Research map / Probabilistic and scientific modeling / Causal discovery
High-recall causal discovery for autocorrelated time series with latent confounders
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| increase preliminary-phase iterations k from 0 to 1 (parent default conditions) (ablation) | LPCMCI · simulated autocorrelated data | recall and precision | Helped |
| increase k beyond 1 up to 4 (ablation) | LPCMCI · simulated autocorrelated data | recall | Helped |
| increase k (larger conditioning sets) (ablation) | LPCMCI · simulated autocorrelated data | runtime | Hurt |
| LPCMCI (k=4) vs SVAR-FCI and SVAR-RFCI | constraint-based latent causal discovery · simulated autocorrelated data | contemporaneous orientation recall: +0.4 or more | Helped |
| LPCMCI (k=0) vs SVAR-FCI/RFCI | constraint-based latent causal discovery · simulated autocorrelated data | precision (lagged orientation) | Hurt |
| increase k to 3-4 on non-time-series data | LPCMCI · non-time-series models | false positives | Hurt |
| increase k on discrete variables with G-test | LPCMCI · discrete models | performance | Hurt |
Closest papers by meaning
- Differentiable Causal Discovery for Latent Hierarchical Causal Models (ICLR 2025 · similarity 0.90)
- Discovering Mixtures of Structural Causal Models from Time Series Data (ICML 2024 · similarity 0.90)
- On the Recoverability of Causal Relations from Temporally Aggregated I.I.D. Data (ICML 2024 · similarity 0.89)
- Local Identifying Causal Relations in the Presence of Latent Variables (ICML 2025 · similarity 0.89)
- Learning Causal Relations from Subsampled Time Series with Two Time-Slices (ICML 2024 · similarity 0.89)
- Latent Variable Causal Discovery under Selection Bias (ICML 2025 · similarity 0.89)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.