Replication Data for: Uncovering LLMs for Service-Composition: Challenges and Opportunities
R. Pesl, M. Stötzner, I. Georgievski, and M. Aiello. Dataset, (2023)Related to: Pesl, R.D., Stötzner, M., Georgievski, I., Aiello, M.: Uncovering LLMs for Service-Composition: Challenges and Opportunities. In: ICSOC 2023 Workshops (2023).
DOI: 10.18419/darus-3767
Abstract
Experimental results for the ICSOC 2023 AI-PA position paper Üncovering LLMs for Service-Composition: Challenges and Opportunities. "Exemplars: List of scenarios found in the Google Scholar literature search.Experiment 1 Service Discovery: Chat history for experiment 1 asking ChatGPT for existing real services. Experiment 2 Service Composition: Chat history and service composition for experiment 2 asking ChatGPT for a service composition in Python using a natural language task and the list of services from experiment 1. Experiment 3 Combined Service Discovery and Composition: Chat history and service composition for experiment 3 asking ChatGPT for a service composition in Python using a natural language task without a list of services. Each experiment in the dataset has its own folder (use the tree view to see the folder layout of the files). Chats in experiments 2 and 3 are accompanied by their service composition in Python from that chat as an extra file.
Pesl, Robin D./University of Stuttgart, Institute of Architecture of Application Systems, Stötzner, Miles/University of Stuttgart, Institute of Software Engineering, Georgievski, Ilche/University of Stuttgart, Institute of Architecture of Application Systems, Aiello, Marco/University of Stuttgart, Institute of Architecture of Application Systems
orcid-numbers
Pesl, Robin D./0000-0002-5980-9395, Stötzner, Miles/0000-0003-1538-5516, Georgievski, Ilche/0000-0001-6745-0063, Aiello, Marco/0000-0002-0764-2124
Related to: Pesl, R.D., Stötzner, M., Georgievski, I., Aiello, M.: Uncovering LLMs for Service-Composition: Challenges and Opportunities. In: ICSOC 2023 Workshops (2023)
%0 Generic
%1 pesl2023replication
%A Pesl, Robin D.
%A Stötzner, Miles
%A Georgievski, Ilche
%A Aiello, Marco
%D 2023
%K darus mult ubs_10005 ubs_20008 ubs_30079 ubs_40104 ubs_40295 unibibliografie
%R 10.18419/darus-3767
%T Replication Data for: Uncovering LLMs for Service-Composition: Challenges and Opportunities
%X Experimental results for the ICSOC 2023 AI-PA position paper Üncovering LLMs for Service-Composition: Challenges and Opportunities. "Exemplars: List of scenarios found in the Google Scholar literature search.Experiment 1 Service Discovery: Chat history for experiment 1 asking ChatGPT for existing real services. Experiment 2 Service Composition: Chat history and service composition for experiment 2 asking ChatGPT for a service composition in Python using a natural language task and the list of services from experiment 1. Experiment 3 Combined Service Discovery and Composition: Chat history and service composition for experiment 3 asking ChatGPT for a service composition in Python using a natural language task without a list of services. Each experiment in the dataset has its own folder (use the tree view to see the folder layout of the files). Chats in experiments 2 and 3 are accompanied by their service composition in Python from that chat as an extra file.
@misc{pesl2023replication,
abstract = {Experimental results for the ICSOC 2023 AI-PA position paper "Uncovering LLMs for Service-Composition: Challenges and Opportunities. "Exemplars: List of scenarios found in the Google Scholar literature search.Experiment 1 Service Discovery: Chat history for experiment 1 asking ChatGPT for existing real services. Experiment 2 Service Composition: Chat history and service composition for experiment 2 asking ChatGPT for a service composition in Python using a natural language task and the list of services from experiment 1. Experiment 3 Combined Service Discovery and Composition: Chat history and service composition for experiment 3 asking ChatGPT for a service composition in Python using a natural language task without a list of services. Each experiment in the dataset has its own folder (use the tree view to see the folder layout of the files). Chats in experiments 2 and 3 are accompanied by their service composition in Python from that chat as an extra file. },
added-at = {2023-12-14T10:28:49.000+0100},
affiliation = {Pesl, Robin D./University of Stuttgart, Institute of Architecture of Application Systems, Stötzner, Miles/University of Stuttgart, Institute of Software Engineering, Georgievski, Ilche/University of Stuttgart, Institute of Architecture of Application Systems, Aiello, Marco/University of Stuttgart, Institute of Architecture of Application Systems},
author = {Pesl, Robin D. and Stötzner, Miles and Georgievski, Ilche and Aiello, Marco},
biburl = {https://puma.ub.uni-stuttgart.de/bibtex/2a89c24f47a54e08095f95b79c583af04/unibiblio},
doi = {10.18419/darus-3767},
howpublished = {Dataset},
interhash = {0619f15f280e27d46c8e4a92f7414b79},
intrahash = {a89c24f47a54e08095f95b79c583af04},
keywords = {darus mult ubs_10005 ubs_20008 ubs_30079 ubs_40104 ubs_40295 unibibliografie},
note = {Related to: Pesl, R.D., Stötzner, M., Georgievski, I., Aiello, M.: Uncovering LLMs for Service-Composition: Challenges and Opportunities. In: ICSOC 2023 Workshops (2023)},
orcid-numbers = {Pesl, Robin D./0000-0002-5980-9395, Stötzner, Miles/0000-0003-1538-5516, Georgievski, Ilche/0000-0001-6745-0063, Aiello, Marco/0000-0002-0764-2124},
timestamp = {2023-12-14T10:28:49.000+0100},
title = {Replication Data for: Uncovering LLMs for Service-Composition: Challenges and Opportunities},
year = 2023
}