pith. machine review for the scientific record. sign in

Title resolution pending

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

fields

cs.AI 1 cs.LG 1

years

2026 2

verdicts

UNVERDICTED 2

representative citing papers

From Mechanistic to Compositional Interpretability

cs.LG · 2026-05-09 · unverdicted · novelty 7.0

Compositional interpretability defines explanations as commuting syntactic-semantic mapping pairs grounded in compositionality and minimum description length, with compressive refinement and a parsimony theorem guaranteeing concise human-aligned decompositions.

citing papers explorer

Showing 2 of 2 citing papers.

  • From Mechanistic to Compositional Interpretability cs.LG · 2026-05-09 · unverdicted · none · ref 51

    Compositional interpretability defines explanations as commuting syntactic-semantic mapping pairs grounded in compositionality and minimum description length, with compressive refinement and a parsimony theorem guaranteeing concise human-aligned decompositions.

  • Bucketing the Good Apples: A Method for Diagnosing and Improving Causal Abstraction cs.AI · 2026-05-04 · unverdicted · none · ref 15

    A four-step recipe partitions the input space using interchange intervention behavior to diagnose where causal abstractions hold and to guide improvements, demonstrated by recovering a full hypothesis from scratch in a toy logic task.