完成192项AI不明名单补核并核对预订与交付口径
This commit is contained in:
@@ -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, 1144);
|
||||
assert.equal(research.companies.length, 1154);
|
||||
assert.equal(research.categories.length, 11);
|
||||
assert.equal(research.evidence.length, 3208);
|
||||
assert.equal(research.observations.length, 444);
|
||||
assert.equal(research.evidence.length, 3274);
|
||||
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 });
|
||||
assert.equal(researchPage.status, 200);
|
||||
|
||||
@@ -23,9 +23,9 @@ 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, 1144);
|
||||
assert.equal(initial.evidence.length, 3208);
|
||||
assert.equal(initial.observations.length, 444);
|
||||
assert.equal(initial.companies.length, 1154);
|
||||
assert.equal(initial.evidence.length, 3274);
|
||||
assert.equal(initial.observations.length, 453);
|
||||
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");
|
||||
@@ -64,8 +64,8 @@ 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, 194);
|
||||
assert.equal(snapshot.reviews.filter((r) => r.scope === "dataset").length, 19);
|
||||
assert.equal(snapshot.reviews.filter((r) => r.scope === "companies").length, 198);
|
||||
assert.equal(snapshot.reviews.filter((r) => r.scope === "dataset").length, 21);
|
||||
assert.equal(snapshot.reviews.filter((r) => r.scope === "excluded-candidate").length, 44);
|
||||
const review = snapshot.reviews.find((r) => r.id === "R4")!;
|
||||
assert.deepEqual(reviewCompanyIds(snapshot, review), ["AI007", "AI013", "AI021", "AI034"]);
|
||||
@@ -85,11 +85,11 @@ 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), 1144);
|
||||
assert.equal(summary.reduce((n, c) => n + c.count, 0), 1154);
|
||||
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), 1065);
|
||||
assert.equal(summary.reduce((n, c) => n + c.unknown, 0), 1075);
|
||||
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"));
|
||||
@@ -124,7 +124,7 @@ test("service run rates, legacy freight revenue and paid adoption do not become
|
||||
|
||||
test("technical reviews keep accessible materials separate from tested capabilities", () => {
|
||||
const snapshot = structuredClone(seed) as ResearchSnapshot;
|
||||
assert.equal(snapshot.companies.filter((c) => c.technicalReview).length, 128);
|
||||
assert.equal(snapshot.companies.filter((c) => c.technicalReview).length, 138);
|
||||
assert.equal(snapshot.companies.filter((c) => c.technicalReview?.level === "public-artifact").length, 23);
|
||||
assert.equal(snapshot.companies.filter((c) => c.technicalReview?.level === "independent-test").length, 1);
|
||||
assert.equal(snapshot.companies.find((c) => c.id === "AI051")?.revenueStatus, "unknown");
|
||||
@@ -702,6 +702,52 @@ test("the seventh uncertain cohort separates hardware sales, prepayments and bou
|
||||
assert.ok(!platformIncomeSample(snapshot, { windowDays: null }).points.some((p) => p.observation.id.startsWith("UNCLEAR7-")));
