研究人员正在开发新方法来改进因果发现，即从数据中推断因果关系的过程。一种名为CauTion的方法将大型语言模型（LLMs）与统计算法相结合，以提高准确性和鲁棒性，尤其适用于复杂图。另一个研究重点是将AI规划建立在物理因果关系的基础上，超越简单的下一个词预测，以理解现实世界的后果。此外，研究还在探索如何确保因果推理方法的可靠性和一致性，包括基于基础模型和连续时间系统的因果推理方法，以使其在实际应用中更值得信赖。
AI
arXiv:2606.03332v1 Announce Type: new Abstract: Probabilistic models are typically trained using task-agnostic objectives like log-loss, which can lead to significant errors in downstream estimation. This disconnect is especially critical in Inverse Probability Weighting (IPW) fo…
arXiv:2606.03602v1 Announce Type: cross Abstract: Causal discovery from observational data remains challenging due to the fundamental limitations of purely statistical methods, such as statistical distinguishability within equivalence classes and sensitivity to finite sample size…
arXiv cs.LG
TIER_1English(EN)·Tong Zhao, Ce Guo, Wayne Luk, Emil Lupu, Ray Dipojjwal·
arXiv:2606.03227v1 Announce Type: new Abstract: Causal discovery with instantaneous effects in multivariate time series is challenging, as the instantaneous structure must be acyclic. Prior methods enforce this by either separating instantaneous and lagged estimation into multi-s…
Causal discovery from observational data remains challenging due to the fundamental limitations of purely statistical methods, such as statistical distinguishability within equivalence classes and sensitivity to finite sample sizes. While large language models (LLMs) offer a prom…
Probabilistic models are typically trained using task-agnostic objectives like log-loss, which can lead to significant errors in downstream estimation. This disconnect is especially critical in Inverse Probability Weighting (IPW) for causal inference, where propensity score error…
arXiv cs.LG
TIER_1English(EN)·Valentyn Melnychuk, Vahid Balazadeh, Stefan Feuerriegel, Rahul G. Krishnan·
arXiv:2603.12037v2 Announce Type: replace Abstract: Foundation models based on prior-data fitted networks (PFNs) have shown strong empirical performance in causal inference by framing the task as an in-context learning problem. However, it is unclear whether PFN-based causal esti…
arXiv cs.LG
TIER_1English(EN)·Gongxu Luo, Boyang Sun, Kun Zhang·
arXiv:2606.00568v1 Announce Type: new Abstract: Bulk gene expression profiling, which aggregates pooled RNA across cells within a biological sample, remains important in the single-cell era because it is typically less noisy, more sensitive, and more cost-effective than single-ce…
arXiv:2606.01810v1 Announce Type: new Abstract: Current benchmarks for embodied vision-language planning often favor linguistic next-token prediction over physically grounded next-state reasoning. This rewards models that mimic statistical language priors rather than track causal…
arXiv:2606.01789v1 Announce Type: new Abstract: In graphical causal model, causal discovery aims to construct a causal graph based on numerical data and domain knowledge in plain text. However, the evaluation of causal discovery methods remains a challenge in the area as the prog…
arXiv:2606.00278v1 Announce Type: new Abstract: For many real-world systems, causal ground truth is difficult to obtain, making claims about causal effects hard to assess. We develop methods for evaluating collections of $\binom{n}{2}$ bivariate causal statements over a set of $n…
We provide a brief primer for the idea behind formalising hierarchical causality in the context of complex systems. Here actors are not simply agents. Actors instantiate causation classes. Agents implement local dynamics in given levels or organisation in a given system. Hierarch…
We provide a brief primer for the idea behind formalising hierarchical causality in the context of complex systems. Here actors are not simply agents. Actors instantiate causation classes. Agents implement local dynamics in given levels or organisation in a given system. Hierarch…
arXiv:2605.31156v1 Announce Type: new Abstract: Causal discovery aims to recover directed causal relations from observational and interventional data, providing a basis for mechanistic understanding and reliable decision-making. Causal discovery foundation models (CDFMs) seek to …
arXiv:2605.28880v1 Announce Type: new Abstract: Extending discrete-time causal Prior-data Fitted Networks for time series to continuous time invites writing the mechanism as a stochastic differential equation (SDE) -- but if the SDE is integrated \emph{once per observation gap}, …
arXiv:2605.30015v1 Announce Type: cross Abstract: Supervised Causal Learning (SCL) has shown promise in causal discovery by framing it as a supervised learning problem. However, it suffers from significant out-of-distribution generalization challenges. We reveal three limitations…
Supervised Causal Learning (SCL) has shown promise in causal discovery by framing it as a supervised learning problem. However, it suffers from significant out-of-distribution generalization challenges. We reveal three limitations of previous SCL practices: a significant performa…
Supervised Causal Learning (SCL) has shown promise in causal discovery by framing it as a supervised learning problem. However, it suffers from significant out-of-distribution generalization challenges. We reveal three limitations of previous SCL practices: a significant performa…
