Causal Attribution

Follow this topic Ask about this topic

Causal attribution asks which inputs, model components, or agent actions actually changed an outcome, rather than merely correlating with it; this matters for debugging, fairness, safety, and assigning responsibility. Common approaches use structural causal models and counterfactual interventions, causal versions of Shapley values or integrated gradients, mediation analysis, and replay or activation-patching experiments. Researchers apply these methods to tabular predictions, neural-network mechanisms, LLM reasoning traces, multi-agent failures, and decisions in domains such as finance and biomedicine. A central challenge is that attributions depend on the causal assumptions and estimand, while interactions, confounding, and proxy signals can make plausible explanations fail to reflect what caused the result.

Latest papers

52 papers5 papers in the last four weeks, level with the four weeks before. 0.0% of all new papers.

What Moved the Alarm Score? Causal Attribution with Exact Computation and Scarce-Incident Estimation
Oct 20, 2026Masaaki Takada, Ryusei ShingakiCausal Attribution Shapley Value Attribution
Toshiba Corporation
Causal Integrated Gradients: Scalable Feature Attribution Along Causal Paths
Oct 15, 2026Joran Michiels, Anis Ismail, Maarten De Vos +1Causal Attribution Integrated Gradients
Laboratory of Multi-omics Integrative Bioinformatics, Department of Human Genetics, KU Leuven, Leuven, Belgium · KU Leuven Institute for Single Cell Omics (LISCO), KU Leuven, Leuven, Belgium · Department of Electrical Engineering, KU Leuven, Leuven, Belgium +1
Examining Social Attribution in LLM Reasoning: A Theory-Guided Probing Methodology
Oct 8, 2026Zhaoxin Yu, Qingchao Kong, Dajun Zeng +1Causal Attribution
State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences · School of Artificial Intelligence, University of Chinese Academy of Sciences
From Behavior to Provenance: Attributing Tabular Foundation Models to Synthetic Pretraining Data
Oct 1, 2026Mohamed Bouadi, Nassim Bouarour, Shivam Dubey +2Training Data Attribution Causal Attribution
Lexsi Labs
DoAtlas-2: A Foundation for Self-Evolving Causal Biomedical Discovery
Sep 28, 2026Yulong Li, Rong Xia, Yuxuan Zhang +12Causal Discovery Causal Attribution
MBZUAI
CausalLoss-Fin: Attributing Financial-Agent Loss to Decisions and Infrastructure Faults
Sep 22, 2026Abhishek SharmaAgent Failure Analysis Financial Services
Causal Attribution for Agentic Decisions: Estimators, Coupling, and a Traceability Specification
Sep 6, 2026Ajay Pravin MahaleCausal Attribution Causal Effect Estimation
Hochschule Trier
A Computationally Feasible Framework for Causal Probabilistic Explanation
Sep 3, 2026Rafal Urbaniak, Sam Witty, Daniel Waxman +7Structural Causal Models Actual Causality
Basis Research Institute · Sorbus AI · Massachusetts Institute of Technology +3
EDGE: Error Dependency Graph-Guided Multi-Error Attribution in Multi-Agent LLM Systems
Sep 1, 2026Jun Hou, Priya Pitre, Yi Fang +1Agent Failure Analysis Multi-Agent LLM Systems
Virginia Tech
Causal Evidentiary Governance for High-Risk Machine Learning Systems
Sep 1, 2026Samah Kareem, Barış ÇeliktaşAlgorithmic Auditing Algorithmic Accountability
Department of Computer Engineering, Isik University, Istanbul, Türkiye. · Department of Computer Engineering, I¸sık University, Istanbul, Türkiye.
What Process Evaluation of Coding Agents Actually Measures: Action, Task, and Step Are Three Different Levels
Aug 24, 2026Jiawei He, Mengyu Shi, Jie jia +2Process-Based Agent Evaluation AI Agent Evaluation
Amap, Alibaba Group, China
HANSARD: A Reference Architecture for Forensic Readiness, Runtime Witnessing, and Graded Attribution in Autonomous Multi-Agent AI Systems
Aug 23, 2026Christos Sardianos, Iliana Pla, Vasilis Efthymiou +4AI Agent Monitoring Algorithmic Accountability
Department of Informatics and Telematics, Harokopio University of Athens, Athens, Greece · Department of Informatics, Faculty of Science, Democritus University of Thrace, Kavala, Greece · Department of Electrical and Computer Engineering, University of Western Macedonia, Kozani, Greece +1
AUDITA: certified auditing and causal attribution of adverse outcomes in autonomous multi-agent systems
Aug 23, 2026Zhixu Du, Yiran ChenAI Agent Auditing AI Accountability
Department of Electrical and Computer Engineering, Duke University, Durham, North Carolina, USA
Discovering Efficient and Explainable Communication Topologies for LLM-based Multi-Agent Systems via Causal Inference
Aug 13, 2026Junzhi Li, Peng He, Qirui Ji +3Multi-Agent LLM Systems Causal Attribution
University of Chinese Academy of Sciences · National Key Laboratory of Space Integrated Information System, Institute of Software, Chinese Academy of Sciences · Beijing University of Posts and Telecommunications
CAS: A Causal Attribution Score for Local and Global Explainable Artificial Intelligence
Aug 12, 2026Michael Georgiades, Charalambia VarnavaFeature Attribution Causal Attribution
Department of Computer Science Neapolis University Pafos Cyprus · CaSToRC The Cyprus Institute Nicosia, Cyprus
ConstructCIE: A Dataset for Extracting Causal Information from Construction Accident Narratives
Aug 6, 2026Hung Nguyen, Jaehoon Lee, Namgyun Kim +1Document Information Extraction Causal Attribution
Department of Computer Science, Texas A&M University · Department of Construction Science, Texas A&M University
Computing Actual Causes for Neural Network Predictions under Structured Causal Inputs
Aug 4, 2026Jannick Strobel, Muqsit Azeem, Stefan LeueBranch and Bound Actual Causality
University of Konstanz
From Training to Deployment: Post-Hoc Causal Feature Identification via Sensitivity Ratios
Jul 28, 2026Athanasios Vlontzos, Giorgos Papanastasiou, Bernhard Kainz +1Feature Attribution Causal Attribution
Hologen AI London, UK · Mathematics Research Centre Academy of Athens Athens, GR · FAU Erlangen Nuremberg Imperial College London Erlangen, DE & London, UK +1
Encoding Invisible Causation for Bridge Diagnostic Agents: Triple-Guided Retrieval-Augmented Fine-Tuning with QLoRA
Jul 23, 2026Takato YasunoCausal Attribution Low-Rank Adaptation
Analytic Abduction: Causal Decomposition and Governed Commitment for Human--AI Coordination
Jul 16, 2026Remo PareschiAbductive Reasoning Causal Attribution
Stake Lab, University of Molise, Italy
Faithfulness to Refusal: A Causal Audit of Neuron Selectors
Jul 6, 2026Ananth Eswar, Pratinav Seth, Utsav Avaiya +1Transformer Interpretability Feature Attribution
Lexsi Labs · Work done while at Lexsi Labs.
Actual causality in fault trees
Jul 2, 2026Georgiana Caltais, Milan Lopuhaä-Zwakenberg, Mariëlle StoelingaActual Causality Causal Attribution
University of Twente, The Netherlands · Radboud University, The Netherlands
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
The Curse of Multiple Mediators: Hidden Interaction Effects in Activation Patching
Jun 25, 2026Sankaran Vaidyanathan, David Arbour, Aaron Mueller +2Causal Effect Estimation Causal Attribution
University of Massachusetts Amherst · Adobe Research · Boston University
OpenRCA 2.0: From Outcome Labels to Causal Process Supervision
Jun 25, 2026Aoyang Fang, Yifan Yang, Jin'ao Shang +7LLM Agent Evaluation Causal Attribution
The Chinese University of Hong Kong, Shenzhen · Lero · The Chinese University of Hong Kong
Beyond Shapley: Efficient Computation of Asymmetric Shapley Values
Jun 23, 2026Ezequiel Companeetz, Santiago Cifuentes, Sergio AbriolaCooperative Game Theory Feature Attribution
Departamento de Computación, Facultad de Ciencias Exactas y Naturales, UBA · Instituto de Ciencias de la Computación (ICC), CONICET
Difference-Making without Making a Difference
Jun 23, 2026Sander BeckersActual Causality Causal Attribution
University College London
Local Causal Attribution of Chain-of-Thought Reasoning
Jun 20, 2026Dennis Wei, Yannis Belkhiter, Erik Miehling +1LLM Interpretability Causal Attribution
1IBM Research.
Faithful Action-unit Causal Reasoning for Counterfactually Faithful Emotion Explanations
Jun 14, 2026Van Thong Huynh, Hong Hai Nguyen, Thuy Pham +2Counterfactual Evaluation Counterfactual Explanations
Faculty of CSE, Ho Chi Minh City University of Technology (HCMUT), VNUHCM, Vietnam · Dept. of AI, FPT University, Vietnam · Faculty of DSAI, College of Technology, National Economic University, Vietnam +1
Not All Skills Help: Measuring and Repairing Agent Knowledge
Jun 13, 2026Yixuan Wang, Yiyang Zhou, Yiming Liang +4Causal Attribution LLM Agent Skill Learning
UNC Chapel Hill · Purdue · NVIDIA

