{
  "added_at": "2026-10-17",
  "arxiv_id": "2607.06306",
  "arxiv_version_reviewed": "v2",
  "authors": [
    "Grace Man Chen",
    "Litao Guo",
    "Yifan Wu",
    "Yiyu Chen",
    "Yenchi Tseng",
    "Sicheng Liu",
    "Yuyu Luo",
    "Ying-Cong Chen"
  ],
  "bibtex_url": "https://awesomerea.org/papers/citations/paper-ui2app.bib",
  "code_url": "https://github.com/chenmancm169/UI2App",
  "date_basis": "First arXiv submission date. The reviewed v2 was submitted on 2026-10-04; it is not a separately verified conference publication.",
  "date_basis_zh": "首次提交至 arXiv 的日期。核查的 v2 于 2026-10-04 提交，不视为另行核实的会议出版。",
  "date_precision": "day",
  "description_en": "UI2App evaluates runnable React/TypeScript applications generated from 600 screenshots across 95 web applications. It separates build executability, visual fidelity and screenshot-implied interaction behavior, including cross-route state, using a reference interaction taxonomy and public evaluation pipeline.",
  "description_zh": "UI2App 使用来自 95 个 Web 应用的 600 张截图，评测生成的可运行 React/TypeScript 应用。它通过参考交互分类体系和公开评测流水线，分别衡量构建可执行性、视觉保真度，以及包括跨路由状态在内的截图隐含交互行为。",
  "doi": "10.48550/arXiv.2607.06306",
  "entry_url": "https://awesomerea.org/papers/paper-ui2app/",
  "entry_url_zh": "https://awesomerea.org/zh/papers/paper-ui2app/",
  "evidence_urls": [
    "https://arxiv.org/abs/2607.06306",
    "https://arxiv.org/html/2607.06306v2",
    "https://arxiv.org/pdf/2607.06306v2",
    "https://api.datacite.org/dois/10.48550/arXiv.2607.06306",
    "https://chenmancm169.github.io/UI2App-ProjectPage/",
    "https://github.com/chenmancm169/UI2App/blob/520a59aad0899b1eb61e80351aa1ffbfad9322a4/README.md",
    "https://github.com/chenmancm169/UI2App/blob/520a59aad0899b1eb61e80351aa1ffbfad9322a4/LICENSE",
    "https://github.com/chenmancm169/UI2App/blob/520a59aad0899b1eb61e80351aa1ffbfad9322a4/requirements.txt",
    "https://github.com/chenmancm169/UI2App/blob/520a59aad0899b1eb61e80351aa1ffbfad9322a4/iis/evaluate.py",
    "https://huggingface.co/datasets/UI2App/UI2App/blob/32e6f6193c5c265cf6d8afcbce12b641e3c2a758/README.md",
    "https://huggingface.co/datasets/UI2App/UI2App/blob/32e6f6193c5c265cf6d8afcbce12b641e3c2a758/annotations/rii.jsonl"
  ],
  "first_arxiv_date": "2026-07-07",
  "id": "paper-ui2app",
  "json_url": "https://awesomerea.org/papers/paper-ui2app/record.json",
  "kind": "research",
  "markdown_url": "https://awesomerea.org/papers/paper-ui2app/index.md",
  "markdown_url_zh": "https://awesomerea.org/zh/papers/paper-ui2app/index.md",
  "metadata_notes": "Use v2’s 95 applications and 600 screenshots, not v1’s 45/327 counts. The arXiv DOI is registered. Public code is MIT; the dataset and reference annotations are CC BY 4.0, with upstream code and third-party asset rights separate. The documented pipeline needs Python 3.10+, Node/npm, pnpm, Chromium, Tesseract and model access; Auto IIS additionally needs an authenticated Codex CLI.",
  "metadata_notes_zh": "采用 v2 的 95 个应用与 600 张截图，不混用 v1 的 45/327 数量。arXiv DOI 已注册。公开代码采用 MIT，数据集和参考标注采用 CC BY 4.0；上游代码及第三方资产权利另行处理。文档所述流水线需要 Python 3.10+、Node/npm、pnpm、Chromium、Tesseract 和模型访问权限；Auto IIS 还需要已登录的 Codex CLI。",
  "pdf_url": "https://arxiv.org/pdf/2607.06306v2",
  "project_url": "https://chenmancm169.github.io/UI2App-ProjectPage/",
  "publication_date": "2026-07-07",
  "publication_status": "preprint",
  "record_type": "paper",
  "runtime_tested": false,
  "scope_limitations_en": "Static screenshots underdetermine behavior; the rubric accepts multiple valid implementations rather than proving equivalence to the original application or backend. Auto IIS judges generated source and screenshots without tool execution; human runtime validation covers a 45-application subset. Cross-route state is not necessarily durable persistence across reloads or sessions. Main results use one generation per application-model pair, with repeated runs on a subset.",
  "scope_limitations_zh": "静态截图无法唯一确定行为；评分规则接受多种有效实现，并不证明与原应用或后端等价。Auto IIS 在不执行工具的情况下评判生成源码和截图，人工运行验证覆盖 45 个应用的子集。跨路由状态不一定能在重新加载或会话结束后持久保存。主结果每个应用与模型组合生成一次，重复运行仅覆盖子集。",
  "targets": [
    "website"
  ],
  "title": "UI2App: Benchmarking Visual Interaction Inference in Executable Web Application Generation",
  "title_zh": "UI2App：评测可执行 Web 应用生成中的视觉交互推断",
  "url": "https://arxiv.org/abs/2607.06306",
  "venue": "arXiv",
  "verification": "source-reviewed",
  "verified_at": "2026-10-17",
  "why_fits_en": "Tests reconstruction from observed web interfaces while distinguishing visual copying from inferred interaction logic; its explicit behavior ambiguity makes it a bounded complement to trace-guided reconstruction benchmarks.",
  "why_fits_zh": "评测从已观察 Web 界面进行重建，并区分视觉复制与交互逻辑推断；其明确的行为歧义边界可补充由交互轨迹指导的重建基准。",
  "year": 2026
}