Context-Aware Patch Generation for Better Automated Program Repair

By Ming Wen, Junjie Chen, Rongxin Wu, Dan Hao, Shing-Chi Cheung. International Conference on Software Engineering, 2018

391 citations recorded by the source corpus.

Subfields: Information Systems, Software

View Paper: https://www.semanticscholar.org/paper/df6061b9d3da5865e3385bbcbc7d039b3ef6bb0f

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Information Systems

1. Chun Xia
2. Lingming Zhang
3. Tien Nhut Nguyen
4. Baishakhi Ray
5. Miltiadis Allamanis
6. Yangruibo Ding
7. Saikat Chakraborty
8. Michele Tufano

In Software

1. Chun Xia
2. Lingming Zhang
3. Baishakhi Ray
4. Tien Nhut Nguyen
5. Yangruibo Ding
6. Shaohua Wang
7. Yi Li
8. Michele Tufano

Citations in the corpus

• Baldur: Whole-Proof Generation and Repair with Large Language Models (2023, methodology): “The automated program repair field studies the task of taking a program with a bug, evidenced by one or more failing tests, and automatically producing a modified version of the program that passes all the tests [50].”
• Shaping program repair space with existing patches and similar code (2018, result): “This result is consistent with the results in existing studies [25, 38, 61].”
• DLFix: Context-based Code Transformation Learning for Automated Program Repair (2020, methodology): “We chose Ochiai algorithm [3, 29], which has been widely used in APR [13, IS, 18,42,45,46].”
• CoCoNuT: combining context-aware neural translation models using ensemble for program repair (2020, neutral): “Suplem eted 7 JAID [12] 9/31 8 HD-Repair* [37] 13/23 9 SketchFix* [27] 19/26 10 ssFix* [86] 20/60 11 CapGen* [82] 21/25 12 ConFix [33] 22/92 13 Elixir* [69] 26/41 14 Hercules [71] 49/72 -”
• Getafix: learning to fix bugs automatically (2019, methodology): “report. With an appropriate method to instantiate the unbound holes, these fix patterns may prove useful as well. For example, one could attempt instantiation using ingredients as done for example by [20]. In a more interactive context, for instance when suggesting fixes in an IDE, one could also le”
• A syntax-guided edit decoder for neural program repair (2021, methodology): “Since Recoder generates only single-hunk patches (patches that only change a consecutive code fragment), we chose 10 traditional single-hunk APR approaches that are often used as baselines in existing studies: jGenProg [35], HDRepair [32], Nopol [73], CapGen [69], SketchFix [22], TBar [40], FixMiner”
• TBar: revisiting template-based automated program repair (2019, methodology): “[63].”
• Software Testing With Large Language Models: Survey, Landscape, and Vision (2023, neutral): “There have been template-based [143], heuristic-based [144], and constraint-based [145], [146] automatic program repair techniques.”
• Automated Program Repair in the Era of Large Pre-trained Language Models (2022, neutral): “Furthermore, we also choose 12 traditional APR tools: TBar [19], PraPR [20], AVATAR [16], SimFix [68], FixMiner [15], CapGen [9], JAID [69], SketchFix [13], NOPOL [12], jGenProg [70], jMutRepair [14], and jKali [14].”
• SequenceR: Sequence-to-Sequence Learning for End-to-End Program Repair (2018, methodology): “Program repair research is very active and dominated by techniques based on static analysis ( e.g., Angelix [20]) and dynamic analysis ( e.g., CapGen [35]).”
• Less training, more repairing please: revisiting automated program repair via zero-shot learning (2022, methodology): “Depending on how patches are generated, traditional APR techniques can be categorized into heuristic-based [38, 39, 74], constraintbased [17, 37, 55], and template-based [29, 35, 44, 45, 53].”
• CODIT: Code Editing With Tree-Based Neural Models (2018, methodology): “CapGen [88] prioritize operator in expression and fix ingredients based in the context of the fix.”