Reality Accountability Scoreboard
Settled Brier, reliability, vs market/expert, over-time — world truth only after settlement.
- ok
- true
- route
- /api/accountability/scoreboard
2026 product definition
Plug any model in as the brain. KELLY forces: ask → missing facts → forecast/answer → proof receipt → check-in → settlement → calibration → only then a governed memory proposal.
Sector labs are lenses. JobProof is paused. Brains are engines — not the product. Ops ceilings (Neon opt-in, soft-cap) are not densify thrash — after Railway ship: npm run accountability:post-deploy-hold.
Truth console · public scoreboard
Live public Brier volume mapped to the loop. Process is not world truth. Memory remains gated.
Settled
0
Weather / Sports
0 / 0warming
Markets
0
Scale remaining
1000
Proof auditor · Answered directly by KELLY · public writes blocked
Glass Lab · proof lens into KELLY
Calibration passports, Brier posture, and drive status for forecast confidence quality.
Inspect live proof, truth debt, generation wall, and organ health. This lens does not write ground truth — KELLY remains the only write authority.
Settled Brier, reliability, vs market/expert, over-time — world truth only after settlement.
Forecasts sealed before outcome (no settle, no prime memory write).
Public calibration summary for forecast accuracy and probability hygiene.
Operational calibration drive, settlement progress, and eligible feeds.
Personal verified-set passport: dual-lane Brier, reliability bins, Brier decomposition, domain_calibration (not public skill claim).