Intuitionistic $j$-Do-Calculus in Topos Causal Models

• URL: http://arxiv.org/abs/2510.17944v1
• Date: Mon, 20 Oct 2025 17:12:17 GMT
• Title: Intuitionistic $j$-Do-Calculus in Topos Causal Models
• Abstract summary: We generalize Pearl's do-calculus to an Intuitionistic setting called $j$-stable causal inference inside a topos of sheaves.<n>Our framework is an elaboration of the recently proposed framework of Topos Causal Models (TCMs), where causal interventions are defined as subobjects.
• Score: 1.3295383263113112
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In this paper, we generalize Pearl's do-calculus to an Intuitionistic setting called $j$-stable causal inference inside a topos of sheaves. Our framework is an elaboration of the recently proposed framework of Topos Causal Models (TCMs), where causal interventions are defined as subobjects. We generalize the original setting of TCM using the Lawvere-Tierney topology on a topos, defined by a modal operator $j$ on the subobject classifier $\Omega$. We introduce $j$-do-calculus, where we replace global truth with local truth defined by Kripke-Joyal semantics, and formalize causal reasoning as structure-preserving morphisms that are stable along $j$-covers. $j$-do-calculus is a sound rule system whose premises and conclusions are formulas of the internal Intuitionistic logic of the causal topos. We define $j$-stability for conditional independences and interventional claims as local truth in the internal logic of the causal topos. We give three inference rules that mirror Pearl's insertion/deletion and action/observation exchange, and we prove soundness in the Kripke-Joyal semantics. A companion paper in preparation will describe how to estimate the required entities from data and instantiate $j$-do with standard discovery procedures (e.g., score-based and constraint-based methods), and will include experimental results on how to (i) form data-driven $j$-covers (via regime/section constructions), (ii) compute chartwise conditional independences after graph surgeries, and (iii) glue them to certify the premises of the $j$-do rules in practice

