{
  "schema": "malkerfid-collection-size-review-1",
  "checked_at": "2026-10-25T17:07:55.051777+00:00",
  "status": "metadata_verified_pilot_partial",
  "faroese": {
    "source_url": "https://bendingar.fo/tilfar/",
    "catalogue_url": "https://mtd.setur.fo/en/resource/foroyski-bendingargrunnurin/",
    "page_method": "Rendered official page read in browser after web text extraction returned only JavaScript shell. Download link hrefs and license visibly verified.",
    "page_published_size_labels": [
      "9 MB",
      "9 MB"
    ],
    "label_note": "Approximate webpage labels differ from current exact HTTP Content-Length; use exact byte metadata with date, do not label 9 MB exact.",
    "license": "CC-BY-SA-4.0",
    "license_url": "https://creativecommons.org/licenses/by-sa/4.0/",
    "webpage_restriction": "Footer forbids copying declension examples from the website but permits downloads under the declared resource license. Use the official download files, not copied web paradigms.",
    "files": [
      {
        "name": "KRISTINsnid.csv.zip",
        "url": "https://bendingar.fo/nidurhalsgogn/KRISTINsnid.csv.zip",
        "compressed_archive_bytes": 11434529,
        "last_modified_http": "Sun, 18 Oct 2026 23:06:53 GMT",
        "etag": "\"ae7a21-65e257400b1d4\"",
        "csv_files": [
          {
            "name": "KRISTINsnid.csv",
            "compressed_bytes": 11434117,
            "uncompressed_bytes": 164571000,
            "compression_method": 8,
            "crc32": "062eea55",
            "offset": 0
          }
        ],
        "csv_uncompressed_bytes_total": 164571000,
        "method": "HEAD Content-Length plus 65,536-byte suffix range for ZIP central directory. No archive decompression, complete download, CSV row count or payload checksum verification.",
        "range_received_bytes": 65536,
        "directory_capture_sha256": "52da86d55990b2c5de2836a337e2f34cf51eb932f1d0ee42371f568accf50d9b"
      },
      {
        "name": "Storasnid_allt.zip",
        "url": "https://bendingar.fo/nidurhalsgogn/Storasnid_allt.zip",
        "compressed_archive_bytes": 11601219,
        "last_modified_http": "Sun, 18 Oct 2026 23:15:26 GMT",
        "etag": "\"b10543-65e259299223c\"",
        "csv_files": [
          {
            "name": "Storasnid_ord.csv",
            "compressed_bytes": 652292,
            "uncompressed_bytes": 3480748,
            "compression_method": 8,
            "crc32": "03e2e9fb",
            "offset": 0
          },
          {
            "name": "Storasnid_beygm.csv",
            "compressed_bytes": 10947596,
            "uncompressed_bytes": 131676717,
            "compression_method": 8,
            "crc32": "61a67cae",
            "offset": 652506
          },
          {
            "name": "Storasnid_ritm.csv",
            "compressed_bytes": 102,
            "uncompressed_bytes": 188,
            "compression_method": 8,
            "crc32": "3a808f9c",
            "offset": 11600320
          }
        ],
        "csv_uncompressed_bytes_total": 135157653,
        "method": "HEAD Content-Length plus 65,536-byte suffix range for ZIP central directory. No archive decompression, complete download, CSV row count or payload checksum verification.",
        "range_received_bytes": 65536,
        "directory_capture_sha256": "960bfafb15c38d685b8197f5237644f9b7376b2adbe32aee830f14a774efd408"
      }
    ],
    "word_count": null,
    "inflection_count": null,
    "sample_import_status": "stopped_original_paradigm_goal_incomplete"
  },
  "danish": {
    "source_url": "https://ordregister.dk/doc/COR.SEM.EXT.html",
    "download_url": "https://ordregister.dk/files/cor.sem.ext.1.0.tsv",
    "bytes": 7614547,
    "method": "HEAD only; no TSV body downloaded",
    "last_modified_http": "Tue, 06 Feb 2024 12:29:16 GMT",
    "etag": "\"743053-610b5ba0ae924\"",
    "license": "CC-BY-NC-ND-4.0",
    "license_url": "https://creativecommons.org/licenses/by-nc-nd/4.0/",
    "exact_rows": null,
    "published_rounded_entries": 42000,
    "rounded_count_source": "https://ordregister.dk/",
    "rounding_note": "Official COR2 table labels EXT as 42k. This is an approximate publisher count, not an exact row count.",
    "sample_import_status": "passed_local_import"
  },
  "lsj": {
    "pilot_report": "lsj-pilot-report.json",
    "sample": "lsj-pilot.json",
    "exact_header": "lsj-header.xml",
    "exact_sample": "lsj-20-entries.xmlpart",
    "license": "LSJ-LICENSE-README.md",
    "commit": "51b2f90b515d51ff1052bb9f0c5ec17fa7246859",
    "P_GRC_01": "Stopped at 256 KiB, zero complete entries; header/preface/bibliography only",
    "P_GRC_02": "20 complete beta entries from a separate 64 KiB range; parsed losslessly, 17 senses and 48 citations",
    "full_collection_imported": false,
    "all_collection_entries": null
  },
  "remaining": [
    "Exact Faroese word/form counts and a bounded import example from the licensed download",
    "Exact COR.SEM.EXT rows and its separate licensed usage decision",
    "Full LSJ entry count and validation beyond the 20-entry pilot",
    "No claim that MK-021 is complete"
  ],
  "sample_followup_report": "collection-sample-report.json",
  "sample_followup_checked_at": "2026-10-25T17:46:43.359493+00:00"
}