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 [1].
Mathematical Framework for Online Social Media Auditing
Authors: Wasim Huleihel, Yehonathan Refael
JMLR 2024 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | In this paper, we mathematically formalize this framework and utilize it to construct a data-driven statistical auditing procedure to regulate AF from deflecting users beliefs over time, along with sample complexity guarantees. A major goal going forward is to evince our auditing procedure on real social media content. Specifically, while our work propose a theoretical framework for SMP auditing, we left several fundamental questions that revolve around implementability, such as, how do we know if the framework is effective or useful? What are the metrics that should be used? We are currently investigating these kind of questions. |
| Researcher Affiliation | Academia | Wasim Huleihel EMAIL Department of Electrical Engineering-Systems Tel Aviv University Tel Aviv 6997801, Israel Yehonathan Refael EMAIL Department of Electrical Engineering-Systems Tel Aviv University Tel Aviv 6997801, Israel |
| Pseudocode | Yes | Algorithm 1: Tolerant closeness tester for the i.i.d. pairs, Algorithm 2: Filtered vs. reference auditing procedure, Algorithm 3: Counterfactual auditing procedure |
| Open Source Code | No | The paper does not contain any explicit statements about releasing source code or links to code repositories. The conclusion states: "A major goal going forward is to evince our auditing procedure on real social media content. Specifically, while our work propose a theoretical framework for SMP auditing, we left several fundamental questions that revolve around implementability, such as, how do we know if the framework is effective or useful? What are the metrics that should be used? We are currently investigating these kind of questions." |
| Open Datasets | No | The paper focuses on theoretical development and does not describe or evaluate its methodology using specific, publicly available datasets. It mentions "samples" in a theoretical context, such as "Given sample access the pairs of distributions (Pu, Qu) over [n]". |
| Dataset Splits | No | The paper is theoretical, focusing on mathematical framework and algorithms, and does not conduct experiments requiring dataset splits. No information about training, validation, or test splits is provided. |
| Hardware Specification | No | The paper describes a mathematical framework and algorithms; it does not report on experimental results that would require specific hardware. No hardware specifications are provided. |
| Software Dependencies | No | The paper is theoretical in nature and does not describe any software implementations or list specific software dependencies with version numbers. |
| Experiment Setup | No | The paper is a theoretical work that introduces a mathematical framework and algorithms. It does not include details on experimental setup, hyperparameters, or training configurations. |