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, 1199);
+  assert.equal(research.companies.length, 1202);
   assert.equal(research.categories.length, 11);
-  assert.equal(research.evidence.length, 4673);
+  assert.equal(research.evidence.length, 4689);
   assert.equal(research.observations.length, 453);
   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, 1199);
-    assert.equal(initial.evidence.length, 4673);
+    assert.equal(initial.companies.length, 1202);
+    assert.equal(initial.evidence.length, 4689);
     assert.equal(initial.observations.length, 453);
     const businessReviews = initial.reviews.filter((review) => review.type === businessModelReviewType);
     assert.equal(businessReviews.length, 4);
@@ -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, 216);
-  assert.equal(snapshot.reviews.filter((r) => r.scope === "dataset").length, 144);
-  assert.equal(snapshot.reviews.filter((r) => r.scope === "excluded-candidate").length, 46);
+  assert.equal(snapshot.reviews.filter((r) => r.scope === "companies").length, 219);
+  assert.equal(snapshot.reviews.filter((r) => r.scope === "dataset").length, 145);
+  assert.equal(snapshot.reviews.filter((r) => r.scope === "excluded-candidate").length, 47);
   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), 1199);
+  assert.equal(summary.reduce((n, c) => n + c.count, 0), 1202);
   assert.equal(summary.reduce((n, c) => n + c.self, 0), 58);
   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), 1120);
+  assert.equal(summary.reduce((n, c) => n + c.unknown, 0), 1123);
   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, 184);
+  assert.equal(snapshot.companies.filter((c) => c.technicalReview).length, 187);
   assert.equal(snapshot.companies.filter((c) => c.technicalReview?.level === "public-artifact").length, 26);
   assert.equal(snapshot.companies.filter((c) => c.technicalReview?.level === "independent-test").length, 1);
   assert.equal(snapshot.companies.find((c) => c.id === "AI051")?.revenueStatus, "unknown");
@@ -444,7 +444,7 @@ test("platform samples exclude stale data and keep ARR, estimates and collection
   const invalid = structuredClone(snapshot);
   invalid.observations = invalid.observations.filter((o) => o.company === "MR001" && o.metric === "mrr");
   const first = invalid.observations[0];
-  invalid.observations.push({ ...first, id: "future", observedAt: "2026-11-01", value: 999999 });
+  invalid.observations.push({ ...first, id: "future", observedAt: "2026-11-02", value: 999999 });
   invalid.observations.push({ ...first, id: "bad-date", observedAt: "2026-02-30", value: 999999 });
   invalid.observations.push({ ...first, id: "currency", unit: "EUR", value: 999999 });
   invalid.observations.push({ ...first, id: "older", observedAt: "2026-10-28", value: 1 });
@@ -490,6 +490,20 @@ test("product launch candidates preserve unresolved years and many launches per
   assert.throws(() => validateResearch(snapshot), /research candidate/);
 });
 
+test("the public SR007 roster preserves unique entries and Alven's older operator conflict", () => {
+  const snapshot = seed as ResearchSnapshot;
+  const batch = snapshot.candidateBatches!.find((item) => item.id === "SR007-public-roster-2026-1")!;
+  assert.equal(batch.complete, false, "one public default cohort is not all source coverage");
+  assert.equal(batch.records.length, 79);
+  assert.equal(new Set(batch.records.map((row) => row.url)).size, 79);
+  const alven = batch.records.find((row) => row.name === "Alven")!;
+  assert.equal(alven.status, "pending-year");
+  assert.equal(alven.companyId, undefined);
+  assert.ok(alven.evidenceIds?.includes("SR007R-ALVEN-REG"));
+  assert.ok(!snapshot.observations.some((item) => item.evidence.startsWith("SR007R-")),
+    "roster claims, deployment plans and per-unit prices are not new financial observations");
+});
+
 test("annual launch archives exclude older companies only with evidence and reuse existing records", () => {
   const snapshot = structuredClone(seed) as ResearchSnapshot;
   const batch = snapshot.candidateBatches!.find((b) => b.id === "PH-2025-visible-1")!;
@@ -517,7 +531,7 @@ 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, 130);
+  assert.equal(snapshot.candidateBatches!.flatMap((b) => b.records).filter((r) => r.status === "pending-year").length, 189);
 });
 
 test("product pivots and founder histories do not become new company years or current revenue", () => {

