{"version":"2026-10-19.boundary.1","asOf":"2026-10-19","month":"2026-10","domain":{"id":"math","title":"数学 · 推导与证明","summary":"数值答案、几何构造、机器可检证明和自然语言研究证明需要不同验收；竞赛突破不能代表整个数学职业。","frontierId":"F07","sourceIds":["BS02","BS03"],"terms":[{"term":"形式化 / Lean","definition":"把问题与条件写为机器可检查的逻辑命题；Lean检查所写命题的证明，人检查它是不是原问题。"},{"term":"CoT / pass@k","definition":"CoT是先生成推理步骤；Pass@K表示在指定评测标准下生成K个候选，至少一个通过的题目比例。M01的答案Pass@K核对最终答案，CoT-Pass@K另由模型裁判检查过程；两者都不等于形式证明内核通过。"},{"term":"自然语言核对器","definition":"用模型检查候选论证的语言流程，可能漏错；与严格规则的证明内核不同。"},{"term":"复数标量乘法","definition":"一次复数与复数相乘的算术操作计数；不能直接当成实数乘法次数或程序运行时间。"}]},"focusTask":null,"caseStudy":null,"caseOptions":[{"id":"M01","title":"数值推导：先确定你要验收哪种正确","lead":"得到对的数字，不一定给出了成立的推导。先区分答案、推理步骤和形式证明，再选择核验方法。"}],"tasks":[{"id":"M01","domainId":"math","title":"写出多步数值问题的推导","input":"文字应用题、数量与单位","output":"答案、步骤及可重算表达式","human":"核对单位、条件与每一步理由","acceptance":["数字可重算","条件无遗漏","步骤与答案一致"],"relation":"GSM8K是小学应用题的相近测试；不是专业数学工作覆盖率","workTaskId":null,"actualCoverage":null},{"id":"M02","domainId":"math","title":"构造并检查几何证明","input":"限定平面几何命题和图形关系","output":"证明或辅助构造","human":"核对形式表达、图形假设与推广","acceptance":["每步由允许规则推出","命题没有被削弱","图形退化条件处理"],"relation":"人工翻译到专用经典几何语言的任务，不含不可表达的几何不等式/组合几何；不能推广至任意数学领域。","workTaskId":null,"actualCoverage":null},{"id":"M03","domainId":"math","title":"为形式化命题搜索机器可检证明","input":"用逻辑语言写出的命题、库与环境版本。形式化是把问题及条件写成计算机可逐步核查的语言；Lean是这种证明检查工具。","output":"可由内核检查的证明文件","human":"检查所写形式命题是否正是原问题，核对假设与自然语言含义","acceptance":["固定Lean环境重放通过","不额外假定结论，不用未完成证明占位","自然语言与形式命题一致"],"relation":"形式化已提供命题的证明搜索；不等于自动选题及发表研究","workTaskId":null,"actualCoverage":null},{"id":"M04","domainId":"math","title":"起草自然语言的高难度证明","input":"竞赛级命题、时间与工具约束","output":"供专家评分的完整论证","human":"独立检查严密性、新颖性与适用条件","acceptance":["完整证明而非最终答案","专家逐步核对","公开配置与所有尝试"],"relation":"IMO是严密推理的代理任务；不是职业数学家的任务分布","workTaskId":null,"actualCoverage":null},{"id":"M05","domainId":"math","title":"搜索更好的数学/计算算法","input":"目标问题、可执行评估器与预算","output":"候选算法及验证产物","human":"设计目标/约束，证明并核对总成本","acceptance":["在指定数域中正确","独立验证目标改进","不把算术次数当运行时收益"],"relation":"AlphaEvolve实例是复矩阵乘法搜索，非任意优化项目成功率","workTaskId":null,"actualCoverage":null},{"id":"M06","domainId":"math","title":"检索文献并协作推进研究证明","input":"研究命题、文献与专家反馈","output":"论证草稿、引用与待核对项","human":"选择问题、查原文、判断新颖性与最终发表","acceptance":["引用确实支持命题","语义及逻辑独立核对","失败与人的修改全部保留"],"relation":"专家指导的研究过程案例；不是自主研究完成的受控测量","workTaskId":null,"actualCoverage":null}],"events":[{"id":"M01-2021","taskId":"M01","availableAt":"2021-10-27","eventDate":null,"dateBasis":"按该条支持材料的公开日期进入时间轴；不是实验统一发生日","title":"多候选加验证器开始改善多步计算","kind":"benchmark","mode":"assist","result":"GSM8K包含约8500道2–8步应用题；专门训练的验证器在多候选中选答案，比微调基线更有效。","aiRole":"模型生成多个推导候选，训练出的验证器排序选择，计算器辅助算术。","config":"GPT-3系列微调，生成多个候选并排序；计算器注释","metric":"论文对照发现改进；本条未摘录数值通过率","meaning":"推导并非生成一次就可靠；候选与核对环节开始成为工作流。","limit":"验证器判断不等于数学证明；英语小学题不是专业工作样本。","sourceIds":["BM01"],"comparison":"任务/配置或指标不同，不计算统一增长率","supersedes":null,"actualCoverage":null,"measurementWindow":null},{"id":"M01-2023","taskId":"M01","availableAt":"2023-03-15","eventDate":null,"dateBasis":"按该条支持材料的公开日期进入时间轴；不是实验统一发生日","title":"通用模型在应用题上取得高分","kind":"benchmark","mode":"assist","result":"GPT-4首稿在GSM8K报告92.0%最终答案正确。","aiRole":"通用模型生成多步推导与数字答案；指定应用题最终答案准确率92.0%。","config":"5-shot思维链；预训练含部分GSM8K训练集","metric":"指定测试最终答案准确率","meaning":"可以让模型起草推导，再独立重算数字与步骤。","limit":"训练与提示不同于2021验证器；分数不证明每个中间步骤可靠。","sourceIds":["BM02"],"comparison":"任务/配置或指标不同，不计算统一增长率","supersedes":null,"actualCoverage":null,"measurementWindow":null},{"id":"M01-tools-2023","taskId":"M01","availableAt":"2023-10-23","eventDate":null,"dateBasis":"按所引用固定版本的公开日进入；不是首次发现或运行日","title":"文字推导与程序计算分工","kind":"benchmark","mode":"assist","result":"GSM8K测试1,318题；同一表2中Codex CoT 63.1%、PoT 71.6%，采用少样本贪心设置。","aiRole":"模型生成计算表达，由解释器算出数值；推导语义仍须核对。","config":"code-davinci-002；Python3.8/SymPy；同论文提示/执行系统比较","metric":"最终答案准确率，不是每条推导正确率","meaning":"数值答案可由执行器复算；题意到表达式的转换不因能运行而自动正确。","limit":"小学多步题，不代表高难证明或自然语言推导全通过。","sourceIds":["BF06"],"comparison":"只解释这一来源/任务/配置；不与其他题集连成增长曲线","supersedes":null,"actualCoverage":null,"measurementWindow":null},{"id":"M02-2024","taskId":"M02","availableAt":"2024-01-17","eventDate":null,"dateBasis":"按该条支持材料的公开日期进入时间轴；不是实验统一发生日","title":"专用系统找到非显然几何构造","kind":"benchmark","mode":"bounded","result":"AlphaGeometry在IMO-AG-30的30道平面几何题中解出25道。","aiRole":"系统提出辅助构造并用符号引擎推演；限定30题中完成25题。","config":"2000–2022年IMO历史题；人工翻译成专用语言的经典平面几何命题，语言模型提出辅助构造、符号引擎推演。","metric":"25/30限定几何题；标准竞赛时间限制","meaning":"辅助构造搜索可以由系统承担，命题和推演范围仍需核对。","limit":"表达法不含不能转换的几何不等式和组合几何；不是全部平面几何或25/30数学研究工作可委派。","sourceIds":["BM03","BM09"],"comparison":"任务/配置或指标不同，不计算统一增长率","supersedes":null,"actualCoverage":null,"measurementWindow":null},{"id":"M03-2024","taskId":"M03","availableAt":"2024-07-25","eventDate":null,"dateBasis":"按该条支持材料的公开日期进入时间轴；不是实验统一发生日","title":"形式证明扩展到多种竞赛命题","kind":"benchmark","mode":"bounded","result":"AlphaProof完成2道代数与1道数论题；配合AlphaGeometry2，共4/6题、28/42分。","aiRole":"人在形式化后，系统搜索证明；AlphaProof完成2道代数与1道数论题。","config":"专家先形式化；AlphaProof使用Lean；系统部分题耗时最长3天","metric":"组合系统的竞赛分；不是AlphaProof单独4/6","meaning":"系统可搜索机器可检证明，但自然语言与形式命题的转换仍由人承担。","limit":"不能拿组合成绩当Lean工具通用成功率。","sourceIds":["BM04"],"comparison":"任务/配置或指标不同，不计算统一增长率","supersedes":null,"actualCoverage":null,"measurementWindow":null},{"id":"M04-2024","taskId":"M04","availableAt":"2024-07-25