Alibi Explain - producing the explanation evidence

How to produce the per-prediction explanation artifacts the matrix requires (Step 2 row 6, rule R2) with Alibi Explain - Anchors, Integrated Gradients, Kernel/Tree SHAP, ALE, Counterfactual Instances.

Alibi Explain provides explanation algorithms answering: "How do predictions change with feature inputs? Which features matter for a prediction? What minimal changes would alter a prediction? How does each feature contribute to predictions?" per the Alibi Explain docs.

When to use

• Compliance / regulator inquiry: "explain this denied loan prediction" - generate counterfactual + per-feature attribution.
• Model debugging: a single instance got the wrong answer; explain why.
• High-risk system audit (EU AI Act Annex III): every prediction ships with a stored explanation record.

Step 1 - Install

pip install alibi

Per the Alibi Explain docs.

Step 2 - Pick the right explainer category

Per the Alibi Explain docs:

Step 3 - The two-method interface

Every Alibi explainer follows the same pattern:

explainer.fit(X_train)        # Some explainers - preparation phase
explanation = explainer.explain(instance)
print(explanation.data)       # Per-explainer schema

Per the Alibi Explain docs Explainer Interface section.

Step 4 - Anchors example (tabular)

from alibi.explainers import AnchorTabular

predict_fn = lambda x: classifier.predict(x)
explainer = AnchorTabular(
    predict_fn,
    feature_names=FEATURE_NAMES,
    categorical_names=CATEGORICAL_INDEX,
)
explainer.fit(X_train)

explanation = explainer.explain(X_test[0])
print("Anchor: %s" % (" AND ".join(explanation.anchor)))
print("Precision: %.2f" % explanation.precision)
print("Coverage: %.2f" % explanation.coverage)

Anchors return a minimal feature subset such that the prediction holds with precision confidence over coverage of the input space.

Step 5 - Counterfactual example

from alibi.explainers import CounterfactualProto

cf = CounterfactualProto(
    predict_fn,
    shape=X_train[0:1].shape,
    use_kdtree=True,
    theta=10.,
)
cf.fit(X_train)

explanation = cf.explain(X_test[0:1])
print("Counterfactual: %s" % explanation.cf["X"])
print("Original class: %d, CF class: %d" % (
    explanation.orig_class, explanation.cf["class"]
))

Counterfactual = "the closest input that flips the prediction" - auditor-friendly format.

Step 6 - Persist explanations as audit records

import json
from pathlib import Path

def explain_and_log(instance_id, instance, explainer, log_dir="explanations"):
    explanation = explainer.explain(instance)
    record = {
        "instance_id": instance_id,
        "timestamp": "...",
        "explainer": type(explainer).__name__,
        "data": explanation.data,
        "meta": explanation.meta,
    }
    Path(log_dir, f"{instance_id}.json").write_text(json.dumps(record))

For high-risk systems, store every explanation alongside the prediction (immutable audit log). Pair with an audit-trail test skill for storage assertions.

Step 7 - Don't confuse with alibi-detect

Alibi Explain is the explanation library. Drift detection uses the sister package alibi-detect (pip install alibi-detect) - that covers concept drift, adversarial detection, outlier detection. They share governance but are separate packages.

Anti-patterns

Limitations

• Counterfactual explainers can produce out-of-distribution instances; constrain via prototypes or domain rules.
• Integrated Gradients requires gradient access (TF/PyTorch native); no support for opaque APIs (SaaS LLMs).

References

• Alibi Explain docs - explainer categories, interface, install, per-method documentation