Private alpha · onboarding scientists & funds
The Market Computation Model

A new way to compute — and to earn.

Encode an optimization problem; the market relaxes to the answer, and the trades that get there return a profit — a trading method built for scientists and engineers.

Live on Binance FuturesNet-profitable solvesNon-custodial
Encode · Relax · Extractlive substrate
Your problem
minimize
f(x)
6 variables
THE
Market
computing…
Answer
x* = [1.00, …]
Profit
+ $60
the equilibrium is the solution — the path is the return
8
Solver classes, verified
100%
Run on live capital
+$60
Net, per $1k solve
0
Custody of your funds
The shift

Stop predicting. Start solving.

Same market — a completely different game. One asks you to guess. The other asks you to solve.

The old way
Conventional trading
  • Predict where prices go
    A directional bet on the market.
  • Win some, lose some
    A fragile edge that decays.
  • You're left with a position
    No knowledge produced — only risk.
The Samādhān way
Solve a problem
  • State a problem to solve
    Mathematics, not a bet.
  • The market relaxes to the answer
    Its equilibrium is the solution.
  • Keep the answer — and the profit
    Two outputs from one run.
How it works

The market does the computing. You read the answer.

01

Encode

State your problem — an objective, a system, a constraint set — and it becomes structured orders on a live market.

02

Perturb

Samādhān calibrates the market’s dynamics (θ, σ, μ) and nudges prices away from rest.

03

Relax

Mean-reversion and arbitrage pull prices to the one configuration that satisfies your problem.

04

Extract

The fills spell out the solution. The trades along the way return a profit.

Mean-reversion

Prices follow an Ornstein–Uhlenbeck pull toward equilibrium — physical relaxation.

Constraints as forces

A residual r = Ax−b becomes a restoring force, zero exactly at the solution.

Adversarial amplification

Arb bots trade away your spreads for profit — correcting constraints, funding the solve.

Proven on real science

The hardest problems, run on the market.

Full benchmark report →

Not toy demos — each was encoded and solved with real capital on a live exchange, and recorded with publication-grade results.

Computational biology

E. coli metabolism

23 metabolic fluxes fit to ¹³C-MFA data under 18 mass-balance + 12 thermodynamic constraints.

constraints satisfied
Optimization

Rosenbrock 6D

The classic non-convex benchmark, minimized live across six mean-reverting pairs.

f = 0.36 · net-profitable
Chemistry

Lennard-Jones clusters

Minimum-energy configuration of an atomic cluster — hard global optimization.

min-energy found
Linear algebra

Toeplitz eigenvalue

Dominant eigenvalue of a structured 8×8 matrix, read from market relaxation.

err 0.0009
Logic

Boolean satisfiability

Every clause satisfied at once; each violation a penalty force.

valid · 29s
Graphs

Shortest path

Path-cost constraints push flow onto the minimum-cost route.

path correct
Dynamics

Euler ODE

Initial-value problems integrated as the residual is driven to zero.

converged
Machine learning

LLM steering

Steer a model toward a target behaviour with the MCM optimizer.

benchmarked
One run, two outputs

You leave with the answer — and the return.

Solution
x* = [1.00, 1.01, …, 0.87]

Residual 0.15 · confidence 0.70 · verified against the known global minimum of the 6D Rosenbrock function.

Return
+$16 → +$89

Per solve on $1,000 of working capital — PnL stayed positive across the entire 31-minute run. The computation paid for itself.

ScientistsEngineersQuant fundsResearchers

Put your hardest problem into the market.

Samādhān is in private alpha. Tell us what you want solved.