Experiments
Queue governed training runs (time-based splits, walk-forward, skill gate) and review the experiment history, including imported research records.
Models have no execution authority
Research metadata only. Models cannot submit orders, set position size, approve trades, override risk rejections, change policy or promote themselves. At most, a model in the paper stage may rank or filter deterministic candidates. Training data and results are historical (or explicitly labelled synthetic) and make no profitability claim.
Training configuration
Insufficient permissions
Requires role trader
Viewing is allowed; queuing training jobs requires role trader or higher.
Job queue
Loading jobs…
Experiment history
Loading experiments…