","eventDate":null,"dateBasis":"按该条支持材料的公开日期进入时间轴；不是实验统一发生日","title":"证明稿仍依赖人工形式语言翻译","kind":"benchmark","mode":"assist","result":"IMO2024组合系统4/6题、28/42分，先由专家翻译到形式语言，再得到证明。","aiRole":"系统证明人工翻译后的题目，再由人衔接到自然语言解答。","config":"研究专用系统；部分问题计算最长3天","metric":"竞赛题结果，流程需翻译","meaning":"严密证明的局部搜索已有证据，自然语言交接还需要人补桥。","limit":"不同于普通聊天模型直接接题；与2025题目不同。","sourceIds":["BM04"],"comparison":"任务/配置或指标不同，不计算统一增长率","supersedes":null,"actualCoverage":null,"measurementWindow":null},{"id":"M03-2025","taskId":"M03","availableAt":"2025-04-30","eventDate":null,"dateBasis":"按该条支持材料的公开日期进入时间轴；不是实验统一发生日","title":"开放证明模型可按预算测量","kind":"benchmark","mode":"bounded","result":"DeepSeek-Prover-V2-671B CoT在miniF2F-test：pass@1为61.9%，pass@32为82.4%，pass@8192为88.9%。","aiRole":"开放模型为已形式化命题生成机器可检证明；结果随候选预算改变。","config":"671B、先生成推理步骤（CoT）；Lean 4.9.0证明检查环境；论文采用并再次修订的miniF2F-test共244题，每题最多8192候选。数学库与环境沿论文说明，本页未核对具体commit。","metric":"给定样本预算下至少一份机器可检证明的题目比例","meaning":"证明搜索可委派给开放模型；预算与核验环境需要一起交接。","limit":"88.9%不是一次调用准确率；题集有修订，不与原始题集或IMO年度得分直接连线。","sourceIds":["BM06"],"comparison":"任务/配置或指标不同，不计算统一增长率","supersedes":null,"actualCoverage":null,"measurementWindow":null},{"id":"M05-2025","taskId":"M05","availableAt":"2025-05-14","eventDate":null,"dateBasis":"按该条支持材料的公开日期进入时间轴；不是实验统一发生日","title":"候选算法搜索改善复矩阵乘法","kind":"benchmark","mode":"bounded","result":"AlphaEvolve发现4×4复矩阵乘法只用48次复数标量乘法，原已知Strassen构造49次。","aiRole":"系统搜索并验证候选算法；指定复矩阵乘法构造从49降到48次标量乘法。","config":"Gemini提出代码、自动验证与演化搜索；指定数域/目标","metric":"同一指定算法问题的算术次数改善","meaning":"可以把候选方案探索交给搜索系统，人设计验证器并核对总成本。","limit":"不是实数标量48次；不保证任意硬件运行更快。","sourceIds":["BM07"],"comparison":"同一指定复数问题的49→48可比；旧基线1969年，不等于AI年度增长速度","supersedes":null,"actualCoverage":null,"measurementWindow":null},{"id":"M04-2025","taskId":"M04","availableAt":"2025-07-21","eventDate":null,"dateBasis":"按该条支持材料的公开日期进入时间轴；不是实验统一发生日","title":"自然语言接题并交付可评分证明","kind":"benchmark","mode":"bounded","result":"高级Gemini Deep Think研究版本用自然语言完成5/6题、35/42分，达到IMO2025金牌标准。","aiRole":"特定研究版本直接接自然语言题目并输出证明；2025比赛5/6题解出。","config":"额外强化学习与并行思考；官方文述4.5小时时限；IMO协调者按学生标准评分","metric":"特定研究系统的比赛得分","meaning":"约一年间，人工形式化交接扩展到直接自然语言输入与证明输出。","limit":"题目、系统与计算配置均变化；不是所有Gemini产品具备同样能力。","sourceIds":["BM05"],"comparison":"任务/配置或指标不同，不计算统一增长率","supersedes":null,"actualCoverage":null,"measurementWindow":null},{"id":"M01-trace-2025","taskId":"M01","availableAt":"2025-10-02","eventDate":null,"dateBasis":"按所引用固定版本的公开日进入；不是首次发现或运行日","title":"答案命中与推理过程判定给出不同图景","kind":"benchmark","mode":"assist","result":"Wen等在Qwen2.5-32B/DAPO-Qwen-32B的AIME24/25配置中观察：高K下答案覆盖可接近，但裁判接受的过程覆盖仍有差距；只保留定性图结论。","aiRole":"重复生成解答，再由模型裁判检查过程；这不是无需人的正式证明。","config":"Qwen2.5-32B与DAPO-Qwen-