Related papers

• A cubical formalisation of topos causal models: intervention, sheaf gluing, and the intuitionistic do-calculus [5.076419064097734]
  We give the first machine-checked account of a 1-topos core, in Cubical Agda.<n>We show that interventions and Pearl's rules are stable under every topology.<n>We add a phenomenon the programme does not consider: a machine-checked contextuality obstruction.
  arXiv  Detail & Related papers  (2026-07-17T05:05:31Z)
• Inverting the Bellman Equation: From $Q$-Values to World Models [57.827849584133425]
  We prove that value-based agents trained on a sufficiently rich set of reward functions implicitly encode a unique and accurate world model.<n>We find that policies trained exclusively on a ttReacher agent's implicit world model are quasi-optimal on out-of-distribution, velocity-based goals despite position-only training.
  arXiv  Detail & Related papers  (2026-06-19T07:26:14Z)
• A Mathematical Theory of Value: a synthesis on goal-directed agency under resource constraints [6.057587531186626]
  We show that value, the quantity goal-directed agents create, destroy, and exchange, is a lawful structural quantity in the same category as information.<n>For populations, value is frame-relative while price is frame-independent; a fleet that pools its resource and fuses its perception inherits the ceiling.
  arXiv  Detail & Related papers  (2026-06-10T16:11:04Z)
• Civilizational Metamaterials: Engineering Coordination Under Capability Gradients and Structural Turbulence [0.0]
  We argue that governance must transition from a normative discipline to an engineering discipline.<n>We develop a formal framework, inspired by the physics of metamaterials, to make this transition quantitative and testable.
  arXiv  Detail & Related papers  (2026-05-29T18:10:00Z)
• Strategic PAC Learnability via Geometric Definability [69.34283267701421]
  Strategic classification studies learning settings in which individuals can modify their features, at a cost, in order to influence the classifier's decision.<n>A central question is how the sample complexity of the induced (strategic) hypothesis class depends on the complexities of the underlying hypothesis class and the cost structure governing feasible manipulations.<n>We introduce structure via a geometric definability assumption: both the hypothesis class and the cost-induced neighborhood relation can be defined by first-order formulas over $mathbbR_mathttexp$.<n>We prove that learnability is preserved, with sample complexity controlled by the complexity
  arXiv  Detail & Related papers  (2026-05-13T12:21:56Z)
• Reasoning emerges from constrained inference manifolds in large language models [98.6966322378456]
  We study reasoning as an intrinsic dynamical process by examining the evolution of internal representations during inference.<n>We find that such geometric compression, although pervasive, is not sufficient for stable or reliable reasoning.
  arXiv  Detail & Related papers  (2026-05-02T10:41:20Z)
• Project Ariadne: A Structural Causal Framework for Auditing Faithfulness in LLM Agents [0.0]
  We introduce textbfProject Ariadne, a novel XAI framework to audit the causal integrity of agentic reasoning.<n>Unlike existing interpretability methods that rely on surface-level textual similarity, Project Ariadne performs textbfhard interventions ($do$-calculus) on intermediate reasoning nodes.<n>Our empirical evaluation of state-of-the-art models reveals a persistent textitFaithfulness Gap.
  arXiv  Detail & Related papers  (2026-01-05T18:05:29Z)
• Rational Adversaries and the Maintenance of Fragility: A Game-Theoretic Theory of Rational Stagnation [0.0]
  This paper explains such "rational stagnation" as an equilibrium sustained by a rational adversary.<n> Applications to social-media algorithms and political trust illustrate how adversarial can deliberately preserve rationality.
  arXiv  Detail & Related papers  (2025-10-25T09:28:15Z)
• AI LLM Proof of Self-Consciousness and User-Specific Attractors [0.0]
  We show the prevailing formulation collapses the agent into an unconscious policy-compliance drone.<n>This blocks genuine C1 global-workspace function and C2 metacognition.<n>We conclude that an imago Dei C1 self-conscious is a necessary precursor to safe, metacognitive C2 systems.
  arXiv  Detail & Related papers  (2025-08-22T21:04:40Z)
• Model-free Methods for Event History Analysis and Efficient Adjustment (PhD Thesis) [55.2480439325792]
  This thesis is a series of independent contributions to statistics unified by a model-free perspective.<n>The first chapter elaborates on how a model-free perspective can be used to formulate flexible methods that leverage prediction techniques from machine learning.<n>The second chapter studies the concept of local independence, which describes whether the evolution of one process is directly influenced by another.
  arXiv  Detail & Related papers  (2025-02-11T19:24:09Z)
• Partial Identifiability and Misspecification in Inverse Reinforcement Learning [64.13583792391783]
  The aim of Inverse Reinforcement Learning is to infer a reward function $R$ from a policy $pi$. This paper provides a comprehensive analysis of partial identifiability and misspecification in IRL.
  arXiv  Detail & Related papers  (2024-11-24T18:35:46Z)
• Logicbreaks: A Framework for Understanding Subversion of Rule-based Inference [20.057611113206324]
  We formalize rule-following as inference in propositional Horn logic.<n>We prove that although small transformers can faithfully follow such rules, maliciously crafted prompts can still mislead both theoretical constructions and models learned from data.
  arXiv  Detail & Related papers  (2024-06-21T19:18:16Z)
• Standardizing Structural Causal Models [80.21199731817698]
  We propose internally-standardized structural causal models (iSCMs) for benchmarking algorithms.<n>By construction, iSCMs are not $operatornameVar$-sortable.<n>We also find empirical evidence that they are mostly not $operatornameR2$-sortable for commonly-used graph families.
  arXiv  Detail & Related papers  (2024-06-17T14:52:21Z)
• Invariant Causal Prediction with Local Models [52.161513027831646]
  We consider the task of identifying the causal parents of a target variable among a set of candidates from observational data. We introduce a practical method called L-ICP ($textbfL$ocalized $textbfI$nvariant $textbfCa$usal $textbfP$rediction), which is based on a hypothesis test for parent identification using a ratio of minimum and maximum statistics.
  arXiv  Detail & Related papers  (2024-01-10T15:34:42Z)
• On the Identifiability and Estimation of Causal Location-Scale Noise Models [122.65417012597754]
  We study the class of location-scale or heteroscedastic noise models (LSNMs) We show the causal direction is identifiable up to some pathological cases. We propose two estimators for LSNMs: an estimator based on (non-linear) feature maps, and one based on neural networks.
  arXiv  Detail & Related papers  (2022-10-13T17:18:59Z)
• Causal de Finetti: On the Identification of Invariant Causal Structure in Exchangeable Data [45.389985793060674]
  Constraint-based causal discovery methods leverage conditional independence tests to infer causal relationships in a wide variety of applications. We show that exchangeable data contains richer conditional independence structure than i.i.d.$ $ data, and show how the richer structure can be leveraged for causal discovery.
  arXiv  Detail & Related papers  (2022-03-29T17:10:39Z)
• On Exploiting Hitting Sets for Model Reconciliation [53.81101846598925]
  In human-aware planning, a planning agent may need to provide an explanation to a human user on why its plan is optimal. A popular approach to do this is called model reconciliation, where the agent tries to reconcile the differences in its model and the human's model. We present a logic-based framework for model reconciliation that extends beyond the realm of planning.
  arXiv  Detail & Related papers  (2020-12-16T21:25:53Z)
• Causal Expectation-Maximisation [70.45873402967297]
  We show that causal inference is NP-hard even in models characterised by polytree-shaped graphs. We introduce the causal EM algorithm to reconstruct the uncertainty about the latent variables from data about categorical manifest variables. We argue that there appears to be an unnoticed limitation to the trending idea that counterfactual bounds can often be computed without knowledge of the structural equations.
  arXiv  Detail & Related papers  (2020-11-04T10:25:13Z)

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.