{
  "schema_version": 1,
  "id": "evt-2025-deepseek-r1",
  "slug": "deepseek-r1-reinforcement-learning-reasoning",
  "title": {
    "en": "DeepSeek-R1 shows open reinforcement-learned reasoning at frontier math performance",
    "zh-CN": "DeepSeek-R1 展示开放强化学习推理模型的前沿数学能力"
  },
  "dates": {
    "event": "2025-01-22",
    "first_public_claim": "2025-01-22",
    "paper_release": "2025-01-22",
    "artifact_release": null,
    "independently_verified": null,
    "added_to_chronicle": "2026-09-10",
    "last_updated": "2026-09-11"
  },
  "event_types": [
    "system",
    "benchmark"
  ],
  "significance": {
    "tier": "H3",
    "rationale": {
      "en": "DeepSeek-R1 is historically important to general-purpose reasoning-model development, but its relevance to AI4Math is primarily contextual: mathematics served as a capability benchmark rather than the release contributing a mathematical result, proof, formalization, or math-specific system.",
      "zh-CN": "DeepSeek-R1 对通用推理模型发展具有重要意义，但对 AI4Math 主要属于背景事件：数学主要作为能力评测，而该发布本身并未贡献数学新结果、证明、形式化或数学专项系统。"
    }
  },
  "mathematical_novelty": {
    "type": "benchmark_result"
  },
  "interfaces": [
    "informal",
    "symbolic"
  ],
  "claim": {
    "en": "DeepSeek-R1 and R1-Zero demonstrated strong reasoning behavior from large-scale reinforcement learning, with R1 reported as comparable to OpenAI o1 on reasoning tasks.",
    "zh-CN": "DeepSeek-R1 与 R1-Zero 展示了由大规模强化学习产生的强推理行为，论文报告 R1 在推理任务上可与 OpenAI o1 相比。"
  },
  "summary": {
    "en": "R1-Zero used reinforcement learning without an SFT cold start, while R1 added multi-stage training and released several distilled open models.",
    "zh-CN": "R1-Zero 在无 SFT 冷启动的情况下使用强化学习；R1 则加入多阶段训练并开放多个蒸馏模型。"
  },
  "why_it_matters": {
    "en": "The release accelerated open research on reasoning models, verifier-guided RL and math-specific post-training, providing context for later dedicated AI4Math systems.",
    "zh-CN": "该发布加速了开放社区对推理模型、验证器引导强化学习与数学专项后训练的研究，为后续专门的 AI4Math 系统提供背景。"
  },
  "ai_role": {
    "level": "computation_only",
    "description": {
      "en": "The models perform extended mathematical reasoning learned through reinforcement-learning objectives.",
      "zh-CN": "模型通过强化学习目标学习并执行长程数学推理。"
    }
  },
  "human_contribution": {
    "description": {
      "en": "Researchers designed the RL and cold-start recipes, trained the models and released weights.",
      "zh-CN": "研究者设计 RL 与冷启动方案、训练模型并开放权重。"
    }
  },
  "systems": [
    "deepseek-r1"
  ],
  "organizations": [
    "deepseek"
  ],
  "people": [],
  "problems": [
    "aime",
    "math-benchmark"
  ],
  "methods": [
    "reinforcement-learning",
    "reasoning-model",
    "distillation"
  ],
  "verification": {
    "evidence_level": "E3",
    "status": "paper_released",
    "formal_assurance": "artifact_available",
    "history": [
      {
        "date": "2025-01-22",
        "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-deepseek-r1-2501.12948",
      "tier": "S1",
      "type": "paper",
      "title": "DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning",
      "url": "https://arxiv.org/abs/2501.12948",
      "primary": true,
      "published_date": "2025-01-22",
      "accessed_at": "2026-09-10"
    },
    {
      "id": "github-deepseek-r1",
      "tier": "S1",
      "type": "repository",
      "title": "DeepSeek-R1 model and technical release repository",
      "url": "https://github.com/deepseek-ai/DeepSeek-R1",
      "primary": true,
      "published_date": null,
      "accessed_at": "2026-09-11"
    }
  ],
  "artifacts": [
    {
      "id": "deepseek-r1-repository",
      "kind": "model",
      "title": "DeepSeek-R1 model release and technical artifacts",
      "url": "https://github.com/deepseek-ai/DeepSeek-R1"
    }
  ],
  "relationships": {
    "predecessors": [
      "evt-2024-openai-o1",
      "evt-2024-deepseekmath"
    ],
    "successors": [],
    "related": []
  },
  "timeline": {
    "featured": false,
    "significance": "context"
  },
  "tags": [
    "deepseek",
    "reasoning-model",
    "reinforcement-learning",
    "open-model"
  ],
  "editorial": {
    "created_at": "2026-09-10",
    "last_reviewed": "2026-09-11",
    "reviewers": [
      "Charlie-Wang-03"
    ]
  },
  "corrections": []
}