Beyond Conditional Independence: Root Cause Analysis with Deep Causal Models

Md Musfiqur Rahman; Kenneth Lee; Ziwei Jiang; Padmaja Jonnalagedda; Ruocheng Guo; Murat Kocaoglu

cs.LGSep 29, 2026

Beyond Conditional Independence: Root Cause Analysis with Deep Causal Models

Authors: Md Musfiqur Rahman, Kenneth Lee, Ziwei Jiang, Padmaja Jonnalagedda, Ruocheng Guo, Murat Kocaoglu

Organizations: Electrical and Computer Engineering, Purdue University · Computer Science, Johns Hopkins University · Intuit AI Research · Microsoft

Abstract

Root cause analysis (RCA) is a critical problem in many real-world scenarios. RCA enables the identification of faulty or failing mechanisms in a system by comparing anomalous observations with corresponding reference (i.e., regular) observations. However, existing approaches rely either on heuristic methods or on conditional independence tests with a strong unconfoundedness assumption, and thus fail to exploit other complicated distributional constraints in the presence of latent variables. To relax these assumptions, we model the underlying system as a causal model and the anomalous system as a change in the structural functions of the same causal model. Specifically, to handle unobserved confounders, we establish an implicit connection between distributional constraint testing and root cause analysis. To adapt our approach to data generated from arbitrary causal models, we employ the deep causal model (DCM) framework, in which we design the causal model using neural networks. Finally, we illustrate how our method, RCA-DCM, can utilize different levels of partial graphical knowledge to perform RCA. We evaluate RCA-DCM against state-of-the-art baselines on simulated datasets, a physics-based causal chamber and two micro-service applications. RCA-DCM improves top-1 accuracy over the strongest baseline on both Sock Shop (0.880 vs. 0.752) and Online Boutique (0.776 vs. 0.712), and when the true root cause in the causal chamber is unobserved and acts as a latent confounder, it recovers the exact root-cause set more often than any competing method (perfect recovery rate (PRR) 0.846 vs. 0.731).

Figures & tables

Panel of Figure 1 — Figure 1: Baselines fail when latent confounders are present and non-root-cause variables experience larger distributional shifts than the root causes; Given $F\to T$ , deciding whether $Y$ is a root cause ( $F\to Y$ ) is equivalent to deciding whether $F$ is a valid instrument for the effect of $T$ on $Y$ .

Panel of Figure 2 — Figure 2: (a) No confounding. (b)–(c) Bow graphs with an unobserved confounder between $X$ and $Y$ (dashed $\leftrightarrow$ ).

Panel of Figure 3 — Figure 3: Workflow example. In the true augmented graph the fault shifts $X$ and $Z$ , so $R^{*}=\{X,Z\}$ , and latent confounders act on both $X\leftrightarrow Z$ and $Z\leftrightarrow Y$ . The induced pair $P^{*}=(P^{*}_{n},P^{*}_{a})$ falls outside the shaded Valid-IV region of the input space: it violates the instrumental inequalities for the effect of $X$ on $Z$ , which rules out $F$ being excluded from $Z$ (exclusion condition) and hence forces the edge $F\rightarrow Z$ . Each candidate $V$ is tested by freezing $f_{V}$ while the mechanisms on $\mathbf{V}\setminus\{V\}$ shift freely. The violation makes $\mathbf{V}\setminus\{Z\}$ infeasible, so $\ell^{*}(\mathbf{V}\setminus\{Z\})>0$ certifies that $Z$ lies in every $\texttt{R}\in\texttt{SolRC}(G^{*})$ and hence in $\widehat{\mathcal{R}}$ . For $V=Y$ the score attains zero, which is inconclusive: it is consistent with $\mathbf{V}\setminus\{Y\}\in\texttt{SolRC}(G^{*})$ , and we draw no conclusion from it.

Figure 5: Perfect recovery rate (PRR) with

95\%

confidence intervals. (a) increasing latent confounding, (b) heterogeneous anomalies where a non-cause can out-shift a true cause, (c) real causal-chamber data with the root cause observed vs. hidden. RCA-DCM remains strong across all three settings; comparisons use a paired test, so overlapping intervals do not imply the absence of a difference.

	Sock Shop			Online Boutique
Method	T1	T3	T5	T1	T3	T5
DCM	0.88	0.99	0.99	0.78	0.90	0.98
NSigma	0.75	0.97	0.99	0.70	0.91	0.96
BARO	0.74	0.98	0.99	0.62	0.90	0.94
CIRCA	0.65	0.96	0.99	0.52	0.89	0.98
RCD	0.38	0.54	0.58	0.49	0.59	0.62

Table 1: Average Top-

k

accuracy over the five fault types (best in bold).

Appendix figures & tables4 assets

Supplementary material from the paper’s appendix.

