完成192项AI不明名单补核并核对预订与交付口径

scripts/audit-ai-research.py

@@ -121,6 +121,31 @@ def candidate_register():
     return lines
 
 
+def uncertain_ai_followups():
+    original = {row['source']: row for row in AUDIT['records'] if row['status'] == 'ai-unclear'}
+    rows = [row for batch in DATA.get('candidateBatches', [])
+            if batch['id'].startswith('YC-AI-UNCLEAR-') for row in batch['records']]
+    if not rows:
+        return []
+    urls = [row['url'] for row in rows]
+    assert len(set(urls)) == len(urls), 'Duplicate AI-relevance follow-up URL'
+    rechecks = {row['ycId']: row for row in DATA.get('directoryRechecks', [])}
+    counts = Counter(row['status'] for row in rows)
+    assert set(counts) <= {'linked', 'pending-ai'}
+    for row in rows:
+        assert row['url'] in original and row.get('evidenceIds')
+        baseline = original[row['url']]
+        if row['status'] == 'linked':
+            assert rechecks[baseline['ycId']]['companyId'] == row['companyId']
+        else:
+            assert not row.get('companyId') and baseline['ycId'] not in rechecks
+    unread = len(original) - len(rows)
+    assert unread >= 0
+    return ['', '## 原AI主营不明名单的后续覆盖', '',
+        f"原名单{len(original)}项，已有后续记录{len(rows)}项：{counts['linked']}项关联公司、{counts['pending-ai']}项仍待核AI主营，{unread}项尚无本批系列的后续记录。计数按原始YC页面去重；EveryApp此前的独立复核与末批记录不重复相加。", '',
+        '读完名单只证明每项有可回查的处理记录，不证明待核项均为AI公司，也不证明法律主体、收入或技术效果已独立验证。原始发现审计保持不变，成立年范围外/缺失、成立冲突及其他来源的缺项仍单列。', '']
+
+
 def directory_rechecks():
     rows = DATA.get('directoryRechecks', [])
     if not rows:
@@ -217,13 +242,14 @@ 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 += uncertain_ai_followups()
     lines += directory_rechecks()
     lines += source_register()
     lines += context_methods()
     lines += candidate_register()
     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。', '',
+        '下一轮优先补收入线索的日期及合同定义、成立年冲突、AI主营仍待核项、非YC和非英文来源，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)