Expose ARR disclosure gaps before statistical comparison

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/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

@@ -11,7 +11,26 @@ import { openSiteDatabase } from "../src/lib/site-database";
 import { 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;