Merge pull request '统一 AI 公司研究：ARR 补证、商业模式初评与来源核查' (#42) from codex/ai-research-ph-all26 into main

Reviewed-on: #42

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, 1196);
+  assert.equal(research.companies.length, 1202);
   assert.equal(research.categories.length, 11);
-  assert.equal(research.evidence.length, 4600);
+  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/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

@@ -1,26 +1,37 @@
 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>
@@ -32,6 +43,12 @@ export default function ArrDisclosures({ data, onSelect }: { data: ResearchSnaps
       </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>
+    <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>
@@ -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;
@@ -104,9 +123,14 @@ 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.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);
+    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 +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, 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, 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")!), []);
@@ -166,11 +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), 1196);
+  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), 1117);
+  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"));
@@ -205,8 +229,8 @@ 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, 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");
   assert.match(snapshot.companies.find((c) => c.id === "AI051")!.technicalReview!.testScope!, /Sep 2026/);
@@ -279,9 +303,15 @@ 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 +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 });
@@ -460,6 +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")!;
@@ -487,7 +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, 125);
+  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", () => {
@@ -682,7 +726,8 @@ 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-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

@@ -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 +40,15 @@ 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['url']:
             assert urlsplit(source['url']).scheme in {'http', 'https'} and urlsplit(source['url']).netloc
         for host in source['hosts']:
@@ -49,7 +72,18 @@ 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