.6251 matches, 27 rose, 22 fell

feature.book_imbalance + feature.candle_compression_4h + feature.cascade_clustering_index

Read at 1 minute before the move.

After 30 minutes this setup rose 2% or more in 0 of 49 complete windows (0.0%), against 1.3% with no condition (537 of 42,178): 0.00x.

Best point inside 30 minutes reached +5% or more in 0 of 51 complete windows; worst point fell 5% or more in 0 of 51.

Of the 51 fires, 49 came before the move began and 2 happened while it was already under way. A fire during the move sees it; it does not telegraph it.

About 1.6 a day over 31 days, but 2026-09-05 alone holds 41% of them: this is close to a single episode.

q#fe85bca3 @ dataset fbafe5a9

Compression · 4h ≤ 0.21 and Cascade clustering ≥ 0.62 and how many times the broken short descending resistance had been tested ≥ 37 matches, 3 rose, 4 fell

feature.candle_compression_4h + feature.cascade_clustering_index + feature.desc_resistance_short_broken_touches

Read at 4 hours before the move.

3 rose and 4 fell over 7 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 7 fires, 7 came before the move began; none were during it.

About 0.2 a day, on 6 of 31 days: spread through the record rather than one event.

q#70f537fb @ dataset fbafe5a9

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.