Oct 20, 2026J/K move · Enter open · S save

What Moved the Alarm Score? Causal Attribution with Exact Computation and Scarce-Incident Estimation

Masaaki Takada, Ryusei Shingaki

Toshiba Corporation

Causal Attribution Shapley Value Attribution Structural Causal Models Industrial Fault Diagnosis

Open paper AskPDF arXiv

Alarms in industrial systems and scientific instruments often demand immediate diagnosis despite scarce incident data. To guide intervention, an explanation must trace how changes in the data-generating process propagate through the causal structure to alter the alarm score, rather than merely flagging shifts that may be downstream effects. Yet exact attribution across interacting causal components appears combinatorial, while existing methods often either assume an unchanged causal model or require enough incident data to estimate the changed system reliably. We address this setting by formulating the alarm-score change as a Shapley game over hybrid structural causal model (SCM) states. Treating structural functions and exogenous laws as distinct players yields a finer-grained, function/law-resolved report of how each type of change propagates to the alarm score. The same framework defines realized-event and population reports, with an event--population coherence identity linking their attributions. For ordered linear SCMs and quadratic scores, a causal first- and second-moment recursion combined with quadrature computes the full Shapley vector exactly in polynomial time, eliminating combinatorial computation. To estimate this target from scarce incident data, we adapt a well-observed reference SCM to the incident regime using cross-fitted estimates of mechanism changes and residual moments, and derive attribution-error bounds and top-k recovery guarantees. Experiments on controlled and measured shifts illustrate the diagnoses and assess scaling to hundreds of variables and estimation from small incident samples.