Spontaneous Retrieval from Long-Term Memory for a Cognitive Architecture

Authors: Justin Li, John Laird

AAAI 2015 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental This paper presents the first functional evaluation of spontaneous, uncued retrieval from long-term memory in a cognitive architecture.
Researcher Affiliation Academia Justin Li and John Laird University of Michigan 2260 Hayward Street Ann Arbor, MI 48109-2121 {justinnh, laird}@umich.edu
Pseudocode No The paper describes implementation details in prose but does not include any structured pseudocode or algorithm blocks.
Open Source Code No The paper does not provide any statement or link indicating that the source code for the described methodology is publicly available.
Open Datasets No The puzzles used in this evaluation are gathered from the Unix word list, using compound words that can be completely divided into two shorter words; a total of 550 compound words formed by 195 stems are used, with each stem being used in an average of 2.8 compound words. - No specific link or formal citation provided.
Dataset Splits No The paper states that results are 'averaged over 100 puzzles' but does not specify any training, validation, or test dataset splits.
Hardware Specification No The paper does not provide specific details about the hardware used to run the experiments (e.g., GPU/CPU models, memory, or cloud instances).
Software Dependencies No The paper mentions 'Soar' as the cognitive architecture and 'SQLite database' for implementation, but does not provide specific version numbers for these or any other software dependencies.
Experiment Setup Yes Spreading activation is limited to a distance of two, the distance necessary to reach the solution word (from a stem to its compound words, then from the compound words to the missing link); we briefly discuss the effects of alternate settings of this parameter in the conclusion.