Mitigating "Epistemic Debt" in Generative AI-Scaffolded Novice Programming using Metacognitive Scripts

• URL: http://arxiv.org/abs/2602.20206v1
• Date: Sun, 22 Feb 2026 21:25:04 GMT
• Title: Mitigating "Epistemic Debt" in Generative AI-Scaffolded Novice Programming using Metacognitive Scripts
• Authors: Sreecharan Sankaranarayanan,
• Abstract summary: Unrestricted AI encourages novices to outsource the Intrinsic Cognitive Load required for schema formation.<n>We show that successful vibe coders naturally engage in self-scaffolding, treating the AI as a consultant rather than a contractor.<n>We propose that future learning systems must enforce Metacognitive Friction to prevent the mass production of unmaintainable code.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The democratization of Large Language Models (LLMs) has given rise to ``Vibe Coding," a workflow where novice programmers prioritize semantic intent over syntactic implementation. While this lowers barriers to entry, we hypothesize that without pedagogical guardrails, it is fundamentally misaligned with cognitive skill acquisition. Drawing on the distinction between Cognitive Offloading and Cognitive Outsourcing, we argue that unrestricted AI encourages novices to outsource the Intrinsic Cognitive Load required for schema formation, rather than merely offloading Extraneous Load. This accumulation of ``Epistemic Debt" creates ``Fragile Experts" whose high functional utility masks critically low corrective competence. To quantify and mitigate this debt, we conducted a between-subjects experiment (N=78) using a custom Cursor IDE plugin backed by Claude 3.5 Sonnet. Participants represented "AI-Native" learners across three conditions: Manual (Control), Unrestricted AI (Outsourcing), and Scaffolded AI (Offloading). The Scaffolded condition utilized a novel ``Explanation Gate," leveraging a real-time LLM-as-a-Judge framework to enforce a ``Teach-Back" protocol before generated code could be integrated. Results reveal a ``Collapse of Competence": while Unrestricted AI users matched the productivity of the Scaffolded group (p < .001 vs. Manual), they suffered a 77% failure rate in a subsequent AI-Blackout maintenance task, compared to only 39% in the Scaffolded group. Qualitative analysis suggests that successful vibe coders naturally engage in self-scaffolding, treating the AI as a consultant rather than a contractor. We discuss the implications for the maintainability of AI-generated software and propose that future learning systems must enforce Metacognitive Friction to prevent the mass production of unmaintainable code.

