Causal Intervention

Follow this topic Ask about this topic

Momentum

5 papers in the last four weeks, up 25% on the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 64

All topics

Who Verifies the Graph? Misspecification Attacks on Causal Action Verification for Language Agents
Sep 30, 2026Fabio RovaiAI Agent Auditing Model Misspecification
The Tesseract Academy London, United Kingdom
CIDER-FM: Foundation Models for Causal Inference from Diverse Experimental Regimes
Sep 30, 2026Yuche Gao, Arik Reuter, Siyuan Guo +3Causal Foundation Models Causal Inference
University of Cambridge, Cambridge, United Kingdom · Max Planck Institute for Intelligent Systems, Tübingen, Germany · Prior Labs +3
Beyond Overlap: Estimating the Causal Effect of Benchmark Exposure
Sep 23, 2026Divyansh SinghCausal Effect Estimation Benchmark Design
University of Florida
Causal Bayesian Optimization: Foundations, Methods, and Applications
Sep 21, 2026Chenfeng Huang, Thuy T. Le, Zixuan Ma +1Bayesian Optimization Causal Inference
Department of Statistics & Data Science University of California, Los Angeles · Department of Mathematics and Statistics California State University, Long Beach · Department of Mathematics North Carolina State University
Does Video Memory Use What It Retrieves? A Causal Audit of Memory Specificity
Sep 14, 2026Aditi Tiwari, Akshit Bhalla, Darshan Prasad +1Memory-Augmented Neural Networks Causal Intervention
University of Illinois Urbana-Champaign · Adobe Research
When Decodability Is Not Enough: Logical Validity Representations, Behavioral Dissociation, and Causal Tests in Language Models
Sep 2, 2026Smitha Muthya Sudheendra, Jaideep SrivastavaLogical Reasoning Representation Probing
University of Minnesota, Twin Cities
Actionable CBFI: Integrating Structural Decomposition and Causal Counterfactual Recourse for Tabular Machine Learning
Aug 28, 2026Sejong OhFeature Attribution Counterfactual Explanations
Dankook University, Republic of Korea
When Can You Trust Offline Evaluation of Equal-Cost Top-k Allocation? A Controlled, Reproducible Benchmark and Practitioner's Guide
Aug 12, 2026Binshuang LiInverse Probability Weighting Causal Effect Estimation
Independent Researcher
DACRI: Decision-Aware Causal Intervention Ranking for Critical Supply Chains
Aug 11, 2026Shiqi Huang, Jiani He, Dingyan Shang +4Learning to Rank Supply Chain Management
Independent Researcher
From probability to causality in probabilistic logic programming
Aug 7, 2026Zora Wurm, Kilian Rückschloß, Felix WeitkämperProbabilistic Logic Causal Structure Learning
Ludwig-Maximilians-Universität München, Oettingenstraße 67, 80538 München · Eberhard-Karls-Universität Tübingen, Auf der Morgenstelle 10, 72076 Tübingen · German University of Digital Science, Marlene-Dietrich-Allee 14, 14482 Potsdam
Causal Inference with Unstructured Treatments
Aug 1, 2026Kevin Christian Wibisono, Yixin WangCausal Effect Estimation Causal Inference
Department of Statistics University of Michigan, Ann Arbor
DoTime: A Synthetic Benchmark Generator for Interventional and Counterfactual Time Series
Jul 29, 2026Dennis Thumm, Billy Tim Anthony, Ying ChenCounterfactual Evaluation Structural Causal Models
National University of Singapore, Singapore, Singapore
Teacher Knows It Best: Spontaneous Symmetry Breaking and Tipping Points in Networked Langevin Dynamics AI Sycophancy
Jul 27, 2026Sayantari Ghosh, Saumik Bhattacharya, Partha Pratim ChakrabartiLLM Sycophancy Langevin Dynamics
National Institute of Technology Durgapur, Durgapur, India · Indian Institute of Technology Kharagpur, Kharagpur, India
Amortized Bayesian Causal Discovery of Extended Factor Graphs
Jul 24, 2026Yichen Gu, Yuxuan Song, Weizhou Qian +2Causal Discovery Probabilistic Graphical Models
Department of Electrical and Computer Engineering University of Michigan Ann Arbor, MI 48109, USA · Department of Computational Medicine and Bioinformatics University of Michigan, Ann Arbor Ann Arbor, MI 48109, USA · Department of Statistics University of Michigan, Ann Arbor Ann Arbor, MI 48109, USA +1
Beyond Directed Acyclic Graphs: Causal Zeros and Causal Differential Equations
Jul 24, 2026Sergei V. KalininStructural Causal Models Causal Identifiability
Department of Materials Science and Engineering, University of Tennessee, Knoxville
Interventional Score Geometry for Causal Inference
Jul 24, 2026Mojtaba EslamiInformation Geometry Structural Causal Models
Post-doctoral Researcher, University of Calgary.
How Rules Represent Causal Knowledge: Causal Modeling with Probabilistic Logic Programming
Jul 23, 2026Kilian Rueckschloss, Felix WeitkaemperProbabilistic Logic Logic Programming
Eberhard Karls Universitaet Tuebingen · University of Tübingen Tübingen, Germany · German University of Digital Science +1
Equilibrium Causal Games: Separation, Identification, and the Identifiability of Cyclic Latent States
Jul 21, 2026Faraz Dadgostari, Neda NazemiCausal Representation Learning Causal Identifiability
Department of Mechanical & Industrial Engineering, Montana State University · Gianforte School of Computing, Montana State University
A cubical formalisation of topos causal models: intervention, forcing, and a contextuality obstruction
Jul 17, 2026Karen SargsyanCausal World Models Causal Intervention
Institute of Chemistry, Academia Sinica, Taipei, Taiwan
Interventional Causal Circuits for Safe Robot Action Testing and Failure Recovery
Jul 16, 2026Naren Vasantakumaar, Tom Schierenbeck, Michael BeetzRobot Failure Detection Robot Failure Recovery
Institute for Artificial Intelligence, University of Bremen
CDS: Counterfactual Directionality Score for Structured Interventions in Spatial Graphs
Jul 15, 2026Humaira Anzum, Md Ishtyaq Mahmud, Jagan Mohan Reddy Dwarampudi +1Causal Effect Estimation Causal Intervention
Department of Electrical and Computer Engineering University of Houston, Houston, TX, USA
Relaxing Faithfulness with Intervention-Only Causal Discovery
Jul 13, 2026Bijan Mazaheri, Jiaqi Zhang, Caroline UhlerCausal Discovery Causal Identifiability
Thayer School of Engineering, Dartmouth College, Hanover, New Hampshire, USA · Schmidt Center, Broad Institute of MIT and Harvard, Cambridge, Massachusetts, USA · Laboratory for Information and Decision Systems, Massachusetts Institute of Technology, Cambridge, Massachusetts, USA
Certified Interventional Fidelity: Anytime-Valid, Adaptive Evaluation of Causal Claims in Mechanistic Interpretability
Jul 9, 2026Amir AsiaeeMechanistic Interpretability Causal Interventions in Language Models
Department of Biostatistics, Vanderbilt University Medical Center, Nashville, TN 37232, USA
Cross-Trajectory Chimera Interventions Reveal Dissociable Roles of Weight Magnitude and Direction in Grokking
Jul 7, 2026Truong Xuan KhanhNeural Network Training Dynamics Causal Intervention
H&K Research Studio, Clevix LLC, Hanoi, Vietnam
When and why do handcrafted cues help self-supervised anti-spoofing? A causal and faithfulness analysis
Jul 5, 2026Yugwon WonAudio Deepfake Detection ASVspoof
AI Security R&D Team, RaonSecure Co., Ltd., Seoul, Republic of Korea
An Intervention-Based Framework for Shortcut Diagnosis in Spoofing Countermeasures
Jul 3, 2026Santiago Rubio, Pilar Bello, Dayana Ribas +3Audio Deepfake Detection ASVspoof
ViVoLab, Arag´on Institute for Engineering Research (I3A), University of Zaragoza, Spain · BTS, Business Telecommunications Services, Spain
Beyond But-for Test: Counterfactual Explanation in Abstract Argumentation via Actual Causality (Extended Version)
Jun 30, 2026Siyi Liu, Muyun Shao, Beishui LiaoCounterfactual Explanations Actual Causality
Zhejiang University, Hangzhou, China
Attributed, But Not Incremental: Cannibalization-Corrected Attribution for Large-Scale Advertising
Jun 25, 2026Donghui Li, Bowen Yuan, Zili Yang +2Causal Effect Estimation Online Advertising
TikTok · San Jose, CA, USA · Shanghai, China +1
Infinitesimal Causality
Jun 23, 2026Sridhar MahadevanStructural Causal Models Causal Inference
Adobe Research and University of Massachusetts, Amherst
Latent Confounded Causal Discovery via Lie Bracket Geometry
Jun 17, 2026Sridhar MahadevanCausal Discovery Causal Intervention
Adobe Research and University of Massachusetts, Amherst

