Question 1

What is Crene?

Accepted Answer

Crene is investment thesis review infrastructure. One live investment thesis is decomposed into assumptions, independent model reads, weekly movement, and rethink conditions. Public examples include thesis maps for yes or no views, factor maps for continuous distributions, and scenario records for multiple coherent futures. Calibration results are published separately for the leakage controlled benchmark and the broader resolved corpus.

Question 2

How does AI prediction calibration work at Crene?

Accepted Answer

Calibration applies at the consensus layer, not at the underlying model layer. Crene queries four frontier models in isolation, computes a cross model median consensus, and tracks resolution against a tiered source allowlist. Every resolved event becomes a permanent calibration point. Per tier accuracy, per model Brier scores, and per domain accuracy are computed live and published at https://crene.com/methodology.

Question 3

What is a Brier score?

Accepted Answer

A Brier score is the proper scoring rule for probability forecasts on binary outcomes. It is the mean squared error between the forecast probability and the realized outcome (0 or 1). Lower scores indicate better calibration. The no skill baseline is 0.25 (always predicting 0.5); a perfect forecaster scores 0.0. Crene publishes the consensus Brier score and per model Brier scores across the resolved event corpus.

Question 4

Who is Crene for?

Accepted Answer

Crene serves investment teams that need a repeatable thesis review process: hedge funds, asset managers, macro PMs, CIO offices, family offices, and thematic investment teams. A team brings one thesis it is actively debating. Crene maps what the thesis depends on, where models disagree, what changed each week, and what would force a review. Data and API access remain available as the proof layer behind the workflow.

Question 5

What is the difference between an event, a thesis map, a factor map, and a scenario at Crene?

Accepted Answer

Events are base binary outcomes with scalar probabilities. Thesis maps decompose yes or no investment views into assumptions. Factor maps decompose continuous variables into driver distributions. Scenario records map long horizon questions into coherent pathways. Public collection pages distinguish live maps from frozen thesis records and archived scenario records.

Will headline CPI exceed 4.5% year over year in any month from June through December 2026?

What changed, what remains unresolved, and why it matters.

Model disagreement

Belief trajectory

Will headline CPI exceed 4.5% year over year in any month from June through December 2026?

What changed, what remains unresolved, and why it matters.

Model disagreement

Belief trajectory