Research map / Probabilistic and scientific modeling / Causal discovery
Perceiving the arrow of time in autoregressive motion
Kristof Meding, Dominik Janzing, Bernhard Schölkopf, Felix A. Wichmann
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| human observers vs ResDep on Bimodal noise | Human observers · Bimodal noise | threshold r: 0.67 vs 0.64 | No clear effect |
| neural network instead of humans | Human observers · Bimodal noise | threshold r: 0.67 -> 0.85 | Improved |
| ResDep instead of humans on Super-Gaussian noise | Human observers · Super-Gaussian noise | threshold r: 1.62 -> 1.48 | Improved |
| shorter time series (Exp 2) ResDep vs humans | ResDep · Bimodal r=0.5 | time points for 75%: 17.76 -> 42.67 | Hurt |
| exclude inattentive observer 2 (ablation) | Human observers · Exp 2 | threshold time points: 17.76 -> 15.17 | Improved |
| smoothed Uniform noise instead of Bimodal/Super-Gaussian | Human observers · Exp 1 | accuracy: 50% | Hurt |
| neural network on smoothed Uniform noise vs ResDep | ResDep · smoothed Uniform | accuracy: 70% -> 96% | Improved |
| trial 1-20 to 20-40 (ablation) | Human observers · Exp 1 all noise | accuracy: 82% -> 80% | No clear effect |
Closest papers by meaning
- The Arrow of Time in Multivariate Time Series (ICML 2016 · similarity 0.87)
- On the Identification of Temporal Causal Representation with Instantaneous Dependence (ICLR 2025 · similarity 0.86)
- CaRiNG: Learning Temporal Causal Representation under Non-Invertible Generation Process (ICML 2024 · similarity 0.84)
- Arrow: Accelerator for Time Series Causal Discovery with Time Weaving (ICML 2025 · similarity 0.83)
- Bayesian Active Learning for Bivariate Causal Discovery (ICML 2025 · similarity 0.83)
- A Sparsity Principle for Partially Observable Causal Representation Learning (ICML 2024 · similarity 0.83)
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.
