arXiv cs.AI· Arvind Raghavan, Elias Bareinboim·· 3 天前AI 评分22
从反事实数据中进行因果识别：完备性与边界结果
Causal Identification from Counterfactual Data: Completeness and Bounding Results
AI 导读
针对反事实可实现性带来的 Layer 3 数据，研究者提出 CTFIDU+ 算法，可从任意 Layer 3 分布集合中识别反事实查询，并证明其完备性。该工作进一步刻画了物理可实现分布下反事实可识别性的理论极限，即非参数设定下精确因果推断的根本边界。对于无法识别的关键反事实量，作者推导出新的解析边界，并通过模拟验证反事实数据能收紧这些边界。
正文 · 原文
Abstract:Previous work establishing completeness results for counterfactual identification has been circumscribed to the setting where the input data belongs to observational or interventional distributions (Layers 1 and 2 of Pearl's Causal Hierarchy), since it was generally presumed impossible to obtain data from counterfactual distributions, which belong to Layer 3. However, recent work (Raghavan & Bareinboim, 2025) has formally characterized a family of counterfactual distributions which can be directly estimated via experimental methods - a notion they call counterfactual realizability. This leaves open the question of what additional counterfactual quantities now become identifiable, given this new access to (some) Layer 3 data. To answer this question, we develop the CTFIDU+ algorithm for identifying counterfactual queries from an arbitrary set of Layer 3 distributions, and prove that it is complete for this task. Building on this, we establish the theoretical limit of which counterfactuals can be identified from physically realizable distributions, thus implying the fundamental limit to exact causal inference in the non-parametric setting. Finally, given the impossibility of identifying certain critical types of counterfactuals, we derive novel analytic bounds for such quantities using realizable counterfactual data, and corroborate using simulations that counterfactual data helps tighten the bounds for non-identifiable quantities in practice.
| Comments: | published at ICML'26 |
| Subjects: | Artificial Intelligence (cs.AI); Machine Learning (cs.LG) |
| ACM classes: | F.4.1; G.3 |
| Report number: | Causal AI lab TR-144 |
| Cite as: | arXiv:2602.23541 [cs.AI] |
| (or arXiv:2602.23541v3 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2602.23541 arXiv-issued DOI via DataCite |
Submission history
From: Arvind Raghavan [view email]
[v1]
Thu, 26 Feb 2026 22:48:12 UTC (1,668 KB)
[v2]
Tue, 3 Mar 2026 20:56:54 UTC (1,668 KB)
[v3]
Fri, 9 Oct 2026 20:21:49 UTC (2,034 KB)
来源：arXiv cs.AI · arxiv.org