ExplAIner: A Declarative Query Language for Explaining Classification Models
The XAI community has studied a wide range of queries and scores for explaining predictions of ML models. From a data management perspective, this proliferation of explanation notions calls for declarative query languages in which such notions can be specified, combined, and analyzed uniformly. In this paper, we develop such a framework for Boolean models. We first revisit FOIL, an interpretability query language for black-box models, and show that it has two fundamental limitations: it cannot express central optimality-based explanation queries, and its evaluation problem over decision trees
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 51%spiceai/spiceai →
- PossiblePossibly related (embedding) · 46%osmanuygar/sqlatte →
- PossiblePossibly related (embedding) · 28%interpretml/interpret →
“Possibly related via embedding similarity 0.55 (not asserted). Timestamp check: artifact after paper (+6d).”
- LinkedLinked via arxiv author · 85%Marcelo Arenas →
“ExplAIner: A Declarative Query Language for Explaining Classification Models”
- LinkedLinked via arxiv author · 85%Pablo Barceló →
“ExplAIner: A Declarative Query Language for Explaining Classification Models”
- LinkedLinked via arxiv author · 85%Diego Bustamante →
“ExplAIner: A Declarative Query Language for Explaining Classification Models”
- LinkedLinked via arxiv author · 85%Jose Caraball →
“ExplAIner: A Declarative Query Language for Explaining Classification Models”
- LinkedLinked via arxiv author · 85%María Alejandra Schild →
“ExplAIner: A Declarative Query Language for Explaining Classification Models”