{"total":63,"rows":[{"id":"2106.02997","title":"Causal Abstractions of Neural Networks","created":"2021-06-06","cited_by_count":422,"area":null},{"id":"2303.02536","title":"Finding Alignments Between Interpretable Causal Variables and Distributed Neural Representations","created":"2023-03-05","cited_by_count":209,"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":"2304.05969","title":"Localizing Model Behavior with Path Patching","created":"2023-04-12","cited_by_count":195,"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":"2402.17700","title":"RAVEL: Evaluating Interpretability Methods on Disentangling Language Model Representations","created":"2024-02-27","cited_by_count":79,"area":"mechinterp"},{"id":"2103.14651","title":"Local Explanations via Necessity and Sufficiency: Unifying Theory and Practice","created":"2021-03-27","cited_by_count":45,"area":null},{"id":"2103.15758","title":"Compositional Abstraction Error and a Category of Causal Models","created":"2021-03-29","cited_by_count":33,"area":null},{"id":"2410.09087","title":"Mechanistic?","created":"2024-10-07","cited_by_count":25,"area":"mechinterp"},{"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":"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":"2112.02505","title":"Causal Distillation for Language Models","created":"2021-12-05","cited_by_count":19,"area":null},{"id":"2405.03207","title":"A Philosophical Introduction to Language Models - Part II: The Way Forward","created":"2024-05-06","cited_by_count":18,"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":"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":"2406.13371","title":"Identifiable Causal Representation Learning: Unsupervised, Multi-View, and Multi-Environment","created":"2024-06-19","cited_by_count":12,"area":null},{"id":"2306.14351","title":"Comparing Causal Frameworks: Potential Outcomes, Structural Models, Graphs, and Abstractions","created":"2023-06-25","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":"2305.17139","title":"A Measure-Theoretic Axiomatisation of Causality","created":"2023-05-19","cited_by_count":8,"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":"2501.19335","title":"What is causal about causal models and representations?","created":"2025-01-31","cited_by_count":6,"area":null},{"id":"2502.06536","title":"Sample-efficient Learning of Concepts with Theoretical Guarantees: from Data to Concepts without Interventions","created":"2025-02-10","cited_by_count":6,"area":null},{"id":"2304.11625","title":"Meaningful Causal Aggregation and Paradoxical Confounding","created":"2023-04-23","cited_by_count":5,"area":null},{"id":"2410.07013","title":"Causal Representation Learning in Temporal Data via Single-Parent Decoding","created":"2024-10-09","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":"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":"2601.10531","title":"Coarsening Causal DAG Models","created":"2026-01-15","cited_by_count":4,"area":null},{"id":"2201.10154","title":"Neural Information Squeezer for Causal Emergence","created":"2022-01-25","cited_by_count":3,"area":null},{"id":"2210.10684","title":"Language Models Understand Us, Poorly","created":"2022-10-19","cited_by_count":3,"area":null},{"id":"2309.07703","title":"Causal Entropy and Information Gain for Measuring Causal Control","created":"2023-09-14","cited_by_count":3,"area":null},{"id":"2312.16815","title":"Emergence and Causality in Complex Systems: A Survey on Causal Emergence and Related Quantitative Studies","created":"2023-12-28","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":"2401.13408","title":"Toward A Causal Framework for Modeling Perception","created":"2024-01-24","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":"2501.08429","title":"Modeling Discrimination with Causal Abstraction","created":"2025-01-14","cited_by_count":2,"area":null},{"id":"2310.08377","title":"Do Not Marginalize Mechanisms, Rather Consolidate!","created":"2023-10-12","cited_by_count":1,"area":null},{"id":"2410.05496","title":"Intuitions of Compromise: Utilitarianism vs. Contractualism","created":"2024-10-07","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":"2506.13803","title":"Causality in the human niche: lessons for machine learning","created":"2025-06-13","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":"2512.12804","title":"Causal Counterfactuals Reconsidered","created":"2025-12-14","cited_by_count":1,"area":null},{"id":"2602.19903","title":"Rethinking Chronological Causal Discovery with Signal Processing","created":"2026-02-23","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":"2502.21216","title":"An Algebraic Framework for Hierarchical Probabilistic Abstraction","created":"2025-02-28","cited_by_count":0,"area":null},{"id":"2503.09194","title":"Addressing pitfalls in implicit unobserved confounding synthesis using explicit block hierarchical ancestral sampling","created":"2025-03-12","cited_by_count":0,"area":null},{"id":"2503.12784","title":"Causal Feature Learning in the Social Sciences","created":"2025-03-17","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":"2602.22287","title":"Multi-Level Causal Embeddings","created":"2026-02-25","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":"2610.11947","title":"Score-Based Learning of Cluster DAGs from Interventions","created":"2026-10-08","cited_by_count":0,"area":null},{"id":"2610.18155","title":"When Do Learned Blocks Preserve Causal Meaning? Block Identifiability and Constructive Causal Abstractions","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}