深化20条目录资料并保留发现来源审计

scripts/audit-ai-research.py

@@ -17,6 +17,8 @@ def render():
     cov = DATA['coverage']
     companies = DATA['companies']
     depth = sum(bool(c.get('profileOnly')) for c in companies)
+    origin = sum(bool(c.get('profileOnly')) or c.get('directoryOrigin') == 'yc-2025-2026' for c in companies)
+    promoted = origin - depth
     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)
@@ -24,7 +26,7 @@ def render():
     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 origin == cov['newProfiles']
     assert AUDIT['accessedAt'] == cov['accessedAt']
     assert AUDIT['counts'] == cov
     assert len(AUDIT['records']) == cov['profilesRead']
@@ -42,11 +44,11 @@ def render():
         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"| 新增目录记录 | {cov['newProfiles']:,} | 原始入表来源，后续深化不改变发现计数 |",
         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。", '',
+        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；其中已有{promoted}条原目录记录深化为个案，仍保留目录来源。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 |",