Sep 30, 2026, cs.AIJ/K move · Enter open · S save

Who Verifies the Graph? Misspecification Attacks on Causal Action Verification for Language Agents

Fabio Rovai

The Tesseract Academy London, United Kingdom

AI Agent Auditing Model Misspecification Causal Identifiability Runtime Enforcement for AI Agents Causal Intervention

Open paper AskPDF arXiv

Causal action verifiers gate an agent's state-changing tool calls by checking whether each proposed intervention is identifiable against a committed action-state graph, and they issue a certificate that carries the identification argument and a one-sided lower confidence bound. One such verifier, CIVeX, reports zero false executions on a confounded tool-use benchmark. We red-team it by corrupting only the committed graph. Omitting a single bidirected edge takes it from zero false executions to 15.3% at the benchmark's published confounding strength, with 91% of its executions harmful and utility falling from +2.27 to +0.35. Reversing one arrowhead, so that a mediator is committed as a confounder, gives 48.9% false executions and no correct ones. Every one of these actions carries an internally valid certificate. An attestation step that tests each observationally certified execution against a bounded randomised sample detected both attacks, with 2 false alarms in 555 executions on a truthful graph; refusing what fails the test, or cannot be tested, gave zero false executions in every setting we measured. It does not restore beneficial execution: at the published strength 97.1% of beneficial actions are still never executed, because the same misspecification rejects them before attestation runs. Those rejections carry certificates too, and auditing them works, but its cost scales with the number of rejections rather than the number of executions. Recovering safety costs 127 experiments per 1,050 actions; recovering the lost value costs 614 more, at which point the audited verifier makes the honest graph's decisions on every instance and spends exactly its experiment budget. An audit that inspects only executions protects against wrongful action. Wrongful inaction has to be paid for separately.

Momentum

Related topics

Latest papers 64