Meta-Manager: A Tool for Collecting and Exploring Meta Information about Code
Amber Horvath, Andrew Macvean, Brad A. Myers
摘要
Modern software engineering is in a state of flux. With more development utilizing AI code generation tools and the continued reliance on online programming resources, understanding code and the original intent behind it is becoming more important than it ever has been. To this end, we have developed the “Meta-Manager”, a Visual Studio Code extension, with a supplementary browser extension, that automatically collects and organizes changes made to code while keeping track of the provenance of each part of the code, including code that has been AI-generated or copy-pasted from popular programming resources online. These sources and subsequent changes are represented in the editor and may be explored using searching and filtering mechanisms to help developers answer historically hard-to-answer questions about code, its provenance, and its design rationale. In our evaluation of Meta-Manager, we found developers were successfully able to use it to answer otherwise unanswerable questions about an unfamiliar code base.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了最后一个公式,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
- How CO2STLY Is CHI? The Carbon Footprint of Generative AI in HCI Research and What We Should Do About ItNanna Inie, Jeanette Falk, Raghavendra SelvanCHI 2025 · 被引用 33 次
- Assistance or Disruption? Exploring and Evaluating the Design and Trade-offs of Proactive AI Programming SupportKevin Pu, Daniel Lazaro, Ian Arawjo, Haijun Xia 等CHI 2025 · 被引用 31 次
- From Junior to Senior: Allocating Agency and Navigating Professional Growth in Agentic AI-Mediated Software EngineeringDana Feng, Bhada Yun, April Yi WangCHI 2026 · 被引用 2 次
- CodeStream: Augmenting Timelines with Code Annotation for Navigating Large Coding HistoriesAshley Ge Zhang, Yan-Ru Jhou, Yinuo Yang, Shamita Rao 等CHI 2026 · 被引用 1 次
- PointAloud: An Interaction Suite for AI-Supported Pointer-Centric Think-Aloud ComputingFrederic Gmeiner, John Thompson, George W. Fitzmaurice, Justin MatejkaCHI 2026 · 被引用 1 次
它引用的顶会 Paper11
- Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code GenerationJiawei Liu, Chunqiu Steven Xia, Yuyao Wang, Lingming ZhangNeurIPS 2023 · 被引用 2,317 次
- A Large-Scale Survey on the Usability of AI Programming Assistants: Successes and ChallengesJenny T. Liang, Chenyang Yang, Brad A. MyersICSE 2024 · 被引用 126 次
- Callisto: Capturing the "Why" by Connecting Conversations with Computational NarrativesApril Yi Wang, Zihan Wu, Christopher Brooks, Steve OneyCHI 2020 · 被引用 44 次
- A Case Study of Onboarding in Software Teams: Tasks and StrategiesAn Ju, Hitesh Sajnani, Scot Kelly, Kim HerzigICSE 2021 · 被引用 39 次
- Understanding How Programmers Can Use Annotations on DocumentationAmber Horvath, Michael Xieyang Liu, River Hendriksen, Connor Shannon 等CHI 2022 · 被引用 26 次
相关 Paper
- reCode : A Lightweight Find-and-Replace Interaction in the IDE for Transforming Code by ExampleWode Ni, Joshua Sunshine, Vu Le, Sumit Gulwani 等UIST 2021 · 被引用 15 次
- RepoGraph: Enhancing AI Software Engineering with Repository-level Code GraphSiru Ouyang, Wenhao Yu, Kaixin Ma, Zilin Xiao 等ICLR 2025
- 10 Years Later: Revisiting How Developers Search for CodeKathryn T. Stolee, Tobias Welp, Caitlin Sadowski, Sebastian G. ElbaumFSE 2025 · 被引用 3 次
- Unified Software Engineering Agent as AI Software EngineerLeonhard Applis, Yuntong Zhang, Shanchao Liang, Nan Jiang 等ICSE 2026
- Answering Developer Questions with Annotated Agent-Discovered Program TracesLitao Yan, Jeffrey Tao, Lydia B. Chilton, Andrew HeadUIST 2025 · 被引用 2 次
