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..
Reconstruction and Secrecy under Approximate Distance Queries
Authors: Shay Moran, Elizaveta Nesterova
NeurIPS 2025 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | We study this reconstruction game through a learning-theoretic lens, focusing on the rate and limits of the best possible reconstruction error. Our first result provides a tight geometric characterization of the optimal error in terms of the Chebyshev radius, a classical concept from geometry. This characterization applies to all compact metric spaces (in fact, even to all totally bounded spaces) and yields explicit formulas for natural metric spaces. Our second result addresses the asymptotic behavior of reconstruction, distinguishing between pseudo-finite spaces where the optimal error is attained after finitely many queries and spaces where the approximation curve exhibits a nontrivial decay. We characterize pseudo-finiteness for convex Euclidean spaces. |
| Researcher Affiliation | Collaboration | Shay Moran Department of Mathematics, Technion Department of Computer Science, Technion Department of Data and Decision Sciences, Technion Google research |
| Pseudocode | No | The paper describes the 'Reconstruction Game' with numbered steps, but this is a high-level description of the problem setup and rules, not a detailed algorithm or pseudocode implemented by the authors for their methodology. Similarly, the 'Our strategy proceeds as follows' section in 3.2 is a descriptive overview rather than structured pseudocode. |
| Open Source Code | No | The paper does not contain any explicit statements about releasing code, nor does it provide links to source code repositories. The NeurIPS checklist confirms: "The paper does not involve data or code. All contributions are analytical." |
| Open Datasets | No | The paper is theoretical and does not perform experiments that would require datasets. There is no mention of any datasets being used or made publicly available for the research described. The NeurIPS checklist confirms: "The paper does not involve data or code. All contributions are analytical." |
| Dataset Splits | No | The paper is theoretical and does not involve experiments or datasets, therefore, there are no dataset splits to describe. |
| Hardware Specification | No | The paper is purely theoretical and does not involve any experimental setup or computational simulations, therefore, no hardware specifications are mentioned or required. The NeurIPS checklist confirms: "No compute resources were used, as the paper contains no experiments or computational simulations." |
| Software Dependencies | No | The paper is purely theoretical and does not involve any experimental implementations or software. Therefore, no software dependencies with version numbers are listed or required. |
| Experiment Setup | No | The paper is entirely theoretical and does not present any experimental results. As such, there is no experimental setup, hyperparameters, or system-level training settings described. The NeurIPS checklist confirms: "There are no experiments in this work. The paper is entirely theoretical." |