← Observatory home
Reverse · 3 of 12

Formal Robustness Certificate

Can the local prediction be bounded formally inside the selected region?

image_pattern_cnn2d · Open result image ↗
Formal Robustness Certificate result for the image_pattern_cnn2d fixture
Real output from the small deterministic CNN-2D documentation fixture.

What it shows

An interval-bound certificate with its assumptions and verified radius.

Claim boundary

A certificate applies only to its stated norm, radius, model, input, and verifier assumptions.

Run this with the installed CLI

Point VRAVEN at a validated model bundle. This produces one focused HTML report and works after a normal PyPI installation.

vraven analyse ./my-model \
  --task explain \
  --preset standard \
  --format html \
  --output vraven-report.html

Start with the model-folder guide if your bundle is not prepared yet. The larger documentation fixture is a contributor workflow described in Develop from source.

Generate this view

IntervalBoundVerifier(model).certify(input_tensor, target=target).write_html(output_path)
InputModel bundle, one reference input, selected target
Display modepublication_light
Evidence levelFormal — within stated verifier assumptions
Machine outputreverse/formal_robustness_certificate.html
Related APIvraven.IntervalBoundVerifier
Fixtureimage_pattern_cnn2d

How to read the result

  1. Start with the title and target metadata in the generated report.
  2. Read the strongest structures first, then inspect weaker or opposing evidence.
  3. Check the stated evidence level and status before treating a relationship as causal or formal.
  4. Retain the trace, model version, preprocessing, and VRAVEN version with any published claim.
Reproducibility noteThe screenshot is public documentation evidence. The source run remains local-first; raw provenance files are not published because they can contain machine paths.