MSR 2024
Mon 15 - Tue 16 April 2024 Lisbon, Portugal
co-located with ICSE 2024

The development and training of deep learning models have become increasingly costly and complex. Consequently, software engineers are adopting pre-trained models (PTMs) for their downstream applications. The dynamics of the PTM supply chain remain largely unexplored, signaling a clear need for structured datasets that document not only the metadata but also the subsequent applications of these models. Without such data, the MSR community cannot comprehensively understand the impact of PTM adoption and reuse.

This paper presents the PeaTMOSS dataset, which comprises metadata for 281,638 PTMs and detailed snapshots for all PTMs with over 50 monthly downloads (14,296 PTMs), along with 28,575 open-source software repositories from GitHub that utilize these models. Additionally, the dataset includes 44,337 mappings from 15,129 downstream GitHub repositories to the 2,530 PTMs they use. To enhance the dataset’s comprehensiveness, we developed prompts for a large language model to automatically extract model metadata, including the model’s training datasets, parameters, and evaluation metrics. Our analysis of this dataset provides the first summary statistics for the PTM supply chain, showing the trend of PTM development and common shortcomings of PTM package documentation. Our example application reveals inconsistencies in software licenses across PTMs and their dependent projects. PeaTMOSS lays the foundation for future research, offering rich opportunities to investigate the PTM supply chain. We outline mining opportunities on PTMs, their downstream usage, and cross- cutting questions.

Mon 15 Apr

Displayed time zone: Lisbon change

16:00 - 17:30
Machine learning for Software EngineeringTechnical Papers / Industry Track at Grande Auditório
Chair(s): Diego Costa Concordia University, Canada
16:00
12m
Talk
Whodunit: Classifying Code as Human Authored or GPT-4 Generated - A case study on CodeChef problems
Technical Papers
Oseremen Joy Idialu University of Waterloo, Noble Saji Mathews University of Waterloo, Canada, Rungroj Maipradit University of Waterloo, Joanne M. Atlee University of Waterloo, Mei Nagappan University of Waterloo
DOI Pre-print
16:12
12m
Talk
GIRT-Model: Automated Generation of Issue Report Templates
Technical Papers
Nafiseh Nikehgbal Sharif University of Technology, Amir Hossein Kargaran LMU Munich, Abbas Heydarnoori Bowling Green State University
DOI Pre-print
16:24
12m
Talk
MicroRec: Leveraging Large Language Models for Microservice Recommendation
Technical Papers
Ahmed Saeed Alsayed University of Wollongong, Hoa Khanh Dam University of Wollongong, Chau Nguyen University of Wollongong
16:36
12m
Talk
PeaTMOSS: A Dataset and Initial Analysis of Pre-Trained Models in Open-Source Software
Technical Papers
Wenxin Jiang Purdue University, Jerin Yasmin Queen's University, Canada, Jason Jones Purdue University, Nicholas Synovic Loyola University Chicago, Jiashen Kuo Purdue University, Nathaniel Bielanski Purdue University, Yuan Tian Queen's University, Kingston, Ontario, George K. Thiruvathukal Loyola University Chicago and Argonne National Laboratory, James C. Davis Purdue University
DOI Pre-print
16:48
12m
Talk
Data Augmentation for Supervised Code Translation Learning
Technical Papers
Binger Chen Technische Universität Berlin, Jacek golebiowski Amazon AWS, Ziawasch Abedjan Leibniz Universität Hannover
17:00
12m
Talk
On the Effectiveness of Machine Learning-based Call-Graph Pruning: An Empirical Study
Technical Papers
Amir Mir Delft University of Technology, Mehdi Keshani Delft University of Technology, Sebastian Proksch Delft University of Technology, Netherlands
Pre-print
17:12
12m
Talk
Leveraging GPT-like LLMs to Automate Issue Labeling
Technical Papers
Giuseppe Colavito University of Bari, Italy, Filippo Lanubile University of Bari, Nicole Novielli University of Bari, Luigi Quaranta University of Bari, Italy
Pre-print
17:24
5m
Talk
A Mining Framework for Distributed Systems Developers for Real-Time Alerts and Guidance using Generative AI
Industry Track