arXiv cs.AI· Hoang Dang, Luan Pham, Minh Nguyen·· 1 天前AI 评分31
交互式遥测中的因果发现：面向效应层面的验证框架
Effect-Level Validation for Causal Discovery in Interactive Telemetry
AI 导读
研究提出一种"可采纳性优先"框架，将因果发现得到的图视为结构假设，仅保留能识别目标效应且处理组与对照组重叠充分的图，再用跨算法稳定性、安慰剂、子采样和 E-value 诊断验证效应。在真实 RPG 遥测数据上，可采纳的 DAG 一致给出正向的队列条件风险差 ATE，但幅度随调整集与约束设定变化；已知真值模拟表明这些检查无法排除未测量混杂，且可识别率在不同游戏数据集间不可迁移。
正文 · 原文
Abstract:Causal discovery is increasingly used to analyze telemetry from interactive systems, but a plausible graph does not guarantee an identifiable or reliable product decision. We study this problem for one query: whether early competitive gameplay increases Day-1 retention in a deployed Role-playing game (RPG). We propose an admissibility-first framework that treats discovered graphs as structural hypotheses, keeps only graphs that identify the target effect and have adequate treatment-control overlap, and validates admissible effects through cross-algorithm stability, placebo, subsampling, and E-value diagnostics. On real telemetry, under minimal constraints the admissible runs that return Directed Acyclic Graphs (DAGs) are those whose graphs leave player-versus-player (PvP) with no parents, so they estimate the confounded raw difference; under the full constraint set all are admissible. Runs returning Partial Ancestral Graphs (PAGs) are not evaluated by the DAG gate and are reported separately. The admissible DAGs agree on one adjustment set and return a positive, cohort-conditional risk-difference average treatment effect (ATE), down from a raw retention gap; the estimate keeps its sign under placebo and subsampling checks, but its magnitude changes with the adjustment set and the constraint specification. A known-truth simulation shows that the checks screen identification and stability given the measured variables and cannot certify the absence of unmeasured confounding, and a second game-telemetry dataset shows that identifiability rates do not transfer. Graph-level recovery is therefore a weak proxy for causal reliability; discovery pipelines for decision support should be evaluated at the query and effect level.
| Comments: | Accepted at NeurIPS 2026 (Evaluations and Datasets Track). Camera-ready version, 23 pages |
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2602.08340 [cs.AI] |
| (or arXiv:2602.08340v2 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2602.08340 arXiv-issued DOI via DataCite |
Submission history
From: Luan Pham [view email]
[v1]
Mon, 9 Feb 2026 07:26:55 UTC (192 KB)
[v2]
Thu, 12 Nov 2026 01:28:52 UTC (140 KB)
来源：arXiv cs.AI · arxiv.org