The Public Loss Ledger.
Every resolved call, wins and losses, logged before it closed. Receipts not promises.
The losers render at the same size as the winners. Most services bury the red. We open on it. Counts and per-row outcomes only, loaded live from the same endpoint our admin dashboard reads. Nothing is cached from launch day.
Model validation snapshot
The outcome stream behind this ledger.
Resolved outcomes are the hard part of the claim: this panel links each ledger view to live evidence quality and backtest signal stability.
Telemetry is still loading.
Alert and threshold posture
Model tuning diagnostics
Public view of ML edge evidence and threshold-risk posture from live bucket telemetry.
Loading model telemetry...
Resolved this window
Window-wide count of resolved calls across live CORE and Research Lab super rows. Wins and losses, side by side. No profit factor, no win rate, no averaged return — just the tally and each row's own outcome.
Every resolved call
Each row links to its standalone, timestamped receipt. The default view is the losers, because that is the part nobody else shows.
Resolved predictions only, newest first, last 14 days (up to 200 rows). Net is the realized result for that single row. Information only. Not financial advice.
Verify, then decide.
Read the ledger first, including the worst row and loss context. If it still earns your attention, connect your wallet.
Want to verify the ledger first? Open the loss ledger.
This is the whole pitch: every call logged before it closes, the losses kept in plain sight. Verify the chain, read the wider evidence window, then decide if the desk is worth following.