{"total":18,"rows":[{"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":"2307.15771","title":"The Hydra Effect: Emergent Self-repair in Language Model Computations","created":"2023-07-28","cited_by_count":156,"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":"2311.18639","title":"Targeted Reduction of Causal Models","created":"2023-11-30","cited_by_count":15,"area":null},{"id":"2312.08107","title":"Causal Optimal Transport of Abstractions","created":"2023-12-13","cited_by_count":13,"area":null},{"id":"2503.08980","title":"I Predict Therefore I Am: Is Next Token Prediction Enough to Learn Human-Interpretable Concepts from Data?","created":"2025-03-12","cited_by_count":13,"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":"2304.11625","title":"Meaningful Causal Aggregation and Paradoxical Confounding","created":"2023-04-23","cited_by_count":5,"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":"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":"2503.10834","title":"On the Identifiability of Causal Abstractions","created":"2025-03-13","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":"2510.25005","title":"Cyclic Counterfactuals under Shift-Scale Interventions","created":"2025-10-28","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":"2608.10664","title":"Operationalising Relative Causal Knowledge: Backbone Identifiability from Private Reports on a Shared Outcome","created":"2026-08-11","cited_by_count":0,"area":null},{"id":"2608.14717","title":"Local Gains and Fixed-Assignment Set Losses in Shared Set Decoders","created":"2026-08-12","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}],"next_cursor":null}