Audit 226 Speedrun profiles and classify six current AI businesses

2026-11-01 02:16:52 +08:00
parent 51d6364ddd
commit d631be2617
6 changed files with 6086 additions and 937 deletions
@@ -70,6 +70,29 @@ def source_register():
                assert proof['url'] == audit['url'] and proof['companyId'] is None
                profile_urls.extend(row['url'] for row in batch['records'])
            assert len(profile_urls) == len(set(profile_urls)), 'duplicate profiles across public cohorts'
+        if source['id'] == 'S14' and source.get('profileAudit'):
+            audit = source['profileAudit']
+            entries = audit['records']
+            candidates = {row['id']: row for b in DATA['candidateBatches'] for row in b['records']}
+            evidence_by_id = {row['id']: row for row in DATA['evidence']}
+            assert len(entries) == audit['recordCount'] == audit['readable']
+            assert audit['failed'] == 0 and len({e['candidateId'] for e in entries}) == len(entries)
+            years = Counter(str(e['foundedYear']) for e in entries)
+            assert dict(years) == audit['yearCounts']
+            for entry in entries:
+                row = candidates[entry['candidateId']]
+                proof = evidence_by_id[entry['evidenceId']]
+                assert row['profileStatus'] == 'readable' and proof['url'] == row['url']
+                assert entry['evidenceId'] in row['evidenceIds']
+                assert isinstance(entry['foundedYear'], int) and 1800 <= entry['foundedYear'] <= int(DATA['asOf'][:4])
+                assert isinstance(entry['teamSize'], int) and entry['teamSize'] >= 0
+                assert len(entry['htmlSha256']) == 64 and all(c in '0123456789abcdef' for c in entry['htmlSha256'])
+                if entry['foundedYear'] not in [2025, 2026]:
+                    assert row['status'] == 'outside-cohort' and not row.get('companyId')
+            assert sum(e['foundedYear'] not in [2025, 2026] for e in entries) == audit['outsideTargetYears']
+            assert sum(e['foundedYear'] in [2025, 2026] for e in entries) == audit['targetYearSelfReports']
+            assert sum(candidates[e['candidateId']]['status'] == 'linked' for e in entries) == audit['newLinkedCompanies']
+            assert sum(candidates[e['candidateId']]['status'] == 'pending-ai' for e in entries) == audit['pendingCurrentAIOrIdentity']
        if source['url']:
            assert urlsplit(source['url']).scheme in {'http', 'https'} and urlsplit(source['url']).netloc
        for host in source['hosts']: