- Cautious floor
- 23.9%
- Windows
- 348
Public performance record
See what held up after prediction.
The Money Map publishes liquidation levels first. Later, the actual tape tells us which levels were reached. Every performance claim includes the result, the sample size and a cautious lower bound. Misses stay public. Weak markets are benched.
Levels 1 to 2% from price: 67.7% hit within 24 hours (n 1,920, 620 misses listed). 95% lower bound 65.5%.
Levels 2 to 5% from price: 54.3% hit within 72 hours (n 729, 333 misses listed). 95% lower bound 50.6%.
Levels 5 to 15% from price: 51.5% hit within 7 days (n 801, 388 misses listed). 95% lower bound 48.1%.
How we grade ourselves
In plain English: Our majors levels hit 72% of the time, walk-forward and out-of-sample, checked over 276,328 real windows. The cautious number (95% floor): 67.7%. That is 56.1 points above the no-model mass-weighted baseline (15.9%), cautious floor 45.1 points.
Complete provisional record
Every scored published level, in chronological order.
Hits and misses remain together in this provisional row record. Released headline figures stay separate.
Loading the complete scored row record…
Why this record is different
Published first. Scored later. Weak markets get benched.
Market by market
The strongest proof is specific.
Every coin we track remains in the governed record. 15 of 44 tracked symbols currently publish a rate. A rate appears only with its count and its cautious bound; symbols benched by the served floor (Wilson floor below 25.0%) show the state and the number that benched them. We do not hide failing symbols, and we do not serve you a map whose grade slipped. 32 auto-disabled symbol(s) sit below the publish floor and are grouped in the collapsed section under the table and are benched, never hidden, never blended into the graded rows. Descriptive history, not a forecast.
- Cautious floor
- 58.0%
- Windows
- 348
- Cautious floor
- 30.4%
- Windows
- 344
- Cautious floor
- 53.9%
- Windows
- 346
Open the complete governed table 15 publishing · 44 tracked · failures retained
| Coin | State | Hit rate | Cautious number (95% floor) | Windows | Independent days | Edge vs no-model baseline |
|---|---|---|---|---|---|---|
AAPL AAPL →Measurement noteAAPL levels hit 35% of the time, checked over 119 windows across 13 independent days. The cautious number (95% floor): 15.8%. That is 21.5 points above the no-model mass-weighted baseline (14.2%), cautious floor 1.6 points. |
Serving · floor watch | 35.8% | 15.9% | 119 | 13 | +21.5pp (floor +1.7pp) |
BNB BNB →Measurement noteBNB levels hit 60% of the time, checked over 286 windows across 15 independent days. The cautious number (95% floor): 36.3%. That is 46.4 points above the no-model mass-weighted baseline (14.2%), cautious floor 22.1 points. |
Serving | 60.7% | 36.4% | 286 | 15 | +46.5pp (floor +22.1pp) |
BTC BTC →Measurement noteBTC levels hit 45% of the time, checked over 348 windows across 15 independent days. The cautious number (95% floor): 23.9%. That is 31.2 points above the no-model mass-weighted baseline (14.2%), cautious floor 9.6 points. |
Serving · floor watch | 45.5% | 23.9% | 348 | 15 | +31.2pp (floor +9.7pp) |
COIN COIN →Measurement noteCOIN levels hit 54% of the time, checked over 80 windows across 12 independent days. The cautious number (95% floor): 28.8%. That is 40.2 points above the no-model mass-weighted baseline (14.2%), cautious floor 14.6 points. |
Serving | 54.5% | 28.8% | 80 | 12 | +40.2pp (floor +14.6pp) |
DOGE DOGE →Measurement noteDOGE levels hit 49% of the time, checked over 326 windows across 15 independent days. The cautious number (95% floor): 27.2%. That is 35.4 points above the no-model mass-weighted baseline (14.2%), cautious floor 12.9 points. |
Serving | 49.7% | 27.2% | 326 | 15 | +35.5pp (floor +13.0pp) |
ETH ETH →Measurement noteETH levels hit 82% of the time, checked over 348 windows across 15 independent days. The cautious number (95% floor): 57.9%. That is 68.7 points above the no-model mass-weighted baseline (14.2%), cautious floor 43.7 points. |
Serving | 83.0% | 58.0% | 348 | 15 | +68.7pp (floor +43.7pp) |
PAXG PAXG →Measurement notePAXG levels hit 78% of the time, checked over 164 windows across 14 independent days. The cautious number (95% floor): 52.6%. That is 64.5 points above the no-model mass-weighted baseline (14.2%), cautious floor 38.4 points. |
Serving | 78.8% | 52.7% | 164 | 14 | +64.6pp (floor +38.4pp) |
SOL SOL →Measurement noteSOL levels hit 53% of the time, checked over 344 windows across 15 independent days. The cautious number (95% floor): 30.3%. That is 39.4 points above the no-model mass-weighted baseline (14.2%), cautious floor 16.1 points. |
Serving | 53.7% | 30.4% | 344 | 15 | +39.4pp (floor +16.2pp) |
WLD WLD →Measurement noteWLD levels hit 65% of the time, checked over 336 windows across 15 independent days. The cautious number (95% floor): 40.5%. That is 51.1 points above the no-model mass-weighted baseline (14.2%), cautious floor 26.3 points. |
Serving | 65.4% | 40.6% | 336 | 15 | +51.2pp (floor +26.3pp) |
XAUT XAUT →Measurement noteXAUT levels hit 68% of the time, checked over 209 windows across 15 independent days. The cautious number (95% floor): 43.4%. That is 54.3 points above the no-model mass-weighted baseline (14.2%), cautious floor 29.2 points. |
Serving | 68.6% | 43.5% | 209 | 15 | +54.3pp (floor +29.2pp) |
XAU XAU →Measurement noteXAU levels hit 55% of the time, checked over 325 windows across 15 independent days. The cautious number (95% floor): 31.7%. That is 41.0 points above the no-model mass-weighted baseline (14.2%), cautious floor 17.4 points. |
Serving | 55.3% | 31.7% | 325 | 15 | +41.0pp (floor +17.5pp) |
XRP XRP →Measurement noteXRP levels hit 79% of the time, checked over 346 windows across 15 independent days. The cautious number (95% floor): 53.9%. That is 64.8 points above the no-model mass-weighted baseline (14.2%), cautious floor 39.6 points. |
Serving | 79.1% | 53.9% | 346 | 15 | +64.9pp (floor +39.7pp) |
Auto-disabled (below publish floor): 32 symbol(s). These coins fell under our auto-disable bar and are benched from serving; their rows keep the exact measured state and counters, grouped here so they never blend into the graded table.
| Coin | State | Hit rate | Cautious number (95% floor) | Windows | Independent days | Edge vs no-model baseline |
|---|---|---|---|---|---|---|
1000PEPE 1000PEPE →Why it is withheldBenched by the served-floor governance. The number that benched it is public: at-exclusion floor 14.7% over 15 independent days. Re-inclusion is earned, not assumed: floor ≥ 30.0% held over consecutive confirmed cycles plus sustained time. Live status: accruing. |
Excluded · accruing | — | — | 347 | 15 | — |
AAVE AAVE →Why it is withheldBenched by the served-floor governance. The number that benched it is public: at-exclusion floor 30.5% over 15 independent days. Re-inclusion is earned, not assumed: floor ≥ 30.0% held over consecutive confirmed cycles plus sustained time. Live status: accruing. |
Excluded · accruing | — | — | 307 | 15 | — |
ADA ADA →Why it is withheldBenched by the served-floor governance. The number that benched it is public: at-exclusion floor 21.3% over 15 independent days. Re-inclusion is earned, not assumed: floor ≥ 30.0% held over consecutive confirmed cycles plus sustained time. Live status: accruing. |
Excluded · accruing | — | — | 300 | 15 | — |
APT APT →Why it is withheldBenched by the served-floor governance. The number that benched it is public: at-exclusion floor 15.1% over 15 independent days. Re-inclusion is earned, not assumed: floor ≥ 30.0% held over consecutive confirmed cycles plus sustained time. Live status: accruing. |
Excluded · accruing | — | — | 261 | 15 | — |
ARB ARB →Measurement noteARB levels hit 37% of the time, checked over 325 windows across 15 independent days. The cautious number (95% floor): 18.0%. That is 23.3 points above the no-model mass-weighted baseline (14.2%), cautious floor 3.8 points. |
Serving · floor watch | 37.6% | 18.1% | 325 | 15 | +23.3pp (floor +3.9pp) |
AVAX AVAX →Why it is withheldBenched by the served-floor governance. The number that benched it is public: at-exclusion floor 18.0% over 15 independent days. Re-inclusion is earned, not assumed: floor ≥ 30.0% held over consecutive confirmed cycles plus sustained time. Live status: accruing. |
Excluded · accruing | — | — | 287 | 15 | — |
DOT DOT →Why it is withheldBenched by the served-floor governance. The number that benched it is public: at-exclusion floor 20.4% over 15 independent days. Re-inclusion is earned, not assumed: floor ≥ 30.0% held over consecutive confirmed cycles plus sustained time. Live status: accruing. |
Excluded · accruing | — | — | 264 | 15 | — |
ENA ENA →Why it is withheldBenched by the served-floor governance. The number that benched it is public: at-exclusion floor 16.1% over 15 independent days. Re-inclusion is earned, not assumed: floor ≥ 30.0% held over consecutive confirmed cycles plus sustained time. Live status: accruing. |
Excluded · accruing | — | — | 334 | 15 | — |
HOOD HOOD →Measurement noteHOOD levels hit 28% of the time, checked over 46 windows across 10 independent days. The cautious number (95% floor): 9.7%. That is 13.9 points above the no-model mass-weighted baseline (14.2%), cautious floor -4.5 points. |
Serving | 28.2% | 9.8% | 46 | 10 | +13.9pp (floor -4.5pp) |
HYPE HYPE →Why it is withheldBenched by the served-floor governance. The number that benched it is public: at-exclusion floor 20.5% over 15 independent days. Re-inclusion is earned, not assumed: floor ≥ 30.0% held over consecutive confirmed cycles plus sustained time. Live status: accruing. |
Excluded · accruing | — | — | 341 | 15 | — |
INJ INJ →Why it is withheldBenched by the served-floor governance. The number that benched it is public: at-exclusion floor 9.9% over 15 independent days. Re-inclusion is earned, not assumed: floor ≥ 30.0% held over consecutive confirmed cycles plus sustained time. Live status: accruing. |
Excluded · accruing | — | — | 331 | 15 | — |
LINK LINK →Why it is withheldBenched by the served-floor governance. The number that benched it is public: at-exclusion floor 32.5% over 15 independent days. Re-inclusion is earned, not assumed: floor ≥ 30.0% held over consecutive confirmed cycles plus sustained time. Live status: accruing. |
Excluded · accruing | — | — | 272 | 15 | — |
LTC LTC →Why it is withheldBenched by the served-floor governance. The number that benched it is public: at-exclusion floor 27.4% over 15 independent days. Re-inclusion is earned, not assumed: floor ≥ 30.0% held over consecutive confirmed cycles plus sustained time. Live status: accruing. |
Excluded · accruing | — | — | 244 | 15 | — |
MRVL MRVL →Why it is withheldBenched by the served-floor governance. The number that benched it is public: at-exclusion floor 8.5% over 13 independent days. Re-inclusion is earned, not assumed: floor ≥ 30.0% held over consecutive confirmed cycles plus sustained time. Live status: accruing. |
Excluded · accruing | — | — | 190 | 13 | — |
MSTR MSTR →Why it is withheldBenched by the served-floor governance. The number that benched it is public: at-exclusion floor 12.2% over 15 independent days. Re-inclusion is earned, not assumed: floor ≥ 30.0% held over consecutive confirmed cycles plus sustained time. Live status: accruing. |
Excluded · accruing | — | — | 170 | 15 | — |
NEAR NEAR →Why it is withheldBenched by the served-floor governance. The number that benched it is public: at-exclusion floor 21.1% over 15 independent days. Re-inclusion is earned, not assumed: floor ≥ 30.0% held over consecutive confirmed cycles plus sustained time. Live status: accruing. |
Excluded · accruing | — | — | 345 | 15 | — |
NVDA NVDA →Why it is withheldBenched by the served-floor governance. The number that benched it is public: at-exclusion floor 16.5% over 15 independent days. Re-inclusion is earned, not assumed: floor ≥ 30.0% held over consecutive confirmed cycles plus sustained time. Live status: accruing. |
Excluded · accruing | — | — | 272 | 15 | — |
ONDO ONDO →Why it is withheldBenched by the served-floor governance. The number that benched it is public: at-exclusion floor 15.1% over 15 independent days. Re-inclusion is earned, not assumed: floor ≥ 30.0% held over consecutive confirmed cycles plus sustained time. Live status: accruing. |
Excluded · accruing | — | — | 289 | 15 | — |
OP OP →Why it is withheldBenched by the served-floor governance. The number that benched it is public: at-exclusion floor 17.6% over 15 independent days. Re-inclusion is earned, not assumed: floor ≥ 30.0% held over consecutive confirmed cycles plus sustained time. Live status: accruing. |
Excluded · accruing | — | — | 271 | 15 | — |
POL POL →Why it is withheldBenched by the served-floor governance. The number that benched it is public: at-exclusion floor 23.0% over 15 independent days. Re-inclusion is earned, not assumed: floor ≥ 30.0% held over consecutive confirmed cycles plus sustained time. Live status: accruing. |
Excluded · accruing | — | — | 208 | 15 | — |
SEI SEI →Why it is withheldBenched by the served-floor governance. The number that benched it is public: at-exclusion floor 18.0% over 15 independent days. Re-inclusion is earned, not assumed: floor ≥ 30.0% held over consecutive confirmed cycles plus sustained time. Live status: accruing. |
Excluded · accruing | — | — | 196 | 15 | — |
SNDK SNDK →Why it is withheldBenched by the served-floor governance. The number that benched it is public: at-exclusion floor 9.2% over 15 independent days. Re-inclusion is earned, not assumed: floor ≥ 30.0% held over consecutive confirmed cycles plus sustained time. Live status: accruing. |
Excluded · accruing | — | — | 341 | 15 | — |
SOXL SOXL →Measurement noteSOXL levels hit 9% of the time, checked over 347 windows across 15 independent days. The cautious number (95% floor): 2.1%. That is -4.8 points above the no-model mass-weighted baseline (14.2%), cautious floor -12.1 points. |
Serving · floor watch | 9.5% | 2.1% | 347 | 15 | -4.8pp (floor -12.1pp) |
SUI SUI →Why it is withheldBenched by the served-floor governance. The number that benched it is public: at-exclusion floor 19.6% over 15 independent days. Re-inclusion is earned, not assumed: floor ≥ 30.0% held over consecutive confirmed cycles plus sustained time. Live status: accruing. |
Excluded · accruing | — | — | 324 | 15 | — |
TAO TAO →Why it is withheldBenched by the served-floor governance. The number that benched it is public: at-exclusion floor 17.7% over 15 independent days. Re-inclusion is earned, not assumed: floor ≥ 30.0% held over consecutive confirmed cycles plus sustained time. Live status: accruing. |
Excluded · accruing | — | — | 292 | 15 | — |
TIA TIA →Why it is withheldBenched by the served-floor governance. The number that benched it is public: at-exclusion floor 6.5% over 15 independent days. Re-inclusion is earned, not assumed: floor ≥ 30.0% held over consecutive confirmed cycles plus sustained time. Live status: accruing. |
Excluded · accruing | — | — | 293 | 15 | — |
TRX TRX →Why it is withheldBenched by the served-floor governance. The number that benched it is public: at-exclusion floor 56.8% over 15 independent days. Re-inclusion is earned, not assumed: floor ≥ 30.0% held over consecutive confirmed cycles plus sustained time. Live status: accruing. |
Excluded · accruing | — | — | 217 | 15 | — |
TSLA TSLA →Why it is withheldBenched by the served-floor governance. The number that benched it is public: at-exclusion floor 7.3% over 15 independent days. Re-inclusion is earned, not assumed: floor ≥ 30.0% held over consecutive confirmed cycles plus sustained time. Live status: accruing. |
Excluded · accruing | — | — | 165 | 15 | — |
UNI UNI →Why it is withheldBenched by the served-floor governance. The number that benched it is public: at-exclusion floor 18.6% over 15 independent days. Re-inclusion is earned, not assumed: floor ≥ 30.0% held over consecutive confirmed cycles plus sustained time. Live status: accruing. |
Excluded · accruing | — | — | 316 | 15 | — |
WIF WIF →Why it is withheldBenched by the served-floor governance. The number that benched it is public: at-exclusion floor 16.9% over 15 independent days. Re-inclusion is earned, not assumed: floor ≥ 30.0% held over consecutive confirmed cycles plus sustained time. Live status: accruing. |
Excluded · accruing | — | — | 219 | 15 | — |
XLM XLM →Why it is withheldBenched by the served-floor governance. The number that benched it is public: at-exclusion floor 23.6% over 15 independent days. Re-inclusion is earned, not assumed: floor ≥ 30.0% held over consecutive confirmed cycles plus sustained time. Live status: accruing. |
Excluded · accruing | — | — | 289 | 15 | — |
ZEC ZEC →Why it is withheldBenched by the served-floor governance. The number that benched it is public: at-exclusion floor 12.2% over 15 independent days. Re-inclusion is earned, not assumed: floor ≥ 30.0% held over consecutive confirmed cycles plus sustained time. Live status: accruing. |
Excluded · accruing | — | — | 348 | 15 | — |
Nothing swept aside
Additional records, including the experiments that have not proven edge.
These records matter, but they are not the Money Map’s headline claim. Open any section to inspect its current measured state, counts and cautious bounds.
Directional experiments Includes unvalidated and no-edge states
Directional calls: the honest state: accruing
A separate experiment tries to call DIRECTION (up / down / sideways), pre-registered so the rules cannot be tuned to the result. It publishes a number only after the pre-registered gate clears (enough resolved calls, enough days, and a cautious bound that beats guessing). Until then the state is UNVALIDATED and the counters are the disclosure: evidence in progress, never a signal.
BETA: enough resolved evidence to publish the track record with its bound; the beat-the-base-rate gate has NOT cleared (no edge claim). The graduation gate that remains: the cautious bound of the hit rate (11.0%) must beat the cautious bound of doing nothing (68.2%): not yet cleared.
At 120 resolved calls and 28 days the stream is re-measured against its pre-registered bar: pass or fail, we publish the result. Zero is a real state: the counters ARE the disclosure.
The 3-class number: read this one carefully
Our engine currently calls sideways 100.0% of the time, and the market actually moved sideways 61.5% of the time in this window. So the 61.5% below mostly measures how sideways the market was: it is a sideways-base-rate number, not directional skill. The honest check is the residual (our rate minus the base rate): +0.0pp here. Directional calls emitted in the window: 0. Directional accuracy is UNVALIDATED and we say so rather than dress this number up as proof of foresight.
The per-regime residual check (does the engine beat always-saying-sideways in any volatility regime?) has not been computed yet. The accuracy loop writes it each round. We don’t estimate it.
Discipline and reference advisories Separate records, never blended into map accuracy
Discipline advisories: walk-forward record
The product's discipline advisories (e.g. “hold”) are scored after the fact: 67.4% proved correct, 95% lower bound 52.5%, over 43 independent advisory windows in the trailing 30 days. Independent means de-duplicated: the raw repeat count runs about 1.0× higher from re-emissions of the same open position, and we never count those as independent evidence. Descriptive history, not a forecast.
Reference-desk advisories: no open position needed
The same discipline engine also scores a fixed reference watchlist as hypothetical advice: reference-desk units with no open position behind them, graded by the identical 4-hour rule as the position advisories above. 45.8% proved correct, 95% lower bound 43.7%, over 2,189 graded reference windows in the trailing 30 days. This block is never blended into the position-advisory record: it has its own count and its own basis. Descriptive history, not a forecast.
Independent tape checks Venue match rate, coverage and seven-day checks
Is the underlying tape real? Independently re-checked
Every few minutes we re-verify our own liquidation tape against independent exchange references. Match rate = how often our tape agreed when a check was possible; coverage = how often a check was possible. Both shown with the check count; neither hides the other.
| Venue | Match rate | 95% floor | Coverage | Checks (7d) |
|---|---|---|---|---|
| binance | 100.0% | 100.0% | 99.9% | 63,840 |
| bybit | 100.0% | 100.0% | 100.0% | 63,840 |
| deribit | 99.3% | 99.2% | 100.0% | 29,925 |
| deribit: measured since 2026-07-29 (REST capture era). Before that, the feed structurally couldn’t see liquidations (no data (capture blind 2023-10→2026-07)), and we say so. | ||||
| kraken | 100.0% | 100.0% | 100.0% | 63,840 |
| okx | 99.8% | 99.8% | 100.0% | 63,840 |
From proof to product
See the measured levels on the Money Map.
Start with the delayed BTC map without an account. Move to real time only if the product earns it.
Data freshness: levels calibrated 2026-11-16T12:53:11Z · ledger built 2026-11-16T12:49:06Z · engine 3-class measured 2026-11-16T12:19:01Z · advisories scored 2026-11-16 13:20 UTC · X/Twitter news corpus PAUSED (API credits depleted since 2026-08-12 01:44 UTC): an honest gap, disclosed