32B；DeepSeek-R1-0528-Qwen3-8B裁判，每条推导裁判3次；any至少1次接受/all全部接受/majority多数接受；生成候选K最高1024","metric":"最终答案与裁判接受的推理过程是不同目标","meaning":"选择验收对象会改变所谓能力边界；需要核对过程和裁判可靠性。","limit":"图值未数字化；依赖模型裁判，不能称Lean内核通过或无争议正确推理。","sourceIds":["BM12"],"comparison":"只解释这一来源/任务/配置；不与其他题集连成增长曲线","supersedes":null,"actualCoverage":null,"measurementWindow":null},{"id":"M01-answer-2025","taskId":"M01","availableAt":"2025-11-24","eventDate":null,"dateBasis":"按所引用固定版本的公开日进入；不是首次发现或运行日","title":"多次尝试的答案覆盖不等于单次可靠","kind":"benchmark","mode":"assist","result":"Yue等在特定模型/题集上比较不同采样K的答案覆盖；高预算下基础模型与RLVR模型的覆盖可能接近。","aiRole":"通过重复采样寻找正确答案；每次尝试与推理正确性需要另外核验。","config":"Qwen2.5-7B-Base 与 SimpleRL-Qwen2.5-7B；AIME24 K=1024、MATH500 K=128；主实验T=0.6；仅选固定v5这一组作方法参考","metric":"Pass@K：K次中至少一次答案命中，不是单次或过程保证","meaning":"记录全部尝试和选答案成本，不能只展示最终成功的一次。","limit":"有限采样与不同题目/训练条件；不据此断言RL永远没有新能力。","sourceIds":["BM11"],"comparison":"只解释这一来源/任务/配置；不与其他题集连成增长曲线","supersedes":null,"actualCoverage":null,"measurementWindow":null},{"id":"M06-2026","taskId":"M06","availableAt":"2026-02-11","eventDate":null,"dateBasis":"按该条支持材料的公开日期进入时间轴；不是实验统一发生日","title":"专家协作的研究Agent过程公开","kind":"case","mode":"assist","result":"Deep Think/Aletheia使用生成、核对、修订与原文搜索循环。一个具体协作例是独立集问题：研究哪些网络顶点能彼此不相邻地选出；Aletheia提出高层证明路线，研究者将它补成完整严密证明。","aiRole":"研究Agent检索文献、起草和迭代论证；专家仍指导并核对研究。","config":"研究Agent、Google Search/web browsing、专家方向与反馈","metric":"研究过程/产物报告；本条无通用成功率","meaning":"AI参与文献与局部论证，数学家继续选题、核对引用和新颖性。","limit":"本条选择人机协作切片；报告中的其它自主案例需另审。自然语言核对器不是Lean内核，不能据此得出任意研究题自主完成率；原文也提醒成功案例稀少、语义误解和引用错误。","sourceIds":["BM08","BM10"],"comparison":"任务/配置或指标不同，不计算统一增长率","supersedes":null,"actualCoverage":null,"measurementWindow":null}],"sources":[{"id":"BM01","title":"GSM8K：多步应用题与验证器","url":"https://arxiv.org/html/2110.14168v1","publishedAt":"2021-10-27","kind":"研究基准","locator":"§2数据；§4.2验证器；§4与附录C计算器","limit":"英语小学应用题，计算器和多候选验证配置；不等于研究数学","family":"BM01","readAt":"2026-10-14","readingScope":"本轮直接阅读所列原文位置；未复跑实验","dateBasis":"页面标示发布日期或固定预印本v1页首日期","status":"active"},{"id":"BM02","title":"GPT-4技术报告首稿","url":"https://arxiv.org/html/2303.08774v1","publishedAt":"2023-03-15","kind":"发布方基准","locator":"表2 GSM-8K；附录E训练集使用","limit":"5-shot思维链，训练含部分GSM8K训练集；最终答案分不保证每步论证正确","family":"BM02","readAt":"2026-10-14","readingScope":"本轮直接阅读所列原文位置；未复跑实验","dateBasis":"页面标示发布日期或固定预印本v1页首日期","status":"active"},{"id":"BM03","title":"AlphaGeometry发布","url":"https://deepmind.google/blog/alphageometry-an-olympiad-level-ai-system-for-geometry/","publishedAt":"2024-01-17","kind":"发布方基准","locator":"IMO-AG-30与symbolic