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..

On Learning Verifiers and Implications to Chain-of-Thought Reasoning

Authors: Maria-Florina Balcan, Avrim Blum, Zhiyuan Li, Dravyansh Sharma

NeurIPS 2025 | Venue PDF | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical The main contribution is theoretical.
Researcher Affiliation Academia Maria-Florina Balcan Carnegie Mellon University EMAIL Avrim Blum TTIC EMAIL Zhiyuan Li TTIC EMAIL Dravyansh Sharma TTIC, Northwestern University EMAIL
Pseudocode Yes Algorithm 1 Intersection of Consistent Verifiers
Open Source Code No The main contribution is theoretical.
Open Datasets No The main contribution is theoretical.
Dataset Splits No The main contribution is theoretical.
Hardware Specification No The main contribution is theoretical.
Software Dependencies No The main contribution is theoretical.
Experiment Setup No The main contribution is theoretical.