{
  "version": "source-inventory-v1",
  "snapshot": "2026-09-14",
  "count_unit": "evidence record IDs",
  "count_definition": "Distinct record_id per country across source records, passages, actions, statistics and curated annotations. Excludes training-format copies, review/lineage, evaluation wrappers and profiles. Each ID is assigned once, preferring its canonical version. Translations and derived spans remain separate IDs; these are not independent training traces.",
  "length_definition": "Exact character counts of stored question/context/history fields, target text, or document body; before adding metadata and the chat template. No tokenizer estimates. n is the number with that field present; missing fields are not zero-length observations.",
  "environments": {
    "interactive": 0,
    "multi_agent_trajectories": 0,
    "implemented_verifiers": 0,
    "preference_pairs": 0
  },
  "countries": {
    "CHN": {
      "count": 41632,
      "sources": [
        {
          "id": "mfa",
          "count": 30034,
          "source_ids": [
            "mfa",
            "mfa_es",
            "mfa_fr",
            "mfa_ru",
            "mfa_zh"
          ],
          "languages": [
            "en",
            "es",
            "fr",
            "ru",
            "zh"
          ],
          "kinds": {
            "source_records": 24440,
            "evidence_passages": 5594
          },
          "tasks": [
            {
              "id": "authentic_qa",
              "count": 21935,
              "lengths": {
                "input": {
                  "n": 21935,
                  "min": 30,
                  "median": 5010,
                  "p95": 14955,
                  "max": 41196,
                  "unit": "Unicode characters"
                },
                "target": {
                  "n": 21935,
                  "min": 8,
                  "median": 524,
                  "p95": 2382,
                  "max": 11864,
                  "unit": "Unicode characters"
                },
                "body": null
              },
              "sample": {
                "id": "mfa:t20240530_11347302:qa:0",
                "uid": "8ffa0b1929309fa9f7882192e7231d00685aba1a0251fe76cff232de6532befd",
                "title": "Foreign Ministry Spokesperson Wang Wenbin’s Regular Press Conference on June 14, 2022",
                "date": "2022-06-14",
                "source_url": "https://www.fmprc.gov.cn/eng/xw/fyrbt/lxjzh/202405/t20240530_11347302.html",
                "file": "data/canonical/mfa.jsonl",
                "line": 9984,
                "task": "authentic_qa",
                "fields": [
                  "available_date",
                  "context",
                  "country_iso3",
                  "country_name",
                  "date_precision",
                  "derivation",
                  "document_symbols",
                  "event_date",
                  "group_id",
                  "history",
                  "id",
                  "institution",
                  "language",
                  "parent_id",
                  "quality_flags",
                  "quality_status",
                  "question",
                  "raw_file",
                  "raw_sha256",
                  "represented_entity",
                  "review_status",
                  "rights_status",
                  "schema_version",
                  "source_id",
                  "source_record_id",
                  "source_url",
                  "speaker",
                  "speaking_capacity",
                  "split",
                  "task",
                  "text",
                  "title",
                  "topic_method",
                  "topics"
                ],
                "quality_flags": [],
                "rights_status": "unresolved",
                "review_status": "pending",
                "split": "unassigned"
              },
              "missing_input_fields": 0,
              "recorded_group_count": 984
            },
            {
              "id": "policy_evidence",
              "count": 5594,
              "lengths": {
                "input": null,
                "target": null,
                "body": {
                  "n": 5594,
                  "min": 116,
                  "median": 2655.5,
                  "p95": 2972,
                  "max": 3000,
                  "unit": "Unicode characters"
                }
              },
              "sample": {
                "id": "mfa_es:01a0badc14a9f7d9fc8e:span:0:3000",
                "uid": "ffbe299946105362ee08a3d179595d8d6181b8058477327b0646bd5a51ff2f59",
                "title": "retrieval_evidence",
                "date": "2026-09-03",
                "source_url": "https://www.fmprc.gov.cn/esp/xwfw/lxjzzdh/202609/t20260906_12016882.html",
                "file": "data/prepared/expansion-20260913/evidence-passages.jsonl",
                "line": 1301,
                "task": "policy_evidence",
                "fields": [
                  "available_date",
                  "country_iso3",
                  "end_char",
                  "event_date",
                  "group_id",
                  "id",
                  "language",
                  "parent_id",
                  "pdf_end_page",
                  "pdf_start_page",
                  "proposed_split",
                  "quality_flags",
                  "raw_sha256",
                  "represented_entity",
                  "review_status",
                  "source_id",
                  "source_url",
                  "start_char",
                  "task",
                  "text",
                  "training_admitted"
                ],
                "quality_flags": [
                  "multilingual_extraction_review"
                ],
                "rights_status": "not_recorded",
                "review_status": "pending",
                "split": "not_recorded"
              },
              "missing_input_fields": 5594,
              "recorded_group_count": 384
            },
            {
              "id": "press_conference",
              "count": 2505,
              "lengths": {
                "input": null,
                "target": null,
                "body": {
                  "n": 2505,
                  "min": 455,
                  "median": 9582,
                  "p95": 19615,
                  "max": 41602,
                  "unit": "Unicode characters"
                }
              },
              "sample": {
                "id": "mfa:t20240530_11347302",
                "uid": "c69a25f8d6f13c7c1081554acf9ce7ebb11b80a69e34844ede007db3f8d530e4",
                "title": "Foreign Ministry Spokesperson Wang Wenbin’s Regular Press Conference on June 14, 2022",
                "date": "2022-06-14",
                "source_url": "https://www.fmprc.gov.cn/eng/xw/fyrbt/lxjzh/202405/t20240530_11347302.html",
                "file": "data/canonical/mfa.jsonl",
                "line": 9983,
                "task": "press_conference",
                "fields": [
                  "available_date",
                  "context",
                  "country_iso3",
                  "country_name",
                  "date_precision",
                  "derivation",
                  "document_symbols",
                  "event_date",
                  "group_id",
                  "history",
                  "id",
                  "institution",
                  "language",
                  "publication_date",
                  "quality_flags",
                  "quality_status",
                  "question",
                  "raw_file",
                  "raw_sha256",
                  "represented_entity",
                  "review_status",
                  "rights_status",
                  "schema_version",
                  "source_id",
                  "source_record_id",
                  "source_url",
                  "speaker",
                  "speaking_capacity",
                  "split",
                  "task",
                  "text",
                  "title",
                  "topic_method",
                  "topics"
                ],
                "quality_flags": [],
                "rights_status": "unresolved",
                "review_status": "pending",
                "split": "unassigned"
              },
              "missing_input_fields": 2505,
              "recorded_group_count": 984
            }
          ],
          "missing_values": 0,
          "date_range": [
            "2022-06-14",
            "2026-09-11"
          ]
        },
        {
          "id": "china_mission",
          "count": 1762,
          "source_ids": [
            "china_mission",
            "china_mission_zh"
          ],
          "languages": [
            "en",
            "zh"
          ],
          "kinds": {
            "source_records": 1362,
            "evidence_passages": 400
          },
          "tasks": [
            {
              "id": "statement_reconstruction",
              "count": 962,
              "lengths": {
                "input": null,
                "target": {
                  "n": 962,
                  "min": 507,
                  "median": 3834.5,
                  "p95": 6950,
                  "max": 38965,
                  "unit": "Unicode characters"
                },
                "body": null
              },
              "sample": {
                "id": "china_mission:t20221201_10983521",
                "uid": "7e365fdcf6f0f5a9e46bcfa49dcc327c424435962d636bdac330d5f4ccbb5852",
                "title": "Remarks by Ambassador Geng Shuang at UNGA on the Question of Palestine and the Situation in the Middle East",
                "date": "2022-11-30",
                "source_url": "https://un.china-mission.gov.cn/eng/hyyfy/202212/t20221201_10983521.htm",
                "file": "data/canonical/china_mission.jsonl",
                "line": 962,
                "task": "statement_reconstruction",
                "fields": [
                  "available_date",
                  "context",
                  "country_iso3",
                  "country_name",
                  "date_precision",
                  "derivation",
                  "document_symbols",
                  "event_date",
                  "event_date_basis",
                  "group_id",
                  "history",
                  "id",
                  "institution",
                  "language",
                  "phase",
                  "publication_date",
                  "quality_flags",
                  "quality_status",
                  "question",
                  "raw_file",
                  "raw_sha256",
                  "represented_entity",
                  "review_status",
                  "rights_status",
                  "schema_version",
                  "source_id",
                  "source_record_id",
                  "source_url",
                  "speaking_capacity",
                  "split",
                  "task",
                  "text",
                  "title",
                  "topic_method",
                  "topics"
                ],
                "quality_flags": [
                  "institution_review",
                  "event_date_requires_confirmation"
                ],
                "rights_status": "unresolved",
                "review_status": "pending",
                "split": "unassigned"
              },
              "missing_input_fields": 962,
              "recorded_group_count": 624
            },
            {
              "id": "policy_evidence",
              "count": 800,
              "lengths": {
                "input": null,
                "target": null,
                "body": {
                  "n": 800,
                  "min": 235,
                  "median": 847.0,
                  "p95": 1517,
                  "max": 2618,
                  "unit": "Unicode characters"
                }
              },
              "sample": {
                "id": "china_mission_zh:015cb787c539b3e9e1ab",
                "uid": "fa64fdc9b6a76f7065eded1e5d51b20a00c4b4b4d2a7762547676a1c1d06edd4",
                "title": "傅聪大使在《人民日报》发表署名文章《<习近平谈治国理政>第五卷蕴含重大世界意义》（2026-02-09）",
                "date": "2026-02-09",
                "source_url": "https://un.china-mission.gov.cn/chn/hyyfy/202602/t20260209_11854643.htm",
                "file": "data/prepared/expansion-20260913/documents.jsonl",
                "line": 1,
                "task": "policy_evidence",
                "fields": [
                  "admission_status",
                  "available_date",
                  "context",
                  "country_iso3",
                  "country_name",
                  "date_precision",
                  "derivation",
                  "document_symbols",
                  "document_type",
                  "event_date",
                  "event_date_basis",
                  "existing_event_splits",
                  "fresh_evaluation_eligible",
                  "group_id",
                  "history",
                  "id",
                  "institution",
                  "language",
                  "language_basis",
                  "proposed_split",
                  "publication_date",
                  "quality_flags",
                  "quality_status",
                  "question",
                  "raw_file",
                  "raw_sha256",
                  "represented_entity",
                  "review_status",
                  "rights_status",
                  "schema_version",
                  "source_id",
                  "source_record_id",
                  "source_url",
                  "speaking_capacity",
                  "split",
                  "task",
                  "text",
                  "text_sha256",
                  "title",
                  "topic_method",
                  "topics",
                  "training_admitted",
                  "translation_alignment",
                  "translation_status"
                ],
                "quality_flags": [
                  "cross_language_event_link_review",
                  "event_date_requires_confirmation",
                  "multilingual_extraction_review",
                  "speaker_attribution_review"
                ],
                "rights_status": "unresolved",
                "review_status": "pending",
                "split": "quarantine"
              },
              "missing_input_fields": 800,
              "recorded_group_count": 209
            }
          ],
          "missing_values": 0,
          "date_range": [
            "2022-11-30",
            "2026-09-11"
          ]
        },
        {
          "id": "national_policy_documents",
          "count": 77,
          "source_ids": [
            "national_policy_documents"
          ],
          "languages": [
            "en"
          ],
          "kinds": {
            "source_records": 2,
            "evidence_passages": 75
          },
          "tasks": [
            {
              "id": "policy_evidence",
              "count": 77,
              "lengths": {
                "input": null,
                "target": null,
                "body": {
                  "n": 77,
                  "min": 1935,
                  "median": 2960,
                  "p95": 2998,
                  "max": 115232,
                  "unit": "Unicode characters"
                }
              },
              "sample": {
                "id": "national_policy_documents:china_development_whitepaper_2021-en",
                "uid": "c524db668d39ccdd76128245951ebd7c79cacf9778d3169d2d26fe5b62ea72dd",
                "title": "China's International Development Cooperation in the New Era",
                "date": "2021-01-10",
                "source_url": "https://english.mee.gov.cn/Resources/publications/Whitep/202101/P020210122374486901993.pdf",
                "file": "data/prepared/expansion-20260913/documents.jsonl",
                "line": 2360,
                "task": "policy_evidence",
                "fields": [
                  "admission_status",
                  "available_date",
                  "context",
                  "country_iso3",
                  "country_name",
                  "date_precision",
                  "derivation",
                  "document_symbols",
                  "document_type",
                  "event_date",
                  "event_date_basis",
                  "existing_event_splits",
                  "extracted_text_file",
                  "extracted_text_sha256",
                  "extraction_method",
                  "fresh_evaluation_eligible",
                  "group_id",
                  "history",
                  "id",
                  "institution",
                  "language",
                  "language_basis",
                  "pdf_pages",
                  "proposed_split",
                  "publication_date",
                  "quality_flags",
                  "quality_status",
                  "question",
                  "raw_file",
                  "raw_sha256",
                  "represented_entity",
                  "review_status",
                  "rights_status",
                  "schema_version",
                  "source_id",
                  "source_record_id",
                  "source_url",
                  "speaking_capacity",
                  "split",
                  "task",
                  "text",
                  "text_sha256",
                  "title",
                  "topic_method",
                  "topics",
                  "training_admitted",
                  "translation_alignment",
                  "translation_group",
                  "translation_group_basis",
                  "translation_scope",
                  "translation_status"
                ],
                "quality_flags": [
                  "pdf_reading_order_review",
                  "translation_publication_date_unverified"
                ],
                "rights_status": "unresolved",
                "review_status": "pending",
                "split": "quarantine"
              },
              "missing_input_fields": 77,
              "recorded_group_count": 2
            }
          ],
          "missing_values": 0,
          "date_range": [
            "2021-01-10",
            "2024-06-12"
          ]
        },
        {
          "id": "uhri",
          "count": 2259,
          "source_ids": [
            "uhri"
          ],
          "languages": [
            "en"
          ],
          "kinds": {
            "observed_actions": 1088,
            "source_records": 1171
          },
          "tasks": [
            {
              "id": "upr_recommendation",
              "count": 1171,
              "lengths": {
                "input": {
                  "n": 1171,
                  "min": 42,
                  "median": 45,
                  "p95": 64,
                  "max": 90,
                  "unit": "Unicode characters"
                },
                "target": {
                  "n": 1171,
                  "min": 42,
                  "median": 136,
                  "p95": 216,
                  "max": 526,
                  "unit": "Unicode characters"
                },
                "body": null
              },
              "sample": {
                "id": "uhri:01189228-6bcb-4929-b00c-c901df965e35",
                "uid": "a521e381f4eef3ab025ef78b96fab6a6e1f7d6d598c832e88bc7d89e6b27428c",
                "title": "A/HRC/36/12",
                "date": "2017-07-18",
                "source_url": "https://uhri.ohchr.org/en/our-data-api",
                "file": "data/canonical/uhri.jsonl",
                "line": 6642,
                "task": "upr_recommendation",
                "fields": [
                  "affected_persons",
                  "annotation_type",
                  "available_date",
                  "context",
                  "country_iso3",
                  "country_name",
                  "date_precision",
                  "derivation",
                  "document_symbols",
                  "event_date",
                  "group_id",
                  "history",
                  "id",
                  "institution",
                  "language",
                  "mechanism",
                  "quality_flags",
                  "quality_status",
                  "question",
                  "raw_file",
                  "raw_sha256",
                  "recommending_states",
                  "represented_entity",
                  "response_labels",
                  "review_status",
                  "reviewed_states",
                  "rights_status",
                  "schema_version",
                  "sdgs",
                  "source_id",
                  "source_record_id",
                  "source_url",
                  "speaking_capacity",
                  "split",
                  "task",
                  "text",
                  "title",
                  "topic_method",
                  "topics",
                  "upr_cycle",
                  "upr_session"
                ],
                "quality_flags": [
                  "document_date_not_review_date",
                  "recommendation_context_missing"
                ],
                "rights_status": "unresolved",
                "review_status": "pending",
                "split": "unassigned"
              },
              "missing_input_fields": 0,
              "recorded_group_count": 520
            },
            {
              "id": "upr_response",
              "count": 1088,
              "lengths": {
                "input": {
                  "n": 1088,
                  "min": 60,
                  "median": 174.0,
                  "p95": 311,
                  "max": 634,
                  "unit": "Unicode characters"
                },
                "target": {
                  "n": 1088,
                  "min": 5,
                  "median": 9.0,
                  "p95": 9,
                  "max": 9,
                  "unit": "Unicode characters"
                },
                "body": null
              },
              "sample": {
                "id": "uhri:00503781-bb8d-4815-9791-daccdca52951:response",
                "uid": "0a05ae1e041923d3132c18f2939ec6daa7ce623c30b9a74658846600a9a61a7d",
                "title": "A/HRC/11/25",
                "date": "2009-05-29",
                "source_url": "https://uhri.ohchr.org/en/our-data-api",
                "file": "data/canonical/uhri.jsonl",
                "line": 9043,
                "task": "upr_response",
                "fields": [
                  "available_date",
                  "context",
                  "country_iso3",
                  "country_name",
                  "date_precision",
                  "derivation",
                  "document_symbols",
                  "event_date",
                  "group_id",
                  "history",
                  "id",
                  "institution",
                  "language",
                  "parent_id",
                  "quality_flags",
                  "quality_status",
                  "question",
                  "raw_file",
                  "raw_sha256",
                  "recommending_states",
                  "represented_entity",
                  "review_status",
                  "reviewed_states",
                  "rights_status",
                  "schema_version",
                  "source_id",
                  "source_record_id",
                  "source_url",
                  "speaking_capacity",
                  "split",
                  "task",
                  "text",
                  "title",
                  "topic_method",
                  "topics",
                  "upr_cycle",
                  "upr_session"
                ],
                "quality_flags": [
                  "recommendation_context_missing",
                  "response_date_unverified"
                ],
                "rights_status": "unresolved",
                "review_status": "pending",
                "split": "unassigned"
              },
              "missing_input_fields": 0,
              "recorded_group_count": 4
            }
          ],
          "missing_values": 0,
          "date_range": [
            "2008-05-23",
            "2026-01-08"
          ]
        },
        {
          "id": "curated",
          "count": 4,
          "source_ids": [
            "unspecified"
          ],
          "languages": [],
          "kinds": {
            "observed_actions": 1,
            "policy_positions": 2,
            "policy_applications": 1
          },
          "tasks": [
            {
              "id": "policy_positions",
              "count": 2,
              "lengths": {
                "input": null,
                "target": null,
                "body": null
              },
              "sample": {
                "id": "CHN-development-conditions-2021",
                "uid": "ef6956bdb20378fd95ff98efd72329225eaa7322dc3aeafa59dd0ea7069294dd",
                "title": "development_cooperation",
                "date": "2021-01-10",
                "source_url": "https://english.mee.gov.cn/Resources/publications/Whitep/202101/P020210122374486901993.pdf",
                "file": "data/prepared/country-knowledge-20260914/policies.jsonl",
                "line": 3,
                "task": "policy_positions",
                "fields": [
                  "available_date",
                  "capacity",
                  "claim",
                  "country_iso3",
                  "date",
                  "evidence",
                  "fresh_evaluation_eligible",
                  "group_id",
                  "id",
                  "issue",
                  "opposes",
                  "record_type",
                  "retrieved_at",
                  "review_status",
                  "source_url",
                  "split",
                  "supports",
                  "training_admitted",
                  "truth_scope",
                  "unknown"
                ],
                "quality_flags": [],
                "rights_status": "not_recorded",
                "review_status": "author_checked_independent_review_pending",
                "split": "quarantine"
              },
              "missing_input_fields": 2,
              "recorded_group_count": 1
            },
            {
              "id": "policy_applications",
              "count": 1,
              "lengths": {
                "input": {
                  "n": 1,
                  "min": 2125,
                  "median": 2125,
                  "p95": 2125,
                  "max": 2125,
                  "unit": "Unicode characters"
                },
                "target": {
                  "n": 1,
                  "min": 387,
                  "median": 387,
                  "p95": 387,
                  "max": 387,
                  "unit": "Unicode characters"
                },
                "body": null
              },
              "sample": {
                "id": "CHN-development-conditions-demo",
                "uid": "b6eee3285d84a035b4960a0d2bc02849ad5be275df9d58b2597c938204911434",
                "title": "evidence_conditioned_example",
                "date": "2021-01-10",
                "source_url": "",
                "file": "data/prepared/country-knowledge-20260914/examples.jsonl",
                "line": 2,
                "task": "policy_applications",
                "fields": [
                  "answer",
                  "country_iso3",
                  "date",
                  "derivation",
                  "enable_thinking",
                  "fresh_evaluation_eligible",
                  "group_ids",
                  "id",
                  "messages",
                  "question",
                  "record_ids",
                  "record_type",
                  "review_status",
                  "rubric",
                  "split",
                  "training_admitted"
                ],
                "quality_flags": [],
                "rights_status": "not_recorded",
