{
  "schema_version": 1,
  "id": "evt-2024-lean-workbook",
  "slug": "lean-workbook-synthetic-formalization-dataset",
  "title": {
    "en": "Lean Workbook releases a large formal-informal mathematics dataset",
    "zh-CN": "Lean Workbook 发布大规模形式—非形式数学数据集"
  },
  "dates": {
    "event": "2024-06-06",
    "first_public_claim": "2024-06-06",
    "paper_release": "2024-06-06",
    "artifact_release": null,
    "independently_verified": null,
    "added_to_chronicle": "2026-09-10",
    "last_updated": "2026-09-11"
  },
  "event_types": [
    "dataset",
    "formalization",
    "infrastructure"
  ],
  "significance": {
    "tier": "H2",
    "rationale": {
      "en": "Lean Workbook expanded the supply of paired natural-language and Lean problems for training autoformalizers and provers.",
      "zh-CN": "Lean Workbook 扩大了自然语言数学与 Lean 形式问题配对数据的规模，为自动形式化和证明训练提供资源。"
    }
  },
  "mathematical_novelty": {
    "type": "tooling_only"
  },
  "interfaces": [
    "informal",
    "formal",
    "hybrid"
  ],
  "claim": {
    "en": "Lean Workbook released about 57,000 formal-informal question pairs together with searched proofs and 21 new IMO questions.",
    "zh-CN": "Lean Workbook 发布约 57,000 个形式—非形式问题对、搜索得到的证明以及 21 道新的 IMO 题目。"
  },
  "summary": {
    "en": "An iterative generation-and-filtering pipeline translates natural-language math problems to Lean 4 statements and back.",
    "zh-CN": "迭代式生成与过滤管线把自然语言数学问题翻译为 Lean 4 陈述，并进行反向转换。"
  },
  "why_it_matters": {
    "en": "The dataset lowered a key bottleneck for training larger Lean provers: the scarcity of aligned formal and informal mathematics.",
    "zh-CN": "该数据集缓解了训练大型 Lean 证明器的关键瓶颈——形式与非形式数学对齐数据稀缺。"
  },
  "ai_role": {
    "level": "ai_substantive_support",
    "description": {
      "en": "Models participate in synthetic translation and proof search used to construct the dataset.",
      "zh-CN": "模型参与用于构建数据集的合成翻译与证明搜索。"
    }
  },
  "human_contribution": {
    "description": {
      "en": "Researchers designed the iterative data pipeline, filtering criteria and release.",
      "zh-CN": "研究者设计迭代数据管线、过滤标准与公开发布。"
    }
  },
  "systems": [
    "lean-workbook",
    "lean"
  ],
  "organizations": [
    "shanghai-ai-laboratory"
  ],
  "people": [],
  "problems": [
    "formalization-data"
  ],
  "methods": [
    "synthetic-data",
    "autoformalization",
    "proof-search"
  ],
  "verification": {
    "evidence_level": "E3",
    "status": "paper_released",
    "formal_assurance": "artifact_available",
    "history": [
      {
        "date": "2024-06-06",
        "status": "paper_released",
        "evidence_level": "E2",
        "note": {
          "en": "The Chronicle records this event from the cited primary or official source; the status does not imply independent Chronicle verification.",
          "zh-CN": "Chronicle 依据所引 primary / official source 记录该事件；该状态不表示 Chronicle 已完成独立验证。"
        }
      },
      {
        "date": "2026-09-11",
        "status": "paper_released",
        "evidence_level": "E3",
        "note": {
          "en": "This corpus refresh added a directly inspectable public artifact maintained by the authors or releasing organization. E3 records artifact-level inspectability and does not imply independent verification of the underlying scientific or mathematical claim.",
          "zh-CN": "本轮 corpus 刷新增补了由作者或发布机构维护、可直接检查的公开产物。E3 表示证据已达到可检查 artifact 层级，并不等同于底层科学或数学主张已获得独立验证。"
        }
      }
    ]
  },
  "sources": [
    {
      "id": "arxiv-lean-workbook-2406.03847",
      "tier": "S1",
      "type": "paper",
      "title": "Lean Workbook: A large-scale Lean problem set formalized from natural language math problems",
      "url": "https://arxiv.org/abs/2406.03847",
      "primary": true,
      "published_date": "2024-06-06",
      "accessed_at": "2026-09-10"
    },
    {
      "id": "huggingface-lean-workbook",
      "tier": "S1",
      "type": "dataset",
      "title": "Lean Workbook dataset release",
      "url": "https://huggingface.co/datasets/internlm/Lean-Workbook",
      "primary": true,
      "published_date": null,
      "accessed_at": "2026-09-11"
    }
  ],
  "artifacts": [
    {
      "id": "lean-workbook-dataset",
      "kind": "dataset",
      "title": "Lean Workbook formal-informal dataset",
      "url": "https://huggingface.co/datasets/internlm/Lean-Workbook"
    }
  ],
  "relationships": {
    "predecessors": [
      "evt-2023-proofnet",
      "evt-2024-deepseek-prover-v1"
    ],
    "successors": [],
    "related": []
  },
  "timeline": {
    "featured": true,
    "significance": "primary"
  },
  "tags": [
    "lean",
    "dataset",
    "autoformalization",
    "synthetic-data"
  ],
  "editorial": {
    "created_at": "2026-09-10",
    "last_reviewed": "2026-09-11",
    "reviewers": [
      "Charlie-Wang-03"
    ]
  },
  "corrections": []
}