Audit 226 Speedrun profiles and classify six current AI businesses

apps/docs/scripts/auth-cli.ts

@@ -182,9 +182,9 @@ async function main() {
   assert.equal(researchResponse.status, 200, "authenticated research API");
   assert.ok(researchResponse.headers.get("cache-control")?.includes("no-store"));
   const research = await researchResponse.json();
-  assert.equal(research.companies.length, 1253);
+  assert.equal(research.companies.length, 1259);
   assert.equal(research.categories.length, 11);
-  assert.equal(research.evidence.length, 4909);
+  assert.equal(research.evidence.length, 5144);
   assert.equal(research.observations.length, 491);
   assert.equal((await request("/api/research/ai-companies", { method: "POST", headers })).status, 405);
   const researchPage = await request("/docs/other-research/ai-company-research/overview", { headers });

apps/docs/tests/research.test.ts

@@ -123,8 +123,8 @@ test("research revisions share the authentication database and preserve replay l
     for (let i = 0; i < 20; i++) consumeCode(config, "invalid");
     assert.equal(consumeCode(config, "invalid"), "limited");
     const initial = readResearchSnapshot();
-    assert.equal(initial.companies.length, 1253);
-    assert.equal(initial.evidence.length, 4909);
+    assert.equal(initial.companies.length, 1259);
+    assert.equal(initial.evidence.length, 5144);
     assert.equal(initial.observations.length, 491);
     const businessReviews = initial.reviews.filter((review) => review.type === businessModelReviewType);
     assert.equal(businessReviews.length, 7);
@@ -169,9 +169,9 @@ test("research validation rejects broken evidence and unsafe source links", () =
 
 test("reviews link explicit companies without turning global or excluded cases into companies", () => {
   const snapshot = structuredClone(seed) as ResearchSnapshot;
-  assert.equal(snapshot.reviews.filter((r) => r.scope === "companies").length, 248);
-  assert.equal(snapshot.reviews.filter((r) => r.scope === "dataset").length, 149);
-  assert.equal(snapshot.reviews.filter((r) => r.scope === "excluded-candidate").length, 55);
+  assert.equal(snapshot.reviews.filter((r) => r.scope === "companies").length, 251);
+  assert.equal(snapshot.reviews.filter((r) => r.scope === "dataset").length, 150);
+  assert.equal(snapshot.reviews.filter((r) => r.scope === "excluded-candidate").length, 56);
   const review = snapshot.reviews.find((r) => r.id === "R4")!;
   assert.deepEqual(reviewCompanyIds(snapshot, review), ["AI007", "AI013", "AI021", "AI034"]);
   assert.deepEqual(reviewCompanyIds(snapshot, snapshot.reviews.find((r) => r.id === "CN-R-PSI")!), []);
@@ -190,11 +190,11 @@ test("reviews link explicit companies without turning global or excluded cases i
 test("disclosure counts exclude client income, biographies, targets and duplicate milestones", () => {
   const snapshot = seed as ResearchSnapshot;
   const summary = categorySummary(snapshot);
-  assert.equal(summary.reduce((n, c) => n + c.count, 0), 1253);
+  assert.equal(summary.reduce((n, c) => n + c.count, 0), 1259);
   assert.equal(summary.reduce((n, c) => n + c.self, 0), 63);
   assert.equal(summary.reduce((n, c) => n + c.estimate, 0), 2);
   assert.equal(summary.reduce((n, c) => n + c.platform, 0), 19);
-  assert.equal(summary.reduce((n, c) => n + c.unknown, 0), 1169);
+  assert.equal(summary.reduce((n, c) => n + c.unknown, 0), 1175);
   assert.equal(snapshot.companies.find((c) => c.name === "Rork")?.revenueStatus, "unknown");
   assert.equal(snapshot.companies.find((c) => c.name === "Result")?.revenueStatus, "unknown");
   assert.ok(snapshot.observations.filter((o) => o.selection === "signal").every((o) => o.scope === "公司整体"));
@@ -229,7 +229,7 @@ test("service run rates, legacy freight revenue and paid adoption do not become
 
