Add Endor object model figure source

Reviewed-on: #47

apps/docs/scripts/auth-cli.ts

@@ -182,10 +182,10 @@ 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, 1196);
+  assert.equal(research.companies.length, 1312);
   assert.equal(research.categories.length, 11);
-  assert.equal(research.evidence.length, 4600);
-  assert.equal(research.observations.length, 453);
+  assert.equal(research.evidence.length, 5354);
+  assert.equal(research.observations.length, 495);
   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 });
   assert.equal(researchPage.status, 200);

apps/docs/src/components/AICompanyResearch.tsx

@@ -2,6 +2,8 @@ import { useEffect, useMemo, useRef, useState } from "react";
 import { useRouter } from "next/router";
 import IncomeDistribution from "./IncomeDistribution";
 import ArrDisclosures from "./ArrDisclosures";
+import BusinessModelAssessment from "./BusinessModelAssessment";
+import ResearchCandidates from "./ResearchCandidates";
 import {
   categorySummary, evidenceUrl, technicalReviewLabels, reviewCompanyIds, type ResearchEvidence, type ResearchReview, type ResearchSnapshot,
 } from "@/lib/ai-research";
@@ -56,7 +58,7 @@ export default function AICompanyResearch() {
     : router.isReady && typeof linkedCompany === "string" && data?.companies.some((c) => c.id === linkedCompany)
       ? linkedCompany : null;
   function setSelected(id: string | null) { setSelection({ route: router.asPath, id }); }
-  const [tab, setTab] = useState<"companies" | "revenue" | "sources" | "reviews">("companies");
+  const [tab, setTab] = useState<"companies" | "candidates" | "revenue" | "models" | "sources" | "reviews">("companies");
   const companySection = useRef<HTMLElement>(null);
   const detailSection = useRef<HTMLElement>(null);
   useEffect(() => {
@@ -128,7 +130,7 @@ export default function AICompanyResearch() {
     <section ref={companySection} className="research-section" aria-labelledby="research-records-title">
       <h2 id="research-records-title">研究数据</h2>
       <div className="research-tabs" role="group" aria-label="研究数据视图">
-        {([['companies','公司与产品'],['revenue','收入观测'],['sources','原始证据'],['reviews','核查记录']] as const).map(([id,label]) =>
+        {([['companies','公司与产品'],['candidates','候选与缺项'],['revenue','收入观测'],['models','商业模式初评'],['sources','原始证据'],['reviews','核查记录']] as const).map(([id,label]) =>
           <button key={id} aria-pressed={tab === id} onClick={() => setTab(id)}>{label}</button>)}
       </div>
       {tab === "companies" && <>
@@ -153,6 +155,8 @@ export default function AICompanyResearch() {
         {!filtered.length && <p className="research-message">没有匹配公司，请调整筛选条件。</p>}
         {filtered.length > pageSize && <nav className="research-pagination" aria-label="公司数据分页"><button disabled={page === 0} onClick={() => setPage((n) => n - 1)}>上一页</button><span>{page + 1} / {Math.ceil(filtered.length / pageSize)}</span><button disabled={(page + 1) * pageSize >= filtered.length} onClick={() => setPage((n) => n + 1)}>下一页</button></nav>}
       </>}
+      {tab === "models" && <BusinessModelAssessment data={data} onSelect={setSelected} onChooseCategory={chooseCategory} />}
+      {tab === "candidates" && <ResearchCandidates data={data} onSelect={setSelected} onChooseCategory={chooseCategory} />}
       {tab === "revenue" && <>
         <IncomeDistribution data={data} onSelect={setSelected} />
         <ArrDisclosures data={data} onSelect={setSelected} />

apps/docs/src/components/ArrDisclosures.tsx

@@ -1,29 +1,40 @@
 import { useState } from "react";
 import { evidenceUrl, type ResearchSnapshot } from "@/lib/ai-research";
-import { arrDisclosureCoverage, arrDisclosures } from "@/lib/research-statistics";
+import { arrDisclosureCoverage, arrDisclosures, arrFieldGaps, type ArrFieldGap } from "@/lib/research-statistics";
 
 const labels: Record<string, string> = {
   signal: "企业或当事方披露", estimate: "第三方估算",
   historical: "历史披露", "historical-estimate": "历史估算",
 };
+const gapLabels: Record<ArrFieldGap, string> = {
+  date: "缺有效财务截至日", currency: "USD 未确认（含其他币种）",
+  amount: "下界、近似或非精确金额", estimate: "第三方估算",
+};
 
