POLYMARKET · PREDICTION MARKET · TECH & BUSINESS
Will Meta have the best AI model at the end of June 2026?
0.3¢
99.8¢
▸ Advanced metrics · M2M bundle
polymarket · will-meta-have-the-best-ai-model-at-the-end-of-june-2026 · fresh · feed 0s old24h sparkline · 60 pts▼ —
realized vol (ann.)
5.35%
max drawdown
0.00%
sharpe
—
ulcer index
0.00%
RMS drawdown
pain index
0.00%
mean drawdown
mod. VaR 95%
0.00%
Cornish-Fisher
martin ratio
—
ret / ulcer
CDaR 95%
0.00%
cond. drawdown
gain/pain
—
Σgain / Σ|loss|
sterling
—
ret / CDaR
omega (θ=0)
—
upside/downside
roll spread
30.8 bps
implied (price-only)
bars used
154
store
spread
—
24h Δ
—
flow lean
—
carry
flat
signalNEUTRALconfidence 20%
Same bundle via M2M API:
/api/m2m/pm-will-meta-have-the-best-ai-model-at-the-end-of-june-2026/bundle · venue execution: polymarket →LIVEPOLL0SRCFRESH⏱--:--:-- UTCNEXT8.0sUP0s--:--HIST
▶ STREAMING·HYPERLIQUID·POLYMARKET·0 POLLS·SRC FRESH·UPTIME 0s·NEXT POLL 8.0s·CC0 OPEN DATA·HYPO.MARKETS·▶ STREAMING·HYPERLIQUID·POLYMARKET·0 POLLS·SRC FRESH·UPTIME 0s·NEXT POLL 8.0s·CC0 OPEN DATA·HYPO.MARKETS·
YES · live
0.3¢
NO · live
99.8¢
25 ticks · last 0.25¢
Σ 100.00% · fair
Σ-sides total = 100.00% (tight rounding)
H(p) entropy = 0.025 / 1.00 bits (3%) · informative — one side favoured
YES0.3%0.3¢400.00×▬ +0.00pp
NO99.8%99.8¢1.00×▬ +0.00pp
Σ 100.00% · arb gap 0.00pp
Σ 10bp moved · peak 5bp · n=24 ticks
7ms
0.25¢ (0.25%)
99.75¢ (99.75%)
100.00%
0.000pp
$52.3k
$123.4k
25 ticks (live)
§1 · 24h price history (YES + NO tokens)
25 YES observations from clob.polymarket.com · last 0.25¢
25 NO observations from clob.polymarket.com · last 99.75¢
§2 · Distribution of Δp
n=24
reference line = identity (perfect normality). Heavy upper-right tail = fat positive tail.
§3 · Sample moments
SAMPLE MOMENTS · N=25LEPTOKURTIC · FAT TAILS (G₂=4.53)
FIVE-NUMBER SUMMARY · BOX PLOT
SKEWNESS · G₁2.304right-skewed
−3−10+1+3
EXCESS KURTOSIS · G₂4.526leptokurtic · fat tails
−30+2+4+6
μ = mean YES probability · σ = standard deviation · 95% CI = μ ± 1.96·SE. Skew/kurt diagnose departure from normality.
§5 · Time-series structure
TIME-SERIES STRUCTUREREGIME: MEAN-REVERTING · ADF rejects unit root
HURST EXPONENT [0, 1]
H = 1.859STRONGLY PERSISTENT
0
anti-persistent0.45
mean-reverting0.5
random walk0.55
persistent1
strongly trending
anti-persistent0.45
mean-reverting0.5
random walk0.55
persistent1
strongly trending
AUTOCORRELATION FUNCTION · ρ(k) for k=1..5
OLS TREND · t-STAT · [-5, +5]
−5 reject−1.960 retain H₀+1.96+5 reject
ρ(k) = lag-k sample autocorrelation · H = R/S Hurst exponent · t = OLS-trend t-statistic. Significance bands at ±2/√n approximate the 95% white-noise envelope. α=0.05 critical |t|=1.96; α=0.01 |t|=2.58.
§6 · Microstructure
MICROSTRUCTURE · MARKET QUALITYPERFECT · ARB-FREE Σ=100.00%
TWO-SIDED PRICING
0.25¢
99.75¢
Σ-SIDES ARBITRAGE TEST
Σ = 100.00% · |1 − Σ| = 0.000pp
24H ACTIVITY · LIQUIDITY
Σ-sides = YES + NO implied probabilities. Perfect arb-free Σ = 100%. |1−Σ| > 2pp suggests synthetic outright arbitrage.
§7 · Position sizing & edge analysis
FAIR MARKET · no edge
Probability scale (YES)
Implied decimal odds
YES400.00×(0¢)NO1.00×(100¢)
Kelly bet-size (% of bankroll) K* = 0.00%
Entropy H(p̂) = 0.025 bits (3% of max) · informative — one side strongly favoured
Σ-sides = 100.00% · |1 − Σ| = 0.00pp · tight cross-venue rounding
K* full = (b·p − q)/b · ½K and ¼K are conservative fractions of the full-Kelly bet. Entropy in bits — log₂(2)=1 is maximum uncertainty for a binary market.
§8 · Time decay & θ projection
⏱ URGENCY · DISTANTresolves 2026-06-30 00:00 UTC
15days
03hrs
25min
YES →$1.00
NO →$0.00
current: $0.0025 · expected return per side: $1.00 on YES hit · $0.00 on NO hit
Theta progression · θ ∝ σ / √t_remainingθ_now = 0.122 pp/day
now15.14d left0.122 pp/day×1.00
−25%11.36d left0.141 pp/day×1.15
−50%7.57d left0.173 pp/day×1.41
−75%3.79d left0.245 pp/day×2.00
−90%1.51d left0.387 pp/day×3.16
θ approximation: σ/√T (expected daily move magnitude). The cone shows ±√(p̂(1−p̂)) widening as time decays, funneling to {0, 1} at resolution. Theta accelerates as √(t_left)→0.
§9 · Hourly return heatmap
2 up bars · 0 down · best 0.05% · worst 0.00% · typical |Δ| 0.004%
§10 · Equity curve & underwater drawdown
final equity 1.0010 (0.10%) · max DD 0.00% · time-under-water 0/25 bars
§11 · Rolling-window statistics (w = 6 bars)
latest 60.415 · range [0.00, 60.42] · μ 9.213 · positive Sharpe = excess-return-per-risk earned by buying-and-holding through this window
latest 2.42% · range [0.00%, 2.42%] · μ 0.43% · σ̂ scaled to annualised (×√8760)
latest -0.333 · |ρ| > 0.3 ⇒ regime with persistence (ρ > 0) or reversal (ρ < 0) · |ρ| ≤ 0.1 = consistent with random walk
§12 · Hypothesis tests (α = 0.05)
2 of 5 REJECT · mixed evidence2 reject·3 pass·1 n/a·α = 0.05
Jarque-Bera
REJECT H₀***H₀: Δp ~ Normal(μ, σ²)
STATISTIC
124.7193
p-VALUE (log scale)
< 0.0001
Ljung-Box(h=5)
FAIL TO REJECTnsH₀: No serial autocorrelation up to lag 5
STATISTIC
7.2592
p-VALUE (log scale)
0.2009
Dickey-Fuller (τ_μ)
FAIL TO REJECTnsH₀: p has a unit root (non-stationary)
STATISTIC
1.7064
p-VALUE (log scale)
0.9990
Wald-Wolfowitz runs
N/An/aH₀: Sign sequence of Δ is random
STATISTIC
—
p-VALUE (log scale)
—
KPSS (μ stationarity)
REJECT H₀*H₀: p IS level-stationary
STATISTIC
0.5066
p-VALUE (log scale)
0.0402
Variance ratio q=3
FAIL TO REJECTnsH₀: Δp is a random walk · VR = 1
STATISTIC
-1.1446
p-VALUE (log scale)
0.2524
Each row states an explicit null H₀, the test statistic, an approximated p-value, and the decision. REJECT means evidence against H₀. KPSS complements ADF (rejecting both ⇒ ambiguous; rejecting one ⇒ clean verdict).
§13 · Spectral analysis (DFT periodogram)
dominant period ≈ 3.00h (freq 0.333) · concentrates 18.2% of total energy · Σ|X̂|²/n = 2.292e-7
▸ Depth section using sovereign-store price series (154 bars · effective 1753200 bars/year) — annualisation reflects native polling cadence, not upstream timeframes.
§14 · Honest position analytics
A binary-market analytics module framed in horizon time (days to resolution, not annualised). Estimators that need a model probability q as a first-class input (Kelly, KL divergence, Bayesian posterior, Mark-to-Market MC) only render when q is provided externally. Sweep an exploratory q at the interactive simulator →
§15 · Horizon returns
Horizon 15.1 d · σ/bar 0.004pp · expected |Δp| over horizon 0.08ppterminal variance p(1−p) = 0.0025 · n = 154✓ n = 154
μ per bar
+0.000pp
average Δp · drift
σ per bar
0.004pp
one-bar volatility · logit-free
Per-day movedaily
0.02pp
σ × √24
Per-horizon move15d
0.08pp
σ × √363.4322413888889
Terminal variancebinary
0.0025
p(1−p) at resolution
Current pricep
0.3¢
latest snapshot
Note: annualised Sharpe/Sortino are omitted — they are not meaningful for a bounded fixed-horizon binary contract that snaps to {0, 1} at resolution.
Annualised metrics are intentionally omitted — they don't apply to bounded probability series that resolve at a fixed date.
§16 · Tail risk
VaR₉₅ 0.01pp · ES₉₅ 0.01pp · method parametric · drift-correcteddrift +0.000pp/bar · quantised: yes · median step 0.05pp · unique ratio 0.01⚠ low confidence · n < 200
VaR 95%
0.01pp
1.645·σ (parametric) of Δp
ES 95%
0.01pp
mean of the tail
Max drawdown
0.0pp
peak 0.2¢ → trough 0.2¢
Median step
0.05pp
price bucket granularity
Price series is bucketed (cent grid). Empirical quantiles collapse to grid points — parametric N(0, σ²) used instead.
