English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

A large body of the literature on automated program repair developsapproaches where patches are automatically generated to be validated against anoracle (e.g., a test suite). Because such an oracle can be imperfect, thegenerated patches, although validated by the oracle, may actually be incorrect.Our empirical work investigates different representation learning approachesfor code changes to derive embeddings that are amenable to similaritycomputations of patch correctness identification, and assess the possibility ofaccurate classification of correct patch by combining learned embeddings withengineered features. Experimental results demonstrate the potential of learnedembeddings to empower Leopard (a patch correctness predicting frameworkimplemented in this work) with learning algorithms in reasoning about patchcorrectness: a machine learning predictor with BERT transformer-based learnedembeddings associated with XGBoost achieves an AUC value of about 0.803 in theprediction of patch correctness on a new dataset of 2,147 labeled patches thatwe collected for the experiments. Our investigations show that deep learnedembeddings can lead to complementary/better performance when comparing againstthe state-of-the-art, PATCH-SIM, which relies on dynamic information. Bycombining deep learned embeddings and engineered features, Panther (theupgraded version of Leopard implemented in this work) outperforms Leopard withhigher scores in terms of AUC, +Recall and -Recall, and can accurately identifymore (in)correct patches that cannot be predicted by the classifiers only withlearned embeddings or engineered features. Finally, we use an explainable MLtechnique, SHAP, to empirically interpret how the learned embeddings andengineered features are contributed to the patch correctness prediction.

The Best of Both Worlds: Combining Learned Embeddings with Engineered Features for Accurate Prediction of Correct Patches