 export default function ArrDisclosures({ data, onSelect }: { data: ResearchSnapshot; onSelect: (id: string) => void }) {
   const [category, setCategory] = useState("");
   const [year, setYear] = useState("");
-  const rows = arrDisclosures(data, { category, foundedYear: year ? Number(year) : undefined });
+  const [gap, setGap] = useState<ArrFieldGap | "">("");
+  const claims = arrDisclosures(data, { category, foundedYear: year ? Number(year) : undefined });
+  const rows = claims.filter(({ observation }) => !gap || arrFieldGaps(observation, data.asOf).includes(gap));
+  const gapCounts = (Object.keys(gapLabels) as ArrFieldGap[]).map((id) => ({
+    id, count: claims.filter(({ observation }) => arrFieldGaps(observation, data.asOf).includes(id)).length,
+  }));
+  const completeFields = claims.filter(({ observation }) => !arrFieldGaps(observation, data.asOf).length).length;
   const coverage = arrDisclosureCoverage(data, year ? Number(year) : undefined);
-  const companies = new Set(rows.map((row) => row.company.id));
+  const companies = new Set(claims.map((row) => row.company.id));
   const categories = new Map(data.categories.map((item) => [item.id, item.name]));
   const evidence = new Map(data.evidence.map((item) => [item.id, item]));
   return <section aria-label="ARR披露分类表">
     <h3>2025—2026 年成立公司的 ARR 披露</h3>
-    <p className="research-notice">这是跨时点证据表，共 {companies.size} 家公司、{rows.length} 条记录；同一公司的历史里程碑逐条保留，不能相加或视为独立公司。ARR 标签沿用原始披露，未证明经常性收入定义或审计状态；不纳入 MRR 图表，不计算同期行业均值或造假概率。仅收录明确标注的 ARR；定义冲突、目标、承诺、客户和前雇主收入排除，缺失不作零。</p>
+    <p className="research-notice">这是跨时点证据表，共 {companies.size} 家公司、{claims.length} 条记录；同一公司的历史里程碑逐条保留，不能相加或视为独立公司。ARR 标签沿用原始披露，未证明经常性收入定义或审计状态；不纳入 MRR 图表，不计算同期行业均值或造假概率。仅收录明确标注的 ARR；定义冲突、目标、承诺、客户和前雇主收入排除，缺失不作零。</p>
     <div className="research-filters">
       <label>业务分类<select value={category} onChange={(event) => setCategory(event.target.value)}><option value="">全部分类</option>{data.categories.map((item) => <option key={item.id} value={item.id}>{item.name}</option>)}</select></label>
       <label>成立年份<select value={year} onChange={(event) => setYear(event.target.value)}><option value="">2025 与 2026</option><option value="2025">2025</option><option value="2026">2026</option></select></label>
+      <label>补证项目<select value={gap} onChange={(event) => setGap(event.target.value as ArrFieldGap | "")}><option value="">全部记录</option>{gapCounts.map((item) => <option key={item.id} value={item.id}>{gapLabels[item.id]}（{item.count} 条）</option>)}</select></label>
     </div>
     <div className="research-table-wrap"><table>
-      <caption>ARR 披露覆盖：按所选成立年份、每家公司计一次。点击分类筛选下方证据表。</caption>
+      <caption>ARR 披露覆盖：按公司当前分类及所选成立年份、每家公司计一次。点击分类筛选下方证据表。</caption>
       <thead><tr><th>业务分类</th><th>已采集公司</th><th>企业或当事方披露</th><th>仅第三方估算</th><th>缺少 ARR</th><th>披露覆盖率</th></tr></thead>
       <tbody>{coverage.filter((item) => item.companies > 0).map((item) => <tr key={item.id}>
         <td><button onClick={() => setCategory(item.id)} aria-pressed={category === item.id}>{item.name}</button></td>
@@ -31,10 +42,16 @@ export default function ArrDisclosures({ data, onSelect }: { data: ResearchSnaps
         <td>{new Intl.NumberFormat("zh-CN", { style: "percent", maximumFractionDigits: 1 }).format(item.disclosed / item.companies)}</td>
       </tr>)}</tbody>
     </table></div>
-    <p className="research-muted">分母含仅有目录资料的公司，覆盖率反映本次采集深度，不代表行业披露率。企业披露含历史里程碑，同一公司兼有披露和估算时归企业披露；缺少 ARR 的公司仍可能有其他收入。披露时点、币种与合同定义未对齐，不能将已披露少数公司的均值外推至整个分类，也不能由离散性判断财务造假。</p>
+    <p className="research-muted">分母含仅有目录资料的公司，覆盖率反映本次采集深度，不代表行业披露率。分类及收费模式采用公司当前资料；公司转向或同时经营多个产品时，历史 ARR 未必属于当前业务，需打开公司核对产品、主体与期间，不能据当前分类重归历史收入。企业披露含历史里程碑，同一公司兼有披露和估算时归企业披露；缺少 ARR 的公司仍可能有其他收入。披露时点、币种与合同定义未对齐，不能将已披露少数公司的均值外推至整个分类，也不能由离散性判断财务造假。</p>
+    <aside className="research-notice" aria-label="ARR比较前的补证检查">
+      <strong>ARR 比较前的补证检查</strong>
+      <p>当前分类及成立年下有 {claims.length} 条披露，{completeFields} 条同时具有有效日期、明确 USD、精确金额且不是第三方估算。补证筛选后显示 {rows.length} 条。</p>
+      <div className="income-options">{gapCounts.map((item) => <button key={item.id} aria-pressed={gap === item.id} onClick={() => setGap(gap === item.id ? "" : item.id)}>{gapLabels[item.id]}：{item.count}</button>)}</div>
+      <p>各项可重叠，不能相加为独立公司数。日期必须是经营指标截至日，网页访问、发布或更新时间不能代替；其他币种保留原值，不擅自换算。基础字段齐全也不证明可比，还需对齐收入定义、业务期间、收费模式、主体与独立验证；这些缺项不作为造假判定。</p>
+    </aside>
     <div className="research-table-wrap"><table>
       <caption>金额保留原币种、下界和估算身份；日期栏保留业务截至日缺项</caption>
-      <thead><tr><th>公司 / 分类</th><th>收费与交付模式</th><th>原始 ARR 声明</th><th>时点</th><th>身份 / 限制</th><th>证据</th></tr></thead>
+      <thead><tr><th>公司 / 当前分类</th><th>当前收费与交付模式</th><th>原始 ARR 声明</th><th>时点</th><th>身份 / 限制</th><th>证据</th></tr></thead>
       <tbody>{rows.map(({ company, observation: item }) => {
         const source = evidence.get(item.evidence);
         const url = source && evidenceUrl(source.url);
@@ -42,11 +59,11 @@ export default function ArrDisclosures({ data, onSelect }: { data: ResearchSnaps
           <td><button onClick={() => onSelect(company.id)}>{company.name}</button><small>{categories.get(company.cat)} · {company.year}</small></td>
           <td>{company.businessModel ?? company.price}</td>
           <td>{item.bound !== "=" && item.bound}{new Intl.NumberFormat("zh-CN", { maximumFractionDigits: 2 }).format(item.value)} {item.unit}<small>{item.kind}</small></td>
-          <td>{item.timing}</td><td>{labels[item.selection]}<small>{item.reason}</small></td>
+          <td>{item.timing}</td><td>{labels[item.selection]}<small>{item.reason}</small><small>{arrFieldGaps(item, data.asOf).map((id) => gapLabels[id]).join("；") || "基础字段齐全；定义、期间与主体仍须核实"}</small></td>
           <td>{url ? <a href={url} target="_blank" rel="noopener noreferrer">{item.evidence} ↗</a> : item.evidence}</td>
         </tr>;
       })}</tbody>
     </table></div>
-    {!rows.length && <p>当前筛选没有符合条件的已记录 ARR 声明；不代表这些公司收入为零。</p>}
+    {!rows.length && <p>当前分类、成立年与补证筛选没有符合条件的已记录 ARR 声明；不代表这些公司收入为零。</p>}
   </section>;
 }

apps/docs/src/components/BusinessModelAssessment.tsx

@@ -0,0 +1,32 @@
+import { businessModelReviewType, evidenceUrl, reviewCompanyIds, type ResearchSnapshot } from "@/lib/ai-research";
+
+export default function BusinessModelAssessment({ data, onSelect, onChooseCategory }: {
+  data: ResearchSnapshot; onSelect: (id: string) => void; onChooseCategory: (id: string) => void;
+}) {
+  const reviews = data.reviews.filter((review) => review.type === businessModelReviewType && review.scope === "companies");
+  const evidence = new Map(data.evidence.map((item) => [item.id, item]));
+  return <section aria-labelledby="research-models-title">
+    <h3 id="research-models-title">商业模式初评</h3>
+    <p>从已核个案提炼收费方式、成本约束与下一步验证条件。已知事实与研究判断分列；同一种收费方式可以跨业务分类，以下个案不能代表整个行业。</p>
+    <p className="research-muted">这是基于当前证据的初步评估，不是收入预测或盈利排名。判断能否用于我们的业务，还需用实际客户任务、付费留存与交付成本验证；ARR 或平台 MRR 单独不能证明利润。</p>
+    {reviews.length ? <div className="research-table-wrap"><table>
+      <caption>收费模式与业务分类、公司明细及原始证据相互关联</caption>
+      <thead><tr><th scope="col">模式 / 业务分类</th><th scope="col">已核事实</th><th scope="col">初步判断 / 验证条件</th><th scope="col">参考个案与证据</th></tr></thead>
+      <tbody>{reviews.map((review) => {
+        const companyIds = new Set(reviewCompanyIds(data, review));
+        const companies = data.companies.filter((company) => companyIds.has(company.id));
+        const categories = data.categories.filter((category) => companies.some((company) => company.cat === category.id));
+        return <tr key={review.id}>
+          <td><strong>{review.company}</strong><div>{categories.map((category) => <button key={category.id} onClick={() => onChooseCategory(category.id)}>{category.name}</button>)}</div></td>
+          <td>{review.summary}</td><td>{review.handling}</td>
+          <td><div>{companies.map((company) => <button key={company.id} className="research-company-name" onClick={() => onSelect(company.id)}>{company.name}</button>)}</div>
+            <div>{review.evidenceIds.map((id) => {
+              const item = evidence.get(id); const url = item && evidenceUrl(item.url);
+              return item && url ? <p key={id}><a href={url} target="_blank" rel="noopener noreferrer">{item.title} ↗</a></p> : null;
+            })}</div>
+          </td>
+        </tr>;
+      })}</tbody>
+    </table></div> : <p>当前数据版本尚未记录商业模式初评。</p>}
+  </section>;
+}

