{
  "schema": "malkerfid-collection-sample-report-1",
  "checked_at": "2026-10-25T17:46:43.359493+00:00",
  "task": "MK-021",
  "full_collections_imported": false,
  "total_network_body_bytes": 16384,
  "network_limit_declared_bytes_each": 8192,
  "fo": {
    "pilot_id": "P-FO-01",
    "status": "stopped_original_paradigm_goal_incomplete",
    "downloaded_bytes": 8192,
    "archive_total_bytes": 11434529,
    "inflated_prefix_bytes": 32768,
    "imported_lines": 100,
    "selected_bytes": 5427,
    "column_count": 15,
    "observed_column_2_values": 11,
    "observed_column_3_values": 1,
    "complete_paradigms_verified": 0,
    "target_paradigms": 3,
    "target_pos_coverage_met": false,
    "raw_prefix_sha256": "22ceea88e346a62a940ace8344aeba348e6af8e59681fa3725e405ba46357bd4",
    "selected_bytes_sha256": "360b37410e80d8ecf7e2ccc28ae8a5bccf87018c143c78838085d00197e647cd",
    "source": {
      "url": "https://bendingar.fo/nidurhalsgogn/KRISTINsnid.csv.zip",
      "retrieved_at": "2026-10-25T17:46:37.203124+00:00",
      "last_modified": "Sun, 18 Oct 2026 23:06:53 GMT",
      "etag": "\"ae7a21-65e257400b1d4\"",
      "license": "CC-BY-SA-4.0",
      "license_url": "https://creativecommons.org/licenses/by-sa/4.0/",
      "attribution": "Føroyski bendingargrunnurin; Stofnun Árna Magnússonar í íslenskum fræðum and Fróðskaparsetur Føroya.",
      "retrieval_scope": "One HTTP byte range, bytes 0–8191; not the full collection."
    },
    "acceptance_gaps": [
      "No noun/verb/adjective coverage: the first 100 observed rows have one column-3 value.",
      "No proof that a contiguous local group is the complete paradigm anywhere else in the collection.",
      "Faroese-specific field/status/tag documentation remains unread; original 15 slots retained without mapping.",
      "No CRC or whole-file hash validation is possible from this prefix.",
      "Kaikki comparison and bidirectional lexical index deferred until field semantics and full paradigms are verified."
    ]
  },
  "da": {
    "pilot_id": "P-DA-01",
    "status": "passed_local_import",
    "version": "1.0",
    "downloaded_bytes": 8192,
    "full_file_bytes": 7614547,
    "maximum_planned_bytes": 131072,
    "selected_bytes": 3515,
    "header_lines": 1,
    "records": 20,
    "fields": 3,
    "unique_sense_ids": 20,
    "matched_by_full_sense_id": 20,
    "unmatched_sense_ids": 0,
    "unique_lemma_ids": 19,
    "empty_definition_fields": 0,
    "empty_example_fields": 3,
    "definition_fields_with_ellipsis": 11,
    "definition_fields_with_pipe": 0,
    "example_fields_with_pipe": 3,
    "raw_prefix_sha256": "fe0f23a698eabe69655292435ba7ff3d44d201bba2120352e134efe55674b737",
    "selected_bytes_sha256": "d3b60e1758f8fc81ec649e438b8eea7ca858875ad44beb2bda31dc24e31e5e1a",
    "baseline_full_source_sha256": "864a6d5704aa49914eb4ce634799678a20d843d11e8cce8310b4736bf5908724",
    "baseline_selected_snapshot_sha256": "072deeb5e416f8760d301e4f3259a9674038105d0b5909a76d36393227bcc69e",
    "source": {
      "url": "https://ordregister.dk/files/cor.sem.ext.1.0.tsv",
      "retrieved_at": "2026-10-25T17:46:43.359493+00:00",
      "last_modified": "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/",
      "attribution": "Det Danske Sprog- og Litteraturselskab (DSL) and Center for Sprogteknologi, Københavns Universitet (CST).",
      "retrieval_scope": "One HTTP byte range, bytes 0–8191; not the full collection."
    },
    "acceptance_gaps": [
      "Public-use NonCommercial compatibility and NoDerivatives scope remain unresolved.",
      "Example citation sources are not present in the TSV and were not fetched from DDO.",
      "20 rows are a prefix sample, not a representative quality estimate or a count of the full resource."
    ]
  },
  "public_payload_policy": {
    "may_publish": "This metrics/report object, summaries, source links, license attribution and test outcomes.",
    "must_not_publish": [
      "raw source byte prefixes",
      "selected lexical TSV/CSV",
      "parsed lexical JSON",
      "baseline sense snapshot"
    ],
    "no_definitions_translated": true,
    "no_baseline_dictionary_changed": true
  },
  "rebuild": {
    "offline": true,
    "script_sha256": "42b81e06011cbe9e48feefaac7dd0ca8c67d74c05ebaccdc159d81093d906c08",
    "command": "python tools/build_collection_samples.py --directory content/collection-samples",
    "source_snapshot_hash_verification_command": "python tools/build_collection_samples.py --directory content/collection-samples --baseline-root ."
  }
}