deduction介绍","limit":"2000–2022年30道平面几何题；专用符号系统，不能外推全部数学","family":"alphageometry-study","readAt":"2026-10-14","readingScope":"本轮直接阅读所列原文位置；未复跑实验","dateBasis":"页面标示发布日期或固定预印本v1页首日期","status":"active"},{"id":"BM04","title":"AlphaProof与AlphaGeometry 2：IMO2024","url":"https://deepmind.google/blog/ai-solves-imo-problems-at-silver-medal-level/","publishedAt":"2024-07-25","kind":"竞赛结果","locator":"人工形式化说明；4/6题与28/42分","limit":"4.5小时×两场是学生制度；系统耗时最长3天，不是同时间预算","family":"imo-deepmind","readAt":"2026-10-14","readingScope":"本轮直接阅读所列原文位置；未复跑实验","dateBasis":"页面标示发布日期或固定预印本v1页首日期","status":"active"},{"id":"BM05","title":"Gemini Deep Think：IMO2025","url":"https://deepmind.google/blog/advanced-version-of-gemini-with-deep-think-officially-achieves-gold-medal-standard-at-the-international-mathematical-olympiad/","publishedAt":"2025-07-21","kind":"竞赛结果","locator":"Breakthrough Performance；Making the most；IMO认证范围脚注","limit":"特定高级研究版本；不同年度题目/配置；认证解答不等于审计整个运行","family":"imo-deepmind","readAt":"2026-10-14","readingScope":"本轮直接阅读所列原文位置；未复跑实验","dateBasis":"页面标示发布日期或固定预印本v1页首日期","status":"active"},{"id":"BM06","title":"DeepSeek-Prover-V2首稿","url":"https://arxiv.org/html/2504.21801v1","publishedAt":"2025-04-30","kind":"研究基准","locator":"§3及§3.1 Experimental Results；表1（671B CoT/候选预算）、表2（题目类别）；附录C题集修订。","limit":"671B CoT的88.9%为pass@8192；82.4%为pass@32，61.9%为pass@1；不是首试成功率","family":"BM06","readAt":"2026-10-14","readingScope":"本轮直接阅读所列原文位置；未复跑实验","dateBasis":"页面标示发布日期或固定预印本v1页首日期","status":"active"},{"id":"BM07","title":"AlphaEvolve发布","url":"https://deepmind.google/blog/alphaevolve-a-gemini-powered-coding-agent-for-designing-advanced-algorithms/","publishedAt":"2025-05-14","kind":"发布方研究","locator":"自动评估流程；Discovering new algorithms中的4×4复矩阵","limit":"48次复数标量乘法不等于48次实数乘法或完整运行时加速","family":"alphaevolve","readAt":"2026-10-14","readingScope":"本轮直接阅读所列原文位置；未复跑实验","dateBasis":"页面标示发布日期或固定预印本v1页首日期","status":"active"},{"id":"BM08","title":"Deep Think/Aletheia研究协作","url":"https://deepmind.google/blog/accelerating-mathematical-and-scientific-discovery-with-gemini-deep-think/","publishedAt":"2026-02-11","kind":"发布方研究","locator":"The Frontier of Pure Mathematics；generator/verifier/reviser与expert collaboration","limit":"发布方研究过程报告，专家指导；未复核全部研究产物，不提供通用证明成功率","family":"aletheia-research","readAt":"2026-10-14","readingScope":"本轮直接阅读所列原文位置；未复跑实验","dateBasis":"页面标示发布日期或固定预印本v1页首日期","status":"active"},{"id":"BS02","title":"数学推理综述","url":"https://arxiv.org/html/2506.08446v1","publishedAt":"2025-06-10","kind":"综述","locator":"§3推理组成；§4方法；§5–6局限","limit":"综述用于任务框架与机制，不回填更早年份的已知成绩","family":"BS02","readAt":"2026-10-14","readingScope":"本轮直接阅读所列原文位置；未复跑实验","dateBasis":"页面标示发布日期或固定预印本v1页首日期","status":"active"},{"id":"BS03","title":"自动形式化综述","url":"https