apps/docs/src/components/ResearchCandidates.tsx

@@ -0,0 +1,75 @@
+import { useMemo, useState } from "react";
+import { evidenceUrl, type ResearchCandidateBatch, type ResearchSnapshot } from "@/lib/ai-research";
+
+type CandidateStatus = ResearchCandidateBatch["records"][number]["status"];
+const statusLabels: Record<CandidateStatus, string> = {
+  "pending-year": "成立年或主体待核", "pending-ai": "AI 主营待核", linked: "已关联公司",
+  "existing-outside-cohort": "已关联范围外对照", "outside-cohort": "范围外候选", promotion: "推广活动",
+};
+const pageSize = 20;
+const sourceNames: Record<string, string> = {
+  S01: "Y Combinator", S02: "TechCrunch AI", S04: "Product Hunt", S05: "Sacra",
+  S10: "机器之心", S11: "36氪", S13: "TrustMRR", S14: "a16z Speedrun",
+};
+const sourceLabel = (id: string) => `${id} · ${sourceNames[id] ?? "其他来源"}`;
+
+function SourceLink({ url, label }: { url: string | null; label: string }) {
+  const safe = url && evidenceUrl(url);
+  return safe ? <a href={safe} target="_blank" rel="noopener noreferrer">{label} ↗</a> : <span>{label}（链接未取得）</span>;
+}
+
+export default function ResearchCandidates({ data, onSelect, onChooseCategory }: {
+  data: ResearchSnapshot; onSelect: (id: string) => void; onChooseCategory: (id: string) => void;
+}) {
+  const [source, setSource] = useState("");
+  const [batchId, setBatchId] = useState("");
+  const [category, setCategory] = useState("");
+  const [status, setStatus] = useState<CandidateStatus | "pending" | "">("pending");
+  const [query, setQuery] = useState("");
+  const [page, setPage] = useState(0);
+  const all = useMemo(() => (data.candidateBatches ?? []).flatMap((batch) => batch.records.map((record) => ({ batch, record }))), [data.candidateBatches]);
+  const sources = [...new Set(all.map(({ batch }) => batch.sourceId))].sort();
+  const batches = (data.candidateBatches ?? []).filter((batch) => !source || batch.sourceId === source);
+  const matched = all.filter(({ batch, record }) => (!source || batch.sourceId === source)
+    && (!batchId || batch.id === batchId) && (!category || record.categoryId === category)
+    && `${record.name} ${record.id} ${record.note}`.toLocaleLowerCase().includes(query.trim().toLocaleLowerCase()));
+  const pending = (value: CandidateStatus) => value === "pending-year" || value === "pending-ai";
+  const rows = matched.filter(({ record }) => !status || (status === "pending" ? pending(record.status) : record.status === status));
+  const companies = new Map(data.companies.map((company) => [company.id, company]));
+  const evidence = new Map(data.evidence.map((item) => [item.id, item]));
+  const categories = new Map(data.categories.map((item) => [item.id, item.name]));
+  return <section aria-labelledby="research-candidates-title">
+    <h3 id="research-candidates-title">候选与缺项</h3>
+    <p>展示已登记的有限来源批次及后续核查。默认显示成立年、主体或 AI 主营待核的条目；待核不是确认排除，也不计入公司表。每行是一次发现位置，同一公司或产品可以重复出现。</p>
+    <p className="research-muted">候选初分类与公司表数量分开，来源批次不等全年或全站名单。原始发现范围及后续结论见每行说明；暂无收入资料不作零，推广活动也不算公司。</p>
+    <div className="research-filters">
+      <label className="research-query">搜索候选<input type="search" value={query} placeholder="名称、编号或核查说明" onChange={(event) => { setQuery(event.target.value); setPage(0); }} /></label>
+      <label>发现来源<select value={source} onChange={(event) => { setSource(event.target.value); setBatchId(""); setPage(0); }}><option value="">全部已登记来源</option>{sources.map((id) => <option key={id} value={id}>{sourceLabel(id)}</option>)}</select></label>
+      <label>发现批次<select value={batchId} onChange={(event) => { setBatchId(event.target.value); setPage(0); }}><option value="">全部批次</option>{batches.map((batch) => <option key={batch.id} value={batch.id}>{batch.id}</option>)}</select></label>
+      <label>候选初分类<select value={category} onChange={(event) => { setCategory(event.target.value); setPage(0); }}><option value="">全部分类</option>{data.categories.map((item) => <option key={item.id} value={item.id}>{item.name}</option>)}</select></label>
+      <label>核查状态<select value={status} onChange={(event) => { setStatus(event.target.value as typeof status); setPage(0); }}>
+        <option value="">全部状态（{matched.length}）</option><option value="pending">全部待核（{matched.filter(({ record }) => pending(record.status)).length}）</option>
+        {Object.entries(statusLabels).map(([id, label]) => <option key={id} value={id}>{label}（{matched.filter(({ record }) => record.status === id).length}）</option>)}
+      </select></label>
+    </div>
+    <p role="status">{rows.length} 个发现位置匹配；不是独立公司数。</p>
+    <div className="research-table-wrap"><table>
+      <caption>有限来源候选与处理记录；选择关联公司查看主数据，原始证据直接链接来源</caption>
+      <thead><tr><th scope="col">候选</th><th scope="col">初分类 / 状态</th><th scope="col">来源及范围</th><th scope="col">核查结论 / 缺项</th><th scope="col">关联公司 / 证据</th></tr></thead>
+      <tbody>{rows.slice(page * pageSize, (page + 1) * pageSize).map(({ batch, record }) => {
+        const company = record.companyId && companies.get(record.companyId);
+        return <tr key={record.id}>
+          <td><SourceLink url={record.url} label={record.name} /><small>{record.id}</small></td>
+          <td><button onClick={() => onChooseCategory(record.categoryId)} aria-label={`查看${categories.get(record.categoryId)}分类内的公司`}>{categories.get(record.categoryId)}</button><small>{statusLabels[record.status]}</small></td>
+          <td><SourceLink url={batch.url} label={sourceLabel(batch.sourceId)} /><small>{batch.id} · 读取 {batch.accessedAt}</small><details><summary>发现批次范围</summary><p>{batch.scope}</p><p>{batch.complete ? "该批次标记已完成；不代表来源全站覆盖。" : "该批次仍保留覆盖缺项。"}</p></details></td>
+          <td>{record.note}</td>
+          <td>{company ? <button className="research-company-name" onClick={() => onSelect(company.id)}>{company.name}</button> : <small>尚未关联公司主记录</small>}
+            {record.evidenceIds?.map((id) => { const item = evidence.get(id); return item ? <p key={id}><SourceLink url={item.url} label={id} /></p> : null; })}
+          </td>
+        </tr>;
+      })}</tbody>
+    </table></div>
+    {!rows.length && <p>当前筛选没有已登记的候选记录；不代表该来源或分类没有公司。</p>}
+    {rows.length > pageSize && <nav className="research-pagination" aria-label="候选与缺项分页"><button disabled={page === 0} onClick={() => setPage((value) => value - 1)}>上一页</button><span>{page + 1} / {Math.ceil(rows.length / pageSize)}</span><button disabled={(page + 1) * pageSize >= rows.length} onClick={() => setPage((value) => value + 1)}>下一页</button></nav>}
+  </section>;
+}

