Reconcile current YC coverage accounting with source boundaries

content/research/ai-companies.seed.json

@@ -1,5 +1,5 @@
 {
-  "version": "2026-11-01-arr-time-basis-1",
+  "version": "2026-11-01-source-accounting-1",
   "asOf": "2026-10-31",
   "scope": "全球公开资料研究：保留首批个案，并扩展核查2025—2026八个YC批次候选池；成立年份以官方公司页面字段为依据。",
   "limitations": [

content/research/ai-income-analysis.json

@@ -1,5 +1,5 @@
 {
-  "sourceVersion": "2026-11-01-arr-time-basis-1",
+  "sourceVersion": "2026-11-01-source-accounting-1",
   "asOf": "2026-10-31",
   "metric": "platform-mrr-usd",
   "sampleUnit": "product-or-business",

scripts/audit-ai-research.py

@@ -16,6 +16,20 @@ SOURCE_SLUG = 'ai-company-research/02-coverage-and-gaps'
 BASE = '/docs/other-research/ai-company-research/overview'
 
 
+def yc_coverage_summary():
+    companies = {row['id']: row for row in DATA['companies']}
+    imported = [companies[f"YC{row['ycId']}"] for row in AUDIT['records'] if row['status'] == 'imported']
+    profile_only = sum(bool(row.get('profileOnly')) for row in imported)
+    groups = {}
+    for label, prefix in [('unclearAI', 'YC-AI-UNCLEAR-'), ('missingYear', 'YC-MISSING-YEAR-'),
+                          ('dateConflict', 'YC-DATE-CONFLICT-')]:
+        rows = [row for batch in DATA.get('candidateBatches', []) if batch['id'].startswith(prefix)
+                for row in batch['records']]
+        groups[label] = {'records': len(rows), 'statuses': dict(sorted(Counter(row['status'] for row in rows).items()))}
+    return {'initialProfiles': len(AUDIT['records']), 'originalImported': len(imported),
+            'profileOnly': profile_only, 'deepenedOriginal': len(imported) - profile_only, **groups}
+
+
 
 def source_register():
     sources = SOURCES['sources']
@@ -26,6 +40,8 @@ def source_register():
     for source in sources:
         assert source['status'] in {'candidate-audit', 'targeted', 'pending', 'context', 'access-limited', 'per-company'}
         assert source['boundary'] and source['nextCheck']
+        if source['id'] == 'S01':
+            assert source.get('coverageSummary') == yc_coverage_summary(), 'YC source summary is stale'
         if source['url']:
             assert urlsplit(source['url']).scheme in {'http', 'https'} and urlsplit(source['url']).netloc
         for host in source['hosts']:
@@ -49,7 +65,18 @@ def source_register():
         company_ids = {e['companyId'] for e in evidence if e['companyId']}
         observations = sum(o['evidence'] in evidence_ids for o in DATA['observations'])
         name = f"[{source['name']}]({source['url']})" if source['url'] else source['name']
-        lines.append(f"| {source['id']} {name} | {statuses[source['status']]} | {len(evidence)} / {len(company_ids)} / {observations} | {source['boundary']} | {source['nextCheck']} |")
+        boundary = source['boundary']
+        if source['id'] == 'S01':
+            summary = source['coverageSummary']
+            boundary += (f" 当前原候选池{summary['initialProfiles']}项，原新增{summary['originalImported']}项中"
+                         f"{summary['profileOnly']}项目录基础资料、{summary['deepenedOriginal']}项深化个案。")
+            for key, label in [('unclearAI', '原AI不明'), ('missingYear', '原缺年'), ('dateConflict', '原日期冲突')]:
+                group = summary[key]
+                labels = {'linked': '关联公司', 'pending-ai': 'AI主营待核',
+                          'pending-year': '成立/主体待核', 'outside-cohort': '范围外'}
+                counts = '、'.join(f'{labels.get(status, status)} {count}' for status, count in group['statuses'].items())
+                boundary += f" {label}{group['records']}项当前：{counts}。"
+        lines.append(f"| {source['id']} {name} | {statuses[source['status']]} | {len(evidence)} / {len(company_ids)} / {observations} | {boundary} | {source['nextCheck']} |")
     lines += ['', 'Dealroom、Product Hunt、机器之心与36氪入口于2026-10-30重新访问。官网首页可读不证明已取得完整筛选结果；安全检测页面不作为文章内容。候选池之外的来源边界尚需建立可回查条目，完成前不宣布来源清单已全部覆盖。', '']
     return lines