missing links

_bibliography/publications.bib

@@ -10,7 +10,8 @@ @inproceedings{yang2024large
   booktitle={Proceedings of the 46th IEEE/ACM International Conference on Software Engineering},
   pages={1--12},
   year={2024},
-  doi={10.1145/3597503.3623342}
+  doi={10.1145/3597503.3623342},
+  code={https://github.com/squaresLab/LLMAO},
 }
 
 
@@ -24,7 +25,6 @@ @INPROCEEDINGS {Ye2023PreciseBugCollector
 abstract = {Bug datasets are vital for enabling deep learning techniques to address software maintenance tasks related to bugs. However, existing bug datasets suffer from precise and scale limitations: they are either small-scale but precise with manual validation or large-scale but imprecise with simple commit message processing. In this paper, we introduce Precise-BugCollector, a precise, multi -language bug collection approach that overcomes these two limitations. PreciseBugCollector is based on two novel components: a) A bug tracker to map the codebase repositories with external bug repositories to trace bug type information, and b) A bug injector to generate project-specific bugs by injecting noise into the correct codebases and then executing them against their test suites to obtain test failure messages. We implement PreciseBugCollector against three sources: 1) A bug tracker that links to the national vulnerability data set (NVD) to collect general-wise vulnerabilities, 2) A bug tracker that links to OSS-Fuzz to collect general-wise bugs, and 3) A bug injector based on 16 injection rules to generate project-wise bugs. To date, PreciseBugCollector comprises 1057818 bugs extracted from 2968 open-source projects. Of these, 12602 bugs are sourced from bug repositories (NVD and OSS-Fuzz), while the remaining 1045216 project-specific bugs are generated by the bug injector. Considering the challenge objectives, we argue that a bug injection approach is highly valuable for the industrial setting, since project-specific bugs align with domain knowledge, share the same codebase, and adhere to the coding style employed in industrial projects.},
 keywords = {industries;deep learning;training;location awareness;software maintenance;computer bugs;manuals},
 doi = {10.1109/ASE56229.2023.00163},
-url = {https://doi.ieeecomputersociety.org/10.1109/ASE56229.2023.00163},
 publisher = {IEEE Computer Society},
 address = {Los Alamitos, CA, USA},
 month = {sep},
@@ -68,6 +68,7 @@ @inproceedings{jainContextualPMT
 address = {New York, NY, USA},
 url = {https://doi.org/10.1145/3611643.3616289},
 doi = {10.1145/3611643.3616289},
+data = {https://zenodo.org/records/7600371},
 abstract = {Mutation testing is a powerful technique for assessing and improving test suite quality that artificially introduces bugs and checks whether the test suites catch them. However, it is also computationally expensive and thus does not scale to large systems and projects. One promising recent approach to tackling this scalability problem uses machine learning to predict whether the tests will detect the synthetic bugs, without actually running those tests. However, existing predictive mutation testing approaches still misclassify 33\% of detection outcomes on a randomly sampled set of mutant-test suite pairs. We introduce MutationBERT, an approach for predictive mutation testing that simultaneously encodes the source method mutation and test method, capturing key context in the input representation. Thanks to its higher precision, MutationBERT saves 33\% of the time spent by a prior approach on checking/verifying live mutants. MutationBERT, also outperforms the state-of-the-art in both same project and cross project settings, with meaningful improvements in precision, recall, and F1 score. We validate our input representation, and aggregation approaches for lifting predictions from the test matrix level to the test suite level, finding similar improvements in performance. MutationBERT not only enhances the state-of-the-art in predictive mutation testing, but also presents practical benefits for real-world applications, both in saving developer time and finding hard to detect mutants that prior approaches do not.},
 booktitle = {Proceedings of the 31st ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering},
 pages = {250–261},
@@ -91,6 +92,7 @@ @INPROCEEDINGS {raoCATLM
 url = {https://doi.ieeecomputersociety.org/10.1109/ASE56229.2023.00193},
 publisher = {IEEE Computer Society},
 address = {Los Alamitos, CA, USA},
+data = {https://github.com/RaoNikitha/CAT-LM},
 month = {sep}
 }