apps/docs/src/lib/ai-research.ts

@@ -1,4 +1,5 @@
 export type ResearchCategory = { id: string; name: string; description: string };
+export const businessModelReviewType = "商业模式初评";
 export const technicalReviewLabels = {
   unreviewed: "技术证据尚未专项评审",
   description: "已读技术自述",

apps/docs/src/lib/research-statistics.ts

@@ -31,6 +31,20 @@ export function arrDisclosureCoverage(snapshot: ResearchSnapshot, foundedYear?:
       missing: companies.length - disclosed.size, records: claims.length };
   });
 }
+
+export type ArrFieldGap = "date" | "currency" | "amount" | "estimate";
+
+/** Prerequisites for inspecting exact, dated USD disclosures; never a comparability or audit verdict. */
+export function arrFieldGaps(observation: ResearchObservation, asOf: string): ArrFieldGap[] {
+  const gaps: ArrFieldGap[] = [];
+  const day = calendarDay(observation.observedAt);
+  const end = calendarDay(asOf);
+  if (day === null || end === null || day > end) gaps.push("date");
+  if (observation.unit !== "USD") gaps.push("currency");
+  if (observation.bound !== "=" || !Number.isFinite(observation.value) || observation.value < 0) gaps.push("amount");
+  if (["estimate", "historical-estimate"].includes(observation.selection)) gaps.push("estimate");
+  return gaps;
+}
 export type IncomeStats = {
   n: number; mean: number; median: number; min: number; max: number;
   sampleDeviation: number | null; cv: number | null; meanMedianRatio: number | null;

apps/docs/tests/research.test.ts

@@ -8,10 +8,29 @@ import coverageAudit from "../../../content/research/ai-companies.coverage.json"
 import incomeReference from "../../../content/research/ai-income-analysis.json";
 import { readResearchSnapshot } from "../src/lib/ai-research-store";
 import { openSiteDatabase } from "../src/lib/site-database";
-import { categorySummary, evidenceUrl, reviewCompanyIds, validateResearch, type ResearchSnapshot } from "../src/lib/ai-research";
+import { businessModelReviewType, categorySummary, evidenceUrl, reviewCompanyIds, validateResearch, type ResearchSnapshot } from "../src/lib/ai-research";
 import { consumeCode, initializeStore } from "../src/lib/auth-store";
 import { newAuthConfig } from "../src/lib/auth";
-import { arrDisclosureCoverage, arrDisclosures, compareIncomeGroups, describeIncome, groupIncome, platformIncomeSample } from "../src/lib/research-statistics";
+import { arrDisclosureCoverage, arrDisclosures, arrFieldGaps, compareIncomeGroups, describeIncome, groupIncome, platformIncomeSample } from "../src/lib/research-statistics";
+
+test("ARR field checks distinguish missing dates, other currencies, bounds and estimates", () => {
+  const observation = { ...seed.observations[0], metric: "arr", unit: "USD", value: 100,
+    bound: "=", selection: "signal", observedAt: "2026-10-30" } as ResearchSnapshot["observations"][number];
+  assert.deepEqual(arrFieldGaps(observation, "2026-10-31"), []);
+  for (const observedAt of [undefined, "2026-02-30", "2026-11-01"])
+    assert.deepEqual(arrFieldGaps({ ...observation, observedAt }, "2026-10-31"), ["date"]);
+  assert.deepEqual(arrFieldGaps({ ...observation, unit: "EUR" }, "2026-10-31"), ["currency"],
+    "known foreign currencies stay distinct without an invented USD conversion");
+  assert.deepEqual(arrFieldGaps({ ...observation, unit: "原文$，币种待核", bound: ">",
+    selection: "historical-estimate", observedAt: undefined }, "2026-10-31"), ["date", "currency", "amount", "estimate"]);
+  assert.deepEqual(arrFieldGaps({ ...observation, value: Number.NaN }, "2026-10-31"), ["amount"]);
+  assert.deepEqual(arrFieldGaps({ ...observation, value: -1 }, "2026-10-31"), ["amount"]);
+  assert.deepEqual(arrFieldGaps({ ...observation, value: 0 }, "2026-10-31"), [], "disclosed zero is a valid amount");
+  const rows = arrDisclosures(seed as ResearchSnapshot);
+  assert.ok(rows.length > 0);
+  assert.ok(rows.every(({ observation: claim }) => arrFieldGaps(claim, seed.asOf).length > 0),
+    "the current ledger cannot be described as a complete dated exact USD sample");
+});
 
 test("income interpretations compare sufficient samples within a provider and known billing model", () => {
   const snapshot = structuredClone(seed) as ResearchSnapshot;
@@ -73,7 +92,8 @@ test("ARR ledger preserves historical estimates without promoting targets, run r
   const ids = new Set(rows.map((row) => row.observation.id));
   for (const id of ["O064", "O065", "O066", "O069", "O070", "O071", "O046"])
     assert.ok(ids.has(id), `${id}: historical claims, estimates and unknown currencies remain visible`);
-  for (const id of ["O050", "O052", "O053", "O055", "SR-O-AI067-runrate", "ROCKET-O-arr", "AQ-O-RUNRATE"])
+  for (const id of ["O050", "O052", "O053", "O055", "SR-O-AI067-runrate", "ROCKET-O-arr", "AQ-O-RUNRATE",
+    "SRLEARN1-O-CLAIR-D2C", "SRLEARN1-O-CLAIR-B2B"])
     assert.ok(!ids.has(id), `${id}: excluded or ambiguous records cannot enter the ARR ledger`);
   assert.equal(rows.find((row) => row.observation.id === "O066")?.observation.selection, "historical-estimate");
   assert.equal(rows.find((row) => row.observation.id === "O046")?.observation.unit, "原文$，币种待核");
@@ -104,9 +124,14 @@ 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, 1196);
-    assert.equal(initial.evidence.length, 4600);
-    assert.equal(initial.observations.length, 453);
+    assert.equal(initial.companies.length, 1312);
+    assert.equal(initial.evidence.length, 5354);
+    assert.equal(initial.observations.length, 495);
+    const businessReviews = initial.reviews.filter((review) => review.type === businessModelReviewType);
+    assert.equal(businessReviews.length, 26);
+    assert.deepEqual(businessReviews, seed.reviews.filter((review) => review.type === businessModelReviewType)
+      .sort((a, b) => a.id.localeCompare(b.id)),
+      "business model assessments and company/evidence links persist in the shared database");
     assert.deepEqual(initial.candidateBatches, seed.candidateBatches, "candidate gaps persist in the same database metadata");
     assert.deepEqual(initial.directoryRechecks, seed.directoryRechecks, "follow-up classifications persist without rewriting the discovery audit");
     assert.deepEqual(readResearchSnapshot(), initial, "reopening does not duplicate records");
@@ -145,9 +170,9 @@ 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, 207);
-  assert.equal(snapshot.reviews.filter((r) => r.scope === "dataset").length, 139);
-  assert.equal(snapshot.reviews.filter((r) => r.scope === "excluded-candidate").length, 44);
+  assert.equal(snapshot.reviews.filter((r) => r.scope === "companies").length, 299);
+  assert.equal(snapshot.reviews.filter((r) => r.scope === "dataset").length, 159);
+  assert.equal(snapshot.reviews.filter((r) => r.scope === "excluded-candidate").length, 65);
   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")!), []);
@@ -166,11 +191,11 @@ 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), 1196);
-  assert.equal(summary.reduce((n, c) => n + c.self, 0), 58);
+  assert.equal(summary.reduce((n, c) => n + c.count, 0), 1312);
+  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), 1117);
+  assert.equal(summary.reduce((n, c) => n + c.unknown, 0), 1228);
   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"));
@@ -205,8 +230,8 @@ 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, 181);
-  assert.equal(snapshot.companies.filter((c) => c.technicalReview?.level === "public-artifact").length, 25);
+  assert.equal(snapshot.companies.filter((c) => c.technicalReview).length, 303);
+  assert.equal(snapshot.companies.filter((c) => c.technicalReview?.level === "public-artifact").length, 29);
   assert.equal(snapshot.companies.filter((c) => c.technicalReview?.level === "independent-test").length, 1);
   assert.equal(snapshot.companies.find((c) => c.id === "AI051")?.revenueStatus, "unknown");
   assert.match(snapshot.companies.find((c) => c.id === "AI051")!.technicalReview!.testScope!, /Sep 2026/);
@@ -279,9 +304,15 @@ test("ambiguous ARR claims retain currency, precision and attribution limits", (
   const portfolio = snapshot.observations.filter((o) => o.company === "AI100");
   assert.deepEqual(portfolio.filter((o) => o.selection === "signal").map((o) => o.id), ["SR25-O-DRS-PORTFOLIO"],
     "a product milestone must not be added to its company portfolio as another company");
-  assert.ok(snapshot.observations.filter((o) => o.id.startsWith("SR25-O-")).every((o) =>
-    o.unit !== "USD" && !o.metric && !o.observedAt && o.comparisonGroup === null),
+  const speedrun2025 = snapshot.observations.filter((o) => o.id.startsWith("SR25-O-"));
+  assert.ok(speedrun2025.every((o) =>
+    o.unit !== "USD" && !o.observedAt && o.comparisonGroup === null),
   "access dates and dollar symbols must not invent dated USD income samples");
+  assert.deepEqual(speedrun2025.filter((o) => o.metric).map((o) => [o.id, o.metric]).sort(),
+    [["SR25-O-DRS-PORTFOLIO", "arr"], ["SR25-O-LOOPS-ARR", "arr"]],
+    "explicit company ARR claims retain their metric without inferring currency or reporting dates");
+  assert.ok(platformIncomeSample(snapshot, { windowDays: null }).points.every((point) =>
+    !point.observation.id.startsWith("SR25-O-")), "undated ARR claims never enter platform MRR comparisons");
 });
 
