The moat · server-verified anti-cheat

Integrity is the product.

There is no house RNG — results come off a real server. The only thing that matters is the integrity of the matchup. Every duel runs a forensic gauntlet: demos parsed, behavior scored, risk fused into a posterior, and a verdict issued — auto-cleared, held, or routed to a human. The hard engineering is the moat.

0
Matches scored
0.0%
Precision
0.00%
False-positive rate
Never auto-ban on one match Server-recorded demo forensics
Demo forensics
stat-v1.3.0 · match #4F9C-21A
31%posterior · Auto-clear

Hover a signal to preview its effect on the posterior · illustrative forensics

The pipeline

Every match runs the gauntlet

Event-driven, async, post-match. Each stage is its own bounded context, wired only through the bus — no shared source. A demo enters; a verdict leaves.

1
C5Go

Demo parse

Fetch the server-recorded .dem, parse to structured events + columnar features.

~140 MB demo → parquet
2
C6Python

Feature extraction

Aim kinematics, flick distributions, pre-fire timing, recoil control, snap geometry.

320+ engineered features
3
C6Python

Cheat scoring

Statistical + ML likelihood per vector: aimbot, triggerbot, wallhack.

stat-v1.3.0
4
C7TS

Risk fusion

Fuse scores with account history + the account-link graph into a posterior.

Bayesian posterior
5
C7TS

Enforcement verdict

Auto-clear, hold winnings + restrict, or route to the human review queue.

auto-ban ≥ 0.92 + ≥2 matches
Auto-clear
96.4%of matches

Posterior below the review band. Payout released instantly.

instant settle
Hold + restrict
0.55–0.92review band

High posterior. Winnings held, account restricted pending verdict.

dual-control release
Human review
≥ 0.92posterior

Routed to the C13 console with a full evidence package.

demo + features attached
FPR-gated precision

A wrongful ban is catastrophic — so we never auto-ban on one match

Auto-ban fires only on a posterior ≥ 0.92 sustained across ≥ 2 matches. Everything in the band below routes to a human with the full evidence package. The model is tuned to a false-positive rate, not raw accuracy.

Matches scored
0

every duel, every server

Precision
0.0%

of flags are true cheats

False-positive rate
0.00%

wrongful flags per clean match

Auto-ban rate
0.0%

the rest go to humans

Posterior cheat probabilitystat-v1.3.0
auto-clearhuman reviewauto-ban
0.000.550.921.00

The auto-ban gate is posterior ≥ 0.92 AND ≥ 2 matches. A single high-scoring match never bans — it can only hold winnings and open a review. The cost of a wrongful ban is treated as far higher than a missed catch.

The two-match gate0.92 × 2 matches

Auto-ban only fires when the signal holds across independent matches. One game can single-handedly hold & review — never ban.

Match 10.97
Match 20.39
gate 0.92
Hold + human review
One hot game, one clean — never bans
Posterior distribution

The mass sits near 0 — clean play. The review and ban bands are a thin tail.

~96%
Clear
~3%
Review
~1%
Ban
Recall
0.0%
Auto-clear rate
0.0%
The adversaries

Four attackers, one load-bearing defense

Each adversary needs a distinct detector — but trust tiers gated by stake is the unifying control that blunts all four at once, and doubles as the AML mechanism.

Smurfs / alts

01
Threat

Manufacturing a low rating to farm money off weaker opponents.

Defense

RD-gated rating + device fingerprint + tiered stake ceilings.

Stake gated atBasic+

Boosters / ringers

02
Threat

A stronger player logging into someone else’s account.

Defense

Behavioral baselining + Steam-tenure signals + trust tiers.

Stake gated atVerified+

Collusion / chip-dumping

03
Threat

Linked accounts arranging to move money — the laundering vector.

Defense

Account-link graph + directional-flow detection + dual-control clawbacks.

Stake gated atTrusted+

Cheaters

04
Threat

Aimbot / triggerbot / wallhack running on the server.

Defense

Server-side demo forensics + ML scoring + held-payout on high posterior.

Stake gated atVerified+
The unifying mitigation

Trust tiers gated by stake

A higher stake requires a higher tier — which requires more identity verification, longer tenure, and a cleaner demo-forensic record. One mechanism raises the cost of every attack at once, and satisfies AML obligations. Build it early; it is load-bearing.

Unverified
free only
Basic
≤ $5
Verified
≤ $50
Trusted
≤ $250
Elite
≤ $1,000

Stake ceilings illustrative · money is a per-region feature flag