diff --git a/README.md b/README.md index e1d81cd..6bdd705 100644 --- a/README.md +++ b/README.md @@ -120,6 +120,8 @@ MRR×12仅作为显示单位转换,不改写为公司ARR;公司ARR、估算 页面本身从同一SQLite中的公司与观测记录计算,不读取第二个数据库。 平台同步时间、连接过期状态、业务描述的可编辑性和产品/法律主体未去重限制均保留。 +覆盖审计页位于 `/docs/other-research/ai-company-research/coverage`,分类链接 `overview?category=` 的筛选数据。 +`python3 scripts/audit-ai-research.py --check` 检查候选池逐条计数与覆盖报告一致性;CI在ces-control运行此检查,未更改触发范围。 收入快照报告位于 `/docs/other-research/ai-company-research/income-snapshot`,样本名称链接 `overview?company=` 的公司明细。 `python3 scripts/summarize-ai-income.py --check` 独立复核统计与报告一致性;不触发编译或构建。数据变更后先审查方法,再运行不带参数的命令更新固定快照。 默认7日样本14个产品;90日窗口新增Gojiberry的8月历史点,营销样本的均值和CV随之明显变化。 diff --git a/apps/docs/src/components/AICompanyResearch.tsx b/apps/docs/src/components/AICompanyResearch.tsx index 836687d..2bf970e 100644 --- a/apps/docs/src/components/AICompanyResearch.tsx +++ b/apps/docs/src/components/AICompanyResearch.tsx @@ -36,7 +36,12 @@ export default function AICompanyResearch() { const [error, setError] = useState(false); const [attempt, setAttempt] = useState(0); const [query, setQuery] = useState(""); - const [category, setCategory] = useState(""); + const [categoryChoice, setCategoryChoice] = useState<{ route: string; id: string } | null>(null); + const linkedCategory = router.query.category; + const category = categoryChoice && categoryChoice.route === router.asPath ? categoryChoice.id + : router.isReady && typeof linkedCategory === "string" && data?.categories.some((c) => c.id === linkedCategory) + ? linkedCategory : ""; + function setCategory(id: string) { setCategoryChoice({ route: router.asPath, id }); } const [cohort, setCohort] = useState(""); const [income, setIncome] = useState(""); const [page, setPage] = useState(0); diff --git a/content/catalog.json b/content/catalog.json index 507f3fa..9a192b6 100644 --- a/content/catalog.json +++ b/content/catalog.json @@ -226,6 +226,13 @@ "description": "查看14个产品的平台MRR分布、均值与离散度、历史点敏感性和逐项证据入口。", "slug": "other-research/ai-company-research/income-snapshot", "category": "其他研究" + }, + "ai-company-research/02-coverage-and-gaps": { + "collection": "AI 公司研究", + "group": "公司与市场", + "description": "核对候选池、来源偏差、分类与验证完成度,区分全量读取和定向补充。", + "slug": "other-research/ai-company-research/coverage", + "category": "其他研究" } } } diff --git a/content/docs/ai-company-research/00-overview.md b/content/docs/ai-company-research/00-overview.md index e51ff7b..63aedef 100644 --- a/content/docs/ai-company-research/00-overview.md +++ b/content/docs/ai-company-research/00-overview.md @@ -6,6 +6,8 @@ [收入样本分布快照](/docs/other-research/ai-company-research/income-snapshot)列出当前平台MRR的分组结果、逐项证据入口和历史样本敏感性。 +[资料覆盖与缺项](/docs/other-research/ai-company-research/coverage)区分候选池读取、定向样本、人工复核及尚未核验的字段。 + ## 商业模式初评:截至 2026-10-30 以下为研究假设,用于设计付费试验,尚不足以给行业排收益名次。规模、交付证据和收入来源必须一起看;目录条目数量不是市场需求,平台样本也存在自愿公开与幸存者偏差。 diff --git a/content/docs/ai-company-research/02-coverage-and-gaps.md b/content/docs/ai-company-research/02-coverage-and-gaps.md new file mode 100644 index 0000000..e3f024c --- /dev/null +++ b/content/docs/ai-company-research/02-coverage-and-gaps.md @@ -0,0 +1,71 @@ +# AI 公司资料覆盖与缺项 + +截至 2026-10-30,研究表含1,015条公司或产品记录。YC候选池有逐条读取审计;其他来源为定向补充。清单尚不能作为全球AI公司普查,也不能将收入未知解释为零。 + +[分类和数据工作台](/docs/other-research/ai-company-research/overview)链接原始证据,[收入样本快照](/docs/other-research/ai-company-research/income-snapshot)展示当前可计算的MRR样本。 + +## 候选池与公司表的关系 + +| 环节 | 记录数 | 含义 | +| --- | --- | --- | +| YC批次候选 | 1,428 | 从公开镜像发现,随后读取YC官方页面 | +| 官方页面读取 | 1,428 | 此候选池读取失败0条 | +| 初筛匹配 | 962 | 成立年及AI相关描述通过初筛,尚非逐家商业验证 | +| 与原表重合 | 34 | URL匹配,未再次新增 | +| 新增目录记录 | 928 | 进入公司表,仍需深化核验 | +| 年份不符或缺失 | 268 | 此轮不作为成立年匹配项 | +| AI业务待确认 | 192 | 不强行把背景关键词当主营 | +| 成立年与批次冲突 | 6 | 另保留核查记录 | + +全表由928条目录基础项和87条个案或平台记录组成。候选池已匹配项之外另有53条记录,包含其他来源及发布/转型对照;两种统计边界不同。候选池数字只是该镜像快照的覆盖,Bud等后续定向补充不回填为原候选池已覆盖。 + +## 成立年与证据深度 + +| 维度 | 当前记录 | 解读 | +| --- | --- | --- | +| 记录为2025年成立 | 619 | 成立来源和精度见公司明细 | +| 记录为2026年成立 | 391 | 不将产品发布日期代替成立日 | +| 成立年未知或范围外 | 5 | 发布/转型对照单列,不进入两年成立分组 | +| 目录业务分类人工复核 | 121 | 仅复核主营分类,不代表技术或财务审计 | +| 其他目录基础项 | 807 | 规则初分或资料不足,继续待复核 | +| 有团队数字 | 945 | 多为自报Team Size或Employees,时点与口径不统一 | +| 专项技术证据记录 | 6 | 其中3条自述、2条公开材料、1条第三方评测 | +| 公司披露收入线索 | 17 | 含历史、下界、币种不明及产品业务声明,不等于可比ARR | +| 仅平台收入线索 | 16 | 同时有公司披露者计入上一行,不重复计数 | +| 仅第三方估算 | 1 | 不与直接披露混合 | +| 暂无可用收入数字 | 981 | 包含尚未逐家搜索的目录项,不代表没有收入 | + +## 业务分类与数据入口 + +| 业务类别 | 记录数 | +| --- | --- | +| [基础模型](/docs/other-research/ai-company-research/overview?category=C01) | 29 | +| [算力与模型基础设施](/docs/other-research/ai-company-research/overview?category=C02) | 105 | +| [Agent 开发与运行设施](/docs/other-research/ai-company-research/overview?category=C03) | 50 | +| [软件开发](/docs/other-research/ai-company-research/overview?category=C04) | 109 | +| [企业通用工作](/docs/other-research/ai-company-research/overview?category=C05) | 174 | +| [客户与收入运营](/docs/other-research/ai-company-research/overview?category=C06) | 51 | +| [行业专业应用](/docs/other-research/ai-company-research/overview?category=C07) | 324 | +| [内容与创意](/docs/other-research/ai-company-research/overview?category=C08) | 45 | +| [消费者个人应用](/docs/other-research/ai-company-research/overview?category=C09) | 45 | +| [机器人及实体产业](/docs/other-research/ai-company-research/overview?category=C10) | 80 | +| [业务待分类](/docs/other-research/ai-company-research/overview?category=C00) | 3 | + +## 已使用来源的分布 + +1,086条证据记录对应1,072个不同URL。