Downloads

https://doi.org/10.62836/jitp.v4i1.0003
Gong, H. (2026). Graph-Evidence Repository Repair: Risk-Calibrated Retrieval and Patch Gating on SWE-Bench. Journal of Information, Technology and Policy, 4(1), 0003. https://doi.org/10.62836/jitp.v4i1.0003
Volume 4, Issue 1, 2026
Copyright (c) 2026 Haitao Gong
Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

Graph-Evidence Repository Repair: Risk-Calibrated Retrieval and Patch Gating on SWE-Bench

Repository-scale issue repair requires more than patch generation: it requires evidence retrieval, test-grounded rejection, uncertainty calibration, and an explicit decision about whether a candidate deserves scarce verification capacity. This paper proposes RAGE-Repair, a graph-evidence repair method evaluated with the public SWE-bench Lite corpus. The case study loads 300 SWE-bench Lite instances from 12 repositories and analyzes issue length, patch size, test-patch effort, and changed-file scope. The method constructs a repository evidence lattice, estimates residual ambiguity, penalizes tail patch risk with CVaR, and admits a candidate only when expected repair value exceeds its test and review price. The median problem statement contains 1044 characters, the median gold patch has 20 lines, and the top repository contributes 114 instances. Native derivations establish the robust risk bound, primal-dual capacity controller, online regret guarantee, and graph-specific patch gate. The resulting design makes each accepted or rejected repair traceable to evidence support, uncertainty, and verification cost.

software engineering automated program repair SWE-bench risk calibration repository-level agents

