Explanation in Artificial Intelligence: Insights from the Social Sciences

Catalog evidence and recorded chart appearances. Inclusion is not an endorsement.

Source snapshot imported 2026-10-20. This is not a live feed. Source and contributions.

Evidence and limits

Finding: Human explanations are selective, contrastive, and social, so technically complete accounts may be poor explanations for a user's actual question.

Impact: Strengthen question-specific explanation design. Reject exhaustive trace dumps as sufficient explanation.

Boundary: A synthesis does not establish one best interface. Next: how should the requested contrast determine the evidence shown?

Flags: selective synthesis; no single interface test

Record State: Catalog review recorded; not a performance endorsement

What was reviewed: Structure and relevance screened; not a full evaluation

Inspect original source

Recorded chart appearances

No appearance in the chart editions included in this snapshot. This is not evidence of absence from other editions.