Code Shaping: Iterative Code Editing with Free-form AI-Interpreted Sketching
Ryan Yen, Jian Zhao, Daniel Vogel
摘要
We introduce the concept of code shaping, an interaction paradigm for editing code using free-form sketch annotations directly on top of the code and console output. To evaluate this concept, we conducted a three-stage design study with 18 different programmers to investigate how sketches can communicate intended code edits to an AI model for interpretation and execution. The results show how different sketches are used, the strategies programmers employ during iterative interactions with AI interpretations, and interaction design principles that support the reconciliation between the code editor and sketches. Finally, we demonstrate the practical application of the code shaping concept with two use case scenarios, illustrating design implications from the study.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
引用它的顶会 Paper8
- Vistoria: A Multimodal System to Support Fictional Story Writing through Instrumental Image-Text Co-EditingKexue Fu, Jingfei Huang, Long Ling, Sumin Hong 等CHI 2026 · 被引用 3 次
- GeoTikzBridge: Advancing Multimodal Code Generation for Geometric Perception and ReasoningJiayin Sun, Caixia Sun, Boyu Yang, hailin li 等CVPR 2026 · 被引用 3 次
- Cerebra: Aligning Implicit Knowledge in Interactive SQL AuthoringYunfan Zhou, Qiming Shi, Zhongsu Luo, Xiwen Cai 等CHI 2026 · 被引用 2 次
- How Notations Evolve: A Historical Analysis with Implications for Supporting User-Defined AbstractionsJingyue Zhang, J. D. Zamfirescu-Pereira, Elena L. Glassman, Damien Masson 等CHI 2026 · 被引用 2 次
- SketchDynamics: Exploring Free-Form Sketches for Dynamic Intent Expression in Animation GenerationBoyu Li, Lin-Ping Yuan, Zeyu Wang, Hongbo FuCHI 2026 · 被引用 1 次
它引用的顶会 Paper12
- Grounded Copilot: How Programmers Interact with Code-Generating ModelsShraddha Barke, Michael B. James, Nadia PolikarpovaOOPSLA 2023 · 被引用 408 次
- "What It Wants Me To Say": Bridging the Abstraction Gap Between End-User Programmers and Code-Generating Large Language ModelsMichael Xieyang Liu, Advait Sarkar, Carina Negreanu, Benjamin G. Zorn 等CHI 2023 · 被引用 114 次
- RepoCoder: Repository-Level Code Completion Through Iterative Retrieval and GenerationFengji Zhang, Bei Chen, Yue Zhang, Jacky Keung 等EMNLP 2023 · 被引用 110 次
- Reading Between the Lines: Modeling User Behavior and Costs in AI-Assisted ProgrammingHussein Mozannar, Gagan Bansal, Adam Fourney, Eric HorvitzCHI 2024 · 被引用 88 次
- Exploring Technical Reasoning in Digital Tool UseMiguel A. Renom, Baptiste Caramiaux, Michel Beaudouin-LafonCHI 2022 · 被引用 67 次
相关 Paper
- Vibe Coding Entanglements - Repositioning Boundaries of Intention, Authorship, and Responsibility in Programming with Generative AIJakob Tholander, Martin JonssonCHI 2026 · 被引用 3 次
- Notational Animating: An Interactive Approach to Creating and Editing Animation KeyframesXinyu Shi, Li-Yi Wei, Nanxuan Zhao, Jian Zhao 等CHI 2026 · 被引用 1 次
- An Exploratory Study of ML Sketches and Visual Code AssistantsLuís F. Gomes, Vincent J. Hellendoorn, Jonathan Aldrich, Rui AbreuICSE 2025 · 被引用 2 次
- SketchGPT: A Sketch-based Multimodal Interface for Application-Agnostic LLM InteractionZeyuan Huang, Cangjun Gao, Yaxian Shan, Haoxiang Hu 等UIST 2025 · 被引用 8 次
- How Beginning Programmers and Code LLMs (Mis)read Each OtherSydney Nguyen, Hannah McLean Babe, Yangtian Zi, Arjun Guha 等CHI 2024 · 被引用 66 次