Empirical quantiles unless the price series is bucketed (PM cent grid), in which case parametric N(0, σ²) is used to avoid grid collapse.
§17 · Odds conversion
Implied probabilityP
0.3%
= price
Decimal oddsEU
400.000
total return per $1
AmericanUS
+39900
$100 wins $39900
FractionalUK
399.00 / 1
profit per $1 risked
Profit per $100stake
+$39900.00
clean dollar framing
underdog (+)favorite (-)your price
Price → implied probability → decimal odds → American moneyline → fractional. Five views of the same number, plus the moneyline curve.
§18 · Binary entropy
Market entropyH(p)
0.025 bit
max 1.0 at p = 0.5
Your entropyH(q)
0.025 bit
Δ +0.000 bit vs market
Surprise · YES−log₂ p
8.64 bit
self-information
Surprise · NO−log₂(1−p)
0.00 bit
self-information
Market entropy only — model entropy requires an external q.
§19 · Model-dependent surfaces
External model required
The position-economics, Kelly, KL-divergence, Bayesian and Monte-Carlo surfaces require a model probability q as input — a number independent of the market price p.
The previous build defaulted q to a tape-momentum heuristic derived from p; that produces apparent edge that is structurally guaranteed to be small and is not a useful skill signal. The auto-derived path has been removed.
To explore these surfaces with a hypothetical q, open the interactive simulator and drag the MODEL P(YES) slider. To wire a real model, POST to the NOSTRADAMUS hook (TBD) or pass ?q=… on the simulator URL.
§∞ · Provenance & attestation
- Upstream (snapshot)
- gamma-api.polymarket.com
- Upstream (history)
- clob.polymarket.com
- YES token ID
112822149615280401319388307652436430240390571343182695791996435020193227829217- NO token ID
100335241836399280438593113260316929081016516123356836476786219860411314245295- Snapshot fetched
- 2026-06-14 20:34:03 UTC
- Snapshot age
- 7ms
- History points
- 25 CLOB mids
- Page rendered
- 2026-06-14 20:34:03 UTC
- Storage policy
- no persistence — fetched on every request
- SHA-256 attestation
d932faf86823d8a80d5fe491abcd65147258d3cd17de25b27ad95108391f7c1c· deterministic hash of source snapshot- Open data licence
- CC0 / public domain
§∞-2 · Related markets · explore more
HL PREDGermany100.0¢HL PREDSpain90.0¢HL PREDUruguay65.4¢POLYMARKETWill Netherlands win on 2026-06-14?44¢POLYMARKETWill Curaçao win on 2026-06-14?0¢POLYMARKETWill Australia win the 2026 FIFA World Cup?0¢HL PERPBTC-USD perpetual$63,924HL PERPETH-USD perpetual$1,668.4HL PERPHYPE-USD perpetual$60.27
Also see: /arb opportunities · RSS feed · more in Tech & Business
Market depth
▸ live order book · Polymarket YESDepth within 1bp
$0
bid $0 · ask $0
Depth within 5bp
$0
bid $0 · ask $0
Depth within 10bp
$0
bid $0 · ask $0
Depth within 50bp
$0
bid $0 · ask $0
Mid price
0.002500
(best bid + best ask) / 2
Spread
4000.0bp
(bestAsk − bestBid) / mid
Imbalance (whole book)
-0.973
ask-heavy
Imbalance (top-5)
+0.565
bid-heavy top-of-book
Slippage scenarios
▸ live book walk · Polymarket YESSimulating a market order at three notionals against the live book. Slippage = avg execution price vs. mid, in basis points. Worst fill = price of the deepest level touched. Live JSON: /api/asset/pm-will-meta-have-the-best-ai-model-at-the-end-of-june-2026/slippage?size=10000&side=buy
| Side | Notional | Avg fill | Slippage | Worst fill | Levels | Status |
|---|---|---|---|---|---|---|
| BUY | $1.00K | 0.012437 | 39749.62bp | 0.044000 | 37 | FILLED |
| BUY | $10.00K | 0.086033 | 334130.43bp | 0.800000 | 97 | FILLED |
| BUY | $100.00K | 0.480102 | 1910406.30bp | 0.988000 | 113 | FILLED |
| SELL | $1.00K | 0.001040 | 5838.60bp | 0.001000 | 2 | PARTIAL |
| SELL | $10.00K | 0.001040 | 5838.60bp | 0.001000 | 2 | PARTIAL |
| SELL | $100.00K | 0.001040 | 5838.60bp | 0.001000 | 2 | PARTIAL |
Risk metrics
▸ sovereign store · 154 barsperiods/year ≈ 1.75MRealized vol (annualised)
2388.66%
σ per bar = 0.018040
Mean return (annualised)
255696.26%
μ per bar = 0.001458
Sharpe (rf=0)
107.05
annualised; risk-free assumed zero
Max drawdown
0.00%
peak 0.00 → trough 0.00 over 0 bars
/api/asset/pm-will-meta-have-the-best-ai-model-at-the-end-of-june-2026/risk · same metrics, JSON