arXiv cs.LG
TIER_1English(EN)·Jean Kaddour, Aengus Lynch, Qi Liu, Matt J. Kusner, Ricardo Silva·
arXiv:2206.15475v3 Announce Type: replace Abstract: Causal Machine Learning (CausalML) is an umbrella term for machine learning methods that formalize the data-generation process as a structural causal model (SCM). This perspective enables us to reason about the effects of change…
arXiv cs.LG
TIER_1English(EN)·Biao Ouyang, Tengxue Zhang, Zhihao Zhuang, Yang Shu, Chenjuan Guo, Bin Yang·
arXiv:2605.26759v1 Announce Type: new Abstract: Causal discovery from time series is critical for many real-world applications, such as tracing the root causes of anomalies. Existing approaches typically rely on dataset-specific optimization, making it difficult to transfer their…
arXiv stat.ML
TIER_1English(EN)·Matias D. Cattaneo, Jason M. Klusowski, Ruiqi Rae Yu·
arXiv:2509.11381v3 Announce Type: replace-cross Abstract: Recursive decision trees are widely used to estimate heterogeneous causal treatment effects in experimental and observational studies. These methods are typically implemented using CART-type recursive partitioning, with sp…
arXiv stat.ML
TIER_1English(EN)·Ankur Garg, Michael Stettler, Aaron Schein, Julius von K\"ugelgen·
arXiv:2606.06288v1 Announce Type: new Abstract: Causal representation learning aims to infer the high-level latent causal concepts that give rise to observed low-level measurements. This is particularly relevant for heterogeneous data from different environments or domains since …
arXiv:2606.06440v1 Announce Type: cross Abstract: Data-driven causal relationship identification is pertinent to advancing understanding of complex systems both within and beyond science. Bayesian networks offer a probabilistic method for modelling generic causal relationships vi…
arXiv stat.ML
TIER_1English(EN)·Matteo Tusoni, Giuseppe Masi, Andrea Coletta, Aldo Glielmo, Viviana Arrigoni, Novella Bartolini·
arXiv:2507.12257v4 Announce Type: replace-cross Abstract: Exploring causal relationships in stochastic time series is a challenging yet crucial task with a vast range of applications, including finance, economics, neuroscience, and climate science. Many algorithms for Causal Disc…
Data-driven causal relationship identification is pertinent to advancing understanding of complex systems both within and beyond science. Bayesian networks offer a probabilistic method for modelling generic causal relationships via directed acyclic graphs (DAGs). However, typical…
arXiv stat.ML
TIER_1English(EN)·Julius von Kügelgen·
Causal representation learning aims to infer the high-level latent causal concepts that give rise to observed low-level measurements. This is particularly relevant for heterogeneous data from different environments or domains since distribution shifts often arise through sparse, …
Longitudinal treatment decisions require predicting potential outcomes under future treatment sequences in the presence of time-varying confounding, heterogeneous patient dynamics, and limited domain-specific data. Existing longitudinal causal estimators typically train a new mod…
arXiv:2511.05050v3 Announce Type: replace Abstract: In this study, a scalable online kernel learning framework is proposed for estimating bidirectional causal effects in systems characterized by mutual dependence and heteroskedasticity. Traditional causal inference often focuses …
arXiv stat.ML
TIER_1English(EN)·Mohammad Ali Javidian·
arXiv:2606.01457v1 Announce Type: cross Abstract: Bayesian optimization is a popular way to optimize expensive systems, where every experiment, simulation, or intervention costs time or money. In its standard form, it treats the variables we control as plain inputs to a black box…
arXiv stat.ML
TIER_1English(EN)·Mohammad Ali Javidian·
Bayesian optimization is a popular way to optimize expensive systems, where every experiment, simulation, or intervention costs time or money. In its standard form, it treats the variables we control as plain inputs to a black box and cannot tell apart mere correlation from a rea…
arXiv:2602.23602v2 Announce Type: replace Abstract: Heteroscedasticity -- where the variance of a variable changes with other variables -- is pervasive in real data, and elucidating why it arises from the perspective of statistical moments is crucial in scientific knowledge disco…
arXiv stat.ML
TIER_1English(EN)·Dmitry Zaytsev, Valentina Kuskova, Michael Coppedge·
arXiv:2603.20980v2 Announce Type: replace-cross Abstract: Time-varying causal models provide a powerful framework for studying dynamic scientific systems, yet most existing approaches assume that the underlying causal network is known a priori - an assumption rarely satisfied in …
arXiv stat.ML
TIER_1English(EN)·Valentina Kuskova, Dmitry Zaytsev, Michael Coppedge·
arXiv:2604.18751v1 Announce Type: cross Abstract: Nonlinear machine-learning models are increasingly used to discover causal relationships in time-series data, yet the interpretation of their outputs remains poorly understood. In particular, causal scores produced by regularized …