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].
Decomposition Strategies for Constructive Preference Elicitation
Authors: Paolo Dragone, Stefano Teso, Mohit Kumar, Andrea Passerini
AAAI 2018 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We discuss the theoretical implications of working with parts and present promising empirical results on one synthetic and two realistic constructive problems. |
| Researcher Affiliation | Collaboration | Paolo Dragone University of Trento, Italy TIM-SKIL, Trento, Italy EMAIL Stefano Teso KU Leuven, Belgium EMAIL Mohit Kumar KU Leuven, Belgium EMAIL Andrea Passerini University of Trento, Italy EMAIL |
| Pseudocode | Yes | Algorithm 2 The PCL algorithm. |
| Open Source Code | Yes | Our experimental setup is available at https://github.com/unitn-sml/pcl. |
| Open Datasets | No | The paper describes generating data for a synthetic problem and two realistic problems (training planning, hotel planning) using a user simulation protocol, but it does not provide specific access information (link, DOI, formal citation) to a publicly available or open dataset. |
| Dataset Splits | No | The paper does not provide specific dataset split information (percentages, sample counts, or detailed splitting methodology) for training, validation, or test sets. |
| Hardware Specification | No | The paper does not provide specific hardware details for running its experiments. |
| Software Dependencies | Yes | part-wise inference is cast as a mixed integer linear problem (MILP), and solved with Gecode4. |
| Experiment Setup | Yes | We employed a user simulation protocol similar to that of (Teso, Dragone, and Passerini 2017). First, for each problem, we sampled 20 vectors w at random from a standard normal distribution... We ran PCL and evaluated the impact of user informativeness by progressively increasing α from 0.1, to 0.3, to 0.5. |