 // Retractions and forecasts must stay visible for review without becoming revenue signals.
@@ -414,7 +445,7 @@ 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 });
@@ -460,6 +491,356 @@ 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");
+  const coherence = batch.records.find((row) => row.name === "Coherence Health")!;
+  assert.equal(coherence.status, "pending-ai", "a new coaching business still needs current AI delivery evidence");
+  assert.equal(coherence.companyId, undefined);
+  const followup = snapshot.observations.filter((item) => item.id.startsWith("SR007F2-"));
+  assert.equal(followup.length, 4);
+  assert.ok(followup.every((item) => ["excluded", "adoption"].includes(item.selection) && !item.metric && !item.observedAt));
+  assert.ok(!arrDisclosures(snapshot).some(({ observation }) => observation.id.startsWith("SR007F2-")),
+    "contracted ARR and pipeline are not live ARR disclosures");
+  const thirdFollowup = snapshot.observations.filter((item) => item.id.startsWith("SR007F3-"));
+  assert.equal(thirdFollowup.length, 6);
+  assert.equal(thirdFollowup.filter((item) => item.selection === "excluded").length, 3);
+  assert.equal(thirdFollowup.filter((item) => item.selection === "adoption").length, 3);
+  assert.ok(thirdFollowup.every((item) => !item.metric && !item.observedAt));
+  assert.ok(!arrDisclosures(snapshot).some(({ observation }) => observation.id.startsWith("SR007F3-")),
+    "projected ARR, connected customer assets and prospective contracts are not realized ARR");
+  assert.equal(snapshot.companies.find((item) => item.id === "AI121")!.cat, "C02",
+    "training data and environments are infrastructure rather than demonstrated foundation models");
+  const embrasure = snapshot.companies.find((item) => item.id === "AI122")!;
+  assert.equal(embrasure.technicalReview!.level, "public-artifact");
+  assert.ok(embrasure.technicalReview!.evidenceIds.includes("SR007F3-EMBRASURE-FLOW"),
+    "the public connector supports artifact availability, not independently reproduced warehouse performance");
+  for (const name of ["KIRA", "Leonidas", "Mecone", "PhotonSpear"]) {
+    const candidate = batch.records.find((row) => row.name === name)!;
+    assert.equal(candidate.status, "pending-ai",
+      "serving AI customers or using software controls is not evidence of an AI business");
+    assert.equal(candidate.companyId, undefined);
+  }
+  const maestroClaims = arrDisclosures(snapshot).filter(({ company }) => company.id === "AI130");
+  assert.equal(maestroClaims.length, 2, "keep the two original ARR milestones in the evidence ledger");
+  assert.ok(maestroClaims.every(({ observation }) => observation.selection === "historical" &&
+    arrFieldGaps(observation, snapshot.asOf).includes("date") &&
+    arrFieldGaps(observation, snapshot.asOf).includes("currency")));
+  const cumulative = snapshot.observations.find((item) => item.id === "SR007F4-O-MAESTRO-CUMULATIVE")!;
+  assert.equal(cumulative.selection, "historical");
+  assert.equal(cumulative.metric, undefined, "nine-month cumulative revenue cannot become ARR");
+  const contracted = snapshot.observations.find((item) => item.id === "SR007F4-O-HOID-CONTRACT")!;
+  assert.equal(contracted.selection, "excluded");
+  assert.equal(contracted.metric, undefined, "contracted run rate is not realized ARR");
+  const openwhispr = snapshot.companies.find((item) => item.id === "AI135")!;
+  assert.equal(openwhispr.technicalReview!.level, "public-artifact");
+  assert.ok(openwhispr.technicalReview!.evidenceIds.includes("SR007F5-OPENWHISPR-REPO"));
+  const voiceArr = arrDisclosures(snapshot).find(({ company }) => company.id === openwhispr.id)!.observation;
+  assert.equal(voiceArr.value, 120000);
+  assert.equal(voiceArr.bound, "≥");
+  assert.ok(arrFieldGaps(voiceArr, snapshot.asOf).includes("date"));
+  assert.ok(arrFieldGaps(voiceArr, snapshot.asOf).includes("currency"),
+    "current plan prices cannot supply the currency of an undated investor ARR claim");
+  const voiceUsers = snapshot.observations.find((item) => item.id === "SR007F5-O-OPENWHISPR-DAU")!;
+  assert.equal(voiceUsers.selection, "adoption", "daily active users are not paying subscribers");
+  assert.equal(voiceUsers.metric, undefined);
+  const salesLive = snapshot.observations.find((item) => item.id === "SR007F6-O-OTHELLO-LIVE")!;
+  assert.equal(salesLive.metric, "arr");
+  assert.equal(salesLive.value, 600000, "live ARR must not include contracted ARR or pipeline");
+  for (const suffix of ["CONTRACT", "PIPELINE"]) {
+    const prospective = snapshot.observations.find((item) => item.id === `SR007F6-O-OTHELLO-${suffix}`)!;
+    assert.equal(prospective.selection, "excluded");
+    assert.equal(prospective.metric, undefined);
+  }
+  const professionalService = snapshot.observations.find((item) => item.id === "SR007F6-O-PARCA-RUNRATE")!;
+  assert.equal(professionalService.metric, "annualized-revenue");
+  assert.equal(professionalService.selection, "historical");
+  assert.ok(!arrDisclosures(snapshot).some(({ observation }) => observation.id === professionalService.id),
+    "annualized professional-service revenue is not recurring subscription ARR");
+  assert.equal(snapshot.companies.find((item) => item.id === "AI137")!.technicalReview!.level, "description",
+    "a preliminary external ranking with unresolved methodology is not complete independent verification");
+  const contractFollowup = snapshot.observations.filter((item) => item.id.startsWith("SR007F7-"));
+  assert.equal(contractFollowup.filter((item) => item.selection === "excluded").length, 4);
+  assert.equal(contractFollowup.filter((item) => item.selection === "adoption").length, 1);
+  assert.ok(contractFollowup.every((item) => !item.metric && !item.observedAt));
+  assert.ok(!arrDisclosures(snapshot).some(({ observation }) => observation.id.startsWith("SR007F7-")),
+    "contracted revenue and potential customers' active users cannot become realized ARR");
+  assert.equal(snapshot.companies.find((item) => item.id === "AI144")!.revenueStatus, "unknown",
+    "free current SDK terms and a contracted ARR claim need reconciliation before labeling realized revenue");
+  const scaledrive = batch.records.find((row) => row.name === "scaledrive.ai")!;
+  assert.equal(scaledrive.status, "outside-cohort", "SR007 membership cannot replace a stated 2024 founding year");
+  assert.equal(scaledrive.companyId, undefined);
+  assert.ok(scaledrive.evidenceIds?.includes("SR007F8-SCALEDRIVE-SR"));
+  for (const id of ["AI147", "AI150"]) {
+    assert.equal(snapshot.companies.find((item) => item.id === id)!.technicalReview!.level, "description",
+      "self-hosting and SDK documentation do not establish correctly attributed public source code");
+    assert.equal(snapshot.companies.find((item) => item.id === id)!.revenueStatus, "unknown");
+  }
+  assert.ok(!arrDisclosures(snapshot).some(({ observation }) => observation.id.startsWith("SR007F8-")),
+    "previous-company ARR and financial amounts in document demonstrations are not current revenue");
+  assert.equal(batch.records.filter((row) => row.status === "linked").length, 71);
+  assert.equal(batch.records.filter((row) => row.profileStatus === "archive-only").length, 0,
+    "all reused independent profiles have now been explicitly reread");
