Chain Length and CSPs Learnable with Few Queries

Authors: Christian Bessiere, Cl‚ément Carbonnel, George Katsirelos1420-1427

AAAI 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical The entire paper is a theoretical analysis with proofs and lemmas, without any experimental setup, data, or results section. For example, Section 3 describes "Constraint acquisition and chain length" with a Theorem 7 proof for learnability without any empirical validation.
Researcher Affiliation Academia 1LIRMM, CNRS, University of Montpellier, France {christian.bessiere, clement.carbonnel}@lirmm.fr 2UMR MIA-Paris, INRA, Agro Paris Tech, Universit e Paris-Saclay, Paris, France gkatsi@gmail.com
Pseudocode No The paper describes an algorithm verbally in the proof of Theorem 7, but it does not contain a structured pseudocode block or a clearly labeled algorithm figure.
Open Source Code No The paper is theoretical and does not mention releasing any source code for the described methodology.
Open Datasets No The paper is theoretical and does not mention the use of any datasets, public or otherwise, for training or evaluation.
Dataset Splits No The paper is theoretical and does not describe any dataset splits for training, validation, or testing.
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 theoretical and does not specify any software dependencies with version numbers.
Experiment Setup No The paper is purely theoretical and does not include any details about an experimental setup or hyperparameters.