登记Product Hunt候选并补充Kilo公司个案

scripts/audit-ai-research.py

@@ -52,6 +52,43 @@ def source_register():
     return lines
 
 
+
+def candidate_register():
+    batches = DATA.get('candidateBatches', [])
+    companies = {c['id']: c for c in DATA['companies']}
+    categories = {c['id']: c['name'] for c in DATA['categories']}
+    known_sources = {s['id'] for s in SOURCES['sources']}
+    assert len({b['id'] for b in batches}) == len(batches)
+    all_ids = [r['id'] for b in batches for r in b['records']]
+    assert len(set(all_ids)) == len(all_ids)
+    lines = []
+    statuses = {'pending-year': '成立年待核', 'linked': '已关联公司',
+                'existing-outside-cohort': '已有关联，年份范围外', 'promotion': '推广活动，非公司新增'}
+    for batch in batches:
+        assert batch['sourceId'] in known_sources
+        assert batch['accessedAt'] <= DATA['asOf']
+        assert any(e['url'] == batch['url'] for e in DATA['evidence'])
+        rows = batch['records']
+        counts = Counter(r['status'] for r in rows)
+        assert sum(counts.values()) == len(rows)
+        lines += ['', f"## {batch['sourceId']} 产品发布候选核对", '',
+            f"[发现页面]({batch['url']})，读取于{batch['accessedAt']}。{batch['scope']}", '',
+            f"本批{len(rows)}条：{counts['linked']}条关联公司、{counts['existing-outside-cohort']}条关联范围外对照、{counts['pending-year']}条成立年待核、{counts['promotion']}条推广活动。完整来源覆盖标记：{'已完成' if batch['complete'] else '未完成'}。产品任务的初分类不计入主公司表数量，只有已关联的公司记录进入对应公司明细。候选与缺项随研究版本保存在文档站同一SQLite的研究元数据中。", '',
+            '| 发布卡片 | 产品任务初分 | 核对状态 | 关联公司 | 限制 |', '| --- | --- | --- | --- | --- |']
+        for row in rows:
+            assert row['categoryId'] in categories
+            assert row['status'] in statuses
+            name = f"[{row['name']}]({row['url']})" if row['url'] else row['name']
+            company = '—'
+            if row.get('companyId'):
+                assert row['companyId'] in companies
+                c = companies[row['companyId']]
+                company = f"[{c['name']}]({BASE}?company={c['id']}#research-company-detail)"
+            lines.append(f"| {name} | {categories[row['categoryId']]} | {statuses[row['status']]} | {company} | {row['note']} |")
+        lines += ['', '产品页可读只表示有可访问的资料；本批未将所有产品页完成公司、技术或财务深查。HTTP直接采集返回403，因此不声称取得底层全量列表；后续公开档案与未读页面继续保留缺项。', '']
+    return lines
+
+
 def render():
     cov = DATA['coverage']
     companies = DATA['companies']
@@ -125,6 +162,7 @@ def render():
     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 += source_register()
+    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。', '',