复核EveryApp入表并保留原候选初筛审计

scripts/audit-ai-research.py

@@ -96,6 +96,30 @@ def candidate_register():
     return lines
 
 
+def directory_rechecks():
+    rows = DATA.get('directoryRechecks', [])
+    if not rows:
+        return []
+    original = {row['ycId']: row for row in AUDIT['records']}
+    companies = {c['id']: c for c in DATA['companies']}
+    evidence = {e['id']: e for e in DATA['evidence']}
+    assert len({row['ycId'] for row in rows}) == len(rows)
+    lines = ['', '## 原候选池的后续复核', '',
+        '原始1,428条读取快照与初筛计数保持不变；下表记录当时未入表、后续补足证据后进入公司表的项目。初筛未通过不是永久排除。后续入表不回写为当时已匹配，也不重复计入928条原始新增目录项。', '',
+        '| 原候选 | 原始状态 | 后续公司记录 | 复核证据 | 处理与限制 |', '| --- | --- | --- | --- | --- |']
+    for row in rows:
+        baseline = original[row['ycId']]
+        assert baseline['status'] == row['originalStatus']
+        assert row['reviewedAt'] <= DATA['asOf'] and row['reason']
+        assert row['originalStatus'] in {'ai-unclear', 'year-outside-or-missing', 'date-conflict'}
+        company = companies[row['companyId']]
+        assert row['evidenceIds'] and all(eid in evidence for eid in row['evidenceIds'])
+        proof = '、'.join(f"[{eid}]({evidence[eid]['url']})" for eid in row['evidenceIds'])
+        lines.append(f"| [{baseline['name']} · YC{row['ycId']}]({baseline['source']}) | {row['originalStatus']} | [{company['name']}]({BASE}?company={company['id']}#research-company-detail) | {proof} | {row['reviewedAt']}：{row['reason']} |")
+    lines += ['', f"已记录{len(rows)}条后续复核入表；其余未入表候选仍按原状态保留缺项，不能把这一批复核视为完成全部模糊项。", '']
+    return lines
+
+
 def render():
     cov = DATA['coverage']
     companies = DATA['companies']
@@ -168,6 +192,7 @@ def render():
         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 += directory_rechecks()
     lines += source_register()
     lines += candidate_register()
     lines += ['', '## 尚未满足的研究条件', '',