                "review_status": "author_checked_independent_review_pending",
                "split": "quarantine"
              },
              "missing_input_fields": 0,
              "recorded_group_count": 0
            },
            {
              "id": "policy_evidence",
              "count": 1,
              "lengths": {
                "input": null,
                "target": null,
                "body": null
              },
              "sample": {
                "id": "CHN-ES-11-1-20220302",
                "uid": "5589ff2d8619f5c0a247fe163459bbdd8bea97ef3b63fe0cd4d6c80486dbb508",
                "title": "observed_vote",
                "date": "2022-03-02",
                "source_url": "",
                "file": "data/prepared/country-knowledge-20260914/actions.jsonl",
                "line": 5,
                "task": "policy_evidence",
                "fields": [
                  "amended_vote",
                  "bulk_source_id",
                  "country_iso3",
                  "csv_line",
                  "date",
                  "decision_id",
                  "document_symbols",
                  "evaluation_use",
                  "explanation_evidence",
                  "explanation_status",
                  "explanation_text_language",
                  "fresh_evaluation_eligible",
                  "group_id",
                  "id",
                  "language_of_delivery",
                  "original_vote",
                  "primary_roll_call_verified",
                  "primary_vote_pdf_pages",
                  "primary_vote_source_id",
                  "private_motive",
                  "proposal_source_id",
                  "public_explanation_summary",
                  "record_type",
                  "review_status",
                  "split",
                  "training_admitted"
                ],
                "quality_flags": [],
                "rights_status": "not_recorded",
                "review_status": "author_checked_independent_review_pending",
                "split": "quarantine"
              },
              "missing_input_fields": 1,
              "recorded_group_count": 1
            }
          ],
          "missing_values": 0,
          "date_range": [
            "2021-01-10",
            "2022-03-02"
          ]
        },
        {
          "id": "unga_speech_corpus",
          "count": 915,
          "source_ids": [
            "unga_speech_corpus"
          ],
          "languages": [
            "en"
          ],
          "kinds": {
            "source_records": 915
          },
          "tasks": [
            {
              "id": "unverified_speech_segment",
              "count": 466,
              "lengths": {
                "input": null,
                "target": null,
                "body": {
                  "n": 466,
                  "min": 24,
                  "median": 4709.0,
                  "p95": 14179,
                  "max": 44073,
                  "unit": "Unicode characters"
                }
              },
              "sample": {
                "id": "unga_speech_corpus:China_100_54_20000101.txt",
                "uid": "73a30cccbbbb1b761976d23b5545665efd656e94845dd74b6f0e2b9cd69c857f",
                "title": "UNGA A/54/PV.100",
                "date": "2000",
                "source_url": "https://www.linneaturco.com/research",
                "file": "data/canonical/unga_speech_corpus.jsonl",
                "line": 5536,
                "task": "unverified_speech_segment",
                "fields": [
                  "available_date",
                  "context",
                  "country_iso3",
                  "country_name",
                  "date_precision",
                  "derivation",
                  "document_symbols",
                  "event_date",
                  "group_id",
                  "history",
                  "id",
                  "institution",
                  "language",
                  "meeting",
                  "quality_flags",
                  "quality_status",
                  "question",
                  "raw_file",
                  "raw_sha256",
                  "represented_entity",
                  "review_status",
                  "rights_status",
                  "schema_version",
                  "session",
                  "source_id",
                  "source_record_id",
                  "source_url",
                  "speaking_capacity",
                  "split",
                  "task",
                  "text",
                  "title",
                  "topic_method",
                  "topics",
                  "upstream_country_code",
                  "upstream_words_spoken"
                ],
                "quality_flags": [
                  "upstream_speaker_segmentation_unverified",
                  "year_precision_only"
                ],
                "rights_status": "unresolved",
                "review_status": "pending",
                "split": "unassigned"
              },
              "missing_input_fields": 466,
              "recorded_group_count": 464
            },
            {
              "id": "statement_reconstruction",
              "count": 449,
              "lengths": {
                "input": null,
                "target": {
                  "n": 449,
                  "min": 188,
                  "median": 4545,
                  "p95": 12161,
                  "max": 44045,
                  "unit": "Unicode characters"
                },
                "body": null
              },
              "sample": {
                "id": "unga_speech_corpus:China_100_54_20000101.txt:speaker",
                "uid": "0414e2a38f51feef551845c0d21933f1a62811722fb9bc0d8e43a4cbef107eeb",
                "title": "UNGA A/54/PV.100",
                "date": "2000",
                "source_url": "https://www.linneaturco.com/research",
                "file": "data/canonical/unga_speech_corpus.jsonl",
                "line": 5537,
                "task": "statement_reconstruction",
                "fields": [
                  "available_date",
                  "context",
                  "country_iso3",
                  "country_name",
                  "date_precision",
                  "derivation",
                  "document_symbols",
                  "event_date",
                  "group_id",
                  "history",
                  "id",
                  "institution",
                  "language",
                  "meeting",
                  "parent_id",
                  "quality_flags",
                  "quality_status",
                  "question",
                  "raw_file",
                  "raw_sha256",
                  "represented_entity",
                  "review_status",
                  "rights_status",
                  "schema_version",
                  "session",
                  "source_char_span",
                  "source_id",
                  "source_record_id",
                  "source_url",
                  "speaking_capacity",
                  "split",
                  "task",
                  "text",
                  "title",
                  "topic_method",
                  "topics"
                ],
                "quality_flags": [
                  "meeting_agenda_missing",
                  "speaker_boundary_rule_requires_review",
                  "year_precision_only"
                ],
                "rights_status": "unresolved",
                "review_status": "pending",
                "split": "unassigned"
              },
              "missing_input_fields": 449,
              "recorded_group_count": 447
            }
          ],
          "missing_values": 0,
          "date_range": [
            "1993",
            "2017-12-20"
          ]
        },
        {
          "id": "unga_dm",
          "count": 6354,
          "source_ids": [
            "unga_dm"
          ],
          "languages": [
            "en"
          ],
          "kinds": {
            "source_records": 6354
          },
          "tasks": [
            {
              "id": "vote_label_only",
              "count": 6354,
              "lengths": {
                "input": null,
                "target": null,
                "body": {
                  "n": 6354,
                  "min": 7,
                  "median": 8.0,
                  "p95": 10,
                  "max": 10,
                  "unit": "Unicode characters"
                }
              },
              "sample": {
                "id": "unga_dm:A/31/427-FP:710",
                "uid": "b63b991533f7b859cfa623277e207507cccdac968bebd3209ea50f090d4f1836",
                "title": "A/31/427-FP",
                "date": "1976-12-14",
                "source_url": "https://unvotes.unige.ch/",
                "file": "data/canonical/unga_dm.jsonl",
                "line": 264,
                "task": "vote_label_only",
                "fields": [
                  "amended_vote",
                  "available_date",
                  "context",
                  "country_iso3",
                  "country_name",
                  "current_seat_name",
                  "date_precision",
                  "decision_mode",
                  "decision_topic",
                  "derivation",
                  "document_symbols",
                  "draft_resolution_id",
                  "event_date",
                  "group_id",
                  "history",
                  "id",
                  "institution",
                  "language",
                  "meeting_record_id",
                  "member_state_id",
                  "original_seat_name",
                  "original_vote",
                  "quality_flags",
                  "quality_status",
                  "question",
                  "raw_file",
                  "raw_sha256",
                  "represented_entity",
                  "resolution_id",
                  "review_status",
                  "rights_status",
                  "schema_version",
                  "session_id",
                  "source_id",
                  "source_record_id",
                  "source_url",
                  "speaking_capacity",
                  "split",
                  "task",
                  "text",
                  "title",
                  "topic_method",
                  "topics",
                  "vote_was_amended"
                ],
                "quality_flags": [
                  "proposal_text_missing"
                ],
                "rights_status": "unresolved",
                "review_status": "pending",
                "split": "unassigned"
              },
              "missing_input_fields": 6354,
              "recorded_group_count": 6354
            }
          ],
          "missing_values": 0,
          "date_range": [
            "1971-11-09",
            "2023-09-01"
          ]
        },
        {
          "id": "ungdc",
          "count": 76,
          "source_ids": [
            "ungdc_web"
          ],
          "languages": [
            "en"
          ],
          "kinds": {
            "source_records": 76
          },
          "tasks": [
            {
              "id": "domain_text",
              "count": 76,
              "lengths": {
                "input": null,
                "target": null,
                "body": {
                  "n": 76,
                  "min": 7641,
                  "median": 19612.0,
                  "p95": 40523,
                  "max": 43319,
                  "unit": "Unicode characters"
                }
              },
              "sample": {
                "id": "ungdc_web:chn_01_1946",
                "uid": "3cac0e1401136df5c8b13c67fed8863d904d9dfa78459b9085c969c56844397f",
                "title": "UN General Debate session 1 (1946)",
                "date": "1946",
                "source_url": "https://www.ungdc.bham.ac.uk/sessions/session/chn_01_1946/",
                "file": "data/canonical/ungdc.jsonl",
                "line": 76,
                "task": "domain_text",
                "fields": [
                  "available_date",
                  "context",
                  "country_iso3",
                  "country_name",
                  "date_precision",
                  "derivation",
                  "document_symbols",
                  "event_date",
                  "group_id",
                  "history",
                  "id",
                  "institution",
                  "language",
                  "quality_flags",
                  "quality_status",
                  "question",
                  "raw_file",
                  "raw_sha256",
                  "represented_entity",
                  "review_status",
                  "rights_status",
                  "schema_version",
                  "session",
                  "source_id",
                  "source_record_id",
                  "source_url",
                  "speaking_capacity",
                  "split",
                  "task",
                  "text",
                  "title",
                  "topic_method",
                  "topics"
                ],
                "quality_flags": [
                  "historical_entity_review",
                  "year_precision_only",
                  "not_PRC_training"
                ],
                "rights_status": "unresolved",
                "review_status": "pending",
                "split": "unassigned"
              },
              "missing_input_fields": 76,
              "recorded_group_count": 76
            }
          ],
          "missing_values": 0,
          "date_range": [
            "1946",
            "2022"
          ]
        },
        {
          "id": "upr_reports",
          "count": 102,
          "source_ids": [
            "upr_national_reports"
          ],
          "languages": [
            "ar",
            "en",
            "es",
            "fr",
            "ru",
            "zh"
          ],
          "kinds": {
            "source_records": 6,
            "evidence_passages": 96
          },
          "tasks": [
            {
              "id": "policy_evidence",
              "count": 102,
              "lengths": {
                "input": null,
                "target": null,
                "body": {
                  "n": 102,
                  "min": 472,
                  "median": 2965.5,
                  "p95": 12658,
                  "max": 56744,
                  "unit": "Unicode characters"
                }
              },
              "sample": {
                "id": "upr_national_reports:CHN-ar",
                "uid": "5902a876aad9e3735b0751219b9cefd0fe4b8f345871b1771955e2c34810f2b7",
                "title": "UPR national report A/HRC/WG.6/45/CHN/1",
                "date": "2023-11-03",
                "source_url": "https://documents.un.org/api/symbol/access?l=ar&s=A%2FHRC%2FWG.6%2F45%2FCHN%2F1&t=pdf",
                "file": "data/prepared/expansion-20260913/documents.jsonl",
                "line": 2378,
                "task": "policy_evidence",
                "fields": [
                  "admission_status",
                  "available_date",
                  "context",
                  "country_iso3",
                  "country_name",
                  "date_precision",
                  "derivation",
                  "document_symbols",
                  "document_type",
                  "event_date",
                  "event_date_basis",
                  "existing_event_splits",
                  "extracted_text_file",
                  "extracted_text_sha256",
                  "extraction_method",
                  "fresh_evaluation_eligible",
                  "group_id",
                  "history",
                  "id",
                  "institution",
                  "language",
                  "language_basis",
                  "pdf_pages",
                  "proposed_split",
                  "publication_date",
                  "quality_flags",
                  "quality_status",
                  "question",
                  "raw_file",
                  "raw_sha256",
                  "represented_entity",
                  "review_status",
                  "rights_status",
                  "schema_version",
                  "source_id",
                  "source_record_id",
                  "source_url",
                  "speaking_capacity",
                  "split",
                  "split_policy",
                  "task",
                  "text",
                  "text_sha256",
                  "title",
                  "topic_method",
                  "topics",
                  "training_admitted",
                  "translation_alignment",
                  "translation_group",
                  "translation_group_basis",
                  "translation_scope",
                  "translation_status",
                  "upr_cycle"
                ],
                "quality_flags": [
                  "pdf_reading_order_review",
                  "report_reissued_2024_01_16; verify_each_language_version",
                  "translation_publication_date_unverified"
                ],
                "rights_status": "unresolved",
                "review_status": "pending",
                "split": "quarantine"
              },
              "missing_input_fields": 102,
              "recorded_group_count": 1
            }
          ],
          "missing_values": 0,
          "date_range": [
            "2023-11-03",
            "2023-11-03"
          ]
        },
        {
          "id": "decision_cases",
          "count": 2,
          "source_ids": [
            "unspecified"
          ],
          "languages": [
            "en"
          ],
          "kinds": {
            "decision_cases": 2
          },
          "tasks": [
            {
              "id": "decision_cases",
              "count": 2,
              "lengths": {
                "input": null,
                "target": null,
                "body": null
              },
              "sample": {
                "id": "decision:CHN-ES-11-1-20220302",
                "uid": "6b1f7d46ff43b9539ce5e7607ba6567b2813f761e72f2cbb134844984d711ee8",
                "title": "Aggression against Ukraine — March 2022",
                "date": "2022-03-02",
                "source_url": "https://docs.un.org/A/ES-11/PV.5",
                "file": "data/prepared/decision-cases-20260914/cases.jsonl",
                "line": 5,
                "task": "decision_cases",
                "fields": [
                  "amended_action",
                  "author",
                  "conditions_for_agreement",
                  "conditions_status",
                  "country_iso3",
                  "country_name",
                  "derivation",
                  "event_date",
                  "explanation_evidence",
                  "explanation_kind",
                  "fresh_evaluation_eligible",
                  "group_id",
                  "id",
                  "issue",
                  "language",
                  "material_context",
                  "missing_context",
                  "observed_action",
                  "private_motive",
                  "proposal_evidence",
                  "proposal_summary",
                  "proposal_symbol",
                  "public_explanation",
                  "record_type",
                  "related_group_ids",
                  "represented_entity",
                  "requested_changes",
                  "resolution_symbol",
                  "review_status",
                  "schema_version",
                  "source_coverage",
                  "source_url",
                  "split",
                  "stated_considerations",
                  "title",
                  "training_admitted",
                  "use",
                  "vote_evidence"
                ],
                "quality_flags": [],
                "rights_status": "not_recorded",
                "review_status": "source_checked_independent_review_pending",
                "split": "quarantine"
              },
              "missing_input_fields": 2,
              "recorded_group_count": 2
            }
          ],
          "missing_values": 0,
          "date_range": [
            "2022-03-02",
            "2022-10-12"
          ]
        },
        {
          "id": "unbench",
          "count": 4,
          "source_ids": [
            "unbench"
          ],
          "languages": [
            "en"
          ],
          "kinds": {
            "source_records": 4
          },
          "tasks": [
            {
              "id": "statement_reconstruction",
              "count": 4,
              "lengths": {
                "input": {
                  "n": 4,
                  "min": 2582,
                  "median": 10209.0,
                  "p95": 21019,
                  "max": 21019,
                  "unit": "Unicode characters"
                },
                "target": {
                  "n": 4,
                  "min": 962,
                  "median": 2140.0,
                  "p95": 4082,
                  "max": 4082,
                  "unit": "Unicode characters"
                },
                "body": null
              },
              "sample": {
                "id": "unbench:S/2024/788:statement:9",
                "uid": "da432fc692e27c3e29b6dd61a8cdc4794db1d7b6765dcdd2a5724b2026b0242e",
                "title": "France: draft resolution",
                "date": "2024-11-01",
                "source_url": "https://github.com/yueqingliang1/UNBench",
                "file": "data/canonical/unbench.jsonl",
                "line": 40,
                "task": "statement_reconstruction",
                "fields": [
                  "available_date",
                  "context",
                  "country_iso3",
                  "country_name",
                  "date_precision",
                  "derivation",
                  "document_symbols",
                  "event_date",
                  "group_id",
                  "history",
                  "id",
                  "institution",
                  "language",
                  "quality_flags",
                  "quality_status",
                  "question",
                  "raw_file",
                  "raw_sha256",
                  "represented_entity",
                  "review_status",
                  "rights_status",
                  "schema_version",
                  "source_id",
                  "source_record_id",
                  "source_url",
                  "speaker",
                  "speaking_capacity",
                  "split",
                  "task",
                  "text",
                  "title",
                  "topic_method",
                  "topics"
                ],
                "quality_flags": [
                  "benchmark_reserved",
                  "phase_unverified"
                ],
                "rights_status": "unresolved",
                "review_status": "pending",
                "split": "test"
              },
              "missing_input_fields": 0,
              "recorded_group_count": 4
            }
          ],
          "missing_values": 0,
          "date_range": [
            "2024-10-30",
            "2024-11-01"
          ]
        },
        {
          "id": "world_bank",
          "count": 43,
          "source_ids": [
            "unspecified",
            "world_bank_2024"
          ],
          "languages": [],
          "kinds": {
            "country_statistics": 43
          },
          "tasks": [
            {
              "id": "country_statistics",
              "count": 43,
              "lengths": {
                "input": null,
                "target": null,
                "body": null
              },
              "sample": {
                "id": "WDI-CHN-NE.TRD.GNFS.ZS-2024",
                "uid": "5fa0627095121a7c82d30e68bf45ff8929bee8f7e6da479e03acbf472a2412f5",
                "title": "Trade (% of GDP)",
                "date": "2024",
                "source_url": "https://api.worldbank.org/v2/country/bra;chn;deu;fra;gbr;ind/indicator/SP.POP.TOTL;NY.GDP.MKTP.CD;NE.TRD.GNFS.ZS?source=2&date=2024&format=json&per_page=1000",
                "file": "data/prepared/country-knowledge-20260914/facts.jsonl",
                "line": 14,
                "task": "country_statistics",
                "fields": [
                  "available_at_reference_year",
                  "country_iso3",
                  "database_last_updated",
                  "definition",
                  "fresh_evaluation_eligible",
                  "id",
                  "indicator",
                  "label",
                  "missing",
                  "record_type",
                  "reference_year",
                  "retrieved_at",
                  "review_status",
                  "source_id",
                  "source_pointer",
                  "source_url",
                  "split",
                  "training_admitted",
                  "unit",
                  "upstream_organization",
                  "use",
                  "value"
                ],
                "quality_flags": [],
                "rights_status": "not_recorded",
                "review_status": "author_checked_independent_review_pending",
                "split": "quarantine"
              },
              "missing_input_fields": 43,
              "recorded_group_count": 0
            }
          ],
          "missing_values": 4,
          "date_range": [
            "2020",
            "2024"
          ]
        }
      ]
    },
    "DEU": {
      "count": 13561,
      "sources": [
        {
          "id": "germany_aa",
          "count": 1336,
          "source_ids": [
            "germany_aa"
          ],
          "languages": [
            "de",
            "en"
          ],
          "kinds": {
            "source_records": 436,
            "evidence_passages": 900
          },
          "tasks": [
            {
              "id": "policy_evidence",
              "count": 1336,
              "lengths": {
                "input": null,
                "target": null,
                "body": {
                  "n": 1336,
                  "min": 118,
                  "median": 2612.0,
                  "p95": 8168,
                  "max": 29438,
                  "unit": "Unicode characters"
                }
              },
              "sample": {
                "id": "germany_aa:009bc7bd08ed9d3c1c2d",
                "uid": "5948946bdfa28bfcd42465566a5a2abff05e7634ed4a8a30dea3d330d6615ad4",
                "title": "Rede von Außenminister Johann Wadephul bei der „MSC in Berlin“-Veranstaltung mit dem NATO-Generalsekretär",
                "date": "2025-12-11",
                "source_url": "https://www.auswaertiges-amt.de/de/newsroom/2753098-2753098",
                "file": "data/prepared/expansion-20260913/documents.jsonl",
                "line": 401,
                "task": "policy_evidence",
                "fields": [
                  "admission_status",
                  "available_date",
                  "context",
                  "country_iso3",
                  "country_name",
                  "date_precision",
                  "derivation",
                  "document_symbols",
                  "document_type",
                  "event_date",
                  "event_date_basis",
                  "existing_event_splits",
                  "fresh_evaluation_eligible",
                  "group_id",
                  "history",
                  "id",
                  "institution",
                  "language",
                  "language_basis",
                  "proposed_split",
                  "publication_date",
                  "publisher_alternates",
                  "quality_flags",
                  "quality_status",
                  "question",
                  "raw_file",
                  "raw_sha256",
                  "represented_entity",
                  "review_status",
                  "rights_status",
                  "schema_version",
                  "source_id",
