{
  "added_at": "2026-10-20",
  "arxiv_id": "2608.07038",
  "arxiv_version_reviewed": "v1",
  "authors": [
    "Xiuwei Shang",
    "Li Hu",
    "Xiao Jiang",
    "Jieke Shi",
    "Junda He",
    "Zhou Yang",
    "Shaoyin Cheng",
    "Guoqiang Chen",
    "Weiming Zhang",
    "David Lo"
  ],
  "bibtex_url": "https://awesomerea.org/papers/citations/paper-binjudge.bib",
  "citation": {
    "container_title": "Proceedings of the 41st IEEE/ACM International Conference on Automated Software Engineering",
    "pages": "106-118",
    "publisher": "ACM",
    "sources": [
      "https://api.crossref.org/works/10.1145/3832783.3834339"
    ]
  },
  "code_url": null,
  "date_basis": "Publisher-deposited print publication date; online and arXiv dates are recorded separately.",
  "date_basis_zh": "采用出版方提交的印刷出版日期；在线及 arXiv 日期另行说明。",
  "date_precision": "day",
  "description_en": "BinJudgeBench collects expert judgments for function naming, binary-code summaries and decompilation refinement. BinJudge learns to select a judge configuration for each input and task, evaluating agreement with human scores rather than executable correctness.",
  "description_zh": "BinJudgeBench 收集函数命名、二进制代码摘要及反编译改进的专家评分。BinJudge 学习为每个输入及任务选择评审配置，评估与人工评分的一致性，而非可执行正确性。",
  "doi": "10.1145/3832783.3834339",
  "entry_url": "https://awesomerea.org/papers/paper-binjudge/",
  "entry_url_zh": "https://awesomerea.org/zh/papers/paper-binjudge/",
  "evidence_urls": [
    "https://arxiv.org/abs/2608.07038v1",
    "https://arxiv.org/html/2608.07038v1",
    "https://api.crossref.org/works/10.1145/3832783.3834339",
    "https://zenodo.org/api/records/19247812",
    "https://zenodo.org/records/19310393"
  ],
  "first_arxiv_date": "2026-08-07",
  "id": "paper-binjudge",
  "json_url": "https://awesomerea.org/papers/paper-binjudge/record.json",
  "kind": "research",
  "markdown_url": "https://awesomerea.org/papers/paper-binjudge/index.md",
  "markdown_url_zh": "https://awesomerea.org/zh/papers/paper-binjudge/index.md",
  "metadata_notes": "The arXiv abstract still says accepted, while ACM’s Crossref deposit records ASE 2026 publication on 2026-10-07. Direct ACM access returned HTTP 403. The paper-linked Zenodo concept 19247812 resolves to version 19310393, titled Artifact for BinJudge, with anonymous creator metadata and CC BY 4.0.",
  "metadata_notes_zh": "arXiv 摘要页仍写已录用，ACM 的 Crossref 元数据则记录 ASE 2026 于 2026-10-07 出版。ACM 直接访问返回 HTTP 403。论文链接的 Zenodo 概念记录 19247812 解析到版本 19310393，标题为 Artifact for BinJudge，创建者元数据匿名，声明 CC BY 4.0。",
  "pdf_url": "https://arxiv.org/pdf/2608.07038v1",
  "project_url": "https://zenodo.org/records/19310393",
  "publication_date": "2026-10-07",
  "publication_status": "conference-paper",
  "record_type": "paper",
  "runtime_tested": false,
  "scope_limitations_en": "The router uses five-fold validation on 1,233 annotated outputs. Initial annotators are three authors, with an independent industrial expert checking a subset. Human scores are subjective, and fluent unsupported answers can mislead judges. Correlation on these tasks neither proves program equivalence nor establishes that judges can replace human review.",
  "scope_limitations_zh": "路由器在 1,233 个已标注输出上进行五折验证。初始标注者是三位作者，另有独立产业专家复核子集。人工评分具有主观性，流畅但无依据的回答也可能误导评审。任务上的相关性既不证明程序等价，也不能据此认定评审模型可替代人工复核。",
  "targets": [
    "binary"
  ],
  "title": "Beyond Text Matching: Towards Reference-Free Evaluation for Human-Oriented Binary Reverse Engineering",
  "title_zh": "超越文本匹配：面向人的二进制逆向工程的无参考评估",
  "url": "https://dl.acm.org/doi/10.1145/3832783.3834339",
  "venue": "ASE 2026",
  "verification": "source-reviewed",
  "verified_at": "2026-10-20",
  "why_fits_en": "Provides evidence-oriented evaluation resources for interpreting names, summaries and refined pseudocode.",
  "why_fits_zh": "补充解释恢复名称、代码摘要及改进后伪代码时所需的评估证据。",
  "year": 2026
}