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..

Sampled Estimators For Softmax Must Be Biased

Authors: Li-Chung Lin, Yaxu Liu, Chih-Jen Lin

NeurIPS 2025 | Venue PDF | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical Answer: [NA] . Justification: There is no experiment.
Researcher Affiliation Academia Li-Chung Lin National Taiwan University EMAIL Yaxu Liu National Taiwan University EMAIL Mohamed bin Zayed University of Artificial Intelligence EMAIL Chih-Jen Lin National Taiwan University EMAIL Mohamed bin Zayed University of Artificial Intelligence EMAIL
Pseudocode No The paper describes steps and proves a theoretical result, but it does not contain a clearly labeled pseudocode or algorithm block.
Open Source Code No Answer: [NA] . Justification: There is no experiment.
Open Datasets No Answer: [NA] . Justification: There is no experiment.
Dataset Splits No Answer: [NA] . Justification: There is no experiment.
Hardware Specification No Answer: [NA] . Justification: There is no experiment.
Software Dependencies No The paper does not mention any software dependencies with specific version numbers, as it is a theoretical paper without experiments.
Experiment Setup No Answer: [NA] . Justification: There is no experiment.