Automated Type-IV Clone Generation via LLMs and Deterministic Validation (replication package)

KaminoDatasetGenerator.zip - contains the replication package for the empirical evaluation. It includes the REQUIREMENTS, LICENSE, and STATUS files as requested for the AE track.

Make sure to read the Readme.md inside the root folder for instructions. 

kamino_image.tar - is the docker image provided for reproducilibity (only a small sample of the input dataset is used). The full dataset can be tested by running the code independently. Make sure to read the README file inside the KaminoDatasetGenerator folder to see instructions.

To reuse the fine-tuned models, extract rq3models.zip inside /results/RQ3 and rq4models.zip inside /results/RQ4

The experiment results are in /results

The pilot study results are inside /results/pilot study

The results of exploring the top 50 configurations are inside /results/using top 50 configs

Prompts.pdf  - prompts used for Type-IV clone generation and repairing, implementations are inside /pipeline/src/utils/prompts.py

Refactorings.pdf - contains a description, with examples, of the seven refactorings used as part of the prompts

Hyperparameters - these are inside /pipeline/src/config.py

kamino_clones_dataset.zip - the final dataset, including the three variants (LD, MD, and HD)