The current README identifies Alibi as source-available and distinguishes it from Alibi Detect; exact release license rights require separate review.
Inspect the evidence ↘GOVERNATLAS / PRODUCT DOSSIER
Alibi Explain
Alibi documents a source-available Python library for machine-learning model inspection and explanation.
THE DOCUMENTED SCOPE
What the current evidence describes.
Source-attributed capabilities and limits. Inspect the full record before drawing a conclusion.
Its API separates initialization, fitting and explanation, returning metadata and method-specific explanation data.
Inspect the evidence ↘Alibi documents local and global methods for classification and regression, including Anchors, accumulated local effects, counterfactuals and SHAP methods.
Inspect the evidence ↘01 / CONTEXT & SCOPE
Understand the proposition.
Define the boundary.
The decision to make
Choose the explanation method and its input requirements explicitly. Local anchors, counterfactuals and global summaries answer different questions. The current README calls Alibi source-available, so review the exact release license before assuming an unrestricted open-source deployment. Keep it distinct from the existing Alibi Detect product.
What this record does not establish
Current primary material describes a source-available explanation library, correcting the initial research candidate wording. License permissions, method-specific dependencies and commercial support need separate review; no detection-product parity or causal assurance is inferred.
1 current source · 4 published assertions
Source coverage is a research boundary, not a quality score.
Source coverage is a research boundary, not a quality score.
02 / YOUR EVALUATION
Turn interest into a useful trial.
A
A test worth running
For a synthetic routing classifier, inspect one local explanation and its metadata, then test a documented input change in an authorized environment. Retain fit data, method settings and an unresolved result. Ask a reviewer why the chosen method answers the stated question and why a different method may not.
GovernAtlas editorial proposal. We have not performed this test.
B
Evidence to bring back
- An exact package/license/method/input-requirements manifest.
- An explanation object with settings, evidence references and interpretation limits.
THE OPERATING DETAIL
Match the method to the question and the available access.
GovernAtlas analysis: practical review considerations, not findings from a product test.
03 / DOCUMENTED EVIDENCE
Read the claim. Inspect the basis.
Each statement retains its classification and preserved source. A vendor assertion is not an independent test result.
first party asserted
The current README identifies Alibi as source-available and distinguishes it from Alibi Detect; exact release license rights require separate review.
Source, dates & preserved provenance
Alibi Explain — primary scope and current identity ↗Authority: first party
Observed 2026-10-16 · Reviewed 2026-10-16 · current until 2026-11-15
Artifact SHA-256: 837ae032cd2069bd7547273a6dc2be2dc5e5f9aa9be7a88dfc31ae6e36447a8e
The hash identifies the preserved capture. The live source may have changed.
first party asserted
Its API separates initialization, fitting and explanation, returning metadata and method-specific explanation data.
Source, dates & preserved provenance
Alibi Explain — primary scope and current identity ↗Authority: first party
Observed 2026-10-16 · Reviewed 2026-10-16 · current until 2026-11-15
Artifact SHA-256: 837ae032cd2069bd7547273a6dc2be2dc5e5f9aa9be7a88dfc31ae6e36447a8e
The hash identifies the preserved capture. The live source may have changed.
first party asserted
Alibi documents local and global methods for classification and regression, including Anchors, accumulated local effects, counterfactuals and SHAP methods.
Source, dates & preserved provenance
Alibi Explain — primary scope and current identity ↗Authority: first party
Observed 2026-10-16 · Reviewed 2026-10-16 · current until 2026-11-15
Artifact SHA-256: 837ae032cd2069bd7547273a6dc2be2dc5e5f9aa9be7a88dfc31ae6e36447a8e
The hash identifies the preserved capture. The live source may have changed.
first party asserted
Alibi documents a source-available Python library for machine-learning model inspection and explanation. Scope: primary documentation only; no independent model test, fairness determination, causal finding or compliance approval.
Source, dates & preserved provenance
Alibi Explain — primary scope and current identity ↗Authority: first party
Observed 2026-10-16 · Reviewed 2026-10-16 · current until 2026-11-15
Artifact SHA-256: 837ae032cd2069bd7547273a6dc2be2dc5e5f9aa9be7a88dfc31ae6e36447a8e
The hash identifies the preserved capture. The live source may have changed.
Source register
Alibi Explain — primary scope and current identity ↗first party · captured 2026-10-16
Brand asset provenance
Organization identity asset from its official website; inclusion does not imply endorsement.
Official website ↗ · Original asset ↗04 / BEFORE YOU COMMIT
Better questions.
A clearer decision.
Resolve these with the provider and your own evaluation team.
Can you provide an exact package/license/method/input-requirements manifest for the selected configuration?
Can you provide an explanation object with settings, evidence references and interpretation limits for the selected configuration?
Which exact version, entitlements, data paths and responsible roles apply?
Regulatory applicability requires a separate, current determination. Inclusion is not certification.
KEEP THE RECORD USEFUL
A dossier should stand up to scrutiny.
Have a source that changes this picture? Submit it for editorial review.