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].
Strategic Sequences of Arguments for Persuasion Using Decision Trees
Authors: Emmanuel Hadoux, Anthony Hunter
AAAI 2017 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | In this section, we present the experiments we conducted in order to study the behaviour of each decision rule with respect to the behaviour of the persuadee and the error in the representation of this behaviour by the persuader. |
| Researcher Affiliation | Academia | Emmanuel Hadoux and Anthony Hunter Department of Computer Science, University College London London, UK EMAIL |
| Pseudocode | Yes | Algorithm 1: Decision tree building. Algorithm 2: Experimental run algorithm. |
| Open Source Code | No | The paper does not provide an explicit statement or link for the open-source code of the methodology described in this paper. |
| Open Datasets | No | First, we randomly generate 100 graphs with 8 arguments without cycles. |
| Dataset Splits | No | The paper describes generating graphs and performing simulations, but it does not provide specific train/validation/test dataset splits for reproducibility. |
| Hardware Specification | No | The paper does not provide specific details about the hardware used for running the experiments. |
| Software Dependencies | No | The paper does not list specific software dependencies with version numbers that would be needed to replicate the experiment. |
| Experiment Setup | Yes | First, we randomly generate 100 graphs with 8 arguments without cycles. For each graph, 5 different persuasion goals are randomly selected giving a ο¬nal set of 500 persuasion problems. ... The ambivalent method can be replaced by any update method (see (Hunter 2015) for more methods). ... Figures 2a, 2b, 2c and 2d present the results averaged on 1000 runs performed on each of the 500 graphs for horizons of 2, 4, 6, and 8. |