Load GHAW-H
Read all five tables and construct the core analytical joins.
Open in ColabGHAW-H: A Dataset of
GitHub Agentic Workflow Histories
Upcoming NLBSE 2027 · Co-located with ICSE 2027
GitHub Agentic Workflows Challenge
Use GHAW-H to investigate natural-language agentic workflow specifications, their compiled workflows, and their evolution.
Paper submission: November 13, 2026 (AoE)
Read the call
Dataset Overview
GHAW-H connects repository metadata with the observable history of natural-language workflow specifications and their aligned lock files. It contains 262 repositories, 604 source histories, 2,820 Markdown versions, and 2,820 lock snapshots.
What is included?
262repositories
604source histories
2,820Markdown versions
2,820lock snapshots
Relational schema
Explore the dataset
Dataset Overview
Inspect coverage and reproduce the cumulative adoption figure.
Open in ColabLanguage usage
Compare adoption across repository language ecosystems.
Open in ColabHistory analysis
Explore version depth, history span, and temporal change.
Open in ColabCitation
If you use GHAW-H, please cite the archived v0.1.2 dataset release and identify the version used.
Valenzuela-Toledo, P., Kehrer, T., & Panichella, S. (2026). GHAW-H: A Dataset of GitHub Agentic Workflow Histories (Version v0.1.2) [Dataset]. Zenodo. https://doi.org/10.5281/zenodo.22084012
@dataset{valenzuela_toledo_ghaw_h_2026,
author = {Valenzuela-Toledo, Pablo and Kehrer, Timo and Panichella, Sebastiano},
title = {{GHAW-H}: A Dataset of GitHub Agentic Workflow Histories},
year = {2026},
publisher = {Zenodo},
version = {v0.1.2},
doi = {10.5281/zenodo.22084012},
url = {https://doi.org/10.5281/zenodo.22084012}
}Affiliated institutions
