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..
Learning from Interval Targets
Authors: Rattana Pukdee, Ziqi Ke, Chirag Gupta
NeurIPS 2025 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Finally, we perform extensive experiments on real-world datasets and show that our methods achieve state-of-the-art performance. |
| Researcher Affiliation | Collaboration | Rattana Pukdee Carnegie Mellon University EMAIL Ziqi Ke Bloomberg EMAIL Chirag Gupta Bloomberg EMAIL |
| Pseudocode | No | The paper describes various algorithms and methods (e.g., Minmax, PL (Max), PL (Mean)) but does not present them in a structured pseudocode or algorithm block format. |
| Open Source Code | Yes | Our code is available at https://github.com/bloomberg/interval_targets. |
| Open Datasets | Yes | We empirically validate our theoretical results with comprehensive experiments on five public datasets from the UCI Machine Learning Repository and 18 additional tabular regression datasets [Grinsztajn et al., 2022]... The datasets are from the UCI Machine learning repository [Nash et al., 1994, Brooks et al., 1989, Yeh, 1998, Tfekci and Kaya, 2014] with Creative Commons Attribution 4.0 International (CC BY 4.0) license. |
| Dataset Splits | No | The paper mentions using 'training datasets', 'validation dataset', and evaluating 'test MAE' but does not provide specific percentages or counts for these splits. It states 'We used a validation dataset to select the best hyperparameters' in Appendix L, and refers to using 'the same configuration as [Cheng et al., 2023a]' for setup, but the specific numerical splits are not explicitly provided in this paper. |
| Hardware Specification | No | Question: For each experiment, does the paper provide sufficient information on the computer resources (type of compute workers, memory, time of execution) needed to reproduce the experiments? Answer: [No] Justification: The paper requires a very small amount of compute to run so we did not provide this information. |
| Software Dependencies | No | The paper mentions 'Adam optimizer' and 'Lipschitz MLPs MLPs augmented with spectral normalization layers [Miyato et al., 2018]' but does not provide specific version numbers for these or any other software libraries or frameworks used. |
| Experiment Setup | Yes | For the experimental setup, we used the same configuration as [Cheng et al., 2023a]: the model architecture is a MLP with hidden layers of sizes 10, 20, and 30. We trained the models using the Adam optimizer with a learning rate of 0.001 and a batch size of 512 for 1000 epochs. |