|
||||
});
|
||||
|
||||
test("all original AI-unclear candidates retain a unique follow-up without counting EveryApp twice", () => {
|
||||
const snapshot = seed as ResearchSnapshot;
|
||||
const rows = snapshot.candidateBatches!.filter((b) => b.id.startsWith("YC-AI-UNCLEAR-")).flatMap((b) => b.records);
|
||||
const original = coverageAudit.records.filter((r) => r.status === "ai-unclear");
|
||||
assert.equal(rows.length, 192);
|
||||
assert.equal(new Set(rows.map((r) => r.url)).size, 192);
|
||||
assert.deepEqual(rows.map((r) => r.url), original.map((r) => r.source));
|
||||
assert.equal(rows.filter((r) => r.status === "linked").length, 110);
|
||||
assert.equal(rows.filter((r) => r.status === "pending-ai").length, 82);
|
||||
assert.equal(snapshot.directoryRechecks!.filter((r) => r.ycId === 36088).length, 1);
|
||||
const everyapp = rows.find((r) => r.name === "EveryApp")!;
|
||||
assert.equal(everyapp.companyId, "AI074");
|
||||
assert.equal(snapshot.companies.filter((c) => c.id === "AI074").length, 1);
|
||||
for (const row of rows.filter((r) => r.status === "pending-ai")) {
|
||||
assert.equal(row.companyId, undefined);
|
||||
assert.ok(row.evidenceIds!.length > 0, "unresolved AI relevance has explicit evidence and gaps");
|
||||
}
|
||||
assert.equal(snapshot.coverage!.newProfiles, 928, "later evidence does not rewrite the original discovery accounting");
|
||||
});
|
||||
|
||||
test("the final uncertain cohort separates delivery-start rentals, reservations and upstream costs", () => {
|
||||
const snapshot = seed as ResearchSnapshot;
|
||||
const batch = snapshot.candidateBatches!.find((b) => b.id === "YC-AI-UNCLEAR-8")!;
|
||||
assert.equal(batch.complete, false, "reading the full pool does not resolve all AI, year or financial gaps");
|
||||
assert.equal(batch.records.filter((r) => r.status === "linked").length, 11);
|
||||
assert.equal(batch.records.filter((r) => r.status === "pending-ai").length, 13);
|
||||
const rhem = snapshot.companies.find((c) => c.id === "YC35127")!;
|
||||
assert.match(rhem.price!, /确认交付后/);
|
||||
assert.match(rhem.price!, /99 USD/);
|
||||
assert.equal(rhem.revenueStatus, "unknown");
|
||||
assert.match(snapshot.companies.find((c) => c.id === "YC37272")!.price!, /预约/);
|
||||
assert.match(snapshot.companies.find((c) => c.id === "AI074")!.price!, /有效订阅/);
|
||||
assert.match(snapshot.companies.find((c) => c.id === "YC35396")!.notes, /Coming next/);
|
||||
assert.match(snapshot.companies.find((c) => c.id === "YC36774")!.notes, /Early access/);
|
||||
const figures = snapshot.observations.filter((o) => o.id.startsWith("UNCLEAR8-"));
|
||||
assert.equal(figures.length, 9);
|
||||
assert.ok(figures.every((o) => ["excluded", "adoption"].includes(o.selection) && !o.metric && o.comparisonGroup === null));
|
||||
