SUPERPOLYRIO / RESEARCH SYSTEMSPREDICTION MARKETS — V3 & PML2
EXECUTION, UNDER EXAMINATION

The market,
replayed.

Return to the moment before a trade.
Understand what could fill. Account for what did.

FIG. 01 / EXECUTION FIELDILLUSTRATIVE
SourceExecutionAccount
ORDERED OBSERVATIONS
TWO REPLAY PATHS. ONE ACCOUNTING CONTRACT.SCROLL TO INVESTIGATE
01 / HISTORICAL CASE STUDY

The signal.
The consequence.

Q044 follows trade-flow imbalance through real historical markets. Inspect the simulated trades and the account they left behind.

Q044 / RESEARCH STUDY

Trade-flow imbalance

08–28 JUL 2026 PML2 ARRIVAL-SNAPSHOT VARIANT

Historical market observationsSimulated execution · zero fees
TOTAL PNL / USDC—Includes marked inventory
MAX DRAWDOWN—Full account observation path
FINAL EQUITY / USDC—Initial capital: 10,000 USDC
SIMULATED FILLS—Reading saved execution records
THE ACTUAL INPUT18 observed days / 181 requested

The requested window was February–July 2026. The saved input spans July 8–28 with missing dates. This is a saved research result, not a new run of the current engine.

INSIDE THE MARKET

Find the entry.
Follow the exit.

Three observed markets from the same run. Explore actual recorded prices and a selected pair of simulated fills.

MARKET / YES TOKEN

Reading historical market data…

Download market data ↗
Observed price▲ Buy▼ Sell
Market receive time / UTC—

YES price in cents per share. Gaps over six hours remain open. Markers show simulated fill prices; these can differ from the observed market price.

SELECTED COMPLETE TRADE—
HOLDING TIME—
TRADE REALIZED PNL / USDC—
SHARES / EACH SIDE—
Saved simulated fills for the selected complete trade. Times are UTC.
SIDEFILL TIME / UTCFILL PRICELAST OBSERVED PRICEPRICE AGEFEE / USDC
Reading saved fill records…
Inspect the fill identities +

Markets are selected by observation count and history span, not returns. Only the selected complete trade is marked. These examples do not attribute the shared account's PnL to three markets.

EVERY ORDER HAS AN OUTCOME

Keep the unfilled orders in view.

125,383 order intentions in the saved study.

Study assumptions & source evidenceREAD THE RECORD +

What this case represents

Q044-RELAXED-V1 uses historical native trade observations and arrival-snapshot PML2 simulation. Each order is evaluated against a recovered arrival book; this is not the standard continuous-book replay. Market identity is retrospectively mapped.

Fees are fixed at zero. Valuation carries the last observed native trade across input gaps. Residual inventory remains; marked equity is not fully redeemed cash. No profitability or live-execution claim is made.

Trace the published data

Source checks are loading.

Download study data ↗
02 / THE MODELS

Different evidence.
Explicit assumptions.

A trade print and an order book answer different questions. Keep their execution semantics distinct.

01 / TRADE TAPEV3

What the tape can tell you.

Constrain execution with source trades. Keep source-backed quantities, inferred liquidity, and modeled expectations separate.

02 / ORDER BOOKPML2

What the book makes visible.

Reconstruct snapshots, deltas, and trades. Walk visible depth and track order lifecycles, with explicit maker-queue assumptions.

Checking metadataCapabilities and model definitions only
— TAPE PROFILES— L2 SCENARIOS— VARIANTS
Reading current model definitions…
03 / THE METHOD

A result is only as good
as its provenance.

Every replay connects a frozen input to an execution path, an account, and a traceable result.

01

Freeze the input.

Bind market identity, timestamps, and source hashes. Act only on information visible at the time.

02

Replay the events.

Apply each model's order, latency, and capacity rules. Preserve missing-data states.

03

Account for execution.

Reserve cash or inventory before a fill. Track fees, positions, and settlement in the shared ledger.

04

Keep the evidence.

Bind receipts and hashes to the result. Leave valuation unknown when the evidence is incomplete.

Source evidence & modeled quantities+

Source-backed fills, inferred quantities, and modeled expectations are reported separately. Visible L2 depth does not establish a hypothetical order's actual exchange fill or its queue position.

Funding & Oracle settlement+

Insufficient funds reject an order before liquidity is consumed. Settlement requires matching market identity, final payout, and cutoff evidence. A scheduled end time alone does not authorize redemption.

Time, gaps & recovery+

Event time and local receive time retain separate meanings. Future data cannot repair a past observation. Missing coverage stays DATA_NOT_READY; recovery must verify the original input identity.

About this public research view+

Model definitions are read live. Q044 presents a saved historical research run with simulated execution. Synthetic tutorials have their own page. Full replays accept caller-supplied frozen inputs through the Python, CLI, or private API entrypoints.

INSPECT. REPLAY. UNDERSTAND.

Go back to the evidence.

Explore Q044