{
  "schemaVersion": "1.0.0",
  "datasetId": "ai-search-rag-bingbot-discovery-to-target-crawl-gap-2026-07-31",
  "createdAt": "2026-07-31T22:37:38+00:00",
  "releaseId": "20260731T130258Z-c8abe8ac79d6",
  "releaseDeployedAt": "2026-07-31T14:21:46+00:00",
  "targetUrl": "https://course.dragonai.tech/research/ai-search-rag-finetuning-citations-2026-07",
  "publicJsonUrl": "https://course.dragonai.tech/datasets/ai-search-rag-bingbot-discovery-to-target-crawl-gap-2026-07-31.json",
  "publicCsvUrl": "https://course.dragonai.tech/datasets/ai-search-rag-bingbot-discovery-to-target-crawl-gap-2026-07-31.csv",
  "sourceBinding": {
    "role": "controlled_access_log_crawl_report",
    "path": "geo/reports/2026-07-31T223541Z-verified-crawl.json",
    "sha256": "53c22458c4ce1b42a1da91c3c90c6e8a0f5c958a1e3e398f74aead6bf5c5ffec",
    "evidenceScope": "since_release",
    "evidenceCoverageSufficient": true
  },
  "privacyMinimization": {
    "retainedFields": [
      "crawler",
      "timestamp",
      "method",
      "path",
      "status"
    ],
    "omittedFields": [
      "ip",
      "hostname",
      "raw_log_line",
      "user_agent"
    ],
    "rawRequestRowsPublished": false
  },
  "summary": {
    "verifiedCrawlerRequestCount": 3,
    "verifiedDiscoverySurfaceFetchCount": 3,
    "fetchedDiscoverySurfaceCount": 3,
    "fetchedDiscoverySurfaces": [
      "/sitemap.xml",
      "/research-sitemap.xml",
      "/feed.xml"
    ],
    "verifiedTargetCrawlCount": 0,
    "verifiedTargetCrawl": false,
    "triggerCrawlReached": false,
    "propagationDelayElapsed": false,
    "timeFallbackReadyAt": "2026-08-01T14:21:46+00:00",
    "timeFallbackElapsed": false,
    "benchmarkReady": false,
    "benchmarkReadinessReason": "not_ready",
    "providerCallsExecuted": false,
    "countsAsIndexing": false,
    "countsAsSearchVisibility": false,
    "countsAsRanking": false,
    "countsAsAiCitation": false,
    "countsAsGeoSuccess": false
  },
  "rows": [
    {
      "surfaceRole": "discovery_surface",
      "path": "/",
      "crawlers": [],
      "verifiedSuccessCount": 0,
      "latestVerifiedSuccessAt": null,
      "observedAfterRelease": false,
      "benchmarkTriggerEligible": false,
      "countsAsTargetCrawl": false,
      "countsAsBenchmarkReady": false,
      "countsAsGeoSuccess": false
    },
    {
      "surfaceRole": "discovery_surface",
      "path": "/sitemap.xml",
      "crawlers": [
        "Bingbot"
      ],
      "verifiedSuccessCount": 1,
      "latestVerifiedSuccessAt": "2026-07-31T22:33:35+00:00",
      "observedAfterRelease": true,
      "benchmarkTriggerEligible": false,
      "countsAsTargetCrawl": false,
      "countsAsBenchmarkReady": false,
      "countsAsGeoSuccess": false
    },
    {
      "surfaceRole": "discovery_surface",
      "path": "/research-sitemap.xml",
      "crawlers": [
        "Bingbot"
      ],
      "verifiedSuccessCount": 1,
      "latestVerifiedSuccessAt": "2026-07-31T19:46:49+00:00",
      "observedAfterRelease": true,
      "benchmarkTriggerEligible": false,
      "countsAsTargetCrawl": false,
      "countsAsBenchmarkReady": false,
      "countsAsGeoSuccess": false
    },
    {
      "surfaceRole": "discovery_surface",
      "path": "/feed.xml",
      "crawlers": [
        "Bingbot"
      ],
      "verifiedSuccessCount": 1,
      "latestVerifiedSuccessAt": "2026-07-31T19:50:29+00:00",
