Flexible Model Induction through Heuristic Process Discovery
Authors: Pat Langley, Adam Arvay
AAAI 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | 4 Empirical Studies Our approach to flexible process modeling appears promising, but its effectiveness is an empirical question. In this section, we report results from a number of studies with the two systems. |
| Researcher Affiliation | Academia | Pat Langley Institute for the Study of Learning and Expertise 2164 Staunton Court, Palo Alto, CA 94306 Adam Arvay Department of Computer Science University of Auckland, Auckland 1142 NZ |
| Pseudocode | No | The paper does not contain any pseudocode or clearly labeled algorithm blocks. |
| Open Source Code | No | The paper does not provide any explicit statement about open-sourcing the code for the methodology or a link to a code repository. |
| Open Datasets | Yes | The initial run examined FPM s behavior on a natural data set, reported by Veilleux (1979), that displays a classic predator-prey cycle in which the protist Nasutum feeds on Aurelia, another protist. (...) We also ran FPM on synthetic time series for an aquatic ecosystem from Arvay and Langley (2016) that included phytoplankton, zooplankton, nitrogen, iron, and detritus. |
| Dataset Splits | No | The paper mentions parameters for the SPM module's operation like sampling counts and R2 acceptance threshold, but it does not specify train/validation/test dataset splits needed for reproduction. |
| Hardware Specification | No | The paper does not provide specific details about the hardware used to run the experiments, such as CPU or GPU models. |
| Software Dependencies | No | The paper mentions "Steel Bank Common Lisp" and "Arvay and Langley s (2016) SPM program" but does not provide specific version numbers for these or any other ancillary software components/libraries. |
| Experiment Setup | Yes | The SPM module took 5,000 samples of ten processes each, found up to ten equations for each variable, and used 0.98 as its r2 acceptance threshold. |