+  assert.equal(batch.records.filter((row) => row.profileStatus === "readable").length, 79);
+  const ninthFollowup = snapshot.observations.filter((item) => item.id.startsWith("SR007F9-"));
+  assert.equal(ninthFollowup.length, 10);
+  assert.equal(ninthFollowup.filter((item) => item.selection === "excluded").length, 6);
+  assert.equal(ninthFollowup.filter((item) => item.selection === "adoption").length, 3);
+  const industrialRunRate = ninthFollowup.find((item) => item.id === "SR007F9-O-VALENT-ANNUALIZED")!;
+  assert.equal(industrialRunRate.metric, "annualized-revenue");
+  assert.equal(industrialRunRate.selection, "historical");
+  assert.ok(ninthFollowup.every((item) => !item.observedAt),
+    "access dates and weeks since launch cannot supply precise financial dates");
+  assert.ok(ninthFollowup.filter((item) => item !== industrialRunRate).every((item) => !item.metric));
+  assert.ok(!arrDisclosures(snapshot).some(({ observation }) => observation.id.startsWith("SR007F9-")),
+    "annual contracts without fulfillment evidence, funding, annualized revenue and pipeline remain outside live ARR");
+  for (const id of ["AI152", "AI158"]) {
+    assert.equal(snapshot.companies.find((item) => item.id === id)!.revenueStatus, "unknown",
+      "contracted labels alone cannot establish realized revenue");
+  }
+  assert.equal(snapshot.companies.find((item) => item.id === "AI161")!.cat, "C02",
+    "enterprise workload model specialization is classified by delivery rather than frontier-model slogans");
+  const rereadProfiles = snapshot.evidence.filter((item) => item.id.startsWith("SR007F10-P-"));
+  assert.equal(rereadProfiles.length, 17);
+  assert.equal(new Set(rereadProfiles.map((item) => item.companyId)).size, 17);
+  for (const evidence of rereadProfiles) {
+    const candidate = batch.records.find((row) => row.companyId === evidence.companyId)!;
+    assert.equal(candidate.url, evidence.url);
+    assert.ok(candidate.evidenceIds?.includes(evidence.id), "each reread has an exact profile link");
+  }
+  assert.ok(!snapshot.observations.some((item) => item.id.startsWith("SR007F10-")),
+    "rereading existing financial milestones must not introduce duplicate observations");
+  for (const id of ["AI067", "AI069"]) {
+    assert.equal(snapshot.companies.find((item) => item.id === id)!.cat, "C02",
+      "current hosted-model and training-data delivery are infrastructure");
+  }
+  const oldWorkflowArr = snapshot.observations.find((item) => item.id === "SR-O-AI069-arr")!;
+  assert.equal(oldWorkflowArr.evidence, "SR-E-infragrid", "retain the original workflow revenue evidence");
+  assert.equal(oldWorkflowArr.value, 302000);
+  assert.equal(oldWorkflowArr.observedAt, undefined);
+  assert.ok(snapshot.companies.find((item) => item.id === "AI069")!.notes.includes("历史ARR归属不清"),
+    "a current category change must retain the unresolved historical product attribution");
+});
+
+test("public Speedrun cohort rosters preserve the finite boundary without inventing founding years", () => {
+  const snapshot = seed as ResearchSnapshot;
+  const rosters = snapshot.candidateBatches!.filter((batch) => /^SR00[1-7]-public-roster-2026-1$/.test(batch.id));
+  assert.equal(rosters.length, 7);
+  for (const [index, count] of [25, 25, 32, 42, 59, 59, 79].entries()) {
+    const batch = rosters.find((item) => item.id.startsWith(`SR${String(index + 1).padStart(3, "0")}-`))!;
+    assert.equal(batch.records.length, count);
+    assert.equal(batch.complete, false, "a complete directory page is not completed company-level research");
+  }
+  const rows = rosters.flatMap((batch) => batch.records);
+  assert.equal(rows.length, 321);
+  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, 5);
+  assert.equal(newlyRegistered.filter((row) => row.status === "linked").length, 68);
+  assert.equal(newlyRegistered.filter((row) => row.status === "existing-outside-cohort").length, 1);
+  assert.equal(newlyRegistered.filter((row) => row.status === "outside-cohort").length, 144);
+  assert.equal(newlyRegistered.filter((row) => row.status === "pending-ai").length, 24,
+    "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-") || 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);
+  assert.equal(new Set(variants.map((row) => row.url)).size, 2, "same-name profiles must not be merged by name");
+  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("Speedrun brand dates and survey benchmark scores do not create new-company revenue", () => {
+  const snapshot = seed as ResearchSnapshot;
+  const rows = snapshot.candidateBatches!.flatMap((batch) => batch.records);
+  for (const id of ["SR004R-C11", "SR004R-C20"]) {
+    const row = rows.find((item) => item.id === id)!;
+    assert.equal(row.status, "pending-year", "a known brand year must retain unresolved underlying entity dates");
+    assert.equal(row.companyId, undefined);
+    assert.ok(row.evidenceIds!.some((proof) => proof.startsWith("SR004F2-")));
+  }
+  for (const id of ["SR004R-C08", "SR004R-C15"]) {
+    assert.equal(rows.find((item) => item.id === id)!.status, "pending-ai");
+  }
+  for (const [id, category] of [["AI168", "C06"], ["AI169", "C05"]]) {
+    const company = snapshot.companies.find((item) => item.id === id)!;
+    assert.equal(company.cat, category);
+    assert.equal(company.revenueStatus, "unknown");
+    assert.equal(company.technicalReview!.level, "description");
+  }
+  assert.ok(!snapshot.observations.some((row) => row.evidence.startsWith("SR004F2-")),
+    "brand-deal opportunities, listed fees and survey agreement are not financial observations");
+  const model = snapshot.reviews.find((row) => row.id === "MODEL1-SIMULATION-PANEL")!;
+  assert.deepEqual(reviewCompanyIds(snapshot, model), ["AI169"]);
+  assert.ok(model.evidenceIds.includes("SR004F2-REHEARSALS-PRICE"));
+});
+
+test("recruiting service adoption and official balance sheets do not become ARR", () => {
+  const snapshot = seed as ResearchSnapshot;
+  for (const id of ["AI170", "AI171", "AI172", "AI173", "AI174", "AI175"]) {
+    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");
+  }
+  const accounts = snapshot.evidence.find((row) => row.id === "SR005F3-DEX-ACCOUNTS")!;
+  assert.equal(accounts.companyId, "AI171");
+  assert.equal(new URL(accounts.url).hostname, "find-and-update.company-information.service.gov.uk");
+  assert.equal(accounts.publishedAt, "2026-09-08", "filing date is preserved without becoming a revenue measurement date");
+  assert.ok(!snapshot.observations.some((row) => row.evidence.startsWith("SR005F3-")),
+    "balance-sheet cash, client quotes, salaries and recruiting outcomes do not disclose revenue");
+  const model = snapshot.reviews.find((row) => row.id === "MODEL1-RECRUITING-SERVICE")!;
+  assert.deepEqual(reviewCompanyIds(snapshot, model), ["AI175", "AI171"]);
+  assert.ok(model.evidenceIds.includes("SR005F3-JOOBA-TERMS"));
+});
+
+test("current products preserve unresolved identity and separate trading from software revenue", () => {
+  const snapshot = seed as ResearchSnapshot;
+  const presia = snapshot.candidateBatches!.flatMap((batch) => batch.records)
+    .find((row) => row.id === "SR005R-C44")!;
+  assert.equal(presia.status, "pending-ai");
+  assert.equal(presia.companyId, undefined, "a reused domain does not resolve a changed business entity");
