Causal Abstractions, Categorically Unified

• URL: http://arxiv.org/abs/2510.05033v1
• Date: Mon, 06 Oct 2025 17:09:30 GMT
• Title: Causal Abstractions, Categorically Unified
• Authors: Markus Englberger, Devendra Singh Dhami,
• Abstract summary: We present a categorical framework for relating causal models that represent the same system at different levels of abstraction.<n>Our approach unifies and generalizes previously considered causal abstractions.<n>We discuss how methods from mechanistic interpretability, such as circuit analysis and sparse autoencoders, fit within our framework.
• Score: 9.341830361844337
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We present a categorical framework for relating causal models that represent the same system at different levels of abstraction. We define a causal abstraction as natural transformations between appropriate Markov functors, which concisely consolidate desirable properties a causal abstraction should exhibit. Our approach unifies and generalizes previously considered causal abstractions, and we obtain categorical proofs and generalizations of existing results on causal abstractions. Using string diagrammatical tools, we can explicitly describe the graphs that serve as consistent abstractions of a low-level graph under interventions. We discuss how methods from mechanistic interpretability, such as circuit analysis and sparse autoencoders, fit within our categorical framework. We also show how applying do-calculus on a high-level graphical abstraction of an acyclic-directed mixed graph (ADMG), when unobserved confounders are present, gives valid results on the low-level graph, thus generalizing an earlier statement by Anand et al. (2023). We argue that our framework is more suitable for modeling causal abstractions compared to existing categorical frameworks. Finally, we discuss how notions such as $\tau$-consistency and constructive $\tau$-abstractions can be recovered with our framework.

Related papers

• Causal and Compositional Abstraction [0.0]
  We present a general account of abstractions between low and high level models as natural transformations.<n>This provides a new formalisation of causal abstraction, unifying several notions in the literature.<n>We show that abstraction can be generalised to further compositional models.
  arXiv  Detail & Related papers  (2026-02-18T17:06:09Z)
• Schoenfeld's Anatomy of Mathematical Reasoning by Language Models [56.656180566692946]
  We adopt Schoenfeld's Episode Theory as an inductive, intermediate-scale lens and introduce ThinkARM (Anatomy of Reasoning in Models)<n>ThinkARM explicitly abstracts reasoning traces into functional reasoning steps such as Analysis, Explore, Implement, verify, etc.<n>We show that episode-level representations make reasoning steps explicit, enabling systematic analysis of how reasoning is structured, stabilized, and altered in modern language models.
  arXiv  Detail & Related papers  (2025-12-23T02:44:25Z)
• Causal Abstraction Inference under Lossy Representations [53.18851962820361]
  We introduce a new type of abstractions called projected abstractions that generalize existing definitions to accommodate lossy representations.<n>We show how to construct a projected abstraction from the low-level model and how it translates equivalent observational, interventional, and counterfactual causal queries from low to high-level.
  arXiv  Detail & Related papers  (2025-09-25T21:20:42Z)
• An Algebraic Framework for Hierarchical Probabilistic Abstraction [5.455744338342196]
  We introduce a hierarchical probabilistic abstraction framework aimed at addressing challenges by extending a measure-theoretic foundation for hierarchical abstraction.<n>This approach bridges high-level conceptualization with low-level perceptual data, enhancing interpretability and allowing layered analysis.<n>Our framework provides a robust foundation for abstraction analysis across AI subfields, particularly in aligning System 1 and System 2 thinking.
  arXiv  Detail & Related papers  (2025-02-28T16:47:42Z)
• Aligning Graphical and Functional Causal Abstractions [0.0]
  Causal abstractions allow us to relate causal models on different levels of granularity.<n>Two methods for causal abstractions are common in the literature: (i) graphical abstractions, such as Cluster DAGs, which relate models on a structural level, and (ii) functional abstractions, like $alpha$-abstractions, which relate models by maps between variables and their ranges.
  arXiv  Detail & Related papers  (2024-12-22T16:11:25Z)
• Transitivity Recovering Decompositions: Interpretable and Robust Fine-Grained Relationships [69.04014445666142]
  Transitivity Recovering Decompositions (TRD) is a graph-space search algorithm that identifies interpretable equivalents of abstract emergent relationships. We show that TRD is provably robust to noisy views, with empirical evidence also supporting this finding.
  arXiv  Detail & Related papers  (2023-10-24T16:48:56Z)
• From axioms over graphs to vectors, and back again: evaluating the properties of graph-based ontology embeddings [78.217418197549]
  One approach to generating embeddings is by introducing a set of nodes and edges for named entities and logical axioms structure. Methods that embed in graphs (graph projections) have different properties related to the type of axioms they utilize.
  arXiv  Detail & Related papers  (2023-03-29T08:21:49Z)
• A Formalisation of Abstract Argumentation in Higher-Order Logic [77.34726150561087]
  We present an approach for representing abstract argumentation frameworks based on an encoding into classical higher-order logic. This provides a uniform framework for computer-assisted assessment of abstract argumentation frameworks using interactive and automated reasoning tools.
  arXiv  Detail & Related papers  (2021-10-18T10:45:59Z)
• Structural Landmarking and Interaction Modelling: on Resolution Dilemmas in Graph Classification [50.83222170524406]
  We study the intrinsic difficulty in graph classification under the unified concept of resolution dilemmas'' We propose SLIM'', an inductive neural network model for Structural Landmarking and Interaction Modelling.
  arXiv  Detail & Related papers  (2020-06-29T01:01:42Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.