On Automated and Explainable Provenance of AI-Generated Code

• URL: http://arxiv.org/abs/2608.02329v1
• Date: Mon, 03 Aug 2026 14:50:31 GMT
• Title: On Automated and Explainable Provenance of AI-Generated Code
• Abstract summary: We argue that the next generation of CodeGenAI tools must be built on a foundation of explainable provenance.<n>We describe a research program combining large-scale empirical studies with post-hoc causal and interpretability techniques.
• Score: 56.818202904805446
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Generative AI for code generation has transformed software development, but it has also introduced a critical transparency problem: the origins of AI-generated code are opaque to the developers who use it, the organizations that deploy it, and the compliance professionals responsible for ensuring its legal and quality standards. Existing mitigations flag problematic outputs after the fact without explaining why a model produced them or how future generation could be improved. We present a research vision, grounded in a U.S. NSF-funded research grant, that argues that the next generation of CodeGenAI tools must be built on a foundation of explainable provenance: automated, post-hoc traceability that links generated code back to the prompt components, training data instances, global data features, and internal model components that caused its generation. We grounded this vision in empirical evidence from studies of software developers, model users, and compliance/legal professionals, which show that provenance information is a practical necessity that current tools do not provide. We characterize the problem across four traceability dimensions, outline a research program combining large-scale empirical studies with post-hoc causal and interpretability techniques, and identify the key open challenges that the community must address to realize this vision.

Related papers

• The Case for Vibe Modeling: A Missing Step in AI-Based Trustworthy Software Development [0.7783262415147654]
  We argue that current AI-based development practices focus too heavily on the direct generation of code.<n>We argue for vibe modeling as a lightweight intermediate abstraction between natural language interaction and code generation.
  arXiv  Detail & Related papers  (2026-07-30T09:37:02Z)
• Bridging the Gap on AI-Assisted Scientific Software Development Through Transparency and Traceability [4.466942018046944]
  Researchers are already using large language models to write code, generate test cases, and draft documentation.<n>This ad hoc, ungoverned use of AI represents a systemic risk to scientific software quality.<n>This paper proposes guidance for AI-assisted code development in the context of strict software quality assurance.
  arXiv  Detail & Related papers  (2026-05-17T22:08:52Z)
• A Survey of Vibe Coding with Large Language Models [93.88284590533242]
  "Vibe Coding" is a development methodology where developers validate AI-generated implementations through outcome observation.<n>Despite its transformative potential, the effectiveness of this emergent paradigm remains under-explored.<n>This survey provides the first comprehensive and systematic review of Vibe Coding with large language models.
  arXiv  Detail & Related papers  (2025-10-14T11:26:56Z)
• The Impact of Generative AI on Code Expertise Models: An Exploratory Study [0.0]
  We present an exploratory analysis of how a knowledge model and a Truck Factor algorithm can be affected by GenAI usage.<n>Our findings suggest that as GenAI becomes more integrated into development, the reliability of such metrics may decrease.
  arXiv  Detail & Related papers  (2025-07-10T20:43:08Z)
• Rethinking Data Protection in the (Generative) Artificial Intelligence Era [138.07763415496288]
  We propose a four-level taxonomy that captures the diverse protection needs arising in modern (generative) AI models and systems.<n>Our framework offers a structured understanding of the trade-offs between data utility and control, spanning the entire AI pipeline.
  arXiv  Detail & Related papers  (2025-07-03T02:45:51Z)
• Computational Safety for Generative AI: A Signal Processing Perspective [65.268245109828]
  computational safety is a mathematical framework that enables the quantitative assessment, formulation, and study of safety challenges in GenAI.<n>We show how sensitivity analysis and loss landscape analysis can be used to detect malicious prompts with jailbreak attempts.<n>We discuss key open research challenges, opportunities, and the essential role of signal processing in computational AI safety.
  arXiv  Detail & Related papers  (2025-02-18T02:26:50Z)
• Bridging LLM-Generated Code and Requirements: Reverse Generation technique and SBC Metric for Developer Insights [0.0]
  This paper introduces a novel scoring mechanism called the SBC score.<n>It is based on a reverse generation technique that leverages the natural language generation capabilities of Large Language Models.<n>Unlike direct code analysis, our approach reconstructs system requirements from AI-generated code and compares them with the original specifications.
  arXiv  Detail & Related papers  (2025-02-11T01:12:11Z)
• The Role of Code Proficiency in the Era of Generative AI [10.524937623398003]
  Generative AI models are becoming integral to the developer workspace. However, challenges emerge due to the 'black box' nature of many of these models. This position paper advocates for a 'white box' approach to these generative models.
  arXiv  Detail & Related papers  (2024-04-08T06:20:42Z)
• On the Challenges and Opportunities in Generative AI [155.030542942979]
  We argue that current large-scale generative AI models exhibit several fundamental shortcomings that hinder their widespread adoption across domains.<n>We aim to provide researchers with insights for exploring fruitful research directions, thus fostering the development of more robust and accessible generative AI solutions.
  arXiv  Detail & Related papers  (2024-02-28T15:19:33Z)
• Data-Driven and SE-assisted AI Model Signal-Awareness Enhancement and Introspection [61.571331422347875]
  We propose a data-driven approach to enhance models' signal-awareness. We combine the SE concept of code complexity with the AI technique of curriculum learning. We achieve up to 4.8x improvement in model signal awareness.
  arXiv  Detail & Related papers  (2021-11-10T17:58:18Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.