Appendix

$N_{s}$	$N_{a}$	DCM	BARO	RCD	#Instances
1000	1000	0.63	0.39	0.32	78
1000	500	0.58	0.48	0.48	95
500	500	0.47	0.47	0.31	51
1000	100	0.27	0.35	0.24	131
100	100	0.23	0.24	0.02	62

Appendix

Table 2: Perfect recovery rate (PRR) under varying normal (

N_{s}

) and anomalous (

N_{a}

) sample sizes.

		CPU			MEM			DISK			DELAY			LOSS			Average
Dataset	Method	T1	T3	T5	T1	T3	T5	T1	T3	T5	T1	T3	T5	T1	T3	T5	T1	T3	T5
Sock Shop	DCM	1.00	1.00	1.00	0.96	0.96	0.96	0.76	1.00	1.00	0.92	1.00	1.00	0.76	1.00	1.00	0.88	0.99	0.99
	NSigma	1.00	1.00	1.00	0.96	0.96	0.96	0.64	0.96	1.00	0.60	0.92	1.00	0.56	1.00	1.00	0.75	0.97	0.99
	BARO	1.00	1.00	1.00	0.48	0.96	0.96	0.68	0.96	1.00	0.92	1.00	1.00	0.64	1.00	1.00	0.74	0.98	0.99
	CIRCA	0.96	1.00	1.00	0.56	0.96	0.96	0.68	0.84	1.00	0.48	1.00	1.00	0.56	1.00	1.00	0.65	0.96	0.99
	RCD	0.76	0.92	0.96	0.28	0.48	0.48	0.32	0.52	0.52	0.28	0.48	0.52	0.28	0.32	0.44	0.38	0.54	0.58

Appendix

Table 3: Per-fault Top-1/Top-3/Top-5 accuracy. Best value per column within each dataset is in bold.

Method	Typical time / dataset
BARO	$\sim 0.01$ s
RCD	$\sim 0.4$ s (median)
DCM (ours)	$\sim 41$ s (median)

Appendix

Table 4: Per-dataset wall-clock time in the synthetic setting (

12

variables,

4

latents,

N_{s}=N_{a}=1000

Figure 6: Non-rc $Y$ has higher shift in median than RC $X$ .

Explore similar work

PRIM: Meta-Learned Bayesian Root Cause Analysis
May 9, 2026Christopher Lohse, Anish Dhir, Amadou Ba +3Root Cause Analysis Causal Inferences
University of Dublin, Trinity College, Dublin, Ireland · IBM · Gatsby Computational Neuroscience Unit, University College London +2
StableRCA: Robust Graph-Agnostic Mechanism-Level Root Cause Analysis
Jun 4, 2026Xiaoyu Lin, Nicholas Tagliapietra, Kehan Li +2Root Cause Analysis Causal Graph
Computer Science Department TU Darmstadt, Germany
Root Cause Analysis with Latent Confounders using Partial Ancestral Graphs
Jun 18, 2026Henrique O. Caetano, Rafael Arone, Carlos Dias MacielRoot Cause Analysis Latent Confounders
Signal Processing Laboratory, São Carlos School of Engineering, University of São Paulo, São Paulo, Brazil · Guaratinguetá School of Engineering, São Paulo State University, Guaratinguetá, Brazil

May 9, 2026, cs.LGJ/K move · Enter open · S save

PRIM: Meta-Learned Bayesian Root Cause Analysis

Christopher Lohse, Anish Dhir, Amadou Ba, Bradley Eck+2

University of Dublin, Trinity College, Dublin, Ireland · IBM · Gatsby Computational Neuroscience Unit, University College London+2

Root Cause Analysis Causal Inferences Bayesian Networks Meta-Learning Tabular Prior-Data Fitted Network

Open paper AskPDF arXiv

Root cause analysis (RCA) in complex systems is challenging due to error propagation across multiple variables, the need for structural causal knowledge, and the computational cost of inference at test time. We introduce PRIM (Prior-fitted Root cause Identification with Meta-learning), a causal meta-learning approach that frames RCA as a Bayesian inference task over a synthetic prior of causal models. By marginalising out structural uncertainty, PRIM implicitly identifies changes in the data-generating mechanism between baseline and anomalous periods. In doing so, PRIM infers distributional differences without explicit statistical testing, and implicitly learns causal structure without model fitting at test time. Following the simulation-based meta-learning paradigm of prior-fitted networks, PRIM uses a Model-Averaged Causal Estimation (MACE) transformer neural process that jointly attends over observational and anomalous samples and the causal structure of nodes, enabling zero-shot inference in 17,ms for systems with up to 100 variables. Across synthetic benchmarks and two realistic benchmark datasets, PetShop and CausRCA, PRIM is competitive with methods that are aware of the system's causal graphical structure a priori while outperforming graph-unaware methods on several tasks. Lightweight fine-tuning to specific domains and data dynamics improves performance further.

Abstract

Explore similar work

PRIM: Meta-Learned Bayesian Root Cause Analysis

StableRCA: Robust Graph-Agnostic Mechanism-Level Root Cause Analysis

Root Cause Analysis with Latent Confounders using Partial Ancestral Graphs