://arxiv.org/html/2505.23486v1","publishedAt":"2025-05-29","kind":"综述","locator":"formalization定义；评测/语义对齐讨论","limit":"机器核查形式命题不保证与自然语言原问题等价","family":"BS03","readAt":"2026-10-14","readingScope":"本轮直接阅读所列原文位置；未复跑实验","dateBasis":"页面标示发布日期或固定预印本v1页首日期","status":"active"},{"id":"BM09","title":"AlphaGeometry原始研究","url":"https://www.nature.com/articles/s41586-023-06747-5","publishedAt":"2024-01-17","kind":"同行评议研究","locator":"Empirical evaluation：专用经典几何语言、人工翻译与不能表达的任务范围","limit":"不含不可表达的几何不等式和组合几何；入口可能需浏览器接受cookie","family":"alphageometry-study","readAt":"2026-10-14","readingScope":"独立数学审阅直接核对Empirical evaluation；主Agent该入口遇到cookie重定向；未复跑实验","dateBasis":"页面/论文首稿标示公开日期","status":"active"},{"id":"BM10","title":"Aletheia研究过程固定首稿","url":"https://arxiv.org/html/2602.10177v1","publishedAt":"2026-02-10","kind":"研究预印本","locator":"§3.2人机协作/独立集问题；§4.2局限与语义误解；最终人的署名责任","limit":"本页选取协作实例，不将文中其它自主案例或成功筛选集推广为通用研究成功率","family":"aletheia-research","readAt":"2026-10-14","readingScope":"本轮直接阅读所列原文位置；未复跑实验","dateBasis":"页面/论文首稿标示公开日期","status":"active"},{"id":"BF06","title":"Program of Thoughts：外部计算接口（v4）","url":"https://arxiv.org/html/2211.12588v4","publishedAt":"2023-10-23","kind":"数值任务研究预印本","locator":"§2.2；§3.1数据/实现/指标；§3.2表2","limit":"同底层模型改变提示与执行流程；未匹配完整延迟/预算；不是端到端财务工作通过率","family":"program-of-thoughts","readAt":"2026-10-15","readingScope":"本轮直接核对所列原文位置/版本；未复跑外部实验","dateBasis":"固定v4页首：2023-10-23；不把v4表格倒填v1","status":"active"},{"id":"BM11","title":"RLVR答案覆盖研究（v5）","url":"https://arxiv.org/html/2504.13837v5","publishedAt":"2025-11-24","kind":"推理评测研究预印本","locator":"§3设置；表2；附录C.7覆盖与C.8温度分析","limit":"有限采样只测答案命中；特定模型/任务结果不等于所有推理机制；不与另一论文合并效应","family":"rlvr-answer-support","readAt":"2026-10-15","readingScope":"本轮直接核对所列原文位置/版本；未复跑外部实验","dateBasis":"固定v5：2025-11-24；具体结论以所引用版本为准","status":"active"},{"id":"BM12","title":"RLVR推理过程核验研究（v2）","url":"https://arxiv.org/html/2506.14245v2","publishedAt":"2025-10-02","kind":"推理评测研究预印本","locator":"§3.1图2；§3.2图3；附录A.3裁判方法","limit":"推理过程由模型裁判判定，有any/all/majority规则；不是形式证明内核，图值未可靠转录则定性","family":"rlvr-judged-traces","readAt":"2026-10-15","readingScope":"本轮直接核对所列原文位置/版本；未复跑外部实验","dateBasis":"固定v2页首：2025-10-02；不倒填首次预印本日期","status":"active"}],"scope":"16个编辑选择的代表任务切片；不是完整职业清单或任务覆盖比例。","actualCoverage":null,"knowledgeRule":"主轴按原始材料公开日期；实验/上线时点另列。历史空白仅表示本次未收录证据；后来的质疑不偷偷改写早期结果。","method":{"coverage":"覆盖的含义：在指定输入、环境和验收下，材料支持AI参与哪些动作；未知比例保持null。","speed":"速度的含义：证据节点之间的日历间隔、流程交接变化；指标/样本/预算不一致时，不计算能力增长率或外推一年三年。","sourcePolicy":"综述用于发现任务和原始文献；每条公开主张引用原始论文/官方记录。转载及同一文献家族不累计成独立验证。","selection":"目的性选择三个领域的代表任务，不是穷尽检索或无偏职业采样；基础时间轴于2026-10-14核对，本次精选补充与证据截止2026-10-15，固定论文优先，不把动态榜排名倒填历史。"}}