The pipeline, end to end
Resolution first
An analyst pins down exactly what counts as YES, the resolution source, and the deadline before anyone forecasts. Vague questions make dishonest forecasts.
Independent panels
Multiple frontier models run as separate forecasters, each researching live primary sources on its own. No forecaster sees another’s work — so agreement means something.
Red team & judges
Adversarial reviewers attack every case; judges score what survives. A forecast that can’t defend its reasoning doesn’t ship.
Deterministic aggregation
Panel views pool through published, reproducible math. Independent validators recompute the headline from its own tables — divergence gets rejected, not rounded.
What lands in your report
Each forecaster’s full argument with the sources it actually read — cited and linkable, so you can check the load-bearing claims yourself.
The red team’s strongest objections and how each case held up. You see what almost changed the number, not just the number.
Aggregation tables you can recompute by hand: forecaster views, weights, pooled result, confidence band. The headline follows from the table or it fails validation.
Why this design
Any single model anchors on its first frame. Independent forecasters with opposing briefs surface the considerations one pass misses — and the spread between them is reported as honest uncertainty.
Training data ends; the world doesn’t. Forecasters search the live web at run time, so the probability reflects this morning’s filings and headlines, not last year’s memory.
The final number is never “whatever the model said” — it’s computed outside the models from their structured outputs, then checked against them. Trust the process, verify the math.