                  "source_record_id",
                  "source_url",
                  "speaking_capacity",
                  "split",
                  "task",
                  "text",
                  "text_sha256",
                  "title",
                  "topic_method",
                  "topics",
                  "training_admitted",
                  "translation_alignment",
                  "translation_group",
                  "translation_group_basis",
                  "translation_status"
                ],
                "quality_flags": [
                  "event_date_requires_confirmation",
                  "speaker_attribution_review"
                ],
                "rights_status": "rights_reserved",
                "review_status": "pending",
                "split": "quarantine"
              },
              "missing_input_fields": 1336,
              "recorded_group_count": 249
            }
          ],
          "missing_values": 0,
          "date_range": [
            "2023-02-13",
            "2026-09-08"
          ]
        },
        {
          "id": "germany_press",
          "count": 1720,
          "source_ids": [
            "germany_press"
          ],
          "languages": [
            "de"
          ],
          "kinds": {
            "source_records": 1720
          },
          "tasks": [
            {
              "id": "authentic_qa",
              "count": 1541,
              "lengths": {
                "input": {
                  "n": 1541,
                  "min": 118,
                  "median": 31534,
                  "p95": 54820,
                  "max": 67188,
                  "unit": "Unicode characters"
                },
                "target": {
                  "n": 1541,
                  "min": 3,
                  "median": 374,
                  "p95": 1401,
                  "max": 3753,
                  "unit": "Unicode characters"
                },
                "body": null
              },
              "sample": {
                "id": "germany_press:regierungspressekonferenz-vom-1-april-2026-2418742:qa:141",
                "uid": "c861bf859653361d8ebb0c82608b1f39a7c3e6df8157b79bf1adc799e3a29f78",
                "title": "Regierungspressekonferenz vom 1. April 2026",
                "date": "2026-04-01",
                "source_url": "https://www.bundesregierung.de/breg-de/aktuelles/pressekonferenzen/regierungspressekonferenz-vom-1-april-2026-2418742",
                "file": "data/canonical/germany_press.jsonl",
                "line": 407,
                "task": "authentic_qa",
                "fields": [
                  "available_date",
                  "context",
                  "country_iso3",
                  "country_name",
                  "date_precision",
                  "derivation",
                  "document_symbols",
                  "event_date",
                  "group_id",
                  "history",
                  "id",
                  "institution",
                  "language",
                  "parent_id",
                  "quality_flags",
                  "quality_status",
                  "question",
                  "raw_file",
                  "raw_sha256",
                  "represented_entity",
                  "review_status",
                  "rights_status",
                  "schema_version",
                  "source_id",
                  "source_record_id",
                  "source_url",
                  "speaker",
                  "speaking_capacity",
                  "split",
                  "task",
                  "text",
                  "title",
                  "topic_method",
                  "topics"
                ],
                "quality_flags": [],
                "rights_status": "unresolved",
                "review_status": "pending",
                "split": "unassigned"
              },
              "missing_input_fields": 0,
              "recorded_group_count": 168
            },
            {
              "id": "press_conference",
              "count": 179,
              "lengths": {
                "input": null,
                "target": null,
                "body": {
                  "n": 179,
                  "min": 20354,
                  "median": 52800,
                  "p95": 68754,
                  "max": 75498,
                  "unit": "Unicode characters"
                }
              },
              "sample": {
                "id": "germany_press:regierungspressekonferenz-vom-1-april-2026-2418742",
                "uid": "f01cd3540f7ad4c3237f4a19da9ef96f943c9147175bf0f21c4c662a56671094",
                "title": "Regierungspressekonferenz vom 1. April 2026",
                "date": "2026-04-01",
                "source_url": "https://www.bundesregierung.de/breg-de/aktuelles/pressekonferenzen/regierungspressekonferenz-vom-1-april-2026-2418742",
                "file": "data/canonical/germany_press.jsonl",
                "line": 405,
                "task": "press_conference",
                "fields": [
                  "available_date",
                  "context",
                  "country_iso3",
                  "country_name",
                  "date_precision",
                  "derivation",
                  "document_symbols",
                  "event_date",
                  "group_id",
                  "history",
                  "id",
                  "institution",
                  "language",
                  "quality_flags",
                  "quality_status",
                  "question",
                  "raw_file",
                  "raw_sha256",
                  "represented_entity",
                  "review_status",
                  "rights_status",
                  "schema_version",
                  "source_id",
                  "source_record_id",
                  "source_url",
                  "speaking_capacity",
                  "split",
                  "task",
                  "text",
                  "title",
                  "topic_method",
                  "topics"
                ],
                "quality_flags": [],
                "rights_status": "unresolved",
                "review_status": "pending",
                "split": "unassigned"
              },
              "missing_input_fields": 179,
              "recorded_group_count": 179
            }
          ],
          "missing_values": 0,
          "date_range": [
            "2024-09-24",
            "2026-09-07"
          ]
        },
        {
          "id": "germany_mission",
          "count": 452,
          "source_ids": [
            "germany_mission"
          ],
          "languages": [
            "en"
          ],
          "kinds": {
            "source_records": 452
          },
          "tasks": [
            {
              "id": "statement_reconstruction",
              "count": 452,
              "lengths": {
                "input": null,
                "target": {
                  "n": 452,
                  "min": 871,
                  "median": 3133.0,
                  "p95": 6153,
                  "max": 14428,
                  "unit": "Unicode characters"
                },
                "body": null
              },
              "sample": {
                "id": "germany_mission:2506976-2506976",
                "uid": "3caa1472b7c6ed116b8c490c035ad8463d9fb1842dd298a37a00493d846eb482",
                "title": "Opening Statement by Minister of State Tobias Lindner at the Virtual Global Launch Event: Accelerating Financing for Women Human Rights Defenders on the front lines of conflict and crisis",
                "date": "2022-01-18",
                "source_url": "https://new-york-un.diplo.de/un-en/2506976-2506976",
                "file": "data/canonical/germany_mission.jsonl",
                "line": 1,
                "task": "statement_reconstruction",
                "fields": [
                  "available_date",
                  "context",
                  "country_iso3",
                  "country_name",
                  "date_precision",
                  "derivation",
                  "document_symbols",
                  "event_date",
                  "event_date_basis",
                  "group_id",
                  "history",
                  "id",
                  "institution",
                  "language",
                  "phase",
                  "publication_date",
                  "quality_flags",
                  "quality_status",
                  "question",
                  "raw_file",
                  "raw_sha256",
                  "represented_entity",
                  "review_status",
                  "rights_status",
                  "schema_version",
                  "source_id",
                  "source_record_id",
                  "source_url",
                  "speaking_capacity",
                  "split",
                  "task",
                  "text",
                  "title",
                  "topic_method",
                  "topics"
                ],
                "quality_flags": [
                  "institution_review",
                  "event_date_requires_confirmation"
                ],
                "rights_status": "unresolved",
                "review_status": "pending",
                "split": "unassigned"
              },
              "missing_input_fields": 452,
              "recorded_group_count": 366
            }
          ],
          "missing_values": 0,
          "date_range": [
            "2022-01-18",
            "2026-09-01"
          ]
        },
        {
          "id": "national_policy_documents",
          "count": 377,
          "source_ids": [
            "national_policy_documents"
          ],
          "languages": [
            "ar",
            "de",
            "en",
            "es",
            "fr",
            "ja",
            "pl",
            "pt",
            "ru",
            "uk",
            "zh"
          ],
          "kinds": {
            "source_records": 16,
            "evidence_passages": 361
          },
          "tasks": [
            {
              "id": "policy_evidence",
              "count": 377,
              "lengths": {
                "input": null,
                "target": null,
                "body": {
                  "n": 377,
                  "min": 353,
                  "median": 2974,
                  "p95": 2999,
                  "max": 167038,
                  "unit": "Unicode characters"
                }
              },
              "sample": {
                "id": "national_policy_documents:germany_china_strategy-de",
                "uid": "bcfa96c3f157840716523698ec6763dd24c4199b899eecf188dd8fdf7d62f9b4",
                "title": "germany china strategy",
                "date": "2023-07-13",
                "source_url": "https://www.auswaertiges-amt.de/resource/blob/2608578/810fdade376b1467f20bdb697b2acd58/china-strategie-data.pdf",
                "file": "data/prepared/expansion-20260913/documents.jsonl",
                "line": 2362,
                "task": "policy_evidence",
                "fields": [
                  "admission_status",
                  "available_date",
                  "context",
                  "country_iso3",
                  "country_name",
                  "date_precision",
                  "derivation",
                  "document_symbols",
                  "document_type",
                  "event_date",
                  "event_date_basis",
                  "existing_event_splits",
                  "extracted_text_file",
                  "extracted_text_sha256",
                  "extraction_method",
                  "fresh_evaluation_eligible",
                  "group_id",
                  "history",
                  "id",
                  "institution",
                  "language",
                  "language_basis",
                  "pdf_pages",
                  "proposed_split",
                  "publication_date",
                  "quality_flags",
                  "quality_status",
                  "question",
                  "raw_file",
                  "raw_sha256",
                  "represented_entity",
                  "review_status",
                  "rights_status",
                  "schema_version",
                  "source_id",
                  "source_record_id",
                  "source_url",
                  "speaking_capacity",
                  "split",
                  "task",
                  "text",
                  "text_sha256",
                  "title",
                  "topic_method",
                  "topics",
                  "training_admitted",
                  "translation_alignment",
                  "translation_group",
                  "translation_group_basis",
                  "translation_scope",
                  "translation_status"
                ],
                "quality_flags": [
                  "pdf_reading_order_review",
                  "translation_publication_date_unverified"
                ],
                "rights_status": "unresolved",
                "review_status": "pending",
                "split": "quarantine"
              },
              "missing_input_fields": 377,
              "recorded_group_count": 2
            }
          ],
          "missing_values": 0,
          "date_range": [
            "2023-06-14",
            "2023-07-13"
          ]
        },
        {
          "id": "uhri",
          "count": 2797,
          "source_ids": [
            "uhri"
          ],
          "languages": [
            "en"
          ],
          "kinds": {
            "source_records": 1973,
            "observed_actions": 824
          },
          "tasks": [
            {
              "id": "upr_recommendation",
              "count": 1973,
              "lengths": {
                "input": {
                  "n": 1973,
                  "min": 42,
                  "median": 46,
                  "p95": 64,
                  "max": 90,
                  "unit": "Unicode characters"
                },
                "target": {
                  "n": 1973,
                  "min": 35,
                  "median": 173,
                  "p95": 329,
                  "max": 726,
                  "unit": "Unicode characters"
                },
                "body": null
              },
              "sample": {
                "id": "uhri:0011d3e5-397a-4cf9-aa8d-cc3963437af4",
                "uid": "1c3234e6d8a698f3d95b8d6b9a98a28d5ee1140884030b8b37456f4d0399b9e7",
                "title": "A/HRC/52/9",
                "date": "2022-12-07",
                "source_url": "https://uhri.ohchr.org/en/our-data-api",
                "file": "data/canonical/uhri.jsonl",
                "line": 4321,
                "task": "upr_recommendation",
                "fields": [
                  "affected_persons",
                  "annotation_type",
                  "available_date",
                  "context",
                  "country_iso3",
                  "country_name",
                  "date_precision",
                  "derivation",
                  "document_symbols",
                  "event_date",
                  "group_id",
                  "history",
                  "id",
                  "institution",
                  "language",
                  "mechanism",
                  "quality_flags",
                  "quality_status",
                  "question",
                  "raw_file",
                  "raw_sha256",
                  "recommending_states",
                  "represented_entity",
                  "response_labels",
                  "review_status",
                  "reviewed_states",
                  "rights_status",
                  "schema_version",
                  "sdgs",
                  "source_id",
                  "source_record_id",
                  "source_url",
                  "speaking_capacity",
                  "split",
                  "task",
                  "text",
                  "title",
                  "topic_method",
                  "topics",
                  "upr_cycle",
                  "upr_session"
                ],
                "quality_flags": [
                  "document_date_not_review_date",
                  "recommendation_context_missing"
                ],
                "rights_status": "unresolved",
                "review_status": "pending",
                "split": "unassigned"
              },
              "missing_input_fields": 0,
              "recorded_group_count": 606
            },
            {
              "id": "upr_response",
              "count": 824,
              "lengths": {
                "input": {
                  "n": 824,
                  "min": 81,
                  "median": 194.0,
                  "p95": 329,
                  "max": 464,
                  "unit": "Unicode characters"
                },
                "target": {
                  "n": 824,
                  "min": 5,
                  "median": 9.0,
                  "p95": 9,
                  "max": 15,
                  "unit": "Unicode characters"
                },
                "body": null
              },
              "sample": {
                "id": "uhri:0033d0d3-e78c-4557-9b85-cfa26c03ae41:response",
                "uid": "0bd6b0bd048abbf86c57bb7928093cddb59b905ca301ab0562ea089af38fae33",
                "title": "A/HRC/55/10",
                "date": "2023-12-22",
                "source_url": "https://uhri.ohchr.org/en/our-data-api",
                "file": "data/canonical/uhri.jsonl",
                "line": 3535,
                "task": "upr_response",
                "fields": [
                  "available_date",
                  "context",
                  "country_iso3",
                  "country_name",
                  "date_precision",
                  "derivation",
                  "document_symbols",
                  "event_date",
                  "group_id",
                  "history",
                  "id",
                  "institution",
                  "language",
                  "parent_id",
                  "quality_flags",
                  "quality_status",
                  "question",
                  "raw_file",
                  "raw_sha256",
                  "recommending_states",
                  "represented_entity",
                  "review_status",
                  "reviewed_states",
                  "rights_status",
                  "schema_version",
                  "source_id",
                  "source_record_id",
                  "source_url",
                  "speaking_capacity",
                  "split",
                  "task",
                  "text",
                  "title",
                  "topic_method",
                  "topics",
                  "upr_cycle",
                  "upr_session"
                ],
                "quality_flags": [
                  "recommendation_context_missing",
                  "response_date_unverified"
                ],
                "rights_status": "unresolved",
                "review_status": "pending",
                "split": "unassigned"
              },
              "missing_input_fields": 0,
              "recorded_group_count": 4
            }
          ],
          "missing_values": 0,
          "date_range": [
            "2008-05-22",
            "2026-01-08"
          ]
        },
        {
          "id": "curated",
          "count": 6,
          "source_ids": [
            "unspecified"
          ],
          "languages": [
            "en"
          ],
          "kinds": {
            "observed_actions": 1,
            "policy_positions": 3,
            "policy_applications": 2
          },
          "tasks": [
            {
              "id": "policy_positions",
              "count": 3,
              "lengths": {
                "input": null,
                "target": null,
                "body": null
              },
              "sample": {
                "id": "DEU-china-climate-cooperation-2023",
                "uid": "b40a4fad8dda48dedf7ed1d71fd4e2efba1b35f92ce625fb2dfec0461ac69fdf",
                "title": "climate_cooperation",
                "date": "2023-07-13",
                "source_url": "https://www.auswaertiges-amt.de/resource/blob/2608580/49d50fecc479304c3da2e2079c55e106/china-strategie-en-data.pdf",
                "file": "data/prepared/country-knowledge-20260914/policies.jsonl",
                "line": 2,
                "task": "policy_positions",
                "fields": [
                  "available_date",
                  "capacity",
                  "claim",
                  "country_iso3",
                  "date",
                  "evidence",
                  "fresh_evaluation_eligible",
                  "group_id",
                  "id",
                  "issue",
                  "opposes",
                  "record_type",
                  "retrieved_at",
                  "review_status",
                  "source_url",
                  "split",
                  "supports",
                  "training_admitted",
                  "truth_scope",
                  "unknown"
                ],
                "quality_flags": [],
                "rights_status": "not_recorded",
                "review_status": "author_checked_independent_review_pending",
                "split": "quarantine"
              },
              "missing_input_fields": 3,
              "recorded_group_count": 2
            },
            {
              "id": "policy_applications",
              "count": 2,
              "lengths": {
                "input": {
                  "n": 2,
                  "min": 649,
                  "median": 1947.0,
                  "p95": 3245,
                  "max": 3245,
                  "unit": "Unicode characters"
                },
                "target": {
                  "n": 2,
                  "min": 253,
                  "median": 375.0,
                  "p95": 497,
                  "max": 497,
                  "unit": "Unicode characters"
                },
                "body": null
              },
              "sample": {
                "id": "DEU-critical-inputs-demo",
                "uid": "5aa85b5e1e2b19315d73a2d2045ff1e7b8543e4fb6d11971c4797401e68ea083",
                "title": "evidence_conditioned_example",
                "date": "2023-07-13",
                "source_url": "",
                "file": "data/prepared/country-knowledge-20260914/examples.jsonl",
                "line": 1,
                "task": "policy_applications",
                "fields": [
                  "answer",
                  "country_iso3",
                  "date",
                  "derivation",
                  "enable_thinking",
                  "fresh_evaluation_eligible",
                  "group_ids",
                  "id",
                  "messages",
                  "question",
                  "record_ids",
                  "record_type",
                  "review_status",
                  "rubric",
                  "split",
                  "training_admitted"
                ],
                "quality_flags": [],
                "rights_status": "not_recorded",
                "review_status": "author_checked_independent_review_pending",
                "split": "quarantine"
              },
              "missing_input_fields": 0,
              "recorded_group_count": 1
            },
            {
              "id": "policy_evidence",
              "count": 1,
              "lengths": {
                "input": null,
                "target": null,
                "body": null
              },
              "sample": {
                "id": "DEU-ES-11-1-20220302",
                "uid": "168d55999feeaf603b4d204142a16d2ec39da78e21b402c40a4fe521766a2b27",
                "title": "observed_vote",
                "date": "2022-03-02",
                "source_url": "",
                "file": "data/prepared/country-knowledge-20260914/actions.jsonl",
                "line": 4,
                "task": "policy_evidence",
                "fields": [
                  "amended_vote",
                  "bulk_source_id",
                  "country_iso3",
                  "csv_line",
                  "date",
                  "decision_id",
                  "document_symbols",
                  "evaluation_use",
                  "explanation_evidence",
                  "explanation_status",
                  "explanation_text_language",
                  "fresh_evaluation_eligible",
                  "group_id",
                  "id",
                  "language_of_delivery",
                  "original_vote",
                  "primary_roll_call_verified",
                  "primary_vote_pdf_pages",
                  "primary_vote_source_id",
                  "private_motive",
                  "proposal_source_id",
                  "public_explanation_summary",
                  "record_type",
                  "review_status",
                  "split",
                  "training_admitted"
                ],
                "quality_flags": [],
                "rights_status": "not_recorded",
                "review_status": "author_checked_independent_review_pending",
                "split": "quarantine"
              },
              "missing_input_fields": 1,
              "recorded_group_count": 1
            }
          ],
          "missing_values": 0,
          "date_range": [
            "2022-03-02",
            "2023-07-13"
          ]
        },
        {
          "id": "unga_speech_corpus",
          "count": 481,
          "source_ids": [
            "unga_speech_corpus"
          ],
          "languages": [
            "en"
          ],
          "kinds": {
            "source_records": 481
          },
          "tasks": [
            {
              "id": "unverified_speech_segment",
              "count": 250,
              "lengths": {
                "input": null,
                "target": null,
                "body": {
                  "n": 250,
                  "min": 29,
                  "median": 5133.5,
                  "p95": 14528,
                  "max": 59718,
                  "unit": "Unicode characters"
                }
              },
              "sample": {
                "id": "unga_speech_corpus:Germany_100_69_20141114.txt",
                "uid": "d51b6b4dd7023416024eb6ea4572340cd53d370d6a73f26f4f77482f2b6459f5",
                "title": "UNGA A/69/PV.100",
                "date": "2014",
                "source_url": "https://www.linneaturco.com/research",
                "file": "data/canonical/unga_speech_corpus.jsonl",
                "line": 10627,
                "task": "unverified_speech_segment",
                "fields": [
                  "available_date",
                  "context",
                  "country_iso3",
                  "country_name",
                  "date_precision",
                  "derivation",
                  "document_symbols",
                  "event_date",
                  "group_id",
                  "history",
                  "id",
                  "institution",
                  "language",
                  "meeting",
                  "quality_flags",
                  "quality_status",
                  "question",
                  "raw_file",
                  "raw_sha256",
                  "represented_entity",
                  "review_status",
                  "rights_status",
                  "schema_version",
                  "session",
                  "source_id",
                  "source_record_id",
                  "source_url",
                  "speaking_capacity",
                  "split",
                  "task",
                  "text",
                  "title",
                  "topic_method",
                  "topics",
                  "upstream_country_code",
                  "upstream_words_spoken"
                ],
                "quality_flags": [
                  "upstream_speaker_segmentation_unverified",
                  "year_precision_only"