content/research/ai-companies.sources.json

@@ -1,5 +1,5 @@
 {
-  "version": "2026-11-01-source-accounting-1",
+  "version": "2026-11-01-sr007-public-roster-1",
   "scopeConfirmedAt": "2026-10-30",
   "acceptance": "以确认的公开来源清单为边界，逐条核对并标明缺项。",
   "provenance": "S01—S12恢复自已提交用户的《AI公司研究_来源与分类模板》来源清单；S13—S16单列后续已使用的补充证据渠道，不将使用次数当作全量覆盖。",
@@ -3040,9 +3040,22 @@
         "speedrun.a16z.com"
       ],
       "initialAccess": "见具体证据访问记录",
-      "boundary": "投资机构公司介绍定向样本，收入数字仍多来自公司。 新增8项2026名录定向核查并登记候选台账（7项SR007、Bota SR006），不等全部批次或两年目录。 另登记8项2025年定向公司（SR005一项、SR006五项、SR007两项）；动态目录静态仅外壳、浏览器超时，不认定全量。 另从2026竞赛名单追Bounty的SR007原始档案；GMV及经常客户承诺非自身已实现ARR，非完整目录。",
-      "nextCheck": "核币种、相对时间及管线/履历；未读取的页面保持缺项。 区分live ARR、signed/contracted ARR、固定法律承诺费用、管线、目标交易量及客户收益；Nexor原$不自动当USD，财务日历截至日和合同底表留缺。 补Hotbox两个ARR时点、OneGC试点包含关系及律所/平台收入拆分、Omi等待名单付费转化、DRS应用与合并口径、Cedar签约履行和Loops可读官网。",
-      "limitation": "来源可读不等于声明已独立验证。"
+      "boundary": "原有投资方公司定向个案和2025/2026补查保留。2026-11-01普通公开HTML内嵌载荷明确默认SR007的79条，逐一登记20关联（17复用、3新增）/59主体年份待核；75普通UUID链接与79载荷分列。此前文本仅外壳不等无名单，本次不执行站点脚本或读取私有接口。SR005/SR006公开参数仍返回默认SR007，其他批次/两年目录未穷尽。投资方和公司宣传收入非独立验证，Bounty部署/承诺及Alven当前部署金额不作已实现ARR。",
+      "nextCheck": "先补SR007剩余59条独立档案、官网及成立/主体与AI主营；同时建立其他批次的公开边界，不能按请求参数认读取成功。Alven的ROOMSS2024/品牌2025与海外主体沿革、各公司币种/日历财务日/实际合同和人工、设备、模型成本待核；原Nexor/Hotbox/OneGC/Omi/DRS/Cedar/Loops缺项继续保留。",
+      "limitation": "来源可读不等于声明已独立验证。",
+      "rosterAudit": {
+        "url": "https://speedrun.a16z.com/companies",
+        "accessedAt": "2026-11-01",
+        "method": "匿名普通HTML的__NEXT_DATA__中pageProps.companies；只解析JSON不执行JS",
+        "defaultCohort": "SR007",
+        "reportedCount": 79,
+        "recordCount": 79,
+        "next": null,
+        "previous": null,
+        "htmlUuidProfileLinks": 75,
+        "htmlSha256": "32a8e1d9e6c9a2581077aed058767c46f03cdffdab9b0086ee9bd0c86094e152",
+        "candidateBatchId": "SR007-public-roster-2026-1"
+      }
     },
     {
       "id": "S15",

content/research/ai-income-analysis.json

@@ -1,6 +1,6 @@
 {
-  "sourceVersion": "2026-11-01-source-accounting-1",
-  "asOf": "2026-10-31",
+  "sourceVersion": "2026-11-01-sr007-public-roster-1",
+  "asOf": "2026-11-01",
   "metric": "platform-mrr-usd",
   "sampleUnit": "product-or-business",
   "note": "独立Python复算参考值，仅验证样本计算；不是行业估计或财务审计。",

scripts/audit-ai-research.py

@@ -42,6 +42,13 @@ def source_register():
         assert source['boundary'] and source['nextCheck']
         if source['id'] == 'S01':
             assert source.get('coverageSummary') == yc_coverage_summary(), 'YC source summary is stale'
+        if source['id'] == 'S14' and source.get('rosterAudit'):
+            roster = source['rosterAudit']
+            batch = next(batch for batch in DATA['candidateBatches'] if batch['id'] == roster['candidateBatchId'])
+            assert batch['sourceId'] == 'S14' and not batch['complete']
+            assert roster['defaultCohort'] == 'SR007' and roster['next'] is None
+            assert len(batch['records']) == roster['recordCount'] == roster['reportedCount']
+            assert len({row['url'] for row in batch['records']}) == roster['recordCount']
         if source['url']:
             assert urlsplit(source['url']).scheme in {'http', 'https'} and urlsplit(source['url']).netloc
         for host in source['hosts']: