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..
Distribution Learning Meets Graph Structure Sampling
Authors: Arnab Bhattacharyya, Sutanu Gayen, Philips George John, Sayantan Sen, N. V. Vinodchandran
NeurIPS 2025 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | This work establishes a novel link between the problem of PAC-learning highdimensional graphical models and the task of (efficient) counting and sampling of graph structures, using an online learning framework. The NeurIPS checklist confirms: "The paper has no experimental results." for questions regarding reproducibility of experiments, open access to data and code, experimental setting, statistical significance, and compute resources. |
| Researcher Affiliation | Academia | The authors are affiliated with: Arnab Bhattacharyya (University of Warwick), Sutanu Gayen (IIT Kanpur), Philips George John (CNRS@CREATE & Dept of Computer Science National University of Singapore), Sayantan Sen (Centre for Quantum Technologies National University of Singapore), and N. V. Vinodchandran (University of Nebraska-Lincoln). All listed institutions are universities or public research organizations. |
| Pseudocode | Yes | The paper includes 'Algorithm 1: EWA-based learning for Bayes nets' and 'Algorithm 2: RWM-based learning for Bayes nets' on page 5, which are clearly labeled pseudocode blocks. |
| Open Source Code | No | The NeurIPS checklist, in response to "Does the paper provide open access to the data and code...?" states "Answer: [NA] Justification: The paper has no experimental results requiring code." This indicates no open-source code is provided for the methodology described. |
| Open Datasets | No | The paper is theoretical and does not use any specific datasets for empirical validation. The NeurIPS checklist, in response to "Does the paper fully disclose all the information needed to reproduce the main experimental results...?" states "Answer: [NA] Justification: The paper has no experimental results." Therefore, no open datasets are provided or referenced. |
| Dataset Splits | No | The paper is theoretical and does not involve experiments with datasets. The NeurIPS checklist, in response to "Does the paper fully disclose all the information needed to reproduce the main experimental results...?" states "Answer: [NA] Justification: The paper has no experimental results." Thus, no dataset splits are provided. |
| Hardware Specification | No | The paper is theoretical and does not report experimental results that would require specific hardware. The NeurIPS checklist, in response to "For each experiment, does the paper provide sufficient information on the computer resources...?" states "Answer: [NA] Justification: The paper has no experimental results." Therefore, no hardware specifications are mentioned. |
| Software Dependencies | No | The paper is theoretical and does not contain experimental results. No specific software dependencies with version numbers are mentioned. The NeurIPS checklist states, "The answer NA means that the paper does not include experiments." for related questions. |
| Experiment Setup | No | The paper is theoretical and does not conduct experiments. Therefore, it does not provide details about experimental setup, hyperparameters, or training configurations. The NeurIPS checklist confirms, "The answer NA means that the paper does not include experiments." |