Linear SCM Identification in the Presence of Confounders and Gaussian Noise
Authors: Vahideh Sanjaroonpouri, Pouria Ramazi
ICLR 2025 | Venue PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | The paper primarily focuses on theoretical contributions, presenting theorems (e.g., Theorem 1, Theorem 2, Theorem 3), propositions, lemmas, and mathematical derivations for the identifiability of SCMs. While it includes a "Numerical Examples" section (Section VI), these examples are used to illustrate and demonstrate the theoretical findings with synthetic SCMs, rather than conducting empirical studies, analyzing real-world data, or reporting performance metrics. For instance, Example 1 states "We examine this SCM in three different scenarios to determine whether there are other SCMs with the same PDF" and Example 2 states "The example illustrates given an SCM C, when a permutation matrix P results in a distinct SCM C in the equivalence class of C." The examples numerically verify theoretical properties for specific cases, which is characteristic of theoretical work demonstrating concepts. |
| Researcher Affiliation | Academia | Vahideh Sanjaroon Department of Electrical & Computer Engineering Isfahan University of Technology Isfahan, 8415683111 Iran EMAIL Pouria Ramazi Department of Mathematics & Statistics Brock University St. Catharines, ON L2S 3A1, Canada EMAIL |
| Pseudocode | Yes | Algorithm 1: Finding the SCM equivalent to SCM C and corresponding to permutation matrix P |
| Open Source Code | No | The paper does not contain any explicit statement about releasing source code, nor does it provide any links to a code repository or mention code in supplementary materials. |
| Open Datasets | No | The paper's "Numerical Examples" section (Section VI) describes hypothetical SCMs (e.g., C: X1 = H + 2Z1, X2 = H + X1 + Z2) and specific matrices for illustration, but does not use or refer to any publicly available datasets. The examples are constructed to demonstrate theoretical properties rather than being based on empirical data. |
| Dataset Splits | No | The paper does not conduct experiments on datasets; therefore, there is no mention of training/test/validation dataset splits. |
| Hardware Specification | No | The paper's "Numerical Examples" section, where computational steps are outlined for Algorithm 1, does not provide any specific details about the hardware used to perform these calculations. |
| Software Dependencies | No | The paper does not provide specific ancillary software details, such as library names with version numbers, that would be needed to replicate the numerical examples or any computational aspects of the work. |
| Experiment Setup | No | The paper describes theoretical models and illustrates them with numerical examples. However, it does not involve any experimental setup with hyperparameters, training configurations, or system-level settings typically found in empirical research. |