Notice: 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. Full accuracy metrics and methodology are described in Coakley et alK. L. Coakley, T. Snelleman, H. Hoos, and O. E. Gundersen, "The embrace of open science: An analysis of a decade of AI research and 56 800 conference papers," Under Review, 2026..
Shape Constraints for Set Functions
Authors: Andrew Cotter, Maya Gupta, Heinrich Jiang, Erez Louidor, James Muller, Tamann Narayan, Serena Wang, Tao Zhu
ICML 2019 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experiments on real-world data show the achieved accuracy is similar to deep sets or deep neural networks, but provides guarantees on the model behavior, which makes it easier to explain and debug. |
| Researcher Affiliation | Industry | Google AI, Mountain View, CA. |
| Pseudocode | No | The paper does not contain any structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not provide any concrete access information (e.g., links or explicit statements) to open-source code for the described methodology. |
| Open Datasets | Yes | For the Kaggle puzzles dataset, the goal is to predict the number of sales of each of 199 puzzles over a six month window given its set of customer reviews at the beginning of the six month period. The Kaggle Kickstarter dataset has N = 331,034 examples of Kickstarter campaign titles that are labeled as succeeded or failed. The Kaggle recipes dataset consists of N = 39,774 recipes from 20 cuisines. |
| Dataset Splits | Yes | We split those examples randomly 70/10/20 to form a train/validation/test set, then split the train data 90/10 to train the SFE and the set function on separate train data; the DNN was trained on all 100% of the training data. The dataset was randomly split 70/10/20 into a train/validation/test set, and then the train set was randomly split 90/10 into SFE train set and set function train set. |
| Hardware Specification | No | The paper does not provide any specific details about the hardware used for running its experiments, such as GPU/CPU models or cloud instance types. |
| Software Dependencies | No | The paper mentions a "TensorFlow implementation" but does not specify a version number for TensorFlow or any other software dependencies. |
| Experiment Setup | No | The paper states, "All hyperparameters were validated: see Appendix J for details." This indicates that details exist but are not presented in the main text. |