Struct CausalCollapseModel 

pub struct CausalCollapseModel { /* private fields */ }

EML-enhanced delta prediction for when the analytical formula is insufficient.

Learns corrections for: multi-edge batching, Fiedler staleness, phase transitions. The model trains on the residual (actual - analytical) so the analytical formula provides the baseline and the EML tree only needs to learn the error.

Architecture

• Depth 3, 9 inputs, 1 head
• Inputs: fiedler_u, fiedler_v, edge_weight, current_lambda2, spectral_gap, graph_density, node_count, degree_u, degree_v
• Output: correction to add to the analytical prediction

Implementations

impl CausalCollapseModel

pub fn new() -> Self

Create a new untrained collapse prediction model.

pub fn is_trained(&self) -> bool

Whether the underlying EML model has been trained.

pub fn training_sample_count(&self) -> usize

Number of training samples collected.

pub fn predict(&self, features: &CollapseFeatures) -> f64

Predict with EML correction applied to analytical formula.

When the model is untrained, returns the pure analytical prediction. When trained, adds a learned correction that accounts for higher-order effects like Fiedler staleness and multi-edge batching.

pub fn record(&mut self, features: CollapseFeatures, actual_delta: f64)

Record a ground-truth observation for future training.

actual_delta is the real change in lambda_2 measured after adding the edge. The model trains on the residual (actual - analytical).

pub fn train(&mut self) -> bool

Train the EML correction model.

Requires at least 50 training samples. Returns true if the model converged (MSE < 0.01).

pub fn drain_events(&mut self) -> Vec<EmlEvent>

Drain accumulated EML lifecycle events for ExoChain forwarding.

Trait Implementations

impl Clone for CausalCollapseModel

fn clone(&self) -> Self

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for CausalCollapseModel

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

Formats the value using the given formatter.

impl Default for CausalCollapseModel

fn default() -> Self

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for CausalCollapseModel

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for CausalCollapseModel

fn serialize<__S>(&self, __serializer: __S) -> Result<__S::Ok, __S::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.