for (const suffix of ["OASIVE-OLD-WELLS", "OASIVE-OLD-GOOGLE", "OBSESSION-CALCULATOR", "EVERYAPP-UPSTREAM"]) {
|
||||
assert.equal(figures.find((o) => o.id.endsWith(suffix))!.selection, "excluded");
|
||||
}
|
||||
for (const name of ["Clean", "STASIS", "RATLOG", "Inflection Space Systems", "twentyfour26"]) {
|
||||
assert.equal(batch.records.find((r) => r.name === name)!.status, "pending-ai");
|
||||
}
|
||||
assert.ok(!platformIncomeSample(snapshot, { windowDays: null }).points.some((p) => p.observation.id.startsWith("UNCLEAR8-")));
|
||||
});
|
||||
|
||||
test("Chinese discovery entries preserve unread articles and use separate primary evidence", () => {
|
||||
const snapshot = structuredClone(seed) as ResearchSnapshot;
|
||||
const batch = snapshot.candidateBatches!.find((b) => b.id === "JQ-2026-targeted-1")!;
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -1,5 +1,5 @@
|
||||
{
|
||||
"version": "2026-10-31-ai-unclear-7",
|
||||
"version": "2026-10-31-ai-unclear-8",
|
||||
"scopeConfirmedAt": "2026-10-30",
|
||||
"acceptance": "以确认的公开来源清单为边界，逐条核对并标明缺项。",
|
||||
"provenance": "S01—S12恢复自已提交用户的《AI公司研究_来源与分类模板》来源清单；S13—S16单列后续已使用的补充证据渠道，不将使用次数当作全量覆盖。",
|
||||
@@ -16,7 +16,7 @@
|
||||
"initialAccess": "官网目录可访问",
|
||||
"boundary": "已读取八个2025—2026批次镜像候选池1428条，再核YC官方页面；不声称覆盖全部YC历年或未公开公司。",
|
||||
"limitation": "批次不等于成立年；不代表全部公司",
|
||||
"nextCheck": "已统一企业141、行业252、模型标签26、开发标签51、其余标签34项，共504项新增主营复核。当前928条原YC新增记录保留发现来源，其中基础项871条均已做主营人工复核（871条），57条深化个案。C05规则89保留27/移62，C05标签52保留10/移42；C07规则184保留135/移49，C07标签68保留39/移29；模型标签26保留17/移9，开发标签51保留16/移35，其余标签34保留16/移18。主营复核仍含C00/短简介/混合交付缺项，不等完整产品/技术/财务审计。Tasklet及Native新产品与旧业务链保留，发现审计不改；Freya、Epicenter、Stellon许可及公开材料/厂商基准范围分开。客户收入、估价、资产、节省、管线/意向、预订需求、旧公司收入与示例排除自身ARR；Locke服务run-rate不等ARR，Mixy历史MRR/捐赠、Isengard无期间收入分开。各批证据、观测、核查与主体/收费/人工成本缺项均保留；全部确认来源清单的候选范围、AI不明/成立冲突及公司财务技术缺项继续核，不能声称全来源研究完成。 原AI不明192项已补核七批168项：93新增、6复用、69保留AI主营待核；另此前OpenSEO1项，合计169项有后续记录，其余23项继续。原发现审计/928初始新增不回写。Nori机器人与健康软件分开；Letter当前营销、Kailash当前机器人与YC旧方向差异保留。Nori硬件sales、预付计算余额、客户节省/机队、旧药房/app收入和虚构支付演示不进平台MRR；Graphify函数solver/预算边界及自有基准不当独立验证，生物/材料/自主硬件AI核心缺项继续核。"
|
||||
"nextCheck": "已统一企业141、行业252、模型标签26、开发标签51、其余标签34项，共504项新增主营复核。当前928条原YC新增记录保留发现来源，其中基础项871条均已做主营人工复核（871条），57条深化个案。C05规则89保留27/移62，C05标签52保留10/移42；C07规则184保留135/移49，C07标签68保留39/移29；模型标签26保留17/移9，开发标签51保留16/移35，其余标签34保留16/移18。主营复核仍含C00/短简介/混合交付缺项，不等完整产品/技术/财务审计。Tasklet及Native新产品与旧业务链保留，发现审计不改；Freya、Epicenter、Stellon许可及公开材料/厂商基准范围分开。客户收入、估价、资产、节省、管线/意向、预订需求、旧公司收入与示例排除自身ARR；Locke服务run-rate不等ARR，Mixy历史MRR/捐赠、Isengard无期间收入分开。各批证据、观测、核查与主体/收费/人工成本缺项均保留；全部确认来源清单的候选范围、AI不明/成立冲突及公司财务技术缺项继续核，不能声称全来源研究完成。 原AI不明192项已按原顺序补核八批192项：103新增、7复用（含此前已核EveryApp）、82保留AI主营待核，共110关联；没有再把EveryApp额外加1，全池192项均有可回查后续记录。原发现审计/928初始新增不回写；已读全池不等82项均确认AI，更不等268年范围外/缺失、6日期冲突和其他来源全部完成。Rhem交付后租赁/旧买断、Subvocal预约、EveryApp托管计划/Cloudflare费/OpenSEO套餐、ObsessionDB资源估算与BYOC年度运维分开，不新增可比MRR；市政债未来模块、原型/健康/倍速演示及Clean模型实现缺项保留。"