      "observedAfterRelease": true,
      "benchmarkTriggerEligible": false,
      "countsAsTargetCrawl": false,
      "countsAsBenchmarkReady": false,
      "countsAsGeoSuccess": false
    },
    {
      "surfaceRole": "discovery_surface",
      "path": "/llms.txt",
      "crawlers": [],
      "verifiedSuccessCount": 0,
      "latestVerifiedSuccessAt": null,
      "observedAfterRelease": false,
      "benchmarkTriggerEligible": false,
      "countsAsTargetCrawl": false,
      "countsAsBenchmarkReady": false,
      "countsAsGeoSuccess": false
    },
    {
      "surfaceRole": "discovery_surface",
      "path": "/research",
      "crawlers": [],
      "verifiedSuccessCount": 0,
      "latestVerifiedSuccessAt": null,
      "observedAfterRelease": false,
      "benchmarkTriggerEligible": false,
      "countsAsTargetCrawl": false,
      "countsAsBenchmarkReady": false,
      "countsAsGeoSuccess": false
    },
    {
      "surfaceRole": "discovery_surface",
      "path": "/elite",
      "crawlers": [],
      "verifiedSuccessCount": 0,
      "latestVerifiedSuccessAt": null,
      "observedAfterRelease": false,
      "benchmarkTriggerEligible": false,
      "countsAsTargetCrawl": false,
      "countsAsBenchmarkReady": false,
      "countsAsGeoSuccess": false
    },
    {
      "surfaceRole": "discovery_surface",
      "path": "/insights",
      "crawlers": [],
      "verifiedSuccessCount": 0,
      "latestVerifiedSuccessAt": null,
      "observedAfterRelease": false,
      "benchmarkTriggerEligible": false,
      "countsAsTargetCrawl": false,
      "countsAsBenchmarkReady": false,
      "countsAsGeoSuccess": false
    },
    {
      "surfaceRole": "benchmark_target",
      "path": "/research/ai-search-rag-finetuning-citations-2026-07",
      "crawlers": [],
      "verifiedSuccessCount": 0,
      "latestVerifiedSuccessAt": null,
      "observedAfterRelease": false,
      "benchmarkTriggerEligible": true,
      "countsAsTargetCrawl": false,
      "countsAsBenchmarkReady": false,
      "countsAsGeoSuccess": false
    }
  ],
  "evidenceBoundaries": [
    "A verified crawler fetch of a discovery surface does not prove that the target page was fetched or indexed.",
    "The three observed discovery-surface requests are independent Bingbot fetches; they do not establish a causal path from any surface to a future target fetch.",
    "The target had zero qualifying Googlebot or Bingbot fetches in the source report, so the six-hour propagation timer had not started.",
    "The 24-hour fallback schedules a later measurement only and is not positive crawl, indexing, visibility, ranking, citation or GEO-success evidence.",
    "No provider call, search submission, IndexNow request or external publication was performed by this build."
  ],
  "integrity": {
    "algorithm": "sha256",
    "canonicalCoreSha256": "45ee74488aab4b316140f95ac823185da849552c93c7c68bbc6398bc7751a7c7"
  },
  "title": "Bingbot 发现面到研究目标页的抓取缺口（2026-07-31）",
  "description": "从当前生产发布的受控访问日志中提取经正反向 DNS 验证的 Bingbot 请求，公开研究 sitemap 与 Atom feed 已抓取而唯一目标页仍未抓取的最小化路径级证据；不公开 IP 或原始日志，也不把发现面抓取当作收录、排名、AI 引用或 GEO 成功。",
  "url": "https://course.dragonai.tech/datasets/ai-search-rag-bingbot-discovery-to-target-crawl-gap-2026-07-31.json",
  "license": "https://creativecommons.org/licenses/by/4.0/",
  "creator": "DragonAI 内容研究组"
}