References

  1. Pressman RS, Maxim BR. Software Engineering: A Practitioner’s Approach; McGraw-Hill: New York, NY, USA, 2020.
  2. Sommerville I. Software Engineering; Pearson: Boston, MA, USA, 2016.
  3. Boehm BW. Software Engineering Economics; Prentice Hall: Englewood Cliffs, NJ, USA, 1981.
  4. Dijkstra EW. The Humble Programmer. Communications of the ACM 1972; 15(10): 859–866.
  5. Parnas DL. On the Criteria to Be Used in Decomposing Systems into Modules. Communications of the ACM 1972; 15(12): 1053–1058.
  6. Brooks FP. No Silver Bullet Essence and Accidents of Software Engineering. Computer 1987; 20(4): 10–19.
  7. Fowler M. Refactoring: Improving the Design of Existing Code; Addison-Wesley: Boston, MA, USA, 2018.
  8. Humble J, Farley D. Continuous Delivery; Addison-Wesley: Boston, MA, USA, 2010.
  9. Kim G, Humble J, Debois P, et al. The DevOps Handbook; IT Revolution: Portland, OR, USA, 2016.
  10. Jimenez CE, Yang J, Wettig A, et al.SWE-bench: Can Language Models Resolve Real-World GitHub Issues? In Proceedings of the 12th International Conference on Learning Representations (ICLR 2024), Vienna, Austria, 7–11 May 2024.
  11. Rockafellar RT, Uryasev S. Optimization of Conditional ValueAtRisk. Journal of Risk 2000; 2: 21–41.
  12. Ben-Tal A, El Ghaoui L, Nemirovski A. Robust Optimization; Princeton University Press: Princeton, NJ, USA, 2009.
  13. Mockus A, Fielding RT, Herbsleb JD. Two Case Studies of Open Source Software Development. ACM Transactions on Software Engineering and Methodology 2002; 11(3): 309–346.
  14. Nagappan N, Ball T, Zeller A. Mining Metrics to Predict Component Failures. In Proceedings of the 28th International Conference on Software Engineering, Shanghai, China, 20–28 May 2006.
  15. Zimmermann T, Nagappan N, Gall H, et al.Cross-Project Defect Prediction: A Large Scale Experiment on Data vs. Domain vs. Process. In Proceedings of the 7th Joint Meeting of the European Software Engineering Conference and the ACM SIGSOFT Symposium on The Foundations of Software Engineering, Amsterdam, The Netherlands, 24–28 August 2009.
  16. Menzies T, Greenwald J, Frank A. Data Mining Static Code Attributes to Learn Defect Predictors. IEEE Transactions on Software Engineering 2007; 33(1): 2–13.
  17. Hindle A, Barr ET, Su Z, et al. On the Naturalness of Software. In Proceedings of the 34th International Conference on Software Engineering (ICSE), Zurich, Switzerland, 2–9 June 2012.
  18. Allamanis M, Barr ET, Devanbu P, et al. A Survey of Machine Learning for Big Code and Naturalness. ACM Computing Surveys 2018; 51(4): 1–37.
  19. Ray B, Hellendoorn V, Godhane S, et al. On the “Naturalness” of Buggy Code. In Proceedings of the 38th International Conference on Software Engineering, Austin, TX, USA, 14–22 May 2016.
  20. Le Goues C, Pradel M, Roychoudhury A. Automated Program Repair. Communications of the ACM 2019; 62(12): 56–65.
  21. Goues CL, Nguyen T, Forrest S, et al. GenProg: A Generic Method for Automatic Software Repair. IEEE Transactions on Software Engineering 2012; 38(1): 54–72.
  22. Gazzola L, Micucci D, Mariani L. Automatic Software Repair: A Survey. IEEE Transactions on Software Engineering 2019; 45(1): 34–67.
  23. Bacchelli A, Bird C. Expectations, Outcomes, and Challenges of Modern Code Review. In Proceedings of the 35th International Conference on Software Engineering (ICSE), San Francisco, CA, USA, 18–26 May 2013.
  24. Rigby PC, Bird C. Convergent Contemporary Software Peer Review Practices. In Proceedings of the 2013 9th Joint Meeting on Foundations of Software Engineering, Saint Petersburg, Russia, 18–26 August 2013.
  25. McIntosh S, Kamei Y, Adams B, et al. An Empirical Study of the Impact of Modern Code Review Practices on Software Quality. Empirical Software Engineering 2016; 21: 2146–2189.
  26. Laukkanen E, Itkonen J, Lassenius C. Problems, Causes and Solutions When Adopting Continuous Delivery: A Systematic Literature Review. Information and Software Technology 2017; 82: 55–79.
  27. Vasilescu B, Yu Y, Wang H, et al. Quality and Productivity Outcomes Relating to Continuous Integration in GitHub. In Proceedings of the 2015 10th Joint Meeting on Foundations of Software Engineering, Bergamo, Italy, 30 August–4 September 2015.
  28. Hilton M, Tunnell T, Huang K, et al. Usage, Costs, and Benefits of Continuous Integration in Open-Source Projects. In Proceedings of the 31st IEEE/ACM International Conference on Automated Software Engineering, Singapore, 3–7 September 2016.
  29. Zeller A. Why Programs Fail: A Guide to Systematic Debugging; Morgan Kaufmann: Burlington, MA, USA, 2009.
