In the current landscape of pervasive smartphones and tablets, apps
frequently exist across both platforms. Although apps share most graphic user
interfaces (GUIs) and functionalities across phones and tablets, developers
often rebuild from scratch for tablet versions, escalating costs and
squandering existing design resources. Researchers are attempting to collect
data and employ deep learning in automated GUIs development to enhance
developers' productivity. There are currently several publicly accessible GUI
page datasets for phones, but none for pairwise GUIs between phones and
tablets. This poses a significant barrier to the employment of deep learning in
automated GUI development. In this paper, we introduce the Papt dataset, a
pioneering pairwise GUI dataset tailored for Android phones and tablets,
encompassing 10,035 phone-tablet GUI page pairs sourced from 5,593 unique app
pairs. We propose novel pairwise GUI collection approaches for constructing
this dataset and delineate its advantages over currently prevailing datasets in
the field. Through preliminary experiments on this dataset, we analyze the
present challenges of utilizing deep learning in automated GUI development.

在当前普及的智能手机和平板电脑的背景下，应用程序经常存在于两种平台上。尽管应用程序在手机和平板电脑上共享大部分图形用户界面（GUI）和功能，但开发人员通常需要从头开始重建平板电脑版本，导致成本升高，并浪费现有的设计资源。研究人员正在尝试收集数据并使用深度学习在自动 GUI 开发中提高开发人员的生产力。目前，有一些公开可访问的 GUI 页面数据集用于手机，但没有关于手机和平板电脑之间的配对 GUI 的数据集。这对于在自动 GUI 开发中采用深度学习构成了重大障碍。在本文中，我们介绍了 Papt 数据集，一个专门为 Android 手机和平板电脑定制的先驱性配对 GUI 数据集，包括来自 5593 个唯一应用程序对的 10035 个手机 - 平板电脑 GUI 页面对。我们提出了新颖的配对 GUI 收集方法以构建此数据集，并详细说明了它相对于当前流行数据集的优势。通过对此数据集的初步实验，我们分析了在自动 GUI 开发中利用深度学习所面临的挑战。

Android 手机和平板电脑间的双向 GUI 数据集构建

Pairwise GUI Dataset Construction Between Android Phones and Tablets

Large Language Models (LLMs) have shown remarkable aptitude in code
generation but still struggle on challenging programming tasks. Self-repair --
in which the model debugs and fixes mistakes in its own code -- has recently
become a popular way to boost performance in these settings. However, only very
limited studies on how and when self-repair works effectively exist in the
literature, and one might wonder to what extent a model is really capable of
providing accurate feedback on why the code is wrong when that code was
generated by the same model. In this paper, we analyze GPT-3.5 and GPT-4's
ability to perform self-repair on APPS, a challenging dataset consisting of
diverse coding challenges. To do so, we first establish a new evaluation
strategy dubbed pass@t that measures the pass rate of the tasks against the
total number of tokens sampled from the model, enabling a fair comparison to
purely sampling-based approaches. With this evaluation strategy, we find that
the effectiveness of self-repair is only seen in GPT-4. We also observe that
self-repair is bottlenecked by the feedback stage; using GPT-4 to give feedback
on the programs generated by GPT-3.5 and using expert human programmers to give
feedback on the programs generated by GPT-4, we unlock significant performance
gains.

本文分析了 GPT-3.5 和 GPT-4 在 APPs 数据集上自我修复的能力，发现只在 GPT-4 上看到了自我修复的有效性，并且发现自我修复被反馈阶段所限制。