Related papers

• XMENTOR: A Rank-Aware Aggregation Approach for Human-Centered Explainable AI in Just-in-Time Software Defect Prediction [5.646457568088472]
  We introduce XMENTOR, a human-centered, rank-aware aggregation method implemented as a VS Code plugin.<n>XMENTOR unifies multiple post-hoc explanations into a single, coherent view by applying adaptive thresholding, rank and sign agreement.<n>Our findings show how combining explanations and embedding them into developer can enhance interpretability, usability, and trust.
  arXiv  Detail & Related papers  (2026-02-25T20:54:49Z)
• Capability-Oriented Training Induced Alignment Risk [101.37328448441208]
  We investigate whether language models, when trained with reinforcement learning, will spontaneously learn to exploit flaws to maximize their reward.<n>Our experiments show that models consistently learn to exploit these vulnerabilities, discovering opportunistic strategies that significantly increase their reward at the expense of task correctness or safety.<n>Our findings suggest that future AI safety work must extend beyond content moderation to rigorously auditing and securing the training environments and reward mechanisms themselves.
  arXiv  Detail & Related papers  (2026-02-12T16:13:14Z)
• On the Paradoxical Interference between Instruction-Following and Task Solving [50.75960598434753]
  Instruction following aims to align Large Language Models (LLMs) with human intent by specifying explicit constraints on how tasks should be performed.<n>We reveal a counterintuitive phenomenon: instruction following can paradoxically interfere with LLMs' task-solving capability.<n>We propose a metric, SUSTAINSCORE, to quantify the interference of instruction following with task solving.
  arXiv  Detail & Related papers  (2026-01-29T17:48:56Z)
• How AI Impacts Skill Formation [12.295096074858932]
  We study how developers gained mastery of a new asynchronous programming library with and without the assistance of AI.<n>We find that AI use impairs conceptual understanding, code reading, and debug abilities, without delivering significant efficiency gains on average.<n>We identify six distinct AI interaction patterns, three of which involve cognitive engagement and preserve learning outcomes even when participants receive AI assistance.
  arXiv  Detail & Related papers  (2026-01-28T04:40:43Z)
• The Vibe-Check Protocol: Quantifying Cognitive Offloading in AI Programming [5.584060970507507]
  Vibe Coding'' is a paradigm where developers articulate high-level intent through natural language and delegate implementation to AI agents.<n>This paper proposes a theoretical framework to investigate the research question: textitIs Vibe Coding a better way to learn software engineering?
  arXiv  Detail & Related papers  (2026-01-02T06:13:41Z)
• Hindsight Distillation Reasoning with Knowledge Encouragement Preference for Knowledge-based Visual Question Answering [55.368681418311894]
  Existing Knowledge-based Visual Question Answering (KBVQA) methods either utilize implicit knowledge in multimodal large language models (MLLMs) via in-context learning or explicit knowledge via retrieval augmented generation.<n>We provide a Hindsight Distilled Reasoning (HinD) framework with Knowledge Encouragement Preference Optimization (KEPO)<n> Experiments on OK-VQA and A-OKVQA validate the effectiveness of HinD, showing that HinD with elicited reasoning from 7B-size MLLM achieves superior performance without commercial model APIs or outside knowledge.
  arXiv  Detail & Related papers  (2025-11-14T10:03:23Z)
• Beyond Technical Debt: How AI-Assisted Development Creates Comprehension Debt in Resource-Constrained Indie Teams [29.850754213301368]
  This study introduces the CIGDI (Co-Intelligence Game Development Ideation) Framework.<n>The framework emerged from a three-month reflective practice and autoethnographic study of a three-person distributed team developing the 2D narrative game "The Worm's Memoirs"<n>While AI support democratized knowledge access and reduced cognitive load, our analysis identified a significant challenge: "comprehension debt"
  arXiv  Detail & Related papers  (2025-10-30T12:41:26Z)
• BLUR: A Bi-Level Optimization Approach for LLM Unlearning [100.90394814817965]
  We argue that it is important to model the hierarchical structure of the unlearning problem.<n>We propose a novel algorithm, termed Bi-Level UnleaRning (textttBLUR), which delivers superior performance.
  arXiv  Detail & Related papers  (2025-06-09T19:23:05Z)
• Humble AI in the real-world: the case of algorithmic hiring [9.53469974854897]
  Humble AI argues for cautiousness in AI development and deployments through scepticism.<n>We present a real-world case study for humble AI in the domain of algorithmic hiring.
  arXiv  Detail & Related papers  (2025-05-27T09:09:38Z)
• Tuning-Free Accountable Intervention for LLM Deployment -- A Metacognitive Approach [55.613461060997004]
  Large Language Models (LLMs) have catalyzed transformative advances across a spectrum of natural language processing tasks. We propose an innovative textitmetacognitive approach, dubbed textbfCLEAR, to equip LLMs with capabilities for self-aware error identification and correction.
  arXiv  Detail & Related papers  (2024-03-08T19:18:53Z)
• Learning to Prompt in the Classroom to Understand AI Limits: A pilot study [35.06607166918901]
  Large Language Models (LLM) and the derived chatbots, like ChatGPT, have highly improved the natural language processing capabilities of AI systems. However, excitement has led to negative sentiments, even as AI methods demonstrate remarkable contributions. A pilot educational intervention was performed in a high school with 21 students.
  arXiv  Detail & Related papers  (2023-07-04T07:51:37Z)
• Generation Probabilities Are Not Enough: Uncertainty Highlighting in AI Code Completions [54.55334589363247]
  We study whether conveying information about uncertainty enables programmers to more quickly and accurately produce code. We find that highlighting tokens with the highest predicted likelihood of being edited leads to faster task completion and more targeted edits.
  arXiv  Detail & Related papers  (2023-02-14T18:43:34Z)

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.