A Logic-Based Approach to Causal Discovery: Signal Temporal Logic Perspective
Authors: Nasim Baharisangari, Yucheng Ruan, Chengcheng Zhao, Zhe Xu
IJCAI 2025 | Venue PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experimental results on synthetic and real-world datasets demonstrate that our method achieves superior structural accuracy over state-of-the-art baselines, providing more informative and temporally precise causal models. |
| Researcher Affiliation | Academia | Nasim Baharisangari1 , Yucheng Ruan2 , Chengcheng Zhao2 and Zhe Xu1 1School for Engineering of Matter, Transport and Energy, Arizona State University, Tempe, AZ 85287. 2College of Control and Engineering, Zhejiang University, 310027 Hangzhou, China. |
| Pseudocode | Yes | Alg. 1 illustrates the steps we take to extract time intervals with statistically meaningful trends. Alg. 2 illustrates the steps we take to infer STL formulas for all the time intervals in T for each dimension d in D. Alg. 3 illustrates the steps we take to construct an STLCD G for given sets of STL formulas Φ1, ..., ΦD. |
| Open Source Code | No | The paper does not provide a statement or link indicating that the source code for the described methodology is publicly available. |
| Open Datasets | No | Experimental results on synthetic and real-world datasets demonstrate that our method achieves superior structural accuracy over state-of-the-art baselines, providing more informative and temporally precise causal models. In this subsection, we apply the proposed method to a drug-administration case study where we use synthetic data where the ground truth of the desired behavior is taking the fever-reducer drug for four consecutive days causes the fever to eventually stop in the next days once the four consecutive days are finished . In this case study, we collect on-board vehicular sensory data from CAN bus when the vehicle is under normal operation. |
| Dataset Splits | No | For this case study, we generated the dataset D with 16 positive trajectories and 2 negative trajectories all with the length of T = 25 and two dimensions. For this case study, we generated the dataset D with 16 positive trajectories and 2 negative trajectories all with the length of T = 25 and two dimensions. The dataset D has 9 normalized trajectories with the length of T = 3000 and each trajectory has four dimensions. D has nine positive trajectories and three negative trajectories where positive trajectories represent the situation where the vehicle is under operation (the vehicle is moving) and the negative trajectories represent the situation where the vehicle is not under operation (where the vehicle is static). |
| Hardware Specification | No | The paper does not provide specific hardware details (e.g., GPU/CPU models, processor types) used for running its experiments. |
| Software Dependencies | No | The paper does not provide specific ancillary software details, such as library names with version numbers, needed to replicate the experiment. |
| Experiment Setup | Yes | For this case study, we generated the dataset D with 16 positive trajectories and 2 negative trajectories all with the length of T = 25 and two dimensions. ... We also set M min = 1 and M max = 20. We have inferred 25 STL formulas for each dimension and then calculated the TE among pairs according to temporal precedence constraints. In this case study, we collect on-board vehicular sensory data from CAN bus when the vehicle is under normal operation. ... Fig. 4a shows the obtained results for Vehicle dataset with M min = 90 and M max = 100. Alg. 1 Input: observational time-series dataset D with T time steps and N trajectories with D dimensions, maximum number of intervals M max, minimum number of intervals M min, significance level α = 0.05. If one or several pairs of sub-trajectories yield r 2 0.65 and p-value 0.05, then a linear regression between trajectories ξ1 and ξ2 is deemed statistically meaningful . In Line 4, Alg. 2 randomly chooses N1 N pos trajectories from Dpos to form D1 and randomly chooses N2 N neg trajectories from Dneg to form D2. |