1 vin.diagnostics.summarize

vin.diagnostics.summarize

Summary helpers for VIN v3 inputs, predictions, and cached batch structure.

This module provides a text report spanning actor-visible tensors, candidate CORAL outputs, optional oracle-labelled metrics, and trainable-module structure.

1.1 Functions

Name Description
summarize_vin_v3 Build a human-readable VIN-Core report for one oracle-labelled batch.

1.1.1 summarize_vin_v3

vin.diagnostics.summarize.summarize_vin_v3(
    self,
    batch,
    *,
    include_torchsummary=True,
    torchsummary_depth=3,
)

Build a human-readable VIN-Core report for one oracle-labelled batch.

The summary runs a debug forward pass from the batch’s snippet view and cached actor-visible EVL evidence, then reports tensor shapes/statistics, candidate validity diagnostics, CORAL monotonicity, and optional comparison with oracle labels. Oracle values are used only in the report; they are not passed into the scorer. Correlation is labelled as a pooled candidate association over valid-prefix, candidate-valid, jointly finite pairs; it is not a within-state ranking estimate.

1.1.1.1 Parameters

Name Type Description Default
self VinModelV3 VIN-Core scorer to inspect. required
batch VinOracleBatch Batch carrying candidates, camera rows, cached evidence, and optional oracle supervision. required
include_torchsummary bool Include a parameter/module summary when True. True
torchsummary_depth int Maximum nested module depth for that summary. 3

1.1.1.2 Returns

Name Type Description
str Rendered multiline diagnostic report. The scorer’s original training
str mode is restored before returning.

1.1.1.3 Raises

Name Type Description
ValueError If the oracle batch has a malformed candidate-count or candidate-pose contract. Internal mask construction errors are not converted into an unavailable correlation.
Back to top