 test("technical reviews keep accessible materials separate from tested capabilities", () => {
   const snapshot = structuredClone(seed) as ResearchSnapshot;
-  assert.equal(snapshot.companies.filter((c) => c.technicalReview).length, 244);
+  assert.equal(snapshot.companies.filter((c) => c.technicalReview).length, 250);
   assert.equal(snapshot.companies.filter((c) => c.technicalReview?.level === "public-artifact").length, 28);
   assert.equal(snapshot.companies.filter((c) => c.technicalReview?.level === "independent-test").length, 1);
   assert.equal(snapshot.companies.find((c) => c.id === "AI051")?.revenueStatus, "unknown");
@@ -644,12 +644,15 @@ test("public Speedrun cohort rosters preserve the finite boundary without invent
   assert.equal(new Set(rows.map((row) => row.url)).size, 321);
   const newlyRegistered = rosters.filter((batch) => !batch.id.startsWith("SR007-")).flatMap((batch) => batch.records);
   assert.equal(newlyRegistered.length, 242);
-  assert.equal(newlyRegistered.filter((row) => row.status === "pending-year").length, 226);
-  assert.equal(newlyRegistered.filter((row) => row.status === "linked").length, 9);
+  assert.equal(newlyRegistered.filter((row) => row.status === "pending-year").length, 0);
+  assert.equal(newlyRegistered.filter((row) => row.status === "linked").length, 15);
   assert.equal(newlyRegistered.filter((row) => row.status === "existing-outside-cohort").length, 1);
-  assert.equal(newlyRegistered.filter((row) => row.status === "outside-cohort").length, 6);
+  assert.equal(newlyRegistered.filter((row) => row.status === "outside-cohort").length, 144);
+  assert.equal(newlyRegistered.filter((row) => row.status === "pending-ai").length, 82,
+    "a known self-reported founding year does not by itself establish the current AI business");
+  assert.equal(newlyRegistered.filter((row) => row.profileStatus === "readable").length, 232);
   assert.ok(newlyRegistered.filter((row) => row.status === "outside-cohort").every((row) =>
-    row.profileStatus === "readable" && row.evidenceIds?.some((id) => id.startsWith("SRALL1-P-"))),
+    row.profileStatus === "readable" && row.evidenceIds?.some((id) => (id.startsWith("SRALL1-P-") || id.startsWith("SRPRO1-P-")))),
   "old founding years require independent profile evidence, not cohort age");
   const variants = newlyRegistered.filter((row) => row.name === "Variant");
   assert.equal(variants.length, 2);
@@ -657,6 +660,21 @@ test("public Speedrun cohort rosters preserve the finite boundary without invent
   assert.equal(variants.filter((row) => row.companyId === "AI066").length, 1);
   assert.ok(!snapshot.observations.some((row) => row.evidence.startsWith("SRALL1-")),
     "roster discovery and outside-cohort claims do not create financial observations");
+  const profiles = snapshot.evidence.filter((row) => row.id.startsWith("SRPRO1-P-"));
+  assert.equal(profiles.length, 226);
+  for (const proof of profiles) {
+    const candidate = newlyRegistered.find((row) => row.id === proof.id.slice("SRPRO1-P-".length))!;
+    assert.equal(candidate.url, proof.url);
+    assert.ok(candidate.evidenceIds?.includes(proof.id));
+  }
+  for (const id of ["AI162", "AI163", "AI164", "AI165", "AI166", "AI167"]) {
+    const company = snapshot.companies.find((row) => row.id === id)!;
+    assert.equal(company.year, 2025);
+    assert.equal(company.revenueStatus, "unknown");
+    assert.equal(company.technicalReview!.level, "description");
+  }
+  assert.ok(!snapshot.observations.some((row) => row.evidence.startsWith("SRPRO1-")),
+    "future GPU capacity, free trials, customer savings and unread financial claims are not realized revenue");
 });
 
 test("annual launch archives exclude older companies only with evidence and reuse existing records", () => {
@@ -686,7 +704,7 @@ test("unreconciled directory financials remain source reviews instead of income
   assert.ok(review.evidenceIds.includes("PH-TANA-DR"));
   assert.equal(reviewCompanyIds(snapshot, review).length, 0);
   assert.ok(!snapshot.observations.some((o) => o.evidence === "PH-TANA-DR"));
-  assert.equal(snapshot.candidateBatches!.flatMap((b) => b.records).filter((r) => r.status === "pending-year").length, 357);
+  assert.equal(snapshot.candidateBatches!.flatMap((b) => b.records).filter((r) => r.status === "pending-year").length, 131);
 });
 
 test("product pivots and founder histories do not become new company years or current revenue", () => {

content/research/ai-income-analysis.json

@@ -1,5 +1,5 @@
 {
-  "sourceVersion": "2026-11-01-sr-public-rosters-1",
+  "sourceVersion": "2026-11-01-sr-profile-audit-1",
   "asOf": "2026-11-01",
   "metric": "platform-mrr-usd",
   "sampleUnit": "product-or-business",

scripts/audit-ai-research.py

@@ -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']: