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.
PICProp: Physics-Informed Confidence Propagation for Uncertainty Quantification
Authors: Qianli Shen, Wai Hoh Tang, Zhun Deng, Apostolos Psaros, Kenji Kawaguchi
NeurIPS 2023 | Venue PDF | LLM Run Details | Input Tokens: 25,746 Total number of tokens sent to the LLM as input for this paper's analysis. | Output Tokens: 4,304 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 provide a theorem regarding the validity of our method, and computational experiments, where the focus is on physics-informed learning. |
| Researcher Affiliation | Academia | Qianli Shen National University of Singapore Singapore EMAIL Wai Hoh Tang National University of Singapore Singapore EMAIL Zhun Deng Columbia University USA EMAIL Apostolos Psaros Brown University USA EMAIL Kenji Kawaguchi National University of Singapore Singapore EMAIL |
| Pseudocode | Yes | The developed methods are summarized in Algorithms 1 and 2. |
| Open Source Code | Yes | Code is available at https://github.com/Shen Qianli/PICProp. |
| Open Datasets | No | The paper generates synthetic data with specified noise distributions (e.g., Gaussian, uniform) for its experiments, rather than using a publicly available dataset with concrete access information. |
| Dataset Splits | Yes | In the rest of the examples, we split 10% of the training data as the validation set to select the best λ from {0.0, 0.25, 0.5, 0.75, 1.0}. |
| Hardware Specification | No | The paper mentions support from "Google Cloud Research Credit program" and "National Supercomputing Centre, Singapore", and refers to "GPU" in Table J.2, but does not specify exact GPU models, CPU models, or detailed hardware specifications. |
| Software Dependencies | No | The paper mentions some software implicitly (e.g., PINN, Neural UQ) but does not provide specific version numbers for any libraries, frameworks, or solvers that would be necessary for reproduction. |
| Experiment Setup | Yes | Table J.1: Summary of implementation details, and utilized hyperparameters and architectures in the experiments. (Including MLP arch., inner/meta optimizer, inner/meta lr, hypergrad method, warmup/inner/meta steps, and lambda) |