+  assert.ok(presia.evidenceIds!.includes("SR005F4-PRESIA-ASSET"));
+  for (const id of ["AI176", "AI177", "AI178", "AI179", "AI180"]) {
+    const company = snapshot.companies.find((row) => row.id === id)!;
+    assert.equal(company.revenueStatus, "unknown");
+  }
+  const syzygy = snapshot.companies.find((row) => row.id === "AI180")!;
+  assert.equal(syzygy.technicalReview!.level, "public-artifact");
+  assert.ok(syzygy.technicalReview!.evidenceIds.includes("SR005F4-SYZYGY-FILES"));
+  assert.ok(!snapshot.observations.some((row) => row.evidence.startsWith("SR005F4-")),
+    "landed prices, customer savings, model scores and listed subscriptions are not reported ARR");
+  const supply = snapshot.reviews.find((row) => row.id === "MODEL1-PHYSICAL-SUPPLY")!;
+  assert.deepEqual(reviewCompanyIds(snapshot, supply), ["AI179"]);
+  assert.ok(snapshot.reviews.find((row) => row.id === "MODEL1-LOCAL-CLOUD")!.companyIds!.includes("AI180"));
+});
+
+test("new founding-year reports retain beta, academic and self-reported enforcement boundaries", () => {
+  const snapshot = seed as ResearchSnapshot;
+  for (const id of ["AI181", "AI182", "AI184", "AI185", "AI186"]) {
+    const company = snapshot.companies.find((row) => row.id === id)!;
+    assert.equal(company.year, 2026);
+    assert.equal(company.revenueStatus, "unknown");
+    assert.equal(company.technicalReview!.level, "description");
+  }
+  assert.equal(snapshot.companies.find((row) => row.id === "AI183")!.year, 2025);
+  assert.ok(!snapshot.observations.some((row) => row.evidence.startsWith("SR006F5-")),
+    "trial credits, customer revenue impact, demonstration fundraises and normalized research scores are not ARR");
+  const research = snapshot.reviews.find((row) => row.id === "SR006F5-R-RESEARCH")!;
+  assert.deepEqual(reviewCompanyIds(snapshot, research), ["AI185", "AI169"]);
+  assert.ok(research.evidenceIds.includes("SR004F2-REHEARSALS-BENCH"));
+  const pricing = snapshot.reviews.find((row) => row.id === "MODEL1-MESSAGE-ENFORCEMENT")!;
+  assert.deepEqual(reviewCompanyIds(snapshot, pricing), ["AI186"]);
+  assert.ok(pricing.evidenceIds.includes("SR006F5-ZERODRIFT-TERMS"));
+});
+
+test("rebrands and ambiguous monthly receipts stay outside comparable ARR", () => {
+  const snapshot = seed as ResearchSnapshot;
+  const rows = snapshot.candidateBatches!.flatMap((batch) => batch.records);
+  for (const id of ["SR006R-C37", "SR006R-C54"]) {
+    const row = rows.find((item) => item.id === id)!;
+    assert.equal(row.status, "pending-year");
+    assert.equal(row.companyId, undefined, "brand dates must not overwrite existing legal-entity dates");
+  }
+  const idilio = rows.find((item) => item.id === "SR006R-C22")!;
+  assert.equal(idilio.status, "pending-ai");
+  assert.ok(idilio.evidenceIds!.includes("SR006F6-IDILIO-SR"));
+  assert.ok(!snapshot.observations.some((row) => row.evidence.startsWith("SR006F6-")),
+    "pipeline, retained client revenue, illustrative tax values and undated monthly receipts are not comparable ARR");
+  for (const id of ["AI187", "AI188", "AI189"]) {
+    assert.equal(snapshot.companies.find((row) => row.id === id)!.revenueStatus, "unknown");
+  }
+  const tax = snapshot.reviews.find((row) => row.id === "MODEL1-TAX-PREP")!;
+  assert.deepEqual(reviewCompanyIds(snapshot, tax), ["AI188"]);
+  assert.ok(tax.evidenceIds.includes("SR006F6-GROVE-PRICE"));
+});
+
+test("care and legal delivery preserve financial exclusions and linked cost reviews", () => {
+  const snapshot = seed as ResearchSnapshot;
+  for (const id of ["AI190", "AI191", "AI192", "AI193", "AI194", "AI195"]) {
+    const company = snapshot.companies.find((row) => row.id === id)!;
+    assert.equal(company.revenueStatus, "unknown");
+    assert.equal(company.technicalReview!.level, "description");
+    const candidate = snapshot.candidateBatches!.flatMap((batch) => batch.records)
+      .find((row) => row.companyId === id)!;
+    assert.equal(candidate.status, "linked");
+    assert.equal(candidate.categoryId, company.cat);
+    assert.ok(company.evidenceIds.every((proof) => snapshot.evidence.some((row) => row.id === proof && row.companyId === id)));
+  }
+  assert.ok(!snapshot.observations.some((row) => row.evidence.startsWith("SRCARE1-")),
+    "undefined annual run rate, customer savings, list prices and usage are not comparable ARR");
+  const hardware = snapshot.reviews.find((row) => row.id === "MODEL1-HARDWARE-LIFETIME")!;
+  assert.deepEqual(reviewCompanyIds(snapshot, hardware), ["AI195"]);
+  const clinical = snapshot.reviews.find((row) => row.id === "MODEL1-CARE-OPERATIONS")!;
+  assert.deepEqual(reviewCompanyIds(snapshot, clinical), ["AI191", "AI194"]);
+});
+
+test("enterprise contracts and launch-year conflicts retain their exclusions", () => {
+  const snapshot = structuredClone(seed) as ResearchSnapshot;
+  const accelerator = snapshot.candidateBatches!.flatMap((batch) => batch.records)
+    .find((row) => row.id === "SR006R-C01")!;
+  assert.equal(accelerator.status, "pending-year");
+  assert.equal(accelerator.companyId, undefined);
+  assert.ok(accelerator.evidenceIds!.includes("SRENTER1-ACCELER8-DEALROOM"));
+  for (const [id, value, bound] of [["HEAVI", 100000, "="], ["VERRA", 700000, "≈"]] as const) {
+    const contract = snapshot.observations.find((row) => row.id === `SRENTER1-O-${id}-CONTRACT`)!;
+    assert.equal(contract.value, value);
+    assert.equal(contract.bound, bound);
+    assert.equal(contract.selection, "excluded");
+    assert.equal(contract.observedAt, undefined);
+    assert.equal(contract.comparisonGroup, null);
+    assert.equal(snapshot.companies.find((row) => row.id === contract.company)!.revenueStatus, "unknown");
+    contract.metric = "arr";
+    assert.ok(!arrDisclosures(snapshot).some((row) => row.observation.id === contract.id),
+      "even a wrongly added ARR label must not promote an excluded contract");
+    assert.ok(!platformIncomeSample(snapshot, { windowDays: 90 }).points
+      .some((row) => row.observation.id === contract.id));
+  }
+});
+
+test("financial candidates need current AI evidence before they acquire company and income links", () => {
+  const snapshot = seed as ResearchSnapshot;
+  const candidates = snapshot.candidateBatches!.flatMap((batch) => batch.records);
+  for (const id of ["SR006R-C06", "SR006R-C16", "SR005R-C35", "SR006R-C08"]) {
+    const candidate = candidates.find((row) => row.id === id)!;
+    assert.equal(candidate.status, "pending-ai");
+    assert.equal(candidate.companyId, undefined);
+    assert.ok(candidate.evidenceIds!.some((proof) => proof.startsWith("SRFIN1-")));
+  }
+  const financial = snapshot.reviews.find((row) => row.id === "MODEL1-FINANCIAL-OPERATIONS")!;
+  assert.deepEqual(reviewCompanyIds(snapshot, financial), ["AI202", "AI203", "AI204"]);
+  assert.ok(!snapshot.observations.some((row) => row.evidence.startsWith("SRFIN1-")),
+    "bank size, FX processing, artist revenue, demo portfolios and benchmark scores are not vendor income");
+});
+
 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")!;
@@ -487,7 +868,7 @@ 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, 125);
+  assert.equal(snapshot.candidateBatches!.flatMap((b) => b.records).filter((r) => r.status === "pending-year").length, 136);
 });
 
