foxalgoBias
We do not sell a directional prediction. Below is what the measured data actually says about "up" vs. "down" — and, separately, three specific directional edges we went looking for and did not find. As of 08:08 ET.
SESSION BIAS (today)
Per-market lean for the 6 futures we track: today's active conditions — gap vs. yesterday's close, and whether the overnight Asia session already swept yesterday's high/low — checked against measured findings from verified_findings. A market with no active condition backed by a measured edge shows COIN FLIP, on purpose — that is the honest answer, not a missing feature.
Each cell is a call on whichever side crossed 50%: “YES” means the measured rate points toward the outcome above, “NO” means it points toward the outcome below — the percentage next to it is that called side's own confidence, not a margin over the coin-flip base rate.
Grade = the measured probability band itself, with base rate and delta shown alongside as information only. The cutoffs are product design choices fixed before publication, not fitted to outcomes: S ≥ 86%, A ≥ 81%, B ≥ 77%. Below that the card shows COIN FLIP instead — we do not round a weak read up to a strong lean.
E-mini S&P 500 · LEANS UP YES 87% GRADE S (strong)
IF the Asia session already traded above yesterday's high THEN price breaks yesterday's high sometime after 9:30am ET.
conditional 87.2% vs. base 50.7% · +39.1 pp · 95% CI [84.0, 89.8] · n = 506 · SKEPTIC-CONFIRMED
E-mini Nasdaq 100 · COIN FLIP
none of today's measured conditions moves the odds for this market — today's active state matches no finding with a measured edge.
E-mini Dow · COIN FLIP
none of today's measured conditions moves the odds for this market — today's active state matches no finding with a measured edge.
E-mini Russell 2000 · COIN FLIP
none of today's measured conditions moves the odds for this market — today's active state matches no finding with a measured edge.
Gold · LEANS DOWN YES 67% GRADE D
IF the Asia session already traded below yesterday's low THEN price breaks yesterday's low sometime after 9:30am ET.
conditional 67.3% vs. base 33.2% · +32.4 pp · 95% CI [62.6, 71.7] · n = 401 · SKEPTIC-CONFIRMED
WTI Crude · LEANS DOWN NO 87% GRADE S (strong)
IF the Asia session already traded above yesterday's high THEN price breaks yesterday's low sometime after 9:30am ET.
conditional 13.3% vs. base 38.1% · -27.4 pp · 95% CI [10.5, 16.7] · n = 467 · SKEPTIC-CONFIRMED
46 measured rules (6 S / 5 A / 8 B / 27 D). Default view shows S/A/B only (19).
HTF CONTEXT
Higher-timeframe (daily/weekly) direction: we do not have a measured HTF directional edge to show here. The one HTF-shaped hypothesis we tested — whether agreement across timeframes predicts which way price goes next — came back at 48.8% across 2,011,483 range reads in our own data, not a directional signal. See the falsification below and in the graveyard.
HTF direction: measured as a coin flip in our data. Until a genuine higher-timeframe directional finding survives adversarial review, this section stays a coin flip on purpose, same convention as SESSION BIAS above.
Baseline asymmetry
For each market: P(touch 0.5 ATR up) vs. P(touch 0.5 ATR down) from right now, the difference in percentage points, and the sample size behind it. This is a raw geometric view, not the measured-condition leans above.
The asymmetry you see below comes from position in today's range and time remaining in the session — not from a directional forecast. When price sits near today's low, P(up) exceeds P(dn) simply because there is more room to travel upward than downward before the level is reached; that is geometry, the same geometry a coin flip would show if you nailed it to a bounded range. It is not an opinion about where price is headed next.
Futures
| market | P(touch UP 0.5 ATR) | P(touch DOWN 0.5 ATR) | diff (pp) | n | position in range |
|---|---|---|---|---|---|
| E-mini S&P 500 | 42.7% | 43.0% | -0.2 pp | 11,617 | 64% of today's range |
| E-mini Nasdaq 100 | 42.7% | 43.0% | -0.2 pp | 11,617 | 27% of today's range |
| E-mini Dow | 42.7% | 43.0% | -0.2 pp | 11,617 | 54% of today's range |
| E-mini Russell 2000 | 42.7% | 43.0% | -0.2 pp | 11,617 | 19% of today's range |
| Gold | 47.7% | 47.9% | -0.2 pp | 9,610 | 8% of today's range |
| WTI Crude | 44.7% | 48.2% | -3.5 pp | 9,447 | 96% of today's range |
P(touch by close) — horizon convention follows each symbol's detail page.
