One market. Two different questions.

Movement from now — and the chance of finishing above a fixed round reference.

Rust RTDS price inputs · official Chainlink TWAP

SourcePrice · USDFreshnessObservation ageDelivery bound

Waiting for the Rust stream.

Forecast prices remain Binance BTC/USDT microprice. TWAP60 is an optional training input from the official RTDS E18 payload. The untrained baseline does not use it. TWAP30 is disabled.

Current round WAITING

Fixed reference · USDT
Locked for this round
Current spot microprice
Waiting for a quote
Waiting for fresh market state
Time remainingRound startRound endReference sourceSettlement source

Probability at the fixed round end

YES · final > reference
NO · final ≤ reference
Waiting for a referenced, active round
Diffusion baseline
Difference · not trade edge
Raw / calibratedLearned blendFinal outcomeNot settled

Generic Binance receive-clock rounds. No Polymarket/Kalshi settlement mapping is assumed.

The price champion forecasts 3, 5, 10 and 30 seconds ahead. With more than 30 seconds remaining, this card uses a separate terminal model if one is loaded, otherwise the volatility baseline. During the final 30 seconds it uses the selected price model. Automatic Model A training currently promotes price models only.

Round probability history

Model YES estimate / boundsSame-state baselineOptional market midpoint · unverified mapping
Fixed end and fixed reference. Tail bounds use dashed lines; they are not converted into invented certainty.

Price now vs the fixed reference

Observed micropriceFixed reference
Observed round-price history is restored from the local ledger; not a simulated settlement path.

Short-term microstructure · a different target

These estimates concern t+3/5/10/30 seconds. “Above reference” here is NOT the round outcome unless that horizon is exactly the remaining time.

Feed integrity

VenueBookQuote ageDepth ageGaps

One collector; every strategy consumes the same canonical sample.

Model vs baseline · microstructure

HorizonRowsCRPSBaselineSkill

Lower CRPS is better. Baseline losses use the same timestamp and realized target as the model. Correlated rows are not independent experiments.

Prospective round evaluation

StrategySettled roundsPoint-score rowsBounded rowsBrierBaselineSkillLog lossECE

Scored only after the exact target quote and a live-feed witness arrive. Each round gets equal total weight. Use the compare API for challengers started at different times. Overlapping 5m/15m rounds still share information. Tail-only predictions retain score bounds in the API.

Round & model controls — owner token required

Token stays in this page’s memory only. Read it from runtime\v04\control.token (or the token_file in your configuration). Never share it or put it in a URL.

An existing reference is never edited. A manual reference creates a new round and is labeled manual. Generic rounds are not exchange-listed contracts.

Registered models

No artifacts registered yet. Use the CLI to register an existing v0.2 model or a newly trained model.
One canonical recorder · independent model service · persistent research ledgerEvaluation JSON · Service status · Round state