Artifact for "From Execution to Embedding: Enriching Code Representations with Data Difference Signals for Comment Generation"

This Zenodo archive provides the Artifact Evaluation package for the ICSE 2026 NIER paper:

Giacomo Fantino, Antonio Vetrò, Marco Torchiano, and Federica Cappelluti. 2026. From Execution to Embedding: Enriching Code Representations with Data Difference Signals for Comment Generation. In 2026 IEEE/ACM 48th International Conference on Software Engineering (ICSE-NIER ’26), April 12–18, 2026, Rio de Janeiro, Brazil. https://doi.org/10.1145/3786582.3786826 

The goal of this archive is to ensure long-term availability of the materials needed to reproduce the evaluation results reported in the paper, and to support further reuse of our trained models.

It contains the following files:

• paper.pdf: The accepted ICSE NIER 2026 paper.
• README.md: Main documentation describing artifact purpose, structure, and step-by-step execution instructions.
• LICENSE: file specifying usage and redistribution terms for the artifact
• model/ folder: This folder contains the trained model checkpoints used to reproduce the experimental results reported in the paper.