|
||||
},
|
||||
{
|
||||
"id": "S02",
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
{
|
||||
"sourceVersion": "2026-10-31-ai-unclear-7",
|
||||
"sourceVersion": "2026-10-31-ai-unclear-8",
|
||||
"asOf": "2026-10-31",
|
||||
"metric": "platform-mrr-usd",
|
||||
"sampleUnit": "product-or-business",
|
||||
|
||||
@@ -121,6 +121,31 @@ def candidate_register():
|
||||
return lines
|
||||
|
||||
|
||||
def uncertain_ai_followups():
|
||||
original = {row['source']: row for row in AUDIT['records'] if row['status'] == 'ai-unclear'}
|
||||
rows = [row for batch in DATA.get('candidateBatches', [])
|
||||
if batch['id'].startswith('YC-AI-UNCLEAR-') for row in batch['records']]
|
||||
if not rows:
|
||||
return []
|
||||
urls = [row['url'] for row in rows]
|
||||
assert len(set(urls)) == len(urls), 'Duplicate AI-relevance follow-up URL'
|
||||
rechecks = {row['ycId']: row for row in DATA.get('directoryRechecks', [])}
|
||||
counts = Counter(row['status'] for row in rows)
|
||||
assert set(counts) <= {'linked', 'pending-ai'}
|
||||
for row in rows:
|
||||
assert row['url'] in original and row.get('evidenceIds')
|
||||
baseline = original[row['url']]
|
||||
if row['status'] == 'linked':
|
||||
assert rechecks[baseline['ycId']]['companyId'] == row['companyId']
|
||||
else:
|
||||
assert not row.get('companyId') and baseline['ycId'] not in rechecks
|
||||
unread = len(original) - len(rows)
|
||||
assert unread >= 0
|
||||
return ['', '## 原AI主营不明名单的后续覆盖', '',
|
||||
f"原名单{len(original)}项，已有后续记录{len(rows)}项：{counts['linked']}项关联公司、{counts['pending-ai']}项仍待核AI主营，{unread}项尚无本批系列的后续记录。计数按原始YC页面去重；EveryApp此前的独立复核与末批记录不重复相加。", '',
|
||||
'读完名单只证明每项有可回查的处理记录，不证明待核项均为AI公司，也不证明法律主体、收入或技术效果已独立验证。原始发现审计保持不变，成立年范围外/缺失、成立冲突及其他来源的缺项仍单列。', '']
|
||||
|
||||
|
||||
def directory_rechecks():
|
||||
rows = DATA.get('directoryRechecks', [])
|
||||
if not rows:
|
||||
@@ -217,13 +242,14 @@ def render():
|
||||
lines.append(f"| {name} | {len(entries)} | {len({e['url'] for e in entries})} | {note} |")
|
||||
others = [e for e in DATA['evidence'] if urlsplit(e['url']).netloc not in included]
|
||||
lines.append(f"| 其他官网、评测及公开资料 | {len(others)} | {len({e['url'] for e in others})} | 按每条来源限制理解，不能统一当作独立证据 |")
|
||||
lines += uncertain_ai_followups()
|
||||
lines += directory_rechecks()
|
||||
lines += source_register()
|
||||
lines += context_methods()
|
||||
lines += candidate_register()
|
||||
lines += ['', '## 尚未满足的研究条件', '',
|
||||
'行业ARR比较仍缺统一业务截止日、币种、经常性定义和业务边界。现有平台MRR可描述已采集产品，不足以代表全部新公司。技术评测只覆盖所列版本与任务，不宜跨领域汇总为统一强弱分数。', '',
|
||||
'下一轮优先补收入线索的日期及合同定义、非YC和非英文来源、规则初分的人工复核，以及停止服务或被收购案例。这样能减少“只见赢家”和“只见融资公司”的偏差。公开来源池之外的未披露公司仍无法证明已被穷尽。', '',
|
||||
'下一轮优先补收入线索的日期及合同定义、成立年冲突、AI主营仍待核项、非YC和非英文来源，以及停止服务或被收购案例。这样能减少“只见赢家”和“只见融资公司”的偏差。公开来源池之外的未披露公司仍无法证明已被穷尽。', '',
|
||||
]
|
||||
return '\n'.join(lines)
|
||||
|
||||
|
||||
Reference in New Issue
Block a user