Struct ProbePlan 

pub struct ProbePlan {
    pub probe: usize,
    pub expected_log_growth: f64,
    pub budget_from_scratch: f64,
    pub budget_remaining: f64,
}

The experiment plan for one contested claim: which probe to run, the expected per-observation evidence growth under the alternative, and the design-time resolution budget. This is the loop’s actionable output — hand probes[probe]‘s δ to crate::inference::steering::steer_delta (which enforces the validity radius and reports realized dosimetry), evaluate both hypotheses’ likelihoods on the realized outputs, absorb the log-ratio into the claim’s e-process, re-certify.

Fields

probe: usize

Index into the candidate probe list.

expected_log_growth: f64

Expected log-growth of the deciding e-process, nats/observation, under the alternative (the KL of the hypotheses’ predicted responses in the output-Fisher metric).

budget_from_scratch: f64

Expected observations to cross 1/α from ZERO evidence — the conservative from-scratch budget.

budget_remaining: f64

Expected observations to cross 1/α from the claim’s CURRENT log-evidence — the remaining budget; 0 when already across.

Trait Implementations

impl Clone for ProbePlan

fn clone(&self) -> ProbePlan

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for ProbePlan

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl PartialEq for ProbePlan

fn eq(&self, other: &ProbePlan) -> bool

Tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &Rhs) -> bool

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl StructuralPartialEq for ProbePlan