{
  "added_at": "2026-10-20",
  "arxiv_id": "2610.11556",
  "arxiv_version_reviewed": "v1",
  "authors": [
    "Varun Kohli",
    "Lee Bing Cheng",
    "Nur Hazim Ghazali",
    "Gao Yuze",
    "Daryl Poon",
    "Dinil Mon Divakaran"
  ],
  "bibtex_url": "https://awesomerea.org/papers/citations/paper-sok-source-recovery-reliability.bib",
  "code_url": "https://anonymous.4open.science/r/decompbench-65CB/",
  "date_basis": "First arXiv submission date; no separate proceedings or journal publication was verified.",
  "date_basis_zh": "采用 arXiv 首次提交日期；未核实另行出版的会议论文集或期刊版本。",
  "date_precision": "day",
  "description_en": "This SoK organizes LLM-assisted source-recovery designs and separates compilation, readability, structural and behavioral metrics. Its controlled study varies architecture, compiler optimization and symbol availability, with smaller ablations for input representation, model roles and source language.",
  "description_zh": "该 SoK 组织 LLM 辅助源码恢复方案，并区分编译、可读性、结构与行为指标。受控研究改变架构、编译优化及符号状态，并以较小的消融实验考察输入表示、模型角色和源语言。",
  "doi": null,
  "entry_url": "https://awesomerea.org/papers/paper-sok-source-recovery-reliability/",
  "entry_url_zh": "https://awesomerea.org/zh/papers/paper-sok-source-recovery-reliability/",
  "evidence_urls": [
    "https://arxiv.org/abs/2610.11556v1",
    "https://arxiv.org/html/2610.11556v1",
    "https://anonymous.4open.science/r/decompbench-65CB/README.md",
    "https://anonymous.4open.science/api/repo/decompbench-65CB/file/README.md?v=3a7167f7"
  ],
  "first_arxiv_date": "2026-10-08",
  "id": "paper-sok-source-recovery-reliability",
  "json_url": "https://awesomerea.org/papers/paper-sok-source-recovery-reliability/record.json",
  "kind": "research",
  "markdown_url": "https://awesomerea.org/papers/paper-sok-source-recovery-reliability/index.md",
  "markdown_url_zh": "https://awesomerea.org/zh/papers/paper-sok-source-recovery-reliability/index.md",
  "metadata_notes": "The arXiv v1 article is CC BY 4.0. Its anonymous artifact was readable in a browser; the page shows an October 1 snapshot available until 2027-03-29, without a full Git commit. The inspected README says a fresh database cannot directly re-score shipped generation files; redrawing supplied CSV results is a separate step. Artifact licensing was not established from the inspected README/root list.",
  "metadata_notes_zh": "arXiv v1 文章采用 CC BY 4.0。匿名产物可在浏览器中读取，页面显示 10 月 1 日快照、开放至 2027-03-29，但未暴露完整 Git 提交。已读 README 说明新数据库无法直接对所附生成文件重新评分，重画已有 CSV 结果属于另一层步骤。所查 README 及根目录未确立产物许可。",
  "pdf_url": "https://arxiv.org/pdf/2610.11556v1",
  "project_url": null,
  "publication_date": "2026-10-08",
  "publication_status": "preprint",
  "record_type": "paper",
  "runtime_tested": false,
  "scope_limitations_en": "The 45,000 cases are variants of 500 functions, not independent programs. Input/language ablations use 50 functions; translated language variants were produced with an LLM and checked using finite I/O tests. The study assumes a derivable call interface, is prompt-sensitive and cannot exclude ExeBench pretraining exposure. Test agreement and relocation-masked byte matching have different assumptions.",
  "scope_limitations_zh": "45,000 个案例是 500 个函数的变体，并非独立程序。输入／语言消融使用 50 个函数，跨语言变体由 LLM 翻译后以有限 I/O 测试检查。研究假设调用接口可推导，结果受提示影响，也无法排除 ExeBench 进入预训练。测试一致性与屏蔽重定位位置的字节匹配具有不同假设。",
  "targets": [
    "binary"
  ],
  "title": "SoK: Are LLMs Reliable at Source Code Recovery? A Taxonomy and Empirical Evaluation",
  "title_zh": "SoK：LLM 恢复源码是否可靠？分类体系与实证评估",
  "url": "https://arxiv.org/abs/2610.11556",
  "venue": "arXiv",
  "verification": "source-reviewed",
  "verified_at": "2026-10-20",
  "why_fits_en": "Adds a recent evaluation taxonomy and controlled evidence for comparing source-recovery methods without collapsing distinct correctness signals.",
  "why_fits_zh": "补充近期评估分类与受控证据，用于比较源码恢复方法，并避免混同不同正确性信号。",
  "year": 2026
}