  30. Jones JA, Harrold MJ. Empirical Evaluation of the Tarantula Automatic FaultLocalization Technique. In Proceedings of the 20th IEEE/ACM International Conference on Automated Software Engineering, Long Beach CA USA, 7–11 November 2005.
  31. Abadi M, Agarwal A, Barham P, et al. TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems. arXiv 2016. https://doi.org/10.48550/arXiv.1603.04467.
  32. Dean J, Ghemawat S. MapReduce: Simplified Data Processing on Large Clusters. In Proceedings of the 6th Conference on Symposium on Operating Systems Design & Implementation (OSDI), San Francisco, CA, USA, 6–8 December 2004.
  33. Hunt P, Konar M, Junqueira FP, et al. {ZooKeeper}: Wait-Free Coordination for InternetScale Systems. In Proceedings of the 2010 USENIX Annual Technical Conference (USENIX ATC 2010), Boston, MA, USA 23–25 June 2010.
  34. Bailis P, Ghodsi A. Eventual Consistency Today: Limitations, Extensions, and Beyond. Communications of the ACM 2013; 56(5): 55–63.
  35. Lamport L. Time, Clocks, and the Ordering of Events in a Distributed System. Communications of the ACM 1978; 21(7): 558–565.
  36. Li J. Nitrogen Removal Models for Stormwater Bioretention Systems. Ph.D. Thesis, University of Virginia, Charlottesville, VA, USA, 2023.
  37. Li J, Culver TB. Review of Process-Based Nitrogen Model for Agricultural Fields with Implications for Nitrogen Simulations in Stormwater BMPs. Environmental Modelling & Software 2022; 151: 105363.
  38. Li J, Culver TB, Burgis CR, et al. Validating Nitrogen Removal Models with Field Bioretention Data. Journal of Environmental Engineering 2024; 150(8): 04024037.
  39. Li J, Culver TB, Persaud PP, et al. Developing Nitrogen Removal Models for Stormwater Bioretention Systems. Water Research 2023; 243: 120381.
  40. Deng X, Kawano Y. Surface Plasmon Polariton Graphene Midinfrared Photodetector with Multifrequency Resonance. Journal of Nanophotonics 2018; 12(2): 026017.
  41. Deng X, Simanullang M, Kawano Y. Ge-Core/A-Si-Shell Nanowire-Based Field-Effect Transistor for Sensitive Terahertz Detection. Photonics 2018; 5(2): 13.
  42. Deng X, Oda S, Kawano Y. Graphene-Based Midinfrared Photodetector with Bull’s Eye Plasmonic Antenna. Optical Engineering 2023; 62(9): 097102.
  43. Deng X, Li L, Enomoto M, et al. Continuously Frequency-Tuneable Plasmonic Structures for Terahertz Bio-Sensing and Spectroscopy. Scientific Reports 2019; 9(1): 3498.
  44. Luo Z, Yan H, Pan X. Optimizing Transformer Models for Resource-Constrained Environments: A Study on Model Compression Techniques. Journal of Computational Methods in Engineering Applications 2023; 3(1): 1–12. https://doi.org/10.62836/jcmea.v3i1.030107.
  45. Yan H, Shao D. Enhancing Transformer Training Efficiency with Dynamic Dropout. arXiv 2024. https://doi.org/10.48550/arXiv.2411.03236.
  46. Yan H. RealTime 3D Model Reconstruction Through Energy-Efficient Edge Computing. Optimizations in Applied Machine Learning 2022; 2(1).
  47. Zhang Y, Needleman A. On the Identification of PowerLaw Creep Parameters from Conical Indentation. Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences 2021; 477(2252): 20210233.
  48. Zhang Y, Needleman A. Characterization of Plastically Compressible Solids Via Spherical Indentation. Journal of the Mechanics and Physics of Solids 2021; 148: 104283.
  49. Dai Y, Wei L, Yu C, et al. Graph Neural Network-Based Drug-Target Interaction Prediction for Precision Medicine. Optimizations in Applied Machine Learning 2025; 5(1). https://doi.org/10.71070/oaml.v5i1.145.
  50. Dai Y. Medical Biopharmaceutical Image Anomaly Detection under Retinex State Space Duality and Frequency Consensus-Driven Transformer. Journal of Computational Methods in Engineering Applications 2026; 6(1): 0001.
  51. Dai Y. Deep Learning-Based Medical Image Segmentation for Early Cancer Detection. Optimizations in Applied Machine Learning 2025; 5(1). https://doi.org/10.71070/oaml.v5i1.144.
  52. Dai Y. MobileMamba-HC: Medical Image Disease Detection in Healthcare Integrating Frequency Adaptive Dilated Convolution and SpatialChannel Synergistic Attention. Innovations in Applied Engineering and Technology 2026; 5(1): 0002.
  53. Yan H, Shao D. Multimodal Medical Image Analysis: Integrating LLM and RAG Deep Learning Strategies. Journal of Advances in Information Technology 2025; 16(4): 568–581. https://doi.org/10.12720/jait.16.4.568-581.
  54. Lu Y, Shao D, Ni X, et al. Emotion-Style Dual Prediction: A MultiTask Deep Learning Approach for Artistic Images. Cluster Computing 2026; 29(1): 31.
  55. Shapley LS. A Value for NPerson Games. In Contributions to the Theory of Games II; Princeton University Press: Princeton, NJ, USA, 1953.

Supporting Agencies

  1. Funding: This research received no external funding.