Notice: This website is continuously updated as new conference proceedings and journal volumes are published. Consequently, the figures presented here may differ from those reported in our publications.
A brief overview of our methodology is provided on the Methods page, along with references to publications documenting our approach and links to the code and data used in each study.
The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates.
Marrying Causal Representation Learning with Dynamical Systems for Science
Authors: Dingling Yao, Caroline Muller, Francesco Locatello
NeurIPS 2024 | Venue PDF | LLM Run Details | Input Tokens: 32,309 Total number of tokens sent to the LLM as input for this paper's analysis. | Output Tokens: 6,329 Total number of tokens produced by the LLM (including reasoning/thinking tokens) for this paper's analysis.
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We experiment with a wind simulator with partially known factors of variation. We also apply the resulting model to real-world climate data and successfully answer downstream causal questions in line with existing literature on climate change.Code is available at https://github.com/Causal Learning AI/crl-dynamical-systems. |
| Researcher Affiliation | Academia | Dingling Yao, Caroline Muller, and Francesco Locatello Institute of Science and Technology Austria |
| Pseudocode | No | The paper describes its methods using text and mathematical equations but does not include any explicit pseudocode blocks or algorithm listings. |
| Open Source Code | Yes | Code is available at https://github.com/Causal Learning AI/crl-dynamical-systems. |
| Open Datasets | Yes | We evaluate the models on sea surface temperature dataset SST-V2 [21]. |
| Dataset Splits | Yes | We chunk the time series into slices of 4 years in training while keeping last four years as out-of-distribution forecasting task. |
| Hardware Specification | Yes | All 12 jobs ran with 24GB of RAM, 8 CPU cores, and a single node GPU, which is, in most cases, NVIDIA Ge Force RTX2080Ti. |
| Software Dependencies | No | The paper mentions software like the 'Speedy Weather Julia package' and 'scikit-learn' but does not provide specific version numbers for these or other software dependencies. |
| Experiment Setup | Yes | Table 3: Training setup for wind simulation in 6.2. |