{
  "checkedAt": "2026-10-14T18:44:47+00:00",
  "scope": "Missing original Kave Shtiebel posts only; no Kraimel threads imported",
  "sources": [
    {
      "name": "Arquivo.pt",
      "url": "https://arquivo.pt/wayback/cdx?url=*.kaveshtiebel.com/*&output=json&filter=statuscode:200&collapse=urlkey&limit=10000",
      "records": 1548,
      "threadCaptures": 1,
      "importedThreads": 1,
      "importedPosts": 25
    },
    {
      "name": "AllenAI mC4 Yiddish, mC4_3.1.0 revision",
      "url": "https://huggingface.co/datasets/allenai/c4/tree/mC4_3.1.0/multilingual",
      "matchingPages": 7684,
      "method": "Compared explicit thread IDs, original author/date keys (Hebrew month aliases), normalized body overlap, then checked residual candidates against timezone shifts, username changes and attachments. No corpus fragments imported."
    },
    {
      "name": "Wayback CDX",
      "url": "https://web.archive.org/cdx/search/cdx?url=kaveshtiebel.com/*&output=json&filter=statuscode:200&collapse=urlkey&limit=5",
      "result": "Read timed out"
    },
    {
      "name": "Wayback availability API",
      "url": "https://archive.org/wayback/available?url=kaveshtiebel.com",
      "result": "HTTP 429"
    },
    {
      "name": "Internet Archive item search",
      "url": "https://archive.org/advancedsearch.php?q=kaveshtiebel&output=json",
      "items": 0
    },
    {
      "name": "Common Crawl",
      "successfulIndex": "CC-MAIN-2025-47",
      "successfulRecords": 13,
      "warcRecordsInspected": 1,
      "otherAttempts": [
        "CC-MAIN-2026-39",
        "CC-MAIN-2024-51",
        "CC-MAIN-2023-50",
        "CC-MAIN-2022-49",
        "CC-MAIN-2021-49",
        "CC-MAIN-2020-50",
        "CC-MAIN-2019-51",
        "CC-MAIN-2018-51",
        "CC-MAIN-2017-51",
        "CC-MAIN-2016-50",
        "CC-MAIN-2015-48",
        "CC-MAIN-2014-52",
        "CC-MAIN-2013-48"
      ],
      "otherResults": "503, 504 or timeouts; exact-host retry also timed out"
    },
    {
      "name": "MameLoshnLM / Oytser research corpus",
      "url": "https://github.com/katzurik/MameLoshnLM",
      "result": "Paper reports forum data, but repository currently only exposes README/model links. No original thread corpus downloaded from this project."
    },
    {
      "name": "Original live domain",
      "url": "https://www.kaveshtiebel.com/",
      "result": "Connection timed out"
    }
  ],
  "limits": [
    "Search is bounded and incomplete; crawler outages are recorded, not interpreted as proof content is absent.",
    "Recovered thread 1109 has 25 captured posts on page 1. Page 2 remains unrecovered.",
    "Original dates are preserved; batch dates identify local cataloging/import, not publication."
  ],
  "followUpReport": "recovery-round2/report.json"
}