Skip to content

Trust

Validation and evidence

Every Phoeniks figure carries an evidence level and can be traced to the exact model version and input snapshot that produced it. Validation follows a documented holdout and calibration protocol, and known failure modes are published in the pack rather than omitted.

What this document commits to

Evidence levels
Measured, modelled, inferred, untested
Holdout design
Spatial and temporal, documented first
Portfolio testing
Tail behaviour and spatial covariance
Headline accuracy
Not published; metrics are per context

Key terms on this page

01

Evidence scoring levels#

MeasuredTaken from an authoritative published sourceCitable in a regulatory filing
ModelledProduced by the validated ensembleUsable when labelled as modelled
InferredDerived where direct data is absentIndicative; needs corroboration
UntestedNo validation evidence in this contextNot a basis for a decision
02

Validation protocol#

  • Spatial and temporal holdout design, documented before results are read.
  • Calibration against official statistics and trial data.
  • Tail behaviour and spatial covariance testing for portfolio users.
  • Known limitations stated explicitly in every validation pack.

Frequently asked

Do you publish a headline accuracy number?
No. A single accuracy figure detached from crop, geography and season is not meaningful. Validation metrics are delivered per context in the validation pack.

Related pages

See also

Request access

Institutional access. No self-serve trial.

Request access