FX
| market | P(touch UP 0.5 ATR) | P(touch DOWN 0.5 ATR) | diff (pp) | n | position in range |
|---|---|---|---|---|---|
| EUR/USD | 23.9% | 24.0% | -0.1 pp | 8,521 | 26% of today's range |
| GBP/USD | 23.9% | 24.0% | -0.1 pp | 8,521 | 58% of today's range |
| USD/JPY | 23.9% | 24.0% | -0.1 pp | 8,521 | 79% of today's range |
| AUD/USD | 23.9% | 24.0% | -0.1 pp | 8,521 | 83% of today's range |
| USD/CAD | 23.9% | 24.0% | -0.1 pp | 8,521 | 72% of today's range |
| USD/CHF | 23.9% | 24.0% | -0.1 pp | 8,521 | 67% of today's range |
| NZD/USD | 23.9% | 24.0% | -0.1 pp | 8,521 | 23% of today's range |
| Gold spot (XAU/USD) | 23.9% | 24.0% | -0.1 pp | 8,521 | not cached yet |
| Euro FX futures | 23.9% | 24.0% | -0.1 pp | 8,521 | not cached yet |
| British Pound futures | 23.9% | 24.0% | -0.1 pp | 8,521 | not cached yet |
| Australian Dollar futures | 23.9% | 24.0% | -0.1 pp | 8,521 | not cached yet |
| New Zealand Dollar futures | 23.9% | 24.0% | -0.1 pp | 8,521 | not cached yet |
| Japanese Yen futures | 23.9% | 24.0% | -0.1 pp | 8,521 | not cached yet |
| Canadian Dollar futures | 23.9% | 24.0% | -0.1 pp | 8,521 | not cached yet |
| Swiss Franc futures | 23.9% | 24.0% | -0.1 pp | 8,521 | not cached yet |
P(touch within next 540m) — horizon convention follows each symbol's detail page.
Stocks
| market | P(touch UP 0.5 ATR) | P(touch DOWN 0.5 ATR) | diff (pp) | n | position in range |
|---|---|---|---|---|---|
| S&P 500 ETF (SPY) | 40.8% | 42.0% | -1.2 pp | 1,861 | 74% of today's range |
| Nasdaq 100 ETF (QQQ) | 40.8% | 42.0% | -1.2 pp | 1,861 | 88% of today's range |
| Russell 2000 ETF (IWM) | 40.8% | 42.0% | -1.2 pp | 1,861 | 38% of today's range |
| Dow Jones ETF (DIA) | not yet measured | not yet measured | — | — | not cached yet |
| Apple | 41.8% | 39.7% | +2.1 pp | 4,354 | 7% of today's range |
| Microsoft | 41.8% | 39.7% | +2.1 pp | 4,354 | 5% of today's range |
| Nvidia | 41.8% | 39.7% | +2.1 pp | 4,354 | 98% of today's range |
| Amazon | 41.8% | 39.7% | +2.1 pp | 4,354 | 4% of today's range |
| Alphabet (GOOGL) | 41.8% | 39.7% | +2.1 pp | 4,354 | 31% of today's range |
| Meta Platforms | 41.8% | 39.7% | +2.1 pp | 4,354 | 76% of today's range |
| Tesla | 39.9% | 41.1% | -1.2 pp | 1,152 | 68% of today's range |
| AMD | 39.9% | 41.1% | -1.2 pp | 1,152 | 98% of today's range |
| Netflix | 39.9% | 41.1% | -1.2 pp | 1,152 | 4% of today's range |
P(touch by close 16:00 ET) — horizon convention follows each symbol's detail page.
Historical period 2020-2026, these 12 names selected ex-post (survivorship) — calibration applies to these names, not a random stock. Live frozen scorecard accumulates from launch.
Directional edge we looked for and did not find
Research passes tried to turn something in the data into a genuine directional signal. Here is what happened to each, with the number attached.
Timeframe agreement is not a directional signal
Tested whether multiple timeframes pointing the same way predicts which way price goes next. Across 2,011,483 range reads in our own data (6 futures markets, 5 timeframes, 2010-2026), price moved the agreed way 48.8% of the time when all 5 timeframes agreed and 49.0% of the time when at least four did, against a 50.1% baseline. Agreement of the timeframes is not a directional signal, and it changes the size of the next move by about 1%.
Expansion as a directional signal — the effect was a bug
Raw backtest showed range expansion predicting direction with a +18.4 pp edge. After removing an intrabar lookahead bug, the edge fell to +0.2 pp — the entire effect was the bug, not the signal.
If we find a directional edge that survives our own adversarial review, it will appear here with its sample size. Until then, this section stays empty on purpose. See the graveyard for findings we tested and killed, and the methodology for how review works.