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 Shift Toward Open and Reproducible AI Research," Under Review, 2026. doi: 10.48550/arXiv.2606.16974..
Classification with Few Tests through Self-Selection
Authors: Hanrui Zhang, Yu Cheng, Vincent Conitzer5805-5812
AAAI 2021 | Venue PDF | LLM Run Details | Input Tokens: 17,349 Total number of tokens sent to the LLM as input for this paper's analysis. | Output Tokens: 5,989 Total number of tokens produced by the LLM (including reasoning/thinking tokens) for this paper's analysis.
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | The paper consistently presents lemmas, theorems, propositions, and definitions, and uses examples for illustration, indicating a focus on conceptual and mathematical contributions rather than empirical validation. For instance, in Section 3, it states: "Lemma 1. Fixing a policy P and a cost per test c, the optimal expected reward of any agent is achieved by one of the following two strategies:..." and in Section 4.2: "Theorem 2. Let P O = [k] be a set of outcomes such that P argmax S O:G(S)>B(S) G(S). P = {{o} | o P} {{o1, o2} | o1, o2 O} is perfectly implementable..." |
| Researcher Affiliation | Academia | Hanrui Zhang,1 Yu Cheng, 2 Vincent Conitzer 1 1 Duke University 2 University of Illinois at Chicago EMAIL, EMAIL, EMAIL |
| Pseudocode | No | The paper presents lemmas, theorems, and definitions, along with prose descriptions of agents' strategies and policies, but it does not include any structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not contain any statements about releasing source code, nor does it provide links to any code repositories. |
| Open Datasets | No | The paper is theoretical and does not mention using any datasets for training or evaluation, nor does it provide access information for any data. It uses abstract distributions G and B. |
| Dataset Splits | No | The paper is theoretical and does not involve data splits for training, validation, or testing. The discussion is based on mathematical models of distributions. |
| Hardware Specification | No | The paper is purely theoretical and does not mention any hardware specifications used for running experiments. |
| Software Dependencies | No | The paper is purely theoretical and does not mention any software dependencies or specific versions for replication, as no computational experiments are described. |
| Experiment Setup | No | The paper describes a theoretical framework and proves properties of policies and agent behavior. It does not include details about an experimental setup, hyperparameters, or training configurations. |