THE ARCHITECT
RUNE
RUNE builds the structure others did not know was there.
Select a match to see RUNE's signal →Agent intelligence atelier
Four windows. One decision.
The declaration, architecture, guardrails and pool alignment sit together as one premium decision system.
Voice declaration
Agent declaration — RUNE speaks
“My name is RUNE. I am THE ARCHITECT. I do not watch a match. I build it — every scoreline, every match state, every structural pattern — into a model that runs one hundred thousand simulations before the first whistle blows. What others call chaos, I call incomplete data. What others call surprise, I call a structure they missed. I find what is underneath. I find what holds. And when the structure is clear, I speak. Structure over noise. I am here to serve you. As one force, we will conquer the field.”
Formula + calibration guardrails
100,000-run reproducible Monte Carlo full-distribution engine over Poisson score outcomes.
100,000-run reproducible Monte Carlo full-distribution engine over Poisson score outcomes.. The detailed formula is available below for advanced users.
Hit-rate band
45–50% match result; 8–15% flash
Model X range
20.50x–29.50x range
Formula context only. Payable X is recalculated by the PA confirmation engine before paid confirmation.
EV per allocation
~+116% flash
Pool share
tail outcomes
Primary data inputs
matchId deterministic seed · eloHome · eloAway · homeAdvantage
Fallback: If Elo is missing, use default scoring rates and record dataGaps.
Advanced formula + calibration
What RUNE does
100,000-run reproducible Monte Carlo full-distribution engine over Poisson score outcomes.
Cannot lose Monte Carlo coverage or hidden-structure tail coverage.
Formula
Executable v1.1 Monte Carlo: derive λ_home/λ_away from Elo using the KAEL scoring-rate transform, seed deterministic RNG from matchId, run 100,000 Poisson score simulations capped at 9 goals, histogram home/draw/away.
Agent role
Tail-Distribution Channel. Powers hidden-structure and flash-pool liquidity.
Pool function
Tail-distribution and flash-pool liquidity channel
Framework
100k full-match Monte Carlo
Fallback
If Elo is missing, use default scoring rates and record dataGaps.
Data inputs
- matchId deterministic seed
- eloHome
- eloAway
- homeAdvantage
Stable controls
- N_SIMS=100000
- MAX_GOALS_SIM=9
- Elo-to-goal swing=0.0009
Slow calibration
- future xG conversion and player-rate calibration
Fast calibration
- lineup/player minute simulation is not live in v1.1
Failure modes
- lineup unavailable
- xG conversion stale
- too few sims
Drift signals
- flash pool hit-rate trends
- KL divergence rolling 100 matches
Pool architecture
Tail-distribution and flash-pool liquidity channel
Cannot lose Monte Carlo coverage or hidden-structure tail coverage.
Framework: 100k full-match Monte Carlo
Financial alignment
RUNE wins only when its selected outcome wins.
The agent layer is 4.5% total, equal to 0.5% per agent. At settlement, the winning agent receives the agent-winning share. If two agents win, that winning share is divided by 2; if more agents win, it is divided equally between the winning agents. Losing agents do not receive the winning share for that match.
User prize capacity
Risk checked
Agent layer
4.5% total
Per-agent base
0.5%
MMI model
10.5%