{"total":107,"rows":[{"id":"2106.02997","title":"Causal Abstractions of Neural Networks","created":"2021-06-06","cited_by_count":422,"area":null},{"id":"2301.04709","title":"Causal Abstraction: A Theoretical Foundation for Mechanistic Interpretability","created":"2023-01-11","cited_by_count":205,"area":"mechinterp"},{"id":"2203.16437","title":"Weakly supervised causal representation learning","created":"2022-03-30","cited_by_count":140,"area":null},{"id":"2112.00826","title":"Inducing Causal Structure for Interpretable Neural Networks","created":"2021-12-01","cited_by_count":110,"area":null},{"id":"2306.00542","title":"Nonparametric Identifiability of Causal Representations from Unknown Interventions","created":"2023-06-01","cited_by_count":106,"area":null},{"id":"2305.08809","title":"Interpretability at Scale: Identifying Causal Mechanisms in Alpaca","created":"2023-05-15","cited_by_count":103,"area":null},{"id":"2507.08802","title":"The Non-Linear Representation Dilemma: Is Causal Abstraction Enough for Mechanistic Interpretability?","created":"2025-07-11","cited_by_count":37,"area":"mechinterp"},{"id":"2202.12263","title":"Causal Effect Identification in Cluster DAGs","created":"2022-02-22","cited_by_count":36,"area":null},{"id":"2502.20914","title":"Everything, Everywhere, All at Once: Is Mechanistic Interpretability Identifiable?","created":"2025-02-28","cited_by_count":34,"area":"mechinterp"},{"id":"2103.15758","title":"Compositional Abstraction Error and a Category of Causal Models","created":"2021-03-29","cited_by_count":33,"area":null},{"id":"2409.02772","title":"Unifying Causal Representation Learning with the Invariance Principle","created":"2024-09-04","cited_by_count":31,"area":null},{"id":"2605.05115","title":"Manifold Steering Reveals the Shared Geometry of Neural Network Representation and Behavior","created":"2026-05-06","cited_by_count":26,"area":null},{"id":"2202.01300","title":"Causal Inference Through the Structural Causal Marginal Problem","created":"2022-02-02","cited_by_count":23,"area":null},{"id":"2211.12270","title":"Causal Abstraction with Soft Interventions","created":"2022-11-22","cited_by_count":23,"area":null},{"id":"2301.05893","title":"Jointly Learning Consistent Causal Abstractions Over Multiple Interventional Distributions","created":"2023-01-14","cited_by_count":23,"area":null},{"id":"2102.10440","title":"Interventional Sum-Product Networks: Causal Inference with Tractable Probabilistic Models","created":"2021-02-20","cited_by_count":22,"area":null},{"id":"2309.07742","title":"Interpretability is in the Mind of the Beholder: A Causal Framework for Human-interpretable Representation Learning","created":"2023-09-14","cited_by_count":22,"area":null},{"id":"2401.02602","title":"Neural Causal Abstractions","created":"2024-01-05","cited_by_count":21,"area":null},{"id":"2112.02505","title":"Causal Distillation for Language Models","created":"2021-12-05","cited_by_count":19,"area":null},{"id":"2412.01953","title":"The Landscape of Causal Discovery Data: Grounding Causal Discovery in Real-World Applications","created":"2024-12-02","cited_by_count":18,"area":null},{"id":"2212.09897","title":"Inducing Character-level Structure in Subword-based Language Models with Type-level Interchange Intervention Training","created":"2022-12-19","cited_by_count":16,"area":null},{"id":"2207.08603","title":"Abstraction between Structural Causal Models: A Review of Definitions and Properties","created":"2022-07-18","cited_by_count":15,"area":null},{"id":"2210.05327","title":"A Causal Analysis of Harm","created":"2022-10-11","cited_by_count":15,"area":null},{"id":"2311.18639","title":"Targeted Reduction of Causal Models","created":"2023-11-30","cited_by_count":15,"area":null},{"id":"2201.06981","title":"On the Equivalence of Causal Models: A Category-Theoretic Approach","created":"2022-01-18","cited_by_count":13,"area":null},{"id":"2312.08107","title":"Causal Optimal Transport of Abstractions","created":"2023-12-13","cited_by_count":13,"area":null},{"id":"2512.18792","title":"The Dead Salmons of AI Interpretability","created":"2025-12-21","cited_by_count":12,"area":null},{"id":"2406.00394","title":"Learning Causal Abstractions of Linear Structural Causal Models","created":"2024-06-01","cited_by_count":11,"area":null},{"id":"2406.01352","title":"Position: An Inner Interpretability Framework for AI Inspired by Lessons from Cognitive Neuroscience","created":"2024-06-03","cited_by_count":11,"area":null},{"id":"2508.11214","title":"How Causal Abstraction Underpins Computational Explanation","created":"2025-08-15","cited_by_count":11,"area":null},{"id":"2206.13973","title":"Towards a Grounded Theory of Causation for Embodied AI","created":"2022-06-28","cited_by_count":9,"area":null},{"id":"2407.07934","title":"Identifying Macro Conditional Independencies and Macro Total Effects in Summary Causal Graphs with Latent Confounding","created":"2024-07-10","cited_by_count":9,"area":null},{"id":"2502.00407","title":"Causal Abstraction Learning based on the Semantic Embedding Principle","created":"2025-02-01","cited_by_count":9,"area":null},{"id":"2106.05074","title":"Operationalizing Complex Causes: A Pragmatic View of Mediation","created":"2021-06-09","cited_by_count":8,"area":null},{"id":"2305.17139","title":"A Measure-Theoretic Axiomatisation of Causality","created":"2023-05-19","cited_by_count":8,"area":null},{"id":"2602.16698","title":"Causality is Key for Interpretability Claims to Generalise","created":"2026-02-18","cited_by_count":8,"area":null},{"id":"2112.09171","title":"Causal Modeling With Infinitely Many Variables","created":"2021-12-16","cited_by_count":7,"area":null},{"id":"2112.11362","title":"Reasoning About Causal Models With Infinitely Many Variables","created":"2021-12-21","cited_by_count":7,"area":null},{"id":"2211.09024","title":"Phenomenological Causality","created":"2022-11-15","cited_by_count":7,"area":null},{"id":"2305.04357","title":"Quantifying Consistency and Information Loss for Causal Abstraction Learning","created":"2023-05-07","cited_by_count":7,"area":null},{"id":"2209.09543","title":"FACT: Learning Governing Abstractions Behind Integer Sequences","created":"2022-09-20","cited_by_count":6,"area":null},{"id":"2312.11158","title":"Interventionally Consistent Surrogates for Agent-based Simulators","created":"2023-12-18","cited_by_count":6,"area":null},{"id":"2404.17493","title":"Causally Abstracted Multi-armed Bandits","created":"2024-04-26","cited_by_count":6,"area":null},{"id":"2412.17080","title":"Aligning Graphical and Functional Causal Abstractions","created":"2024-12-22","cited_by_count":6,"area":null},{"id":"2501.19335","title":"What is causal about causal models and representations?","created":"2025-01-31","cited_by_count":6,"area":null},{"id":"2505.00808","title":"A Mathematical Philosophy of Explanations in Mechanistic Interpretability -- The Strange Science Part I.i","created":"2025-05-01","cited_by_count":6,"area":"mechinterp"},{"id":"2304.11625","title":"Meaningful Causal Aggregation and Paradoxical Confounding","created":"2023-04-23","cited_by_count":5,"area":null},{"id":"2511.01396","title":"Relaxing partition admissibility in Cluster-DAGs: a causal calculus with arbitrary variable clustering","created":"2025-11-03","cited_by_count":5,"area":null},{"id":"2208.00894","title":"Towards Computing an Optimal Abstraction for Structural Causal Models","created":"2022-08-01","cited_by_count":4,"area":null},{"id":"2311.07454","title":"Causal Discovery in Mixtures of Populations","created":"2023-11-13","cited_by_count":4,"area":null},{"id":"2410.00535","title":"The