 test("product pivots and founder histories do not become new company years or current revenue", () => {
@@ -682,7 +1063,8 @@ test("the fifth uncertain cohort separates dated ARR, service run rates, booking
   assert.equal(figures.length, 18);
   const dated = figures.find((o) => o.id.endsWith("TRELLIS-ARR-AUG"))!;
   assert.equal(dated.metric, "arr");
-  assert.equal(dated.observedAt, "2026-08-24");
+  assert.equal(dated.observedAt, undefined, "a page maintenance date is not a financial cutoff");
+  assert.ok(arrFieldGaps(dated, snapshot.asOf).includes("date"));
   assert.equal(dated.bound, "≥");
   assert.equal(figures.find((o) => o.id.endsWith("INSTA-RUNRATE"))!.metric, "annualized-revenue");
   assert.equal(figures.find((o) => o.id.endsWith("INSTA-LAUNCH-ARR"))!.metric, "arr");

content/research/ai-income-analysis.json

@@ -1,6 +1,6 @@
 {
-  "sourceVersion": "2026-10-31-ph-all25-1",
-  "asOf": "2026-10-31",
+  "sourceVersion": "2026-11-01-source-closeout-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

@@ -4,7 +4,7 @@ from collections import Counter
 import json
 from pathlib import Path
 import sys
-from urllib.parse import urlsplit
+from urllib.parse import parse_qs, urlsplit
 
 ROOT = Path(__file__).resolve().parents[1]
 DATA = json.loads((ROOT / 'content/research/ai-companies.seed.json').read_text())
@@ -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 +40,63 @@ 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['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['id'] == 'S14' and source.get('publicRosterAudits'):
+            audits = source['publicRosterAudits']
+            assert {a['cohort'] for a in audits} == {f'SR{i:03d}' for i in range(1, 8)}
+            assert len(audits) == 7
+            profile_urls = []
+            for audit in audits:
+                batch = next(b for b in DATA['candidateBatches'] if b['id'] == audit['candidateBatchId'])
+                query = parse_qs(urlsplit(audit['url']).query)
+                assert urlsplit(audit['url']).netloc == 'speedrun.a16z.com'
+                assert query == {'limit': ['100'], 'offset': ['0'], 'cohort': [audit['cohort']]}
+                assert urlsplit(audit['url']).path == '/api/companies/companyparams'
+                assert audit['httpStatus'] == 200 and audit['accessedAt'] <= DATA['asOf']
+                assert audit['next'] is None and audit['previous'] is None
+                assert len(batch['records']) == audit['recordCount'] == audit['reportedCount']
+                assert audit['uniquePublicIds'] == audit['uniqueSlugs'] == audit['recordCount']
+                assert len(audit['responseSha256']) == 64 and all(c in '0123456789abcdef' for c in audit['responseSha256'])
+                assert batch['sourceId'] == 'S14' and not batch['complete']
+                proof = next(e for e in DATA['evidence'] if e['id'] == audit['evidenceId'])
+                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']
+            assert sum(candidates[e['candidateId']]['status'] == 'pending-year' for e in entries) == audit['pendingFoundingIdentity']
+            assert audit['targetYearSelfReports'] == (
+                audit['newLinkedCompanies'] + audit['pendingCurrentAIOrIdentity'] + audit['pendingFoundingIdentity']
+            ), 'self-reported years must retain unresolved brand/entity dates'
         if source['url']:
             assert urlsplit(source['url']).scheme in {'http', 'https'} and urlsplit(source['url']).netloc
         for host in source['hosts']:
@@ -49,7 +120,18 @@ 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