不同URL不自动构成独立验证;同一声明可能由公司、投资方和媒体重复转述。 + +| 来源 | 证据记录 | 不同URL | 用途及限制 | +| --- | --- | --- | --- | +| YC官方目录 | 984 | 975 | 公司自述的成立、团队与业务;英文及加速器样本偏多 | +| TrustMRR | 18 | 18 | 支付平台重建指标及方法;公开者存在选择偏差,非财务审计 | +| a16z Speedrun | 11 | 10 | 投资机构中的公司介绍及收入声明;存在利益关系 | +| TechCrunch | 3 | 3 | 原始采访或报道;转述公司数字不等于查账 | +| Sacra | 3 | 3 | 第三方估算;与直接披露分开 | +| 其他官网、评测及公开资料 | 67 | 63 | 按每条来源限制理解,不能统一当作独立证据 | + +## 尚未满足的研究条件 + +行业ARR比较仍缺统一业务截止日、币种、经常性定义和业务边界。现有平台MRR可描述已采集产品,不足以代表全部新公司。技术评测只覆盖所列版本与任务,不宜跨领域汇总为统一强弱分数。 + +下一轮优先补收入线索的日期及合同定义、非YC和非英文来源、规则初分的人工复核,以及停止服务或被收购案例。这样能减少“只见赢家”和“只见融资公司”的偏差。公开来源池之外的未披露公司仍无法证明已被穷尽。 diff --git a/scripts/audit-ai-research.py b/scripts/audit-ai-research.py new file mode 100644 index 0000000..2070eec --- /dev/null +++ b/scripts/audit-ai-research.py @@ -0,0 +1,107 @@ +"""Summarize observed research coverage; does not claim an exhaustive AI census.""" +import argparse +from collections import Counter +import json +from pathlib import Path +import sys +from urllib.parse import urlsplit + +ROOT = Path(__file__).resolve().parents[1] +DATA = json.loads((ROOT / 'content/research/ai-companies.seed.json').read_text()) +AUDIT = json.loads((ROOT / 'content/research/ai-companies.coverage.json').read_text()) +TARGET = ROOT / 'content/docs/ai-company-research/02-coverage-and-gaps.md' +BASE = '/docs/other-research/ai-company-research/overview' + + +def render(): + cov = DATA['coverage'] + companies = DATA['companies'] + depth = sum(bool(c.get('profileOnly')) for c in companies) + reviewed = sum(bool(c.get('profileOnly')) and '人工复核' in c.get('classificationBasis', '') for c in companies) + years = Counter(c['year'] for c in companies) + income = Counter(c['revenueStatus'] for c in companies) + technical = Counter(c.get('technicalReview', {}).get('level', 'unreviewed') for c in companies) + assert cov['profilesRead'] + cov['failedProfiles'] == cov['candidateRecords'] + assert cov['matchingProfiles'] == cov['existingProfiles'] + cov['newProfiles'] + assert cov['matchingProfiles'] + cov['otherOrMissingYear'] + cov['unclearAI'] + cov['dateConflicts'] == cov['profilesRead'] + assert depth == cov['newProfiles'] + assert AUDIT['accessedAt'] == cov['accessedAt'] + assert AUDIT['counts'] == cov + assert len(AUDIT['records']) == cov['profilesRead'] + assert Counter(x['status'] for x in AUDIT['records']) == { + 'imported': cov['newProfiles'], 'existing': cov['existingProfiles'], + 'year-outside-or-missing': cov['otherOrMissingYear'], + 'ai-unclear': cov['unclearAI'], 'date-conflict': cov['dateConflicts']} + assert len({x['ycId'] for x in AUDIT['records']}) == len(AUDIT['records']) + lines = ['# AI 公司资料覆盖与缺项', '', + f"截至 {DATA['asOf']},研究表含{len(companies):,}条公司或产品记录。YC候选池有逐条读取审计;其他来源为定向补充。清单尚不能作为全球AI公司普查,也不能将收入未知解释为零。", '', + f"[分类和数据工作台]({BASE})链接原始证据,[收入样本快照](/docs/other-research/ai-company-research/income-snapshot)展示当前可计算的MRR样本。", '', + '## 候选池与公司表的关系', '', + '| 环节 | 记录数 | 含义 |', '| --- | --- | --- |', + f"| YC批次候选 | {cov['candidateRecords']:,} | 从公开镜像发现,随后读取YC官方页面 |", + f"| 官方页面读取 | {cov['profilesRead']:,} | 此候选池读取失败{cov['failedProfiles']}条 |", + f"| 初筛匹配 | {cov['matchingProfiles']:,} | 成立年及AI相关描述通过初筛,尚非逐家商业验证 |", + f"| 与原表重合 | {cov['existingProfiles']} | URL匹配,未再次新增 |", + f"| 新增目录记录 | {cov['newProfiles']:,} | 进入公司表,仍需深化核验 |", + f"| 年份不符或缺失 | {cov['otherOrMissingYear']} | 此轮不作为成立年匹配项 |", + f"| AI业务待确认 | {cov['unclearAI']} | 不强行把背景关键词当主营 |", + f"| 成立年与批次冲突 | {cov['dateConflicts']} | 另保留核查记录 |", '', + f"全表由{depth}条目录基础项和{len(companies)-depth}条个案或平台记录组成。候选池已匹配项之外另有{len(companies)-cov['matchingProfiles']}条记录,包含其他来源及发布/转型对照;两种统计边界不同。候选池数字只是该镜像快照的覆盖,Bud等后续定向补充不回填为原候选池已覆盖。", '', + '## 成立年与证据深度', '', + '| 维度 | 当前记录 | 解读 |', '| --- | --- | --- |', + f"| 记录为2025年成立 | {years[2025]} | 成立来源和精度见公司明细 |", + f"| 记录为2026年成立 | {years[2026]} | 不将产品发布日期代替成立日 |", + f"| 成立年未知或范围外 | {sum(v for k,v in years.items() if k not in (2025,2026))} | 发布/转型对照单列,不进入两年成立分组 |", + f"| 目录业务分类人工复核 | {reviewed} | 仅复核主营分类,不代表技术或财务审计 |", + f"| 其他目录基础项 | {depth-reviewed} | 规则初分或资料不足,继续待复核 |", + f"| 有团队数字 | {sum(c['team'] is not None for c in companies)} | 多为自报Team Size或Employees,时点与口径不统一 |", + f"| 专项技术证据记录 | {len(companies)-technical['unreviewed']} | 其中{technical['description']}条自述、{technical['public-artifact']}条公开材料、{technical['independent-test']}条第三方评测 |", + f"| 公司披露收入线索 | {income['self']} | 含历史、下界、币种不明及产品业务声明,不等于可比ARR |", + f"| 仅平台收入线索 | {income['platform']} | 同时有公司披露者计入上一行,不重复计数 |", + f"| 仅第三方估算 | {income['estimate']} | 不与直接披露混合 |", + f"| 暂无可用收入数字 | {income['unknown']} | 包含尚未逐家搜索的目录项,不代表没有收入 |", '', + '## 业务分类与数据入口', '', + '| 业务类别 | 记录数 |', '| --- | --- |', + ] + counts = Counter(c['cat'] for c in companies) + for category in DATA['categories']: + lines.append(f"| [{category['name']}]({BASE}?category={category['id']}) | {counts[category['id']]} |") + lines += ['', '## 已使用来源的分布', '', + f"{len(DATA['evidence']):,}条证据记录对应{len({e['url'] for e in DATA['evidence']}):,}个不同URL。不同URL不自动构成独立验证;同一声明可能由公司、投资方和媒体重复转述。", '', + '| 来源 | 证据记录 | 不同URL | 用途及限制 |', '| --- | --- | --- | --- |', + ] + families = [('YC官方目录', 'www.ycombinator.com', '公司自述的成立、团队与业务;英文及加速器样本偏多'), + ('TrustMRR', 'trustmrr.com', '支付平台重建指标及方法;公开者存在选择偏差,非财务审计'), + ('a16z Speedrun', 'speedrun.a16z.com', '投资机构中的公司介绍及收入声明;存在利益关系'), + ('TechCrunch', 'techcrunch.com', '原始采访或报道;转述公司数字不等于查账'), + ('Sacra', 'sacra.com', '第三方估算;与直接披露分开')] + included = set() + for name, host, note in families: + entries = [e for e in DATA['evidence'] if urlsplit(e['url']).netloc == host] + included.add(host) + lines.append(f"| {name} | {len(entries)} | {len({e['url'] for e in entries})} | {note} |") + others = [e for e in DATA['evidence'] if urlsplit(e['url']).netloc not in included] + lines.append(f"| 其他官网、评测及公开资料 | {len(others)} | {len({e['url'] for e in others})} | 按每条来源限制理解,不能统一当作独立证据 |") + lines += ['', '## 尚未满足的研究条件', '', + '行业ARR比较仍缺统一业务截止日、币种、经常性定义和业务边界。现有平台MRR可描述已采集产品,不足以代表全部新公司。技术评测只覆盖所列版本与任务,不宜跨领域汇总为统一强弱分数。', '', + '下一轮优先补收入线索的日期及合同定义、非YC和非英文来源、规则初分的人工复核,以及停止服务或被收购案例。这样能减少“只见赢家”和“只见融资公司”的偏差。公开来源池之外的未披露公司仍无法证明已被穷尽。', '', + ] + return '\n'.join(lines) + + +def main(): + parser = argparse.ArgumentParser(description=__doc__) + parser.add_argument('--check', action='store_true') + args = parser.parse_args() + content = render() + if args.check: + if not TARGET.exists() or TARGET.read_text() != content: + sys.exit('Research coverage report differs; review and regenerate') + print('Research coverage accounting and report are consistent') + else: + TARGET.write_text(content) + print(TARGET.relative_to(ROOT)) + + +if __name__ == '__main__': + main() diff --git a/scripts/ci.py b/scripts/ci.py index 6f37b87..d066194 100644 --- a/scripts/ci.py +++ b/scripts/ci.py @@ -14,7 +14,8 @@ ROOT = Path(__file__).resolve().parents[1] APP = "endorphin-tabularium-docs" INPUTS = ["Dockerfile", "Dockerfile.ci", ".dockerignore", ".npmrc", "package.json", "pnpm-lock.yaml", "pnpm-workspace.yaml", "apps/docs", "content", "tools/figures", - "scripts/check-container.sh", "scripts/ci.py", "scripts/summarize-ai-income.py"] + "scripts/check-container.sh", "scripts/ci.py", "scripts/summarize-ai-income.py", + "scripts/audit-ai-research.py"] def run(*args: str, capture: bool = False) -> str: @@ -64,6 +65,7 @@ def smoke_image(image: str, name: str) -> None: def main() -> None: os.chdir(ROOT) run(sys.executable, "scripts/summarize-ai-income.py", "--check") + run(sys.executable, "scripts/audit-ai-research.py", "--check") run(sys.executable, "-m", "unittest", "discover", "-s", "scripts", "-p", "test_*.py") scope = os.environ.get("CI_CACHE_SCOPE", "main") if not re.fullmatch(r"main|pr-[0-9]+", scope):