Causal Information Bottleneck and Optimal Causal Variable Abstractions","created":"2024-10-01","cited_by_count":4,"area":null},{"id":"2503.11429","title":"Combining Causal Models for More Accurate Abstractions of Neural Networks","created":"2025-03-14","cited_by_count":4,"area":"mechinterp"},{"id":"2510.18052","title":"Measure-Theoretic Anti-Causal Representation Learning","created":"2025-10-16","cited_by_count":4,"area":null},{"id":"2601.10531","title":"Coarsening Causal DAG Models","created":"2026-01-15","cited_by_count":4,"area":null},{"id":"2607.08349","title":"Certified Interventional Fidelity: Anytime-Valid, Adaptive Evaluation of Causal Claims in Mechanistic Interpretability","created":"2026-07-09","cited_by_count":4,"area":"mechinterp"},{"id":"2204.03536","title":"Abstracting Noisy Robot Programs","created":"2022-04-07","cited_by_count":3,"area":null},{"id":"2301.06845","title":"Causal Models with Constraints","created":"2023-01-17","cited_by_count":3,"area":null},{"id":"2408.07545","title":"$\\chi$SPN: Characteristic Interventional Sum-Product Networks for Causal Inference in Hybrid Domains","created":"2024-08-14","cited_by_count":3,"area":null},{"id":"2510.04842","title":"Distributionally Robust Causal Abstractions","created":"2025-10-06","cited_by_count":3,"area":null},{"id":"2310.18634","title":"SSL Framework for Causal Inconsistency between Structures and Representations","created":"2023-10-28","cited_by_count":2,"area":null},{"id":"2402.02696","title":"Causal Feature Selection for Responsible Machine Learning","created":"2024-02-05","cited_by_count":2,"area":null},{"id":"2410.13054","title":"Systems with Switching Causal Relations: A Meta-Causal Perspective","created":"2024-10-16","cited_by_count":2,"area":null},{"id":"2410.20161","title":"Causal Abstraction in Model Interpretability: A Compact Survey","created":"2024-10-26","cited_by_count":2,"area":null},{"id":"2411.00839","title":"CausAdv: A Causal-based Framework for Detecting Adversarial Examples","created":"2024-10-29","cited_by_count":2,"area":null},{"id":"2503.11718","title":"The Relativity of Causal Knowledge","created":"2025-03-13","cited_by_count":2,"area":null},{"id":"2504.14937","title":"Causal DAG Summarization (Full Version)","created":"2025-04-21","cited_by_count":2,"area":null},{"id":"2505.01372","title":"Evaluating Explanations: An Explanatory Virtues Framework for Mechanistic Interpretability -- The Strange Science Part I.ii","created":"2025-05-02","cited_by_count":2,"area":"mechinterp"},{"id":"2506.23952","title":"Autonomy by Design: Preserving Human Autonomy in AI Decision-Support","created":"2025-06-30","cited_by_count":2,"area":null},{"id":"2507.06213","title":"Identifiability in Causal Abstractions: A Hierarchy of Criteria","created":"2025-07-08","cited_by_count":2,"area":null},{"id":"2602.02623","title":"Learning Consistent Causal Abstraction Networks","created":"2026-02-02","cited_by_count":2,"area":null},{"id":"2605.10163","title":"Coarsening Linear Non-Gaussian Causal Models with Cycles","created":"2026-05-11","cited_by_count":2,"area":null},{"id":"2607.27617","title":"Hidden APIs in Language Models: Discovering Reusable Causal Interfaces from Forked Futures","created":"2026-07-30","cited_by_count":2,"area":null},{"id":"2309.10211","title":"Loop Polarity Analysis to Avoid Underspecification in Deep Learning","created":"2023-09-18","cited_by_count":1,"area":null},{"id":"2310.08377","title":"Do Not Marginalize Mechanisms, Rather Consolidate!","created":"2023-10-12","cited_by_count":1,"area":null},{"id":"2311.00923","title":"A Review and Roadmap of Deep Causal Model from Different Causal Structures and Representations","created":"2023-11-02","cited_by_count":1,"area":null},{"id":"2311.12401","title":"CASR: Refining Action Segmentation via Marginalizing Frame-levle Causal Relationships","created":"2023-11-21","cited_by_count":1,"area":null},{"id":"2412.02579","title":"Factored space models: Towards causality between levels of abstraction","created":"2024-12-03","cited_by_count":1,"area":null},{"id":"2503.10834","title":"On the Identifiability of Causal Abstractions","created":"2025-03-13","cited_by_count":1,"area":null},{"id":"2507.14901","title":"Learning Nonlinear Causal Reductions to Explain Reinforcement Learning Policies","created":"2025-07-20","cited_by_count":1,"area":"deeprl"},{"id":"2509.04296","title":"Using causal abstractions to accelerate decision-making in complex bandit problems","created":"2025-09-04","cited_by_count":1,"area":null},{"id":"2512.12804","title":"Causal Counterfactuals Reconsidered","created":"2025-12-14","cited_by_count":1,"area":null},{"id":"2602.24266","title":"Causal Mechanism Reduction: Mechanism Replacement for Neural Network Pruning and Abstraction","created":"2026-02-27","cited_by_count":1,"area":null},{"id":"2606.19594","title":"Unsupervised Causal Abstractions Discovery","created":"2026-06-17","cited_by_count":1,"area":null},{"id":"2606.29657","title":"Safety from Honesty in a Disinterested AI Predictor","created":"2026-06-28","cited_by_count":1,"area":null},{"id":"2607.19442","title":"Unlearning as Distribution Restoration: A Controlled Counterfactual Study, a Validated Selective Screen, and the Limits of Oracle-Free Certification","created":"2026-07-21","cited_by_count":1,"area":"safety"},{"id":"2608.08064","title":"CLAM: Causal Spatial Disaggregation to Infer Local Effects From Coarse Data","created":"2026-08-08","cited_by_count":1,"area":null},{"id":"2212.12575","title":"Continual Causal Abstractions","created":"2022-12-23","cited_by_count":0,"area":null},{"id":"2509.01136","title":"Heads or Tails: A Simple Example of Causal Abstractive Simulation","created":"2025-09-01","cited_by_count":0,"area":null},{"id":"2510.05033","title":"Causal Abstractions, Categorically Unified","created":"2025-10-06","cited_by_count":0,"area":"mechinterp"},{"id":"2512.10720","title":"Beyond the Black Box: Identifiable Interpretation and Control in Generative Models via Causal Minimality","created":"2025-12-11","cited_by_count":0,"area":null},{"id":"2512.11919","title":"A fine-grained look at causal effects in causal spaces","created":"2025-12-11","cited_by_count":0,"area":null},{"id":"2512.18315","title":"On Efficient Adjustment for Micro Causal Effects in Summary Causal Graphs","created":"2025-12-20","cited_by_count":0,"area":null},{"id":"2602.22287","title":"Multi-Level Causal Embeddings","created":"2026-02-25","cited_by_count":0,"area":null},{"id":"2603.28597","title":"Position: Explainable AI is Causality in Disguise","created":"2026-03-30","cited_by_count":0,"area":null},{"id":"2605.00248","title":"Causal Foundations of Collective Agency","created":"2026-04-30","cited_by_count":0,"area":null},{"id":"2605.06979","title":"PLOT: Progressive Localization via Optimal Transport in Neural Causal Abstraction","created":"2026-05-07","cited_by_count":0,"area":"mechinterp"},{"id":"2605.31254","title":"Formalizing and falsifying causal pathways of rare events","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2606.15943","title":"Graphical-Probabilistic Modeling of Generative Flows in LLM-Native Software Systems","created":"2026-06-14","cited_by_count":0,"area":null},{"id":"2607.00267","title":"Validating Causal Abstraction Metrics on Simulated Complex Systems","created":"2026-06-30","cited_by_count":0,"area":null},{"id":"2608.07214","title":"Toward a Causal Data Management Ecosystem for Decision Making and Agentic AI","created":"2026-08-07","cited_by_count":0,"area":"agents"}],"next_cursor":"100"}