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 Shift Toward Open and Reproducible AI Research," Under Review, 2026. doi: 10.48550/arXiv.2606.16974..
Non-Uniform Multiclass Learning with Bandit Feedback
Authors: Steve Hanneke, Amirreza Shaeiri, Hongao Wang
NeurIPS 2025 | Venue PDF | LLM Run Details | Input Tokens: 24,930 Total number of tokens sent to the LLM as input for this paper's analysis. | Output Tokens: 1,673 Total number of tokens produced by the LLM (including reasoning/thinking tokens) for this paper's analysis.
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | This paper is purely theoretical. |
| Researcher Affiliation | Academia | Steve Hanneke Department of Computer Science Purdue University West Lafayette, IN 47907 EMAIL Amirreza Shaeri Department of Computer Science Purdue University West Lafayette, IN 47907 EMAIL Hongao Wang Department of Computer Science Purdue University West Lafayette, IN 47907 EMAIL |
| Pseudocode | Yes | Algorithm 1 Generic Non-uniform Online Learning Algorithm Algorithm 2 Non-uniform Online Learning Algorithm with Full Supervision |
| Open Source Code | No | Justification: This paper is purely theoretical. |
| Open Datasets | No | Justification: This paper is purely theoretical. |
| Dataset Splits | No | Justification: This paper is purely theoretical. |
| Hardware Specification | No | Justification: This paper is purely theoretical. |
| Software Dependencies | No | Justification: This paper is purely theoretical. |
| Experiment Setup | No | Justification: This paper is purely theoretical. |