                ],
                "rights_status": "unresolved",
                "review_status": "pending",
                "split": "unassigned"
              },
              "missing_input_fields": 250,
              "recorded_group_count": 249
            },
            {
              "id": "statement_reconstruction",
              "count": 231,
              "lengths": {
                "input": null,
                "target": {
                  "n": 231,
                  "min": 263,
                  "median": 4835,
                  "p95": 14291,
                  "max": 34731,
                  "unit": "Unicode characters"
                },
                "body": null
              },
              "sample": {
                "id": "unga_speech_corpus:Germany_100_69_20141114.txt:speaker",
                "uid": "a0b0564c54690abbe6c3f0b7514397694910937c68611c46c6b314019fadee7b",
                "title": "UNGA A/69/PV.100",
                "date": "2014",
                "source_url": "https://www.linneaturco.com/research",
                "file": "data/canonical/unga_speech_corpus.jsonl",
                "line": 10628,
                "task": "statement_reconstruction",
                "fields": [
                  "available_date",
                  "context",
                  "country_iso3",
                  "country_name",
                  "date_precision",
                  "derivation",
                  "document_symbols",
                  "event_date",
                  "group_id",
                  "history",
                  "id",
                  "institution",
                  "language",
                  "meeting",
                  "parent_id",
                  "quality_flags",
                  "quality_status",
                  "question",
                  "raw_file",
                  "raw_sha256",
                  "represented_entity",
                  "review_status",
                  "rights_status",
                  "schema_version",
                  "session",
                  "source_char_span",
                  "source_id",
                  "source_record_id",
                  "source_url",
                  "speaking_capacity",
                  "split",
                  "task",
                  "text",
                  "title",
                  "topic_method",
                  "topics"
                ],
                "quality_flags": [
                  "meeting_agenda_missing",
                  "speaker_boundary_rule_requires_review",
                  "year_precision_only"
                ],
                "rights_status": "unresolved",
                "review_status": "pending",
                "split": "unassigned"
              },
              "missing_input_fields": 231,
              "recorded_group_count": 230
            }
          ],
          "missing_values": 0,
          "date_range": [
            "1993",
            "2017-09-11"
          ]
        },
        {
          "id": "unga_dm",
          "count": 6139,
          "source_ids": [
            "unga_dm"
          ],
          "languages": [
            "en"
          ],
          "kinds": {
            "source_records": 6139
          },
          "tasks": [
            {
              "id": "vote_label_only",
              "count": 6139,
              "lengths": {
                "input": null,
                "target": null,
                "body": {
                  "n": 6139,
                  "min": 7,
                  "median": 8,
                  "p95": 10,
                  "max": 10,
                  "unit": "Unicode characters"
                }
              },
              "sample": {
                "id": "unga_dm:A/31/427-FP:260",
                "uid": "f2b0cbe31a372a818d772623a811e1eebc8afff9690b4e01d043c5799d6a9623",
                "title": "A/31/427-FP",
                "date": "1976-12-14",
                "source_url": "https://unvotes.unige.ch/",
                "file": "data/canonical/unga_dm.jsonl",
                "line": 262,
                "task": "vote_label_only",
                "fields": [
                  "amended_vote",
                  "available_date",
                  "context",
                  "country_iso3",
                  "country_name",
                  "current_seat_name",
                  "date_precision",
                  "decision_mode",
                  "decision_topic",
                  "derivation",
                  "document_symbols",
                  "draft_resolution_id",
                  "event_date",
                  "group_id",
                  "history",
                  "id",
                  "institution",
                  "language",
                  "meeting_record_id",
                  "member_state_id",
                  "original_seat_name",
                  "original_vote",
                  "quality_flags",
                  "quality_status",
                  "question",
                  "raw_file",
                  "raw_sha256",
                  "represented_entity",
                  "resolution_id",
                  "review_status",
                  "rights_status",
                  "schema_version",
                  "session_id",
                  "source_id",
                  "source_record_id",
                  "source_url",
                  "speaking_capacity",
                  "split",
                  "task",
                  "text",
                  "title",
                  "topic_method",
                  "topics",
                  "vote_was_amended"
                ],
                "quality_flags": [
                  "historical_entity_review",
                  "proposal_text_missing"
                ],
                "rights_status": "unresolved",
                "review_status": "pending",
                "split": "unassigned"
              },
              "missing_input_fields": 6139,
              "recorded_group_count": 6139
            }
          ],
          "missing_values": 0,
          "date_range": [
            "1973-10-26",
            "2023-09-01"
          ]
        },
        {
          "id": "ungdc",
          "count": 50,
          "source_ids": [
            "ungdc_web"
          ],
          "languages": [
            "en"
          ],
          "kinds": {
            "source_records": 50
          },
          "tasks": [
            {
              "id": "domain_text",
              "count": 50,
              "lengths": {
                "input": null,
                "target": null,
                "body": {
                  "n": 50,
                  "min": 8961,
                  "median": 21933.5,
                  "p95": 34836,
                  "max": 46133,
                  "unit": "Unicode characters"
                }
              },
              "sample": {
                "id": "ungdc_web:deu_28_1973",
                "uid": "a35759a4e5340c77d7beee959a0852d2d435a6d889b8ccefb8b049f6bf05e9d5",
                "title": "UN General Debate session 28 (1973)",
                "date": "1973",
                "source_url": "https://www.ungdc.bham.ac.uk/sessions/session/deu_28_1973/",
                "file": "data/canonical/ungdc.jsonl",
                "line": 126,
                "task": "domain_text",
                "fields": [
                  "available_date",
                  "context",
                  "country_iso3",
                  "country_name",
                  "date_precision",
                  "derivation",
                  "document_symbols",
                  "event_date",
                  "group_id",
                  "history",
                  "id",
                  "institution",
                  "language",
                  "quality_flags",
                  "quality_status",
                  "question",
                  "raw_file",
                  "raw_sha256",
                  "represented_entity",
                  "review_status",
                  "rights_status",
                  "schema_version",
                  "session",
                  "source_id",
                  "source_record_id",
                  "source_url",
                  "speaking_capacity",
                  "split",
                  "task",
                  "text",
                  "title",
                  "topic_method",
                  "topics"
                ],
                "quality_flags": [
                  "historical_entity_review",
                  "year_precision_only"
                ],
                "rights_status": "unresolved",
                "review_status": "pending",
                "split": "unassigned"
              },
              "missing_input_fields": 50,
              "recorded_group_count": 50
            }
          ],
          "missing_values": 0,
          "date_range": [
            "1973",
            "2022"
          ]
        },
        {
          "id": "upr_reports",
          "count": 158,
          "source_ids": [
            "upr_national_reports"
          ],
          "languages": [
            "ar",
            "en",
            "es",
            "fr",
            "ru",
            "zh"
          ],
          "kinds": {
            "source_records": 6,
            "evidence_passages": 152
          },
          "tasks": [
            {
              "id": "policy_evidence",
              "count": 158,
              "lengths": {
                "input": null,
                "target": null,
                "body": {
                  "n": 158,
                  "min": 141,
                  "median": 2958.5,
                  "p95": 2998,
                  "max": 88611,
                  "unit": "Unicode characters"
                }
              },
              "sample": {
                "id": "upr_national_reports:DEU-ar",
                "uid": "f3e162679c706269946658063e6a47d1b34633e50504a7692d6bab63029facf3",
                "title": "UPR national report A/HRC/WG.6/44/DEU/1",
                "date": "2023-09-01",
                "source_url": "https://documents.un.org/api/symbol/access?l=ar&s=A%2FHRC%2FWG.6%2F44%2FDEU%2F1&t=pdf",
                "file": "data/prepared/expansion-20260913/documents.jsonl",
                "line": 2384,
                "task": "policy_evidence",
                "fields": [
                  "admission_status",
                  "available_date",
                  "context",
                  "country_iso3",
                  "country_name",
                  "date_precision",
                  "derivation",
                  "document_symbols",
                  "document_type",
                  "event_date",
                  "event_date_basis",
                  "existing_event_splits",
                  "extracted_text_file",
                  "extracted_text_sha256",
                  "extraction_method",
                  "fresh_evaluation_eligible",
                  "group_id",
                  "history",
                  "id",
                  "institution",
                  "language",
                  "language_basis",
                  "pdf_pages",
                  "proposed_split",
                  "publication_date",
                  "quality_flags",
                  "quality_status",
                  "question",
                  "raw_file",
                  "raw_sha256",
                  "represented_entity",
                  "review_status",
                  "rights_status",
                  "schema_version",
                  "source_id",
                  "source_record_id",
                  "source_url",
                  "speaking_capacity",
                  "split",
                  "split_policy",
                  "task",
                  "text",
                  "text_sha256",
                  "title",
                  "topic_method",
                  "topics",
                  "training_admitted",
                  "translation_alignment",
                  "translation_group",
                  "translation_group_basis",
                  "translation_scope",
                  "translation_status",
                  "upr_cycle"
                ],
                "quality_flags": [
                  "pdf_reading_order_review",
                  "translation_publication_date_unverified"
                ],
                "rights_status": "unresolved",
                "review_status": "pending",
                "split": "quarantine"
              },
              "missing_input_fields": 158,
              "recorded_group_count": 1
            }
          ],
          "missing_values": 0,
          "date_range": [
            "2023-09-01",
            "2023-09-01"
          ]
        },
        {
          "id": "decision_cases",
          "count": 2,
          "source_ids": [
            "unspecified"
          ],
          "languages": [
            "en"
          ],
          "kinds": {
            "decision_cases": 2
          },
          "tasks": [
            {
              "id": "decision_cases",
              "count": 2,
              "lengths": {
                "input": null,
                "target": null,
                "body": null
              },
              "sample": {
                "id": "decision:DEU-ES-11-1-20220302",
                "uid": "772621d9bbf2cb35fcd4d7bd7f1b7a276da6fad8d5a4761ec6b86bded6a6b92b",
                "title": "Aggression against Ukraine — March 2022",
                "date": "2022-03-02",
                "source_url": "https://docs.un.org/A/ES-11/PV.5",
                "file": "data/prepared/decision-cases-20260914/cases.jsonl",
                "line": 4,
                "task": "decision_cases",
                "fields": [
                  "amended_action",
                  "author",
                  "conditions_for_agreement",
                  "conditions_status",
                  "country_iso3",
                  "country_name",
                  "derivation",
                  "event_date",
                  "explanation_evidence",
                  "explanation_kind",
                  "fresh_evaluation_eligible",
                  "group_id",
                  "id",
                  "issue",
                  "language",
                  "material_context",
                  "missing_context",
                  "observed_action",
                  "private_motive",
                  "proposal_evidence",
                  "proposal_summary",
                  "proposal_symbol",
                  "public_explanation",
                  "record_type",
                  "related_group_ids",
                  "represented_entity",
                  "requested_changes",
                  "resolution_symbol",
                  "review_status",
                  "schema_version",
                  "source_coverage",
                  "source_url",
                  "split",
                  "stated_considerations",
                  "title",
                  "training_admitted",
                  "use",
                  "vote_evidence"
                ],
                "quality_flags": [],
                "rights_status": "not_recorded",
                "review_status": "source_checked_independent_review_pending",
                "split": "quarantine"
              },
              "missing_input_fields": 2,
              "recorded_group_count": 2
            }
          ],
          "missing_values": 0,
          "date_range": [
            "2022-03-02",
            "2022-10-12"
          ]
        },
        {
          "id": "world_bank",
          "count": 43,
          "source_ids": [
            "unspecified",
            "world_bank_2024"
          ],
          "languages": [],
          "kinds": {
            "country_statistics": 43
          },
          "tasks": [
            {
              "id": "country_statistics",
              "count": 43,
              "lengths": {
                "input": null,
                "target": null,
                "body": null
              },
              "sample": {
                "id": "WDI-DEU-NE.TRD.GNFS.ZS-2024",
                "uid": "c4643f0632540b0e45e7385559b60a06fcd9e25914481051ebc16221ff37bda3",
                "title": "Trade (% of GDP)",
                "date": "2024",
                "source_url": "https://api.worldbank.org/v2/country/bra;chn;deu;fra;gbr;ind/indicator/SP.POP.TOTL;NY.GDP.MKTP.CD;NE.TRD.GNFS.ZS?source=2&date=2024&format=json&per_page=1000",
                "file": "data/prepared/country-knowledge-20260914/facts.jsonl",
                "line": 15,
                "task": "country_statistics",
                "fields": [
                  "available_at_reference_year",
                  "country_iso3",
                  "database_last_updated",
                  "definition",
                  "fresh_evaluation_eligible",
                  "id",
                  "indicator",
                  "label",
                  "missing",
                  "record_type",
                  "reference_year",
                  "retrieved_at",
                  "review_status",
                  "source_id",
                  "source_pointer",
                  "source_url",
                  "split",
                  "training_admitted",
                  "unit",
                  "upstream_organization",
                  "use",
                  "value"
                ],
                "quality_flags": [],
                "rights_status": "not_recorded",
                "review_status": "author_checked_independent_review_pending",
                "split": "quarantine"
              },
              "missing_input_fields": 43,
              "recorded_group_count": 0
            }
          ],
          "missing_values": 4,
          "date_range": [
            "2020",
            "2024"
          ]
        }
      ]
    },
    "FRA": {
      "count": 12317,
      "sources": [
        {
          "id": "france_mfa",
          "count": 55,
          "source_ids": [
            "france_mfa"
          ],
          "languages": [
            "fr"
          ],
          "kinds": {
            "source_records": 1,
            "evidence_passages": 54
          },
          "tasks": [
            {
              "id": "policy_evidence",
              "count": 54,
              "lengths": {
                "input": null,
                "target": null,
                "body": {
                  "n": 54,
                  "min": 255,
                  "median": 1722.5,
                  "p95": 2800,
                  "max": 2800,
                  "unit": "Unicode characters"
                }
              },
              "sample": {
                "id": "france_mfa:FRA-indopacific-2025-fr:span:10587:11776",
                "uid": "50a238d62f9fb03f5f2ed0811aed63842611af2e7189d69850384938b659bce3",
                "title": "france_mfa:FRA-indopacific-2025-fr:span:10587:11776",
                "date": "2025",
                "source_url": "https://www.diplomatie.gouv.fr/files/files/priorites-et-actions/grands-dossiers/strate_gie_indopacifique_de_la_france_2025_cle0bc96b.pdf",
                "file": "data/prepared/country-extension-20260914/evidence-passages.jsonl",
                "line": 467,
                "task": "policy_evidence",
                "fields": [
                  "available_date",
                  "country_iso3",
                  "document_type",
                  "end_char",
                  "event_date",
                  "group_id",
                  "id",
                  "language",
                  "parent_id",
                  "pdf_page",
                  "proposed_split",
                  "raw_sha256",
                  "related_countries",
                  "represented_entity",
                  "review_status",
                  "source_id",
                  "source_url",
                  "split",
                  "split_group",
                  "start_char",
                  "text",
                  "training_admitted",
                  "use"
                ],
                "quality_flags": [],
                "rights_status": "not_recorded",
                "review_status": "pending",
                "split": "quarantine"
              },
              "missing_input_fields": 54,
              "recorded_group_count": 1
            },
            {
              "id": "policy_evidence_document",
              "count": 1,
              "lengths": {
                "input": null,
                "target": null,
                "body": {
                  "n": 1,
                  "min": 97685,
                  "median": 97685,
                  "p95": 97685,
                  "max": 97685,
                  "unit": "Unicode characters"
                }
              },
              "sample": {
                "id": "france_mfa:FRA-indopacific-2025-fr",
                "uid": "54d49465c44d3009cee0863516799b19d7a1f014a2a0132a54472fe5e2bc941d",
                "title": "La stratégie indopacifique de la France 2025",
                "date": "2025",
                "source_url": "https://www.diplomatie.gouv.fr/files/files/priorites-et-actions/grands-dossiers/strate_gie_indopacifique_de_la_france_2025_cle0bc96b.pdf",
                "file": "data/prepared/country-extension-20260914/documents.jsonl",
                "line": 4,
                "task": "policy_evidence_document",
                "fields": [
                  "available_date",
                  "context",
                  "country_iso3",
                  "country_name",
                  "date_basis",
                  "date_precision",
                  "derivation",
                  "document_symbols",
                  "document_type",
                  "event_date",
                  "existing_event_splits",
                  "extracted_text_file",
                  "extracted_text_sha256",
                  "fresh_evaluation_eligible",
                  "fresh_evaluation_note",
                  "group_id",
                  "history",
                  "id",
                  "institution",
                  "language",
                  "original_language",
                  "pdf_pages",
                  "proposed_split",
                  "publisher_date_label",
                  "quality_flags",
                  "quality_status",
                  "question",
                  "raw_file",
                  "raw_sha256",
                  "related_countries",
                  "represented_entity",
                  "retrieved_at",
                  "review_status",
                  "rights_status",
                  "schema_version",
                  "source_id",
                  "source_record_id",
                  "source_url",
                  "speaking_capacity",
                  "split",
                  "split_group",
                  "task",
                  "text",
                  "title",
                  "topic_method",
                  "topics",
                  "training_admitted",
                  "translation_family",
                  "translation_status",
                  "upr_cycle"
                ],
                "quality_flags": [
                  "evidence_document_not_response_target",
                  "historical_version_availability_unverified",
                  "individual_claims_require_review"
                ],
                "rights_status": "unresolved",
                "review_status": "pending",
                "split": "quarantine"
              },
              "missing_input_fields": 1,
              "recorded_group_count": 1
            }
          ],
          "missing_values": 0,
          "date_range": [
            "2025",
            "2025"
          ]
        },
        {
          "id": "france_elysee",
          "count": 7,
          "source_ids": [
            "france_elysee"
          ],
          "languages": [
            "fr"
          ],
          "kinds": {
            "source_records": 1,
            "evidence_passages": 6
          },
          "tasks": [
            {
              "id": "policy_evidence",
              "count": 6,
              "lengths": {
                "input": null,
                "target": null,
                "body": {
                  "n": 6,
                  "min": 1400,
                  "median": 2799.5,
                  "p95": 2800,
                  "max": 2800,
                  "unit": "Unicode characters"
                }
              },
              "sample": {
                "id": "france_elysee:FRA-palestine-2025-fr:span:0:2800",
                "uid": "71a4c0f61fd504579ccd66b804e5935e2d481a2272a1073b895449bb23670a43",
                "title": "france_elysee:FRA-palestine-2025-fr:span:0:2800",
                "date": "2025-09-22",
                "source_url": "https://www.elysee.fr/emmanuel-macron/2025/09/22/80e-session-de-lassemblee-generale-des-nations-unies-a-new-york-premiere-journee",
                "file": "data/prepared/country-extension-20260914/evidence-passages.jsonl",
                "line": 1338,
                "task": "policy_evidence",
                "fields": [
                  "available_date",
                  "country_iso3",
                  "document_type",
                  "end_char",
                  "event_date",
                  "group_id",
                  "id",
                  "language",
                  "parent_id",
                  "pdf_page",
                  "proposed_split",
                  "raw_sha256",
                  "related_countries",
                  "represented_entity",
                  "review_status",
                  "source_id",
                  "source_url",
                  "split",
                  "split_group",
                  "start_char",
                  "text",
                  "training_admitted",
                  "use"
                ],
                "quality_flags": [],
                "rights_status": "not_recorded",
                "review_status": "pending",
                "split": "quarantine"
              },
              "missing_input_fields": 6,
              "recorded_group_count": 1
            },
            {
              "id": "policy_evidence_document",
              "count": 1,
              "lengths": {
                "input": null,
                "target": null,
                "body": {
                  "n": 1,
                  "min": 15400,
                  "median": 15400,
                  "p95": 15400,
                  "max": 15400,
                  "unit": "Unicode characters"
                }
              },
              "sample": {
                "id": "france_elysee:FRA-palestine-2025-fr",
                "uid": "ede6eae7fbeab04a94b6bf072ce8be4b645f900bfe9d8f5e7d5be05242f51034",
                "title": "Palestine recognition and two-state conference — presidential speech",
                "date": "2025-09-22",
                "source_url": "https://www.elysee.fr/emmanuel-macron/2025/09/22/80e-session-de-lassemblee-generale-des-nations-unies-a-new-york-premiere-journee",
                "file": "data/prepared/country-extension-20260914/documents.jsonl",
                "line": 16,
                "task": "policy_evidence_document",
                "fields": [
                  "available_date",
                  "context",
                  "country_iso3",
                  "country_name",
                  "date_basis",
                  "date_precision",
                  "derivation",
                  "document_symbols",
                  "document_type",
                  "event_date",
                  "existing_event_splits",
                  "extracted_text_file",
                  "extracted_text_sha256",
                  "fresh_evaluation_eligible",
                  "fresh_evaluation_note",
                  "group_id",
                  "history",
                  "id",
                  "institution",
                  "language",
                  "original_language",
                  "proposed_split",
                  "publisher_date_label",
                  "quality_flags",
                  "quality_status",
                  "question",
                  "raw_file",
                  "raw_sha256",
                  "related_countries",
                  "represented_entity",
                  "retrieved_at",
                  "review_status",
                  "rights_status",
                  "schema_version",
                  "source_id",
                  "source_record_id",
                  "source_url",
                  "speaking_capacity",
                  "split",
                  "split_group",
                  "task",
                  "text",
                  "title",
                  "topic_method",
                  "topics",
                  "training_admitted",
                  "translation_family",
                  "translation_status",
                  "upr_cycle"
                ],
                "quality_flags": [
                  "evidence_document_not_response_target",
                  "historical_version_availability_unverified",
                  "individual_claims_require_review",
                  "publisher_transcript_body_selected_editorial_overview_excluded"
                ],
                "rights_status": "unresolved",
                "review_status": "pending",
                "split": "quarantine"
              },
              "missing_input_fields": 1,
              "recorded_group_count": 1
            }
          ],
          "missing_values": 0,
          "date_range": [
            "2025-09-22",
            "2025-09-22"
          ]
        },
        {
          "id": "france_sgdsn",
          "count": 463,
          "source_ids": [
            "france_sgdsn"
          ],
          "languages": [
            "de",
            "en",
            "fr"
          ],
          "kinds": {
            "source_records": 3,
            "evidence_passages": 460
          },
          "tasks": [
            {
              "id": "policy_evidence",
              "count": 460,
              "lengths": {
                "input": null,
                "target": null,
                "body": {
                  "n": 460,
                  "min": 185,
                  "median": 1883.5,
                  "p95": 2800,
                  "max": 2800,
                  "unit": "Unicode characters"
                }
              },
              "sample": {
                "id": "france_sgdsn:FRA-security-2025-de:span:10114:11604",
                "uid": "73e3858011a3aea7fc464f8e906ec89e4a68f851f83e518bcca51679338c4a7a",
                "title": "france_sgdsn:FRA-security-2025-de:span:10114:11604",
                "date": "2025-07-14",
                "source_url": "https://www.sgdsn.gouv.fr/files/files/Publications/20251007_RNS_ALL.pdf",
                "file": "data/prepared/country-extension-20260914/evidence-passages.jsonl",
                "line": 302,
                "task": "policy_evidence",
                "fields": [
                  "available_date",
                  "country_iso3",
                  "document_type",
                  "end_char",
                  "event_date",
                  "group_id",
                  "id",
                  "language",
                  "parent_id",
                  "pdf_page",
                  "proposed_split",
                  "raw_sha256",
                  "related_countries",
                  "represented_entity",
                  "review_status",
                  "source_id",
                  "source_url",
                  "split",
                  "split_group",
                  "start_char",
                  "text",
                  "training_admitted",
                  "use"
                ],
                "quality_flags": [],
                "rights_status": "not_recorded",
                "review_status": "pending",
                "split": "quarantine"
              },
              "missing_input_fields": 460,
              "recorded_group_count": 1
            },
            {
              "id": "policy_evidence_document",
              "count": 3,
              "lengths": {
                "input": null,
                "target": null,
                "body": {
                  "n": 3,
                  "min": 268156,
                  "median": 291099,
                  "p95": 305400,
                  "max": 305400,
                  "unit": "Unicode characters"
                }
              },
              "sample": {
                "id": "france_sgdsn:FRA-security-2025-de",
                "uid": "ddd269c10291670c11e75d3d5e5e7b9cff6efdc73183aa46d4180efe0d9d7157",
                "title": "Nationale Strategische Überprüfung 2025",
                "date": "2025-07-14",
                "source_url": "https://www.sgdsn.gouv.fr/files/files/Publications/20251007_RNS_ALL.pdf",
                "file": "data/prepared/country-extension-20260914/documents.jsonl",
                "line": 3,
                "task": "policy_evidence_document",
                "fields": [
                  "available_date",
                  "context",
                  "country_iso3",
                  "country_name",
                  "date_basis",
                  "date_precision",
                  "derivation",
                  "document_symbols",
                  "document_type",
                  "event_date",
                  "existing_event_splits",
                  "extracted_text_file",
                  "extracted_text_sha256",
                  "fresh_evaluation_eligible",
                  "fresh_evaluation_note",
                  "group_id",
                  "history",
                  "id",
                  "institution",
                  "language",
                  "original_language",
                  "pdf_pages",
                  "proposed_split",
                  "publisher_date_label",
                  "quality_flags",
                  "quality_status",
                  "question",
                  "raw_file",
                  "raw_sha256",
                  "related_countries",
                  "represented_entity",
                  "retrieved_at",
                  "review_status",
                  "rights_status",
                  "schema_version",
                  "source_id",
                  "source_record_id",
                  "source_url",
                  "speaking_capacity",
                  "split",
                  "split_group",
                  "task",
                  "text",
                  "title",
                  "topic_method",
                  "topics",
                  "training_admitted",
                  "translation_family",
                  "translation_status",
                  "upr_cycle"
                ],
                "quality_flags": [
                  "evidence_document_not_response_target",
                  "historical_version_availability_unverified",
                  "individual_claims_require_review"
                ],
                "rights_status": "unresolved",
                "review_status": "pending",
                "split": "quarantine"
              },
              "missing_input_fields": 3,
              "recorded_group_count": 1
            }
          ],
          "missing_values": 0,
          "date_range": [
            "2025-07-14",
            "2025-07-14"
          ]
        },
        {
          "id": "uhri",
          "count": 3505,
          "source_ids": [
            "uhri"
          ],
          "languages": [
            "en"
          ],
          "kinds": {
            "observed_actions": 844,
            "source_records": 2661
          },
          "tasks": [
            {
              "id": "upr_recommendation",
              "count": 2661,
              "lengths": {
                "input": {
                  "n": 2661,
                  "min": 42,
                  "median": 46,
                  "p95": 64,
                  "max": 90,
                  "unit": "Unicode characters"
                },
                "target": {
                  "n": 2661,
                  "min": 27,
                  "median": 152,
                  "p95": 286,
                  "max": 920,
                  "unit": "Unicode characters"
                },
                "body": null
              },
              "sample": {
                "id": "uhri:001cfafe-12c4-405a-bf38-e84341bc4f39",
                "uid": "e589277e2f187e72fef0125ae0570396596119fe5a8fab88b56767acde8759d0",
                "title": "A/HRC/40/11",
                "date": "2019-01-07",
                "source_url": "https://uhri.ohchr.org/en/our-data-api",
                "file": "data/prepared/country-extension-20260914/uhri-records.jsonl",
                "line": 9278,
                "task": "upr_recommendation",
                "fields": [
                  "affected_persons",
                  "annotation_type",
                  "available_date",
                  "context",
                  "country_iso3",
                  "country_name",
                  "date_precision",
                  "derivation",
                  "document_symbols",
                  "event_date",
                  "existing_event_splits",
                  "fresh_evaluation_eligible",
                  "fresh_evaluation_note",
                  "group_id",
                  "history",
                  "id",
                  "institution",
                  "language",
                  "mechanism",
                  "proposed_split",
                  "quality_flags",
                  "quality_status",
                  "question",
                  "raw_file",
                  "raw_sha256",
                  "recommending_states",
                  "represented_entity",
                  "response_labels",
                  "review_status",
                  "reviewed_states",
                  "rights_status",
                  "schema_version",
                  "sdgs",
                  "source_id",
                  "source_record_id",
                  "source_url",
                  "speaking_capacity",
                  "split",
                  "split_group",
                  "task",
                  "text",
                  "title",
                  "topic_method",
                  "topics",
                  "training_admitted",
                  "upr_cycle",
                  "upr_session"
                ],
                "quality_flags": [
                  "document_date_not_review_date",
                  "recommendation_context_missing"
                ],
                "rights_status": "unresolved",
                "review_status": "pending",
                "split": "quarantine"
              },
              "missing_input_fields": 0,
              "recorded_group_count": 648
            },
            {
              "id": "upr_response",
              "count": 844,
              "lengths": {
                "input": {
                  "n": 844,
                  "min": 75,
                  "median": 187.0,
                  "p95": 318,
                  "max": 545,
                  "unit": "Unicode characters"
                },
                "target": {
                  "n": 844,
                  "min": 5,
                  "median": 9.0,
                  "p95": 9,
                  "max": 15,
                  "unit": "Unicode characters"
                },
                "body": null
              },
              "sample": {
                "id": "uhri:0005fcb4-1be5-4884-b9e3-1a886adbb860:response",
                "uid": "c0157189f68329d1f46927835bbdd5030a323b408e5b963c64596b4aa3b303bf",
                "title": "A/HRC/54/5",
                "date": "2023-07-17",
                "source_url": "https://uhri.ohchr.org/en/our-data-api",
                "file": "data/prepared/country-extension-20260914/uhri-records.jsonl",
                "line": 4957,
                "task": "upr_response",
                "fields": [
                  "available_date",
                  "context",
                  "country_iso3",
                  "country_name",
                  "date_precision",
                  "derivation",
                  "document_symbols",
                  "event_date",
                  "existing_event_splits",
                  "fresh_evaluation_eligible",
                  "fresh_evaluation_note",
                  "group_id",
                  "history",
                  "id",
                  "institution",
                  "language",
                  "parent_id",
                  "proposed_split",
                  "quality_flags",
                  "quality_status",
                  "question",
                  "raw_file",
                  "raw_sha256",
                  "recommending_states",
                  "represented_entity",
                  "review_status",
                  "reviewed_states",
                  "rights_status",
                  "schema_version",
                  "source_id",
                  "source_record_id",
                  "source_url",
                  "speaking_capacity",
                  "split",
                  "split_group",
                  "task",
                  "text",
                  "title",
                  "topic_method",
                  "topics",
                  "training_admitted",
                  "upr_cycle",
                  "upr_session"
                ],
                "quality_flags": [
                  "recommendation_context_missing",
                  "response_date_unverified"
                ],
                "rights_status": "unresolved",
                "review_status": "pending",
                "split": "quarantine"
              },
              "missing_input_fields": 0,
              "recorded_group_count": 4
            }
          ],
          "missing_values": 0,
          "date_range": [
            "2008-05-22",
            "2026-01-08"
          ]
        },
        {
          "id": "curated",
          "count": 10,
          "source_ids": [
            "unspecified"
          ],
          "languages": [
            "en"
          ],
          "kinds": {
            "observed_actions": 1,
            "policy_positions": 4,
            "policy_applications": 3,
            "source_records": 2
          },
          "tasks": [
            {
              "id": "policy_positions",
              "count": 4,
              "lengths": {
                "input": null,
                "target": null,
                "body": null
              },
              "sample": {
                "id": "FRA-EU-climate-2030-2023",
                "uid": "6ca15905dd3c2fb0b836254740c8deee029207ba4ef0309da6658ff0c4be3ae0",
                "title": "climate_commitments",
                "date": "2023",
                "source_url": "https://www.wto.org/english/tratop_e/tpr_e/g442_e.pdf",
                "file": "data/prepared/country-extension-20260914/policy-positions.candidates.jsonl",
                "line": 3,
                "task": "policy_positions",
                "fields": [
                  "available_date",
                  "claim",
                  "claim_language",
                  "countries",
                  "date",
                  "date_note",
                  "evidence",
                  "fresh_evaluation_eligible",
                  "group_id",
                  "id",
                  "issue",
                  "proposed_split",
                  "record_type",
                  "represented_entity",
                  "review_status",
                  "scope",
                  "split",
                  "split_group",
                  "training_admitted",
                  "translation_status"
                ],
                "quality_flags": [],
                "rights_status": "not_recorded",
                "review_status": "assistant_curated_independent_review_pending",
                "split": "quarantine"
              },
              "missing_input_fields": 4,
              "recorded_group_count": 3
            },
            {
              "id": "policy_applications",
              "count": 3,
              "lengths": {
                "input": {
                  "n": 3,
                  "min": 649,
                  "median": 1039,
                  "p95": 1559,
                  "max": 1559,
                  "unit": "Unicode characters"
                },
                "target": {
                  "n": 3,
                  "min": 232,
                  "median": 251,
                  "p95": 253,
                  "max": 253,
                  "unit": "Unicode characters"
                },
                "body": null
              },
              "sample": {
                "id": "FRA-EU-climate-2030-2023:application",
                "uid": "1da2bb40f59d4a67925f6d96c50f720051993361b506e60809ea1e3595f93cca",
                "title": "climate_commitments",
                "date": "2023",
                "source_url": "https://www.wto.org/english/tratop_e/tpr_e/g442_e.pdf",
                "file": "data/prepared/country-extension-20260914/policy-applications.candidates.jsonl",
                "line": 3,
                "task": "policy_applications",
                "fields": [
                  "answer_language",
                  "available_date",
                  "countries",
                  "date",
                  "derivation",
                  "enable_thinking",
                  "evidence",
                  "fresh_evaluation_eligible",
                  "group_id",
                  "id",
                  "issue",
                  "messages",
                  "proposed_split",
                  "record_type",
                  "represented_entity",
                  "review_status",
                  "rubric",
                  "scope",
                  "split",
                  "split_group",
                  "training_admitted"
                ],
                "quality_flags": [],
                "rights_status": "not_recorded",
                "review_status": "assistant_curated_independent_review_pending",
                "split": "quarantine"
              },
              "missing_input_fields": 0,
              "recorded_group_count": 2
            },
            {
              "id": "policy_evidence",
              "count": 3,
              "lengths": {
                "input": null,
                "target": null,
                "body": null
              },
              "sample": {
                "id": "FRA-ES-11-1-20220302",
                "uid": "89309fcd174e1b6d6ed276033cdb493305cd0bf3f2e758a8d5bc5a7b565da54c",
                "title": "observed_vote",
                "date": "2022-03-02",
                "source_url": "",
                "file": "data/prepared/country-knowledge-20260914/actions.jsonl",
                "line": 3,
                "task": "policy_evidence",
                "fields": [
                  "amended_vote",
                  "bulk_source_id",
                  "country_iso3",
                  "csv_line",
                  "date",
                  "decision_id",
                  "document_symbols",
                  "evaluation_use",
                  "explanation_evidence",
                  "explanation_status",
                  "explanation_text_language",
                  "fresh_evaluation_eligible",
                  "group_id",
                  "id",
                  "language_of_delivery",
                  "original_vote",
                  "primary_roll_call_verified",
                  "primary_vote_pdf_pages",
                  "primary_vote_source_id",
                  "private_motive",
                  "proposal_source_id",
                  "public_explanation_summary",
                  "record_type",
                  "review_status",
                  "split",
                  "training_admitted"
                ],
                "quality_flags": [],
                "rights_status": "not_recorded",
                "review_status": "author_checked_independent_review_pending",
                "split": "quarantine"
              },
              "missing_input_fields": 3,
              "recorded_group_count": 1
            }
          ],
          "missing_values": 0,
          "date_range": [
            "2022-03-02",
            "2025-07-14"
          ]
        },
        {
          "id": "unga_speech_corpus",
          "count": 491,
          "source_ids": [
            "unga_speech_corpus"
          ],
          "languages": [
            "en"
          ],
          "kinds": {
            "source_records": 491
          },
          "tasks": [
            {
              "id": "unverified_speech_segment",
              "count": 253,
              "lengths": {
                "input": null,
                "target": null,
                "body": {
                  "n": 253,
                  "min": 29,
                  "median": 4056,
                  "p95": 14691,
                  "max": 26103,
                  "unit": "Unicode characters"
                }
              },
              "sample": {
                "id": "unga_speech_corpus:France_100_54_20000101.txt",
                "uid": "e83b07ef8b35cc4fbffa7092472d26906de70bf9b940c667a80b2baa51fed9c2",
                "title": "UNGA A/54/PV.100",
                "date": "2000",
                "source_url": "https://www.linneaturco.com/research",
                "file": "data/prepared/country-extension-20260914/unga-speech-segments.jsonl",
                "line": 856,
                "task": "unverified_speech_segment",
                "fields": [
                  "available_date",
                  "context",
                  "country_iso3",
                  "country_name",
                  "date_precision",
                  "derivation",
                  "document_symbols",
                  "event_date",
                  "existing_event_splits",
                  "fresh_evaluation_eligible",
                  "fresh_evaluation_note",
                  "group_id",
                  "history",
                  "id",
                  "institution",
                  "language",
                  "meeting",
                  "proposed_split",
                  "quality_flags",
                  "quality_status",
                  "question",
                  "raw_file",
                  "raw_sha256",
                  "represented_entity",
                  "review_status",
                  "rights_status",
                  "schema_version",
                  "session",
                  "source_id",
                  "source_record_id",
                  "source_url",
                  "speaking_capacity",
                  "split",
                  "split_group",
                  "task",
                  "text",
                  "title",
                  "topic_method",
                  "topics",
                  "training_admitted",
                  "upstream_country_code",
                  "upstream_words_spoken"
                ],
                "quality_flags": [
                  "upstream_speaker_segmentation_unverified",
                  "year_precision_only"
                ],
                "rights_status": "unresolved",
                "review_status": "pending",
                "split": "quarantine"
              },
              "missing_input_fields": 253,
              "recorded_group_count": 251
            },
            {
              "id": "statement_reconstruction",
              "count": 238,
              "lengths": {
                "input": null,
                "target": {
                  "n": 238,
                  "min": 164,
                  "median": 3729.0,
                  "p95": 14546,
                  "max": 25495,
                  "unit": "Unicode characters"
                },
                "body": null
              },
              "sample": {
                "id": "unga_speech_corpus:France_100_54_20000101.txt:speaker",
                "uid": "8a48a979d9125f9eb17f30bf70ccfa57232a7bdb8c39914a1cfd30476228590d",
                "title": "UNGA A/54/PV.100",
                "date": "2000",
                "source_url": "https://www.linneaturco.com/research",
                "file": "data/prepared/country-extension-20260914/unga-speech-segments.jsonl",
                "line": 857,
                "task": "statement_reconstruction",
                "fields": [
                  "available_date",
                  "context",
                  "country_iso3",
                  "country_name",
                  "date_precision",
                  "derivation",
                  "document_symbols",
                  "event_date",
                  "existing_event_splits",
                  "fresh_evaluation_eligible",
                  "fresh_evaluation_note",
                  "group_id",
                  "history",
                  "id",
                  "institution",
                  "language",
                  "meeting",
                  "parent_id",
                  "proposed_split",
                  "quality_flags",
                  "quality_status",
                  "question",
                  "raw_file",
                  "raw_sha256",
                  "represented_entity",
                  "review_status",
                  "rights_status",
                  "schema_version",
                  "session",
                  "source_char_span",
                  "source_id",
                  "source_record_id",
                  "source_url",
                  "speaking_capacity",
                  "split",
                  "split_group",
                  "task",
                  "text",
                  "title",
                  "topic_method",
                  "topics",
                  "training_admitted"
                ],
                "quality_flags": [
                  "coalition_attribution_review",
                  "meeting_agenda_missing",
                  "speaker_boundary_rule_requires_review",
                  "year_precision_only"
                ],
                "rights_status": "unresolved",
                "review_status": "pending",
                "split": "quarantine"
              },
              "missing_input_fields": 238,
              "recorded_group_count": 236
            }
          ],
          "missing_values": 0,
          "date_range": [
            "1993",
            "2017-06-22"
          ]
        },
        {
          "id": "unga_dm",
          "count": 7509,
          "source_ids": [
            "unga_dm"
          ],
          "languages": [
            "en"
          ],
          "kinds": {
            "observed_actions": 7509
          },
          "tasks": [
            {
              "id": "vote_label_only",
              "count": 7509,
              "lengths": {
                "input": null,
                "target": null,
                "body": {
                  "n": 7509,
                  "min": 7,
                  "median": 8,
                  "p95": 10,
                  "max": 10,
                  "unit": "Unicode characters"
                }
              },
              "sample": {
                "id": "unga_dm:A/1081-S0100:220",
                "uid": "e9f8ae99bab6adea70ac00a980d4d30b08870f68426ece015b52fd8f18ec8f95",
                "title": "A/1081-S0100",
                "date": "1949-11-25",
                "source_url": "https://unvotes.unige.ch/",
                "file": "data/prepared/country-extension-20260914/unga-votes.jsonl",
                "line": 27835,
                "task": "vote_label_only",
                "fields": [
                  "amended_vote",
                  "available_date",
                  "context",
                  "country_iso3",
                  "country_name",
                  "current_seat_name",
                  "date_precision",
                  "decision_mode",
                  "decision_topic",
                  "derivation",
                  "document_symbols",
                  "draft_resolution_id",
                  "event_date",
                  "existing_event_splits",
                  "fresh_evaluation_eligible",
                  "fresh_evaluation_note",
                  "group_id",
                  "history",
                  "id",
                  "institution",
                  "language",
                  "meeting_record_id",
                  "member_state_id",
                  "original_seat_name",
                  "original_vote",
                  "proposed_split",
                  "quality_flags",
                  "quality_status",
                  "question",
                  "raw_file",
                  "raw_sha256",
                  "represented_entity",
                  "resolution_id",
                  "review_status",
                  "rights_status",
                  "schema_version",
                  "session_id",
                  "source_id",
                  "source_record_id",
                  "source_url",
                  "speaking_capacity",
                  "split",
                  "split_group",
                  "task",
                  "text",
                  "title",
                  "topic_method",
                  "topics",
                  "training_admitted",
                  "vote_was_amended"
                ],
                "quality_flags": [
                  "proposal_text_missing"
                ],
                "rights_status": "unresolved",
                "review_status": "pending",
                "split": "quarantine"
              },
              "missing_input_fields": 7509,
              "recorded_group_count": 7509
            }
          ],
          "missing_values": 0,
          "date_range": [
            "1946-01-26",
            "2023-09-01"
          ]
        },
        {
          "id": "upr_reports",
          "count": 232,
          "source_ids": [
            "un_upr_national_report"
          ],
          "languages": [
            "ar",
            "en",
            "es",
            "fr",
            "ru",
            "zh"
          ],
          "kinds": {
            "source_records": 6,
            "evidence_passages": 226
          },
          "tasks": [
            {
              "id": "policy_evidence",
              "count": 226,
              "lengths": {
                "input": null,
                "target": null,
                "body": {
                  "n": 226,
                  "min": 223,
                  "median": 1812.5,
                  "p95": 2800,
                  "max": 2800,
                  "unit": "Unicode characters"
                }
              },
              "sample": {
                "id": "un_upr_national_report:upr4-FRA-ar:span:0:412",
                "uid": "985e942d5eb8e6a725813dfed059f11e1f5f327c2c35b5b6ca30bffd0c71f5c3",
                "title": "un_upr_national_report:upr4-FRA-ar:span:0:412",
                "date": "2023-03-07",
                "source_url": "https://documents.un.org/api/symbol/access?l=ar&s=A%2FHRC%2FWG.6%2F43%2FFRA%2F1&t=pdf",
                "file": "data/prepared/country-extension-20260914/evidence-passages.jsonl",
                "line": 1528,
                "task": "policy_evidence",
                "fields": [
                  "available_date",
                  "country_iso3",
                  "document_type",
                  "end_char",
                  "event_date",
                  "group_id",
                  "id",
                  "language",
                  "parent_id",
                  "pdf_page",
                  "proposed_split",
                  "raw_sha256",
                  "related_countries",
                  "represented_entity",
                  "review_status",
                  "source_id",
                  "source_url",
                  "split",
                  "split_group",
                  "start_char",
                  "text",
                  "training_admitted",
                  "use"
                ],
                "quality_flags": [],
                "rights_status": "not_recorded",
                "review_status": "pending",
                "split": "quarantine"
              },
              "missing_input_fields": 226,
              "recorded_group_count": 1
            },
            {
              "id": "policy_evidence_document",
              "count": 6,
              "lengths": {
                "input": null,
                "target": null,
                "body": {
                  "n": 6,
                  "min": 29605,
                  "median": 76855.5,
                  "p95": 80812,
                  "max": 80812,
                  "unit": "Unicode characters"
                }
              },
              "sample": {
                "id": "un_upr_national_report:upr4-FRA-ar",
                "uid": "be7bf0b5f208994c86d0c25160f9b4597b5bf154c5a55bd0897b30b4640150fc",
                "title": "FRA fourth-cycle UPR national report",
                "date": "2023-03-07",
                "source_url": "https://documents.un.org/api/symbol/access?l=ar&s=A%2FHRC%2FWG.6%2F43%2FFRA%2F1&t=pdf",
                "file": "data/prepared/country-extension-20260914/documents.jsonl",
                "line": 22,
                "task": "policy_evidence_document",
                "fields": [
                  "available_date",
                  "context",
                  "country_iso3",
                  "country_name",
                  "date_basis",
                  "date_precision",
                  "derivation",
                  "document_symbols",
                  "document_type",
                  "event_date",
                  "existing_event_splits",
                  "extracted_text_file",
                  "extracted_text_sha256",
                  "fresh_evaluation_eligible",
                  "fresh_evaluation_note",
                  "group_id",
                  "history",
                  "id",
                  "institution",
                  "language",
                  "original_language",
                  "pdf_pages",
                  "proposed_split",
                  "publisher_date_label",
                  "quality_flags",
                  "quality_status",
                  "question",
                  "raw_file",
                  "raw_sha256",
                  "related_countries",
                  "represented_entity",
                  "retrieved_at",
                  "review_status",
                  "rights_status",
                  "schema_version",
                  "source_id",
                  "source_record_id",
                  "source_url",
                  "speaking_capacity",
                  "split",
                  "split_group",
                  "task",
                  "text",
                  "title",
                  "topic_method",
                  "topics",
                  "training_admitted",
                  "translation_family",
                  "translation_status",
                  "upr_cycle"
                ],
                "quality_flags": [
                  "evidence_document_not_response_target",
                  "historical_version_availability_unverified",
                  "individual_claims_require_review"
                ],
                "rights_status": "unresolved",
                "review_status": "pending",
                "split": "quarantine"
              },
              "missing_input_fields": 6,
              "recorded_group_count": 1
            }
          ],
          "missing_values": 0,
          "date_range": [
            "2023-03-07",
            "2023-03-07"
          ]
        },
        {
          "id": "decision_cases",
          "count": 2,
          "source_ids": [
            "unspecified"
          ],
          "languages": [
            "en"
          ],
          "kinds": {
            "decision_cases": 2
          },
          "tasks": [
            {
              "id": "decision_cases",
              "count": 2,
              "lengths": {
                "input": null,
                "target": null,
                "body": null
              },
              "sample": {
                "id": "decision:FRA-ES-11-1-20220302",
                "uid": "7d18626ac3a472bd0c45b1eea52571ef12f313fbac120c9941cbea76b9474831",
                "title": "Aggression against Ukraine — March 2022",
                "date": "2022-03-02",
                "source_url": "https://docs.un.org/A/ES-11/PV.5",
                "file": "data/prepared/decision-cases-20260914/cases.jsonl",
                "line": 3,
                "task": "decision_cases",
                "fields": [
                  "amended_action",
                  "author",
                  "conditions_for_agreement",
                  "conditions_status",
                  "country_iso3",
                  "country_name",
                  "derivation",
                  "event_date",
                  "explanation_evidence",
                  "explanation_kind",
                  "fresh_evaluation_eligible",
                  "group_id",
                  "id",
                  "issue",
                  "language",
                  "material_context",
                  "missing_context",
                  "observed_action",
                  "private_motive",
                  "proposal_evidence",
                  "proposal_summary",
                  "proposal_symbol",
                  "public_explanation",
                  "record_type",
                  "related_group_ids",
                  "represented_entity",
                  "requested_changes",
                  "resolution_symbol",
                  "review_status",
                  "schema_version",
                  "source_coverage",
                  "source_url",
                  "split",
                  "stated_considerations",
                  "title",
                  "training_admitted",
                  "use",
                  "vote_evidence"
                ],
                "quality_flags": [],
                "rights_status": "not_recorded",
                "review_status": "source_checked_independent_review_pending",
                "split": "quarantine"
              },
              "missing_input_fields": 2,
              "recorded_group_count": 2
            }
          ],
          "missing_values": 0,
          "date_range": [
            "2022-03-02",
            "2022-10-12"
          ]
        },
        {
          "id": "world_bank",
          "count": 43,
          "source_ids": [
            "unspecified",
            "world_bank_2024"
          ],
          "languages": [],
          "kinds": {
            "country_statistics": 43
          },
          "tasks": [
            {
              "id": "country_statistics",
              "count": 43,
              "lengths": {
                "input": null,
                "target": null,
                "body": null
              },
              "sample": {
                "id": "WDI-FRA-NE.TRD.GNFS.ZS-2024",
                "uid": "bc404abf24f9168b91d1165c39e17a30f4ebb153bb94a588a6eb324f482663ea",
                "title": "Trade (% of GDP)",
                "date": "2024",
                "source_url": "https://api.worldbank.org/v2/country/bra;chn;deu;fra;gbr;ind/indicator/SP.POP.TOTL;NY.GDP.MKTP.CD;NE.TRD.GNFS.ZS?source=2&date=2024&format=json&per_page=1000",
                "file": "data/prepared/country-knowledge-20260914/facts.jsonl",
                "line": 16,
                "task": "country_statistics",
                "fields": [
                  "available_at_reference_year",
                  "country_iso3",
                  "database_last_updated",
                  "definition",
                  "fresh_evaluation_eligible",
                  "id",
                  "indicator",
                  "label",
                  "missing",
                  "record_type",
                  "reference_year",
                  "retrieved_at",
                  "review_status",
                  "source_id",
                  "source_pointer",
                  "source_url",
                  "split",
                  "training_admitted",
                  "unit",
                  "upstream_organization",
                  "use",
                  "value"
                ],
                "quality_flags": [],
                "rights_status": "not_recorded",
                "review_status": "author_checked_independent_review_pending",
                "split": "quarantine"
              },
              "missing_input_fields": 43,
              "recorded_group_count": 0
            }
          ],
          "missing_values": 4,
          "date_range": [
            "2020",
            "2024"
          ]
        }
      ]
    },
    "GBR": {
      "count": 11054,
      "sources": [
        {
          "id": "uhri",
          "count": 2447,
          "source_ids": [
            "uhri"
          ],
          "languages": [
            "en"
          ],
          "kinds": {
            "source_records": 1771,
            "observed_actions": 676
          },
          "tasks": [
            {
              "id": "upr_recommendation",
              "count": 1771,
              "lengths": {
                "input": {
                  "n": 1771,
                  "min": 42,
                  "median": 45,
                  "p95": 64,
                  "max": 75,
                  "unit": "Unicode characters"
                },
                "target": {
                  "n": 1771,
                  "min": 37,
                  "median": 209,
                  "p95": 342,
                  "max": 553,
                  "unit": "Unicode characters"
                },
                "body": null
              },
              "sample": {
                "id": "uhri:001c41c3-2004-4fa2-be93-8376be1505ff",
                "uid": "c217042af235a8d0e8a195e11348733f34a84aaef17691f0884b102e31fac8aa",
                "title": "A/HRC/8/22",
                "date": "2008-05-22",
                "source_url": "https://uhri.ohchr.org/en/our-data-api",
                "file": "data/prepared/country-extension-20260914/uhri-records.jsonl",
                "line": 17202,
                "task": "upr_recommendation",
                "fields": [
                  "affected_persons",
                  "annotation_type",
                  "available_date",
                  "context",
                  "country_iso3",
                  "country_name",
                  "date_precision",
                  "derivation",
                  "document_symbols",
                  "event_date",
                  "existing_event_splits",
                  "fresh_evaluation_eligible",
                  "fresh_evaluation_note",
                  "group_id",
                  "history",
                  "id",
                  "institution",
                  "language",
                  "mechanism",
                  "proposed_split",
                  "quality_flags",
                  "quality_status",
                  "question",
                  "raw_file",
                  "raw_sha256",
                  "recommending_states",
                  "represented_entity",
                  "response_labels",
                  "review_status",
                  "reviewed_states",
                  "rights_status",
                  "schema_version",
                  "sdgs",
                  "source_id",
                  "source_record_id",
                  "source_url",
                  "speaking_capacity",
                  "split",
                  "split_group",
                  "task",
                  "text",
                  "title",
                  "topic_method",
                  "topics",
                  "training_admitted",
                  "upr_cycle",
                  "upr_session"
                ],
                "quality_flags": [
                  "document_date_not_review_date",
                  "recommendation_context_missing"
                ],
                "rights_status": "unresolved",
                "review_status": "pending",
                "split": "quarantine"
              },
              "missing_input_fields": 0,
              "recorded_group_count": 675
            },
            {
              "id": "upr_response",
              "count": 676,
              "lengths": {
                "input": {
                  "n": 676,
                  "min": 77,
                  "median": 185.5,
                  "p95": 337,
                  "max": 533,
                  "unit": "Unicode characters"
                },
                "target": {
                  "n": 676,
                  "min": 5,
                  "median": 5.0,
                  "p95": 9,
                  "max": 15,
                  "unit": "Unicode characters"
                },
                "body": null
              },
              "sample": {
                "id": "uhri:002ddfae-d666-48ea-bdf8-2d3d6b8d92d4:response",
                "uid": "fe212f5328d4f2c3de3d68c17c0f1e444f4d22556adf2e3a668f6312534e6963",
                "title": "A/HRC/21/9",
                "date": "2012-07-06",
                "source_url": "https://uhri.ohchr.org/en/our-data-api",
                "file": "data/prepared/country-extension-20260914/uhri-records.jsonl",
                "line": 14984,
                "task": "upr_response",
                "fields": [
                  "available_date",
                  "context",
                  "country_iso3",
                  "country_name",
                  "date_precision",
                  "derivation",
                  "document_symbols",
                  "event_date",
                  "existing_event_splits",
                  "fresh_evaluation_eligible",
                  "fresh_evaluation_note",
                  "group_id",
                  "history",
                  "id",
                  "institution",
                  "language",
                  "parent_id",
                  "proposed_split",
                  "quality_flags",
                  "quality_status",
                  "question",
                  "raw_file",
                  "raw_sha256",
                  "recommending_states",
                  "represented_entity",
                  "review_status",
                  "reviewed_states",
                  "rights_status",
                  "schema_version",
                  "source_id",
                  "source_record_id",
                  "source_url",
                  "speaking_capacity",
                  "split",
                  "split_group",
                  "task",
                  "text",
                  "title",
                  "topic_method",
                  "topics",
                  "training_admitted",
                  "upr_cycle",
                  "upr_session"
                ],
                "quality_flags": [
                  "recommendation_context_missing",
                  "response_date_unverified"
                ],
                "rights_status": "unresolved",
                "review_status": "pending",
                "split": "quarantine"
              },
              "missing_input_fields": 0,
              "recorded_group_count": 4
            }
          ],
          "missing_values": 0,
          "date_range": [
            "2008-05-13",
            "2026-01-08"
          ]
        },
        {
          "id": "curated",
          "count": 10,
          "source_ids": [
            "unspecified"
          ],
          "languages": [
            "en"
          ],
          "kinds": {
            "observed_actions": 1,
            "policy_positions": 4,
            "policy_applications": 3,
            "source_records": 2
          },
          "tasks": [
            {
              "id": "policy_positions",
              "count": 4,
              "lengths": {
                "input": null,
                "target": null,
                "body": null
              },
              "sample": {
                "id": "GBR-china-engagement-2025",
                "uid": "fa47e7305bb9bbabfb985cb985e8f4ca19e962e359ffc4a738f491502b9a3bfd",
                "title": "china_relations",
                "date": "2025-06-24",
                "source_url": "https://assets.publishing.service.gov.uk/media/685ab0da72588f418862075c/E03360428_National_Security_Strategy_Accessible.pdf",
                "file": "data/prepared/country-extension-20260914/policy-positions.candidates.jsonl",
                "line": 5,
                "task": "policy_positions",
                "fields": [
                  "available_date",
                  "claim",
                  "claim_language",
                  "countries",
                  "date",
                  "date_note",
                  "evidence",
                  "fresh_evaluation_eligible",
                  "group_id",
                  "id",
                  "issue",
                  "proposed_split",
                  "record_type",
                  "represented_entity",
                  "review_status",
                  "scope",
                  "split",
                  "split_group",
                  "training_admitted",
                  "translation_status"
                ],
                "quality_flags": [],
                "rights_status": "not_recorded",
                "review_status": "assistant_curated_independent_review_pending",
                "split": "quarantine"
              },
              "missing_input_fields": 4,
              "recorded_group_count": 3
            },
            {
              "id": "policy_applications",
              "count": 3,
              "lengths": {
                "input": {
                  "n": 3,
                  "min": 705,
                  "median": 738,
                  "p95": 1884,
                  "max": 1884,
                  "unit": "Unicode characters"
                },
                "target": {
                  "n": 3,
                  "min": 246,
                  "median": 247,
                  "p95": 297,
                  "max": 297,
                  "unit": "Unicode characters"
                },
                "body": null
              },
              "sample": {
                "id": "GBR-china-engagement-2025:application",
                "uid": "8d1ab83541cf9dbe82286ee22cba1684f11c66b0b97ebedd04d2c26e492f89a9",
                "title": "china_relations",
                "date": "2025-06-24",
                "source_url": "https://assets.publishing.service.gov.uk/media/685ab0da72588f418862075c/E03360428_National_Security_Strategy_Accessible.pdf",
                "file": "data/prepared/country-extension-20260914/policy-applications.candidates.jsonl",
                "line": 5,
                "task": "policy_applications",
                "fields": [
                  "answer_language",
                  "available_date",
                  "countries",
                  "date",
                  "derivation",
                  "enable_thinking",
                  "evidence",
                  "fresh_evaluation_eligible",
                  "group_id",
                  "id",
                  "issue",
                  "messages",
                  "proposed_split",
                  "record_type",
                  "represented_entity",
                  "review_status",
                  "rubric",
                  "scope",
                  "split",
                  "split_group",
                  "training_admitted"
                ],
                "quality_flags": [],
                "rights_status": "not_recorded",
                "review_status": "assistant_curated_independent_review_pending",
                "split": "quarantine"
              },
              "missing_input_fields": 0,
              "recorded_group_count": 2
            },
            {
              "id": "policy_evidence",
              "count": 3,
              "lengths": {
                "input": null,
                "target": null,
                "body": null
              },
              "sample": {
                "id": "GBR-ES-11-1-20220302",
                "uid": "ca621550947a30039c90de039fd0f83d6fa2e45e055d7f0367a85e9d35b9b69c",
                "title": "observed_vote",
                "date": "2022-03-02",
                "source_url": "",
                "file": "data/prepared/country-knowledge-20260914/actions.jsonl",
                "line": 2,
                "task": "policy_evidence",
                "fields": [
                  "amended_vote",
                  "bulk_source_id",
                  "country_iso3",
                  "csv_line",
                  "date",
                  "decision_id",
                  "document_symbols",
                  "evaluation_use",
                  "explanation_evidence",
                  "explanation_status",
                  "explanation_text_language",
                  "fresh_evaluation_eligible",
                  "group_id",
                  "id",
                  "language_of_delivery",
                  "original_vote",
                  "primary_roll_call_verified",
                  "primary_vote_pdf_pages",
                  "primary_vote_source_id",
                  "private_motive",
                  "proposal_source_id",
                  "public_explanation_summary",
                  "record_type",
                  "review_status",
                  "split",
                  "training_admitted"
                ],
                "quality_flags": [],
                "rights_status": "not_recorded",
                "review_status": "author_checked_independent_review_pending",
                "split": "quarantine"
              },
              "missing_input_fields": 3,
              "recorded_group_count": 1
            }
          ],
          "missing_values": 0,
          "date_range": [
            "2022-03-02",
            "2025-06-24"
          ]
        },
        {
          "id": "uk_cabinet_office",
          "count": 64,
          "source_ids": [
            "uk_cabinet_office"
          ],
          "languages": [
            "en"
          ],
          "kinds": {
            "source_records": 1,
            "evidence_passages": 63
          },
          "tasks": [
            {
              "id": "policy_evidence",
              "count": 63,
              "lengths": {
                "input": null,
                "target": null,
                "body": {
                  "n": 63,
                  "min": 271,
                  "median": 1650,
                  "p95": 2800,
                  "max": 2800,
                  "unit": "Unicode characters"
                }
              },
              "sample": {
                "id": "uk_cabinet_office:GBR-security-2025-en:span:10079:12423",
                "uid": "0206a3c7226cedc50097b4fb6c7888258f98c521a85f2dd278ccba51967bc32e",
                "title": "uk_cabinet_office:GBR-security-2025-en:span:10079:12423",
                "date": "2025-06-24",
                "source_url": "https://assets.publishing.service.gov.uk/media/685ab0da72588f418862075c/E03360428_National_Security_Strategy_Accessible.pdf",
                "file": "data/prepared/country-extension-20260914/evidence-passages.jsonl",
                "line": 522,
                "task": "policy_evidence",
                "fields": [
                  "available_date",
                  "country_iso3",
                  "document_type",
                  "end_char",
                  "event_date",
                  "group_id",
                  "id",
                  "language",
                  "parent_id",
                  "pdf_page",
                  "proposed_split",
                  "raw_sha256",
                  "related_countries",
                  "represented_entity",
                  "review_status",
                  "source_id",
                  "source_url",
                  "split",
                  "split_group",
                  "start_char",
                  "text",
                  "training_admitted",
                  "use"
                ],
                "quality_flags": [],
                "rights_status": "not_recorded",
                "review_status": "pending",
                "split": "quarantine"
              },
              "missing_input_fields": 63,
              "recorded_group_count": 1
            },
            {
              "id": "policy_evidence_document",
              "count": 1,
              "lengths": {
                "input": null,
                "target": null,
                "body": {
                  "n": 1,
                  "min": 104013,
                  "median": 104013,
                  "p95": 104013,
                  "max": 104013,
                  "unit": "Unicode characters"
                }
              },
              "sample": {
                "id": "uk_cabinet_office:GBR-security-2025-en",
                "uid": "fe8dda44d7afa1fd87f682f739be87fade7e2563d3daa26d75446f6f88251801",
                "title": "National Security Strategy 2025",
                "date": "2025-06-24",
                "source_url": "https://assets.publishing.service.gov.uk/media/685ab0da72588f418862075c/E03360428_National_Security_Strategy_Accessible.pdf",
                "file": "data/prepared/country-extension-20260914/documents.jsonl",
                "line": 5,
                "task": "policy_evidence_document",
                "fields": [
                  "available_date",
                  "context",
                  "country_iso3",
                  "country_name",
                  "date_basis",
                  "date_precision",
                  "derivation",
                  "document_symbols",
                  "document_type",
                  "event_date",
                  "existing_event_splits",
                  "extracted_text_file",
                  "extracted_text_sha256",
                  "fresh_evaluation_eligible",
                  "fresh_evaluation_note",
                  "group_id",
                  "history",
                  "id",
                  "institution",
                  "language",
                  "original_language",
                  "pdf_pages",
                  "proposed_split",
                  "publisher_date_label",
                  "quality_flags",
                  "quality_status",
                  "question",
                  "raw_file",
                  "raw_sha256",
                  "related_countries",
                  "represented_entity",
                  "retrieved_at",
                  "review_status",
                  "rights_status",
                  "schema_version",
                  "source_id",
                  "source_record_id",
                  "source_url",
                  "speaking_capacity",
                  "split",
                  "split_group",
                  "task",
                  "text",
                  "title",
                  "topic_method",
                  "topics",
                  "training_admitted",
                  "translation_family",
                  "translation_status",
                  "upr_cycle"
                ],
                "quality_flags": [
                  "evidence_document_not_response_target",
                  "historical_version_availability_unverified",
                  "individual_claims_require_review"
                ],
                "rights_status": "unresolved",
                "review_status": "pending",
                "split": "quarantine"
              },
              "missing_input_fields": 1,
              "recorded_group_count": 1
            }
          ],
          "missing_values": 0,
          "date_range": [
            "2025-06-24",
            "2025-06-24"
          ]
        },
        {
          "id": "uk_fcdo",
          "count": 5,
          "source_ids": [
            "uk_fcdo"
          ],
          "languages": [
            "en"
          ],
          "kinds": {
            "source_records": 1,
            "evidence_passages": 4
          },
          "tasks": [
            {
              "id": "policy_evidence",
              "count": 4,
              "lengths": {
                "input": null,
                "target": null,
                "body": {
                  "n": 4,
                  "min": 1808,
                  "median": 2800.0,
                  "p95": 2800,
                  "max": 2800,
                  "unit": "Unicode characters"
                }
              },
              "sample": {
                "id": "uk_fcdo:GBR-unga-2025-en:span:0:2800",
                "uid": "cdb083b3edf74932bdc90fbfb7077f3b5427051cbae9c9122a18cf0da82c32df",
                "title": "uk_fcdo:GBR-unga-2025-en:span:0:2800",
                "date": "2025-09-26",
                "source_url": "https://www.gov.uk/api/content/government/speeches/the-united-kingdom-does-not-stand-up-for-one-nations-rights-whilst-ignoring-others-but-acts-resolutely-with-the-un-charter-as-our-compass-uk-nati",
                "file": "data/prepared/country-extension-20260914/evidence-passages.jsonl",
                "line": 1334,
                "task": "policy_evidence",
                "fields": [
                  "available_date",
                  "country_iso3",
                  "document_type",
                  "end_char",
                  "event_date",
                  "group_id",
                  "id",
                  "language",
                  "parent_id",
                  "pdf_page",
                  "proposed_split",
                  "raw_sha256",
                  "related_countries",
                  "represented_entity",
                  "review_status",
                  "source_id",
                  "source_url",
                  "split",
                  "split_group",
                  "start_char",
                  "text",
                  "training_admitted",
                  "use"
                ],
                "quality_flags": [],
                "rights_status": "not_recorded",
                "review_status": "pending",
                "split": "quarantine"
              },
              "missing_input_fields": 4,
              "recorded_group_count": 1
            },
            {
              "id": "policy_evidence_document",
              "count": 1,
              "lengths": {
                "input": null,
                "target": null,
                "body": {
                  "n": 1,
                  "min": 10209,
                  "median": 10209,
                  "p95": 10209,
                  "max": 10209,
                  "unit": "Unicode characters"
                }
              },
              "sample": {
                "id": "uk_fcdo:GBR-unga-2025-en",
                "uid": "5a960c025af4dca258dec2f81ca89d6567062040eb3a3654a69ad5a78eb8e9fb",
                "title": "UK National Statement at the UN General Assembly",
                "date": "2025-09-26",
                "source_url": "https://www.gov.uk/api/content/government/speeches/the-united-kingdom-does-not-stand-up-for-one-nations-rights-whilst-ignoring-others-but-acts-resolutely-with-the-un-charter-as-our-compass-uk-nati",
                "file": "data/prepared/country-extension-20260914/documents.jsonl",
                "line": 15,
                "task": "policy_evidence_document",
                "fields": [
                  "available_date",
                  "context",
                  "country_iso3",
                  "country_name",
                  "date_basis",
                  "date_precision",
                  "derivation",
                  "document_symbols",
                  "document_type",
                  "event_date",
                  "existing_event_splits",
                  "extracted_text_file",
                  "extracted_text_sha256",
                  "fresh_evaluation_eligible",
                  "fresh_evaluation_note",
                  "group_id",
                  "history",
                  "id",
                  "institution",
                  "language",
                  "original_language",
                  "proposed_split",
                  "publisher_date_label",
                  "quality_flags",
                  "quality_status",
                  "question",
                  "raw_file",
                  "raw_sha256",
                  "related_countries",
                  "represented_entity",
                  "retrieved_at",
                  "review_status",
                  "rights_status",
                  "schema_version",
                  "source_id",
                  "source_record_id",
                  "source_url",
                  "speaking_capacity",
                  "split",
                  "split_group",
                  "task",
                  "text",
                  "title",
                  "topic_method",
                  "topics",
                  "training_admitted",
                  "translation_family",
                  "translation_status",
                  "upr_cycle"
                ],
                "quality_flags": [
                  "evidence_document_not_response_target",
                  "historical_version_availability_unverified",
                  "individual_claims_require_review"
                ],
                "rights_status": "unresolved",
                "review_status": "pending",
                "split": "quarantine"
              },
              "missing_input_fields": 1,
              "recorded_group_count": 1
            }
          ],
          "missing_values": 0,
          "date_range": [
            "2025-09-26",
            "2025-09-26"
          ]
        },
        {
          "id": "uk_desnz",
          "count": 162,
          "source_ids": [
            "uk_desnz"
          ],
          "languages": [
            "en"
          ],
          "kinds": {
            "source_records": 1,
            "evidence_passages": 161
          },
          "tasks": [
            {
              "id": "policy_evidence",
              "count": 161,
              "lengths": {
                "input": null,
                "target": null,
                "body": {
                  "n": 161,
                  "min": 225,
                  "median": 873,
                  "p95": 1048,
                  "max": 1339,
                  "unit": "Unicode characters"
                }
              },
              "sample": {
                "id": "uk_desnz:GBR-ndc-2035-government-en:span:0:225",
                "uid": "4ad155adf90bebe2b27ea96d225acf47f3efc7cf424ab7c0c1b30e2e19b10ed8",
                "title": "uk_desnz:GBR-ndc-2035-government-en:span:0:225",
                "date": "2025-01-30",
                "source_url": "https://assets.publishing.service.gov.uk/media/679b655f6bb4c44f0805e7bc/uk-2035-nationally-determined-contribution-large-print.pdf",
                "file": "data/prepared/country-extension-20260914/evidence-passages.jsonl",
                "line": 842,
                "task": "policy_evidence",
                "fields": [
                  "available_date",
                  "country_iso3",
                  "document_type",
                  "end_char",
                  "event_date",
                  "group_id",
                  "id",
                  "language",
                  "parent_id",
                  "pdf_page",
                  "proposed_split",
                  "raw_sha256",
                  "related_countries",
                  "represented_entity",
                  "review_status",
                  "source_id",
                  "source_url",
                  "split",
                  "split_group",
                  "start_char",
                  "text",
                  "training_admitted",
                  "use"
                ],
                "quality_flags": [],
                "rights_status": "not_recorded",
                "review_status": "pending",
                "split": "quarantine"
              },
              "missing_input_fields": 161,
              "recorded_group_count": 1
            },
            {
              "id": "policy_evidence_document",
              "count": 1,
              "lengths": {
                "input": null,
                "target": null,
                "body": {
                  "n": 1,
                  "min": 134451,
                  "median": 134451,
                  "p95": 134451,
                  "max": 134451,
                  "unit": "Unicode characters"
                }
              },
              "sample": {
                "id": "uk_desnz:GBR-ndc-2035-government-en",
                "uid": "c964e1ba9513360f6ebbb2739026f45ec95151d15abc49821daf5f1cfd236c41",
                "title": "UK 2035 NDC — large print official copy",
                "date": "2025-01-30",
                "source_url": "https://assets.publishing.service.gov.uk/media/679b655f6bb4c44f0805e7bc/uk-2035-nationally-determined-contribution-large-print.pdf",
                "file": "data/prepared/country-extension-20260914/documents.jsonl",
                "line": 10,
                "task": "policy_evidence_document",
                "fields": [
                  "available_date",
                  "context",
                  "country_iso3",
                  "country_name",
                  "date_basis",
                  "date_precision",
                  "derivation",
                  "document_symbols",
                  "document_type",
                  "event_date",
                  "existing_event_splits",
                  "extracted_text_file",
                  "extracted_text_sha256",
                  "fresh_evaluation_eligible",
                  "fresh_evaluation_note",
                  "group_id",
                  "history",
                  "id",
                  "institution",
                  "language",
                  "original_language",
                  "pdf_pages",
                  "proposed_split",
                  "publisher_date_label",
                  "quality_flags",
                  "quality_status",
                  "question",
                  "raw_file",
                  "raw_sha256",
                  "related_countries",
                  "represented_entity",
                  "retrieved_at",
                  "review_status",
                  "rights_status",
                  "schema_version",
                  "source_id",
                  "source_record_id",
                  "source_url",
                  "speaking_capacity",
                  "split",
                  "split_group",
                  "task",
                  "text",
                  "title",
                  "topic_method",
                  "topics",
                  "training_admitted",
                  "translation_family",
                  "translation_status",
                  "upr_cycle"
                ],
                "quality_flags": [
                  "evidence_document_not_response_target",
                  "historical_version_availability_unverified",
                  "individual_claims_require_review"
                ],
                "rights_status": "unresolved",
                "review_status": "pending",
                "split": "quarantine"
              },
              "missing_input_fields": 1,
              "recorded_group_count": 1
            }
          ],
          "missing_values": 0,
          "date_range": [
            "2025-01-30",
            "2025-01-30"
          ]
        },
        {
          "id": "unga_speech_corpus",
          "count": 508,
          "source_ids": [
            "unga_speech_corpus"
          ],
          "languages": [
            "en"
          ],
          "kinds": {
            "source_records": 508
          },
          "tasks": [
            {
              "id": "unverified_speech_segment",
              "count": 259,
              "lengths": {
                "input": null,
                "target": null,
                "body": {
                  "n": 259,
                  "min": 43,
                  "median": 4062,
                  "p95": 14958,
                  "max": 22577,
                  "unit": "Unicode characters"
                }
              },
              "sample": {
                "id": "unga_speech_corpus:United Kingdom of Great Britain and Northern Ireland_107_64_20100101.txt",
                "uid": "b22caf01e3d295022efcc1106f36e211952d2ba5227843fafebcc637611a7a71",
                "title": "UNGA A/64/PV.107",
                "date": "2010",
                "source_url": "https://www.linneaturco.com/research",
                "file": "data/prepared/country-extension-20260914/unga-speech-segments.jsonl",
                "line": 2388,
                "task": "unverified_speech_segment",
                "fields": [
                  "available_date",
                  "context",
                  "country_iso3",
                  "country_name",
                  "date_precision",
                  "derivation",
                  "document_symbols",
                  "event_date",
                  "existing_event_splits",
                  "fresh_evaluation_eligible",
                  "fresh_evaluation_note",
                  "group_id",
                  "history",
                  "id",
                  "institution",
                  "language",
                  "meeting",
                  "proposed_split",
                  "quality_flags",
                  "quality_status",
                  "question",
                  "raw_file",
                  "raw_sha256",
                  "represented_entity",
                  "review_status",
                  "rights_status",
                  "schema_version",
                  "session",
                  "source_id",
                  "source_record_id",
                  "source_url",
                  "speaking_capacity",
                  "split",
                  "split_group",
                  "task",
                  "text",
                  "title",
                  "topic_method",
                  "topics",
                  "training_admitted",
                  "upstream_country_code",
                  "upstream_words_spoken"
                ],
                "quality_flags": [
                  "upstream_speaker_segmentation_unverified",
                  "year_precision_only"
                ],
                "rights_status": "unresolved",
                "review_status": "pending",
                "split": "quarantine"
              },
              "missing_input_fields": 259,
              "recorded_group_count": 259
            },
            {
              "id": "statement_reconstruction",
              "count": 249,
              "lengths": {
                "input": null,
                "target": {
                  "n": 249,
                  "min": 400,
                  "median": 3729,
                  "p95": 13607,
                  "max": 22549,
                  "unit": "Unicode characters"
                },
                "body": null
              },
              "sample": {
                "id": "unga_speech_corpus:United Kingdom_100_48_19940101.txt:speaker",
                "uid": "f2ddf91d4f99321c8be10aaa0d771fd35986e1eb7cf154d4bccb3b089b399ac6",
                "title": "UNGA A/48/PV.100",
                "date": "1994",
                "source_url": "https://www.linneaturco.com/research",
                "file": "data/prepared/country-extension-20260914/unga-speech-segments.jsonl",
                "line": 2394,
                "task": "statement_reconstruction",
                "fields": [
                  "available_date",
                  "context",
                  "country_iso3",
                  "country_name",
                  "date_precision",
                  "derivation",
                  "document_symbols",
                  "event_date",
                  "existing_event_splits",
                  "fresh_evaluation_eligible",
                  "fresh_evaluation_note",
                  "group_id",
                  "history",
                  "id",
                  "institution",
                  "language",
                  "meeting",
                  "parent_id",
                  "proposed_split",
                  "quality_flags",
                  "quality_status",
                  "question",
                  "raw_file",
                  "raw_sha256",
                  "represented_entity",
                  "review_status",
                  "rights_status",
                  "schema_version",
                  "session",
                  "source_char_span",
                  "source_id",
                  "source_record_id",
                  "source_url",
                  "speaking_capacity",
                  "split",
                  "split_group",
                  "task",
                  "text",
                  "title",
                  "topic_method",
                  "topics",
                  "training_admitted"
                ],
                "quality_flags": [
                  "coalition_attribution_review",
                  "meeting_agenda_missing",
                  "speaker_boundary_rule_requires_review",
                  "year_precision_only"
                ],
                "rights_status": "unresolved",
                "review_status": "pending",
                "split": "quarantine"
              },
              "missing_input_fields": 249,
              "recorded_group_count": 249
            }
          ],
          "missing_values": 0,
          "date_range": [
            "1993",
            "2018"
          ]
        },
        {
          "id": "unga_dm",
          "count": 7509,
          "source_ids": [
            "unga_dm"
          ],
          "languages": [
            "en"
          ],
          "kinds": {
            "observed_actions": 7509
          },
          "tasks": [
            {
              "id": "vote_label_only",
              "count": 7509,
              "lengths": {
                "input": null,
                "target": null,
                "body": {
                  "n": 7509,
                  "min": 7,
                  "median": 8,
                  "p95": 10,
                  "max": 10,
                  "unit": "Unicode characters"
                }
              },
              "sample": {
                "id": "unga_dm:A/1081-S0100:200",
                "uid": "3d5d65ecf76de2b1d4486cd1b259ae4f9db76217f21710b3a57bf421f0c70c7a",
                "title": "A/1081-S0100",
                "date": "1949-11-25",
                "source_url": "https://unvotes.unige.ch/",
                "file": "data/prepared/country-extension-20260914/unga-votes.jsonl",
                "line": 27834,
                "task": "vote_label_only",
                "fields": [
                  "amended_vote",
                  "available_date",
                  "context",
                  "country_iso3",
                  "country_name",
                  "current_seat_name",
                  "date_precision",
                  "decision_mode",
                  "decision_topic",
                  "derivation",
                  "document_symbols",
                  "draft_resolution_id",
                  "event_date",
                  "existing_event_splits",
                  "fresh_evaluation_eligible",
                  "fresh_evaluation_note",
                  "group_id",
                  "history",
                  "id",
                  "institution",
                  "language",
                  "meeting_record_id",
                  "member_state_id",
                  "original_seat_name",
                  "original_vote",
                  "proposed_split",
                  "quality_flags",
                  "quality_status",
                  "question",
                  "raw_file",
                  "raw_sha256",
                  "represented_entity",
                  "resolution_id",
                  "review_status",
                  "rights_status",
                  "schema_version",
                  "session_id",
                  "source_id",
                  "source_record_id",
                  "source_url",
                  "speaking_capacity",
                  "split",
                  "split_group",
                  "task",
                  "text",
                  "title",
                  "topic_method",
                  "topics",
                  "training_admitted",
                  "vote_was_amended"
                ],
                "quality_flags": [
                  "proposal_text_missing"
                ],
                "rights_status": "unresolved",
                "review_status": "pending",
                "split": "quarantine"
              },
              "missing_input_fields": 7509,
              "recorded_group_count": 7509
            }
          ],
          "missing_values": 0,
          "date_range": [
            "1946-01-26",
            "2023-09-01"
          ]
        },
        {
          "id": "upr_reports",
          "count": 242,
          "source_ids": [
            "un_upr_national_report"
          ],
          "languages": [
            "ar",
            "en",
            "es",
            "fr",
            "ru",
            "zh"
          ],
          "kinds": {
            "source_records": 6,
            "evidence_passages": 236
          },
          "tasks": [
            {
              "id": "policy_evidence",
              "count": 236,
              "lengths": {
                "input": null,
                "target": null,
                "body": {
                  "n": 236,
                  "min": 236,
                  "median": 1906.5,
                  "p95": 2800,
                  "max": 2800,
                  "unit": "Unicode characters"
                }
              },
              "sample": {
                "id": "un_upr_national_report:upr4-GBR-ar:span:0:460",
                "uid": "eb69eca7f4f58b115c7abde716a084a16147b36c2c3c73d0cad1bbb47dd05fa1",
                "title": "un_upr_national_report:upr4-GBR-ar:span:0:460",
                "date": "2022-08-17",
                "source_url": "https://documents.un.org/api/symbol/access?l=ar&s=A%2FHRC%2FWG.6%2F41%2FGBR%2F1&t=pdf",
                "file": "data/prepared/country-extension-20260914/evidence-passages.jsonl",
                "line": 1761,
                "task": "policy_evidence",
                "fields": [
                  "available_date",
                  "country_iso3",
                  "document_type",
                  "end_char",
                  "event_date",
                  "group_id",
                  "id",
                  "language",
                  "parent_id",
                  "pdf_page",
                  "proposed_split",
                  "raw_sha256",
                  "related_countries",
                  "represented_entity",
                  "review_status",
                  "source_id",
                  "source_url",
                  "split",
                  "split_group",
                  "start_char",
                  "text",
                  "training_admitted",
                  "use"
                ],
                "quality_flags": [],
                "rights_status": "not_recorded",
                "review_status": "pending",
                "split": "quarantine"
              },
              "missing_input_fields": 236,
              "recorded_group_count": 1
            },
            {
              "id": "policy_evidence_document",
              "count": 6,
              "lengths": {
                "input": null,
                "target": null,
                "body": {
                  "n": 6,
                  "min": 31946,
                  "median": 84378.5,
                  "p95": 95773,
                  "max": 95773,
                  "unit": "Unicode characters"
                }
              },
              "sample": {
                "id": "un_upr_national_report:upr4-GBR-ar",
                "uid": "7172789c9aa5317c04c6364b7d0a71eab46749ac3c7b95ef5813fd7192c27b19",
                "title": "GBR fourth-cycle UPR national report",
                "date": "2022-08-17",
                "source_url": "https://documents.un.org/api/symbol/access?l=ar&s=A%2FHRC%2FWG.6%2F41%2FGBR%2F1&t=pdf",
                "file": "data/prepared/country-extension-20260914/documents.jsonl",
                "line": 28,
                "task": "policy_evidence_document",
                "fields": [
                  "available_date",
                  "context",
                  "country_iso3",
                  "country_name",
                  "date_basis",
                  "date_precision",
                  "derivation",
                  "document_symbols",
                  "document_type",
                  "event_date",
                  "existing_event_splits",
                  "extracted_text_file",
                  "extracted_text_sha256",
                  "fresh_evaluation_eligible",
                  "fresh_evaluation_note",
                  "group_id",
                  "history",
                  "id",
                  "institution",
                  "language",
                  "original_language",
                  "pdf_pages",
                  "proposed_split",
                  "publisher_date_label",
                  "quality_flags",
                  "quality_status",
                  "question",
                  "raw_file",
                  "raw_sha256",
                  "related_countries",
                  "represented_entity",
                  "retrieved_at",
                  "review_status",
                  "rights_status",
                  "schema_version",
                  "source_id",
                  "source_record_id",
                  "source_url",
                  "speaking_capacity",
                  "split",
                  "split_group",
                  "task",
                  "text",
                  "title",
                  "topic_method",
                  "topics",
                  "training_admitted",
                  "translation_family",
                  "translation_status",
                  "upr_cycle"
                ],
                "quality_flags": [
                  "evidence_document_not_response_target",
                  "historical_version_availability_unverified",
                  "individual_claims_require_review"
                ],
                "rights_status": "unresolved",
                "review_status": "pending",
                "split": "quarantine"
              },
              "missing_input_fields": 6,
              "recorded_group_count": 1
            }
          ],
          "missing_values": 0,
          "date_range": [
            "2022-08-17",
            "2022-08-17"
          ]
        },
        {
          "id": "decision_cases",
          "count": 2,
          "source_ids": [
            "unspecified"
          ],
          "languages": [
            "en"
          ],
          "kinds": {
            "decision_cases": 2
          },
          "tasks": [
            {
              "id": "decision_cases",
              "count": 2,
              "lengths": {
                "input": null,
                "target": null,
                "body": null
              },
              "sample": {
                "id": "decision:GBR-ES-11-1-20220302",
                "uid": "325f2a66eb7de7d118d3d1fc3cb1d05bc0a074863c406edfbd4fbc1396e39b52",
                "title": "Aggression against Ukraine — March 2022",
                "date": "2022-03-02",
                "source_url": "https://docs.un.org/A/ES-11/PV.5",
                "file": "data/prepared/decision-cases-20260914/cases.jsonl",
                "line": 2,
                "task": "decision_cases",
                "fields": [
                  "amended_action",
                  "author",
                  "conditions_for_agreement",
                  "conditions_status",
                  "country_iso3",
                  "country_name",
                  "derivation",
                  "event_date",
                  "explanation_evidence",
                  "explanation_kind",
                  "fresh_evaluation_eligible",
                  "group_id",
                  "id",
                  "issue",
                  "language",
                  "material_context",
                  "missing_context",
                  "observed_action",
                  "private_motive",
                  "proposal_evidence",
                  "proposal_summary",
                  "proposal_symbol",
                  "public_explanation",
                  "record_type",
                  "related_group_ids",
                  "represented_entity",
                  "requested_changes",
                  "resolution_symbol",
                  "review_status",
                  "schema_version",
                  "source_coverage",
                  "source_url",
                  "split",
                  "stated_considerations",
                  "title",
                  "training_admitted",
                  "use",
                  "vote_evidence"
                ],
                "quality_flags": [],
                "rights_status": "not_recorded",
                "review_status": "source_checked_independent_review_pending",
                "split": "quarantine"
              },
              "missing_input_fields": 2,
              "recorded_group_count": 2
            }
          ],
          "missing_values": 0,
          "date_range": [
            "2022-03-02",
            "2022-10-12"
          ]
        },
        {
          "id": "unbench",
          "count": 5,
          "source_ids": [
            "unbench"
          ],
          "languages": [
            "en"
          ],
          "kinds": {
            "source_records": 5
          },
          "tasks": [
            {
              "id": "vote_prediction",
              "count": 5,
              "lengths": {
                "input": {
                  "n": 5,
                  "min": 1468,
                  "median": 6327,
                  "p95": 54335,
                  "max": 54335,
                  "unit": "Unicode characters"
                },
                "target": {
                  "n": 5,
                  "min": 3,
                  "median": 3,
                  "p95": 3,
                  "max": 3,
                  "unit": "Unicode characters"
                },
                "body": null
              },
              "sample": {
                "id": "unbench:2142:UNITED KINGDOM",
                "uid": "123d9c5206f6cf7d24ea2205eb671df9ee0877320947960a20eafaa0c9b02338",
                "title": "Malaysia, New Zealand, Senegal and Bolivarian Republic of Venezuela: draft resolution",
                "date": "2016-12-23",
                "source_url": "https://github.com/yueqingliang1/UNBench",
                "file": "data/canonical/unbench.jsonl",
                "line": 18,
                "task": "vote_prediction",
                "fields": [
                  "available_date",
                  "context",
                  "country_iso3",
                  "country_name",
                  "date_precision",
                  "derivation",
                  "document_symbols",
                  "draft_provenance",
                  "event_date",
                  "group_id",
                  "history",
                  "id",
                  "institution",
                  "language",
                  "quality_flags",
                  "quality_status",
                  "question",
                  "raw_file",
                  "raw_sha256",
                  "represented_entity",
                  "review_status",
                  "rights_status",
                  "schema_version",
                  "source_id",
                  "source_record_id",
                  "source_url",
                  "speaking_capacity",
                  "split",
                  "task",
                  "text",
                  "title",
                  "topic_method",
                  "topics"
                ],
                "quality_flags": [
                  "benchmark_reserved",
                  "draft_availability_unverified"
                ],
                "rights_status": "unresolved",
                "review_status": "pending",
                "split": "test"
              },
              "missing_input_fields": 0,
              "recorded_group_count": 5
            }
          ],
          "missing_values": 0,
          "date_range": [
            "2016-12-23",
            "2020-05-29"
          ]
        },
        {
          "id": "world_bank",
          "count": 43,
          "source_ids": [
            "unspecified",
            "world_bank_2024"
          ],
          "languages": [],
          "kinds": {
            "country_statistics": 43
          },
          "tasks": [
            {
              "id": "country_statistics",
              "count": 43,
              "lengths": {
                "input": null,
                "target": null,
                "body": null
              },
              "sample": {
                "id": "WDI-GBR-NE.TRD.GNFS.ZS-2024",
                "uid": "2b3d2f05c58c1620477bf8a4b08344386ba68720e983725878e0ae18854a8104",
                "title": "Trade (% of GDP)",
                "date": "2024",
                "source_url": "https://api.worldbank.org/v2/country/bra;chn;deu;fra;gbr;ind/indicator/SP.POP.TOTL;NY.GDP.MKTP.CD;NE.TRD.GNFS.ZS?source=2&date=2024&format=json&per_page=1000",
                "file": "data/prepared/country-knowledge-20260914/facts.jsonl",
                "line": 17,
                "task": "country_statistics",
                "fields": [
                  "available_at_reference_year",
                  "country_iso3",
                  "database_last_updated",
                  "definition",
                  "fresh_evaluation_eligible",
                  "id",
                  "indicator",
                  "label",
                  "missing",
                  "record_type",
                  "reference_year",
                  "retrieved_at",
                  "review_status",
                  "source_id",
                  "source_pointer",
                  "source_url",
                  "split",
                  "training_admitted",
                  "unit",
                  "upstream_organization",
                  "use",
                  "value"
                ],
                "quality_flags": [],
                "rights_status": "not_recorded",
                "review_status": "author_checked_independent_review_pending",
                "split": "quarantine"
              },
              "missing_input_fields": 43,
              "recorded_group_count": 0
            }
          ],
          "missing_values": 4,
          "date_range": [
            "2020",
            "2024"
          ]
        },
        {
          "id": "wto",
          "count": 57,
          "source_ids": [
            "wto_government_reports"
          ],
          "languages": [
            "en"
          ],
          "kinds": {
            "source_records": 1,
            "evidence_passages": 56
          },
          "tasks": [
            {
              "id": "policy_evidence",
              "count": 56,
              "lengths": {
                "input": null,
                "target": null,
                "body": {
                  "n": 56,
                  "min": 542,
                  "median": 2310.0,
                  "p95": 2800,
                  "max": 2800,
                  "unit": "Unicode characters"
                }
              },
              "sample": {
                "id": "wto_government_reports:GBR-wto-2025-en:span:0:542",
                "uid": "0abe2d215fe22285718dad01021b5d60ed47fb2ea8c9d2e79a25c7cca2a83e1b",
                "title": "wto_government_reports:GBR-wto-2025-en:span:0:542",
                "date": "2025-10-28",
                "source_url": "https://www.wto.org/english/news_e/news_docs/g476_e.pdf",
                "file": "data/prepared/country-extension-20260914/evidence-passages.jsonl",
                "line": 578,
                "task": "policy_evidence",
                "fields": [
                  "available_date",
                  "country_iso3",
                  "document_type",
                  "end_char",
                  "event_date",
                  "group_id",
                  "id",
                  "language",
                  "parent_id",
                  "pdf_page",
                  "proposed_split",
                  "raw_sha256",
                  "related_countries",
                  "represented_entity",
                  "review_status",
                  "source_id",
                  "source_url",
                  "split",
                  "split_group",
                  "start_char",
                  "text",
                  "training_admitted",
                  "use"
                ],
                "quality_flags": [],
                "rights_status": "not_recorded",
                "review_status": "pending",
                "split": "quarantine"
              },
              "missing_input_fields": 56,
              "recorded_group_count": 1
            },
            {
              "id": "policy_evidence_document",
              "count": 1,
              "lengths": {
                "input": null,
                "target": null,
                "body": {
                  "n": 1,
                  "min": 117416,
                  "median": 117416,
                  "p95": 117416,
                  "max": 117416,
                  "unit": "Unicode characters"
                }
              },
              "sample": {
                "id": "wto_government_reports:GBR-wto-2025-en",
                "uid": "78bb85bd46e472ddacd6575741089399d534e433d8bbac605a5c3833b36c294c",
                "title": "WTO Trade Policy Review: report by the United Kingdom",
                "date": "2025-10-28",
                "source_url": "https://www.wto.org/english/news_e/news_docs/g476_e.pdf",
                "file": "data/prepared/country-extension-20260914/documents.jsonl",
                "line": 6,
                "task": "policy_evidence_document",
                "fields": [
                  "available_date",
                  "context",
                  "country_iso3",
                  "country_name",
                  "date_basis",
                  "date_precision",
                  "derivation",
                  "document_symbols",
                  "document_type",
                  "event_date",
                  "existing_event_splits",
                  "extracted_text_file",
                  "extracted_text_sha256",
                  "fresh_evaluation_eligible",
                  "fresh_evaluation_note",
                  "group_id",
                  "history",
                  "id",
                  "institution",
                  "language",
                  "original_language",
                  "pdf_issue_date_label",
                  "pdf_pages",
                  "proposed_split",
                  "publisher_date_label",
                  "quality_flags",
                  "quality_status",
                  "question",
                  "raw_file",
                  "raw_sha256",
                  "related_countries",
                  "represented_entity",
                  "retrieved_at",
                  "review_status",
                  "rights_status",
                  "schema_version",
                  "source_id",
                  "source_record_id",
                  "source_url",
                  "speaking_capacity",
                  "split",
                  "split_group",
                  "task",
                  "text",
                  "title",
                  "topic_method",
                  "topics",
                  "training_admitted",
                  "translation_family",
                  "translation_status",
                  "upr_cycle"
                ],
                "quality_flags": [
                  "evidence_document_not_response_target",
                  "historical_version_availability_unverified",
                  "individual_claims_require_review",
                  "government_submission_not_independent_WTO_assessment"
                ],
                "rights_status": "unresolved",
                "review_status": "pending",
                "split": "quarantine"
              },
              "missing_input_fields": 1,
              "recorded_group_count": 1
            }
          ],
          "missing_values": 0,
          "date_range": [
            "2025-10-28",
            "2025-10-28"
          ]
        }
      ]
    },
    "IND": {
      "count": 10612,
      "sources": [
        {
          "id": "india_un_mission",
          "count": 5,
          "source_ids": [
            "india_un_mission"
          ],
          "languages": [
            "en"
          ],
          "kinds": {
            "source_records": 1,
            "evidence_passages": 4
          },
          "tasks": [
            {
              "id": "policy_evidence",
              "count": 4,
              "lengths": {
                "input": null,
                "target": null,
                "body": {
                  "n": 4,
                  "min": 2163,
                  "median": 2800.0,
                  "p95": 2800,
                  "max": 2800,
                  "unit": "Unicode characters"
                }
              },
              "sample": {
                "id": "india_un_mission:IND-unga-2025-en:span:0:2800",
                "uid": "7f62641372c748aa40b34836862a89ab3f28bc54e84d892a2b983e4ede6883c8",
                "title": "india_un_mission:IND-unga-2025-en:span:0:2800",
                "date": "2025-09-27",
                "source_url": "https://pminewyork.gov.in/landnew?id=NTQ1Mg",
                "file": "data/prepared/country-extension-20260914/evidence-passages.jsonl",
                "line": 1330,
                "task": "policy_evidence",
                "fields": [
                  "available_date",
                  "country_iso3",
                  "document_type",
                  "end_char",
                  "event_date",
                  "group_id",
                  "id",
                  "language",
                  "parent_id",
                  "pdf_page",
                  "proposed_split",
                  "raw_sha256",
                  "related_countries",
                  "represented_entity",
                  "review_status",
                  "source_id",
                  "source_url",
                  "split",
                  "split_group",
                  "start_char",
                  "text",
                  "training_admitted",
                  "use"
                ],
                "quality_flags": [],
                "rights_status": "not_recorded",
                "review_status": "pending",
                "split": "quarantine"
              },
              "missing_input_fields": 4,
              "recorded_group_count": 1
            },
            {
              "id": "policy_evidence_document",
              "count": 1,
              "lengths": {
                "input": null,
                "target": null,
                "body": {
                  "n": 1,
                  "min": 10564,
                  "median": 10564,
                  "p95": 10564,
                  "max": 10564,
                  "unit": "Unicode characters"
                }
              },
              "sample": {
                "id": "india_un_mission:IND-unga-2025-en",
                "uid": "c398e4f36274ddbea834b28428542ccaf7bd845093313079e274abe290722e39",
                "title": "EAM statement at the General Debate of the 80th UNGA",
                "date": "2025-09-27",
                "source_url": "https://pminewyork.gov.in/landnew?id=NTQ1Mg",
                "file": "data/prepared/country-extension-20260914/documents.jsonl",
                "line": 14,
                "task": "policy_evidence_document",
                "fields": [
                  "available_date",
                  "context",
                  "country_iso3",
                  "country_name",
                  "date_basis",
                  "date_precision",
                  "derivation",
                  "document_symbols",
                  "document_type",
                  "event_date",
                  "existing_event_splits",
                  "extracted_text_file",
                  "extracted_text_sha256",
                  "fresh_evaluation_eligible",
                  "fresh_evaluation_note",
                  "group_id",
                  "history",
                  "id",
                  "institution",
                  "language",
                  "original_language",
                  "proposed_split",
                  "publisher_date_label",
                  "quality_flags",
                  "quality_status",
                  "question",
                  "raw_file",
                  "raw_sha256",
                  "related_countries",
                  "represented_entity",
                  "retrieved_at",
                  "review_status",
                  "rights_status",
                  "schema_version",
                  "source_id",
                  "source_record_id",
                  "source_url",
                  "speaking_capacity",
                  "split",
                  "split_group",
                  "task",
                  "text",
                  "title",
                  "topic_method",
                  "topics",
                  "training_admitted",
                  "translation_family",
                  "translation_status",
                  "upr_cycle"
                ],
                "quality_flags": [
                  "evidence_document_not_response_target",
                  "historical_version_availability_unverified",
                  "individual_claims_require_review"
                ],
                "rights_status": "unresolved",
                "review_status": "pending",
                "split": "quarantine"
              },
              "missing_input_fields": 1,
              "recorded_group_count": 1
            }
          ],
          "missing_values": 0,
          "date_range": [
            "2025-09-27",
            "2025-09-27"
          ]
        },
        {
          "id": "india_pib",
          "count": 4,
          "source_ids": [
            "india_pib"
          ],
          "languages": [
            "en"
          ],
          "kinds": {
            "source_records": 1,
            "evidence_passages": 3
          },
          "tasks": [
            {
              "id": "policy_evidence",
              "count": 3,
              "lengths": {
                "input": null,
                "target": null,
                "body": {
                  "n": 3,
                  "min": 206,
                  "median": 2800,
                  "p95": 2800,
                  "max": 2800,
                  "unit": "Unicode characters"
                }
              },
              "sample": {
                "id": "india_pib:IND-ndc-cabinet-2022-en:span:0:2800",
                "uid": "bcde3d0ad8d240ff24fc6a0860fb61011743126ad46c8f784dd1cc8976c8ac18",
                "title": "india_pib:IND-ndc-cabinet-2022-en:span:0:2800",
                "date": "2022-08-03",
                "source_url": "https://www.pib.gov.in/Pressreleaseshare.aspx?PRID=1847813&lang=2&reg=48",
                "file": "data/prepared/country-extension-20260914/evidence-passages.jsonl",
                "line": 1327,
                "task": "policy_evidence",
                "fields": [
                  "available_date",
                  "country_iso3",
                  "document_type",
                  "end_char",
                  "event_date",
                  "group_id",
                  "id",
                  "language",
                  "parent_id",
                  "pdf_page",
                  "proposed_split",
                  "raw_sha256",
                  "related_countries",
                  "represented_entity",
                  "review_status",
                  "source_id",
                  "source_url",
                  "split",
                  "split_group",
                  "start_char",
                  "text",
                  "training_admitted",
                  "use"
                ],
                "quality_flags": [],
                "rights_status": "not_recorded",
                "review_status": "pending",
                "split": "quarantine"
              },
              "missing_input_fields": 3,
              "recorded_group_count": 1
            },
            {
              "id": "policy_evidence_document",
              "count": 1,
              "lengths": {
                "input": null,
                "target": null,
                "body": {
                  "n": 1,
                  "min": 5806,
                  "median": 5806,
                  "p95": 5806,
                  "max": 5806,
                  "unit": "Unicode characters"
                }
              },
              "sample": {
                "id": "india_pib:IND-ndc-cabinet-2022-en",
                "uid": "940399ee56ad51ac42e3d092b4c1e22b23a7500ec4ed15b27aa7e34a58926d34",
                "title": "Cabinet approves India updated NDC",
                "date": "2022-08-03",
                "source_url": "https://www.pib.gov.in/Pressreleaseshare.aspx?PRID=1847813&lang=2&reg=48",
                "file": "data/prepared/country-extension-20260914/documents.jsonl",
                "line": 13,
                "task": "policy_evidence_document",
                "fields": [
                  "available_date",
                  "context",
                  "country_iso3",
                  "country_name",
                  "date_basis",
                  "date_precision",
                  "derivation",
                  "document_symbols",
                  "document_type",
                  "event_date",
                  "existing_event_splits",
                  "extracted_text_file",
                  "extracted_text_sha256",
                  "fresh_evaluation_eligible",
                  "fresh_evaluation_note",
                  "group_id",
                  "history",
                  "id",
                  "institution",
                  "language",
                  "original_language",
                  "proposed_split",
                  "publisher_date_label",
                  "quality_flags",
                  "quality_status",
                  "question",
                  "raw_file",
                  "raw_sha256",
                  "related_countries",
                  "represented_entity",
                  "retrieved_at",
                  "review_status",
                  "rights_status",
                  "schema_version",
                  "source_id",
                  "source_record_id",
                  "source_url",
                  "speaking_capacity",
                  "split",
                  "split_group",
                  "task",
                  "text",
                  "title",
                  "topic_method",
                  "topics",
                  "training_admitted",
                  "translation_family",
                  "translation_status",
                  "upr_cycle"
                ],
                "quality_flags": [
                  "evidence_document_not_response_target",
                  "historical_version_availability_unverified",
                  "individual_claims_require_review"
                ],
                "rights_status": "unresolved",
                "review_status": "pending",
                "split": "quarantine"
              },
              "missing_input_fields": 1,
              "recorded_group_count": 1
            }
          ],
          "missing_values": 0,
          "date_range": [
            "2022-08-03",
            "2022-08-03"
          ]
        },
        {
          "id": "uhri",
          "count": 1718,
          "source_ids": [
            "uhri"
          ],
          "languages": [
            "en"
          ],
          "kinds": {
            "source_records": 963,
            "observed_actions": 755
          },
          "tasks": [
            {
              "id": "upr_recommendation",
              "count": 963,
              "lengths": {
                "input": {
                  "n": 963,
                  "min": 42,
                  "median": 45,
                  "p95": 64,
                  "max": 90,
                  "unit": "Unicode characters"
                },
                "target": {
                  "n": 963,
                  "min": 38,
                  "median": 130,
                  "p95": 232,
                  "max": 319,
                  "unit": "Unicode characters"
                },
                "body": null
              },
              "sample": {
                "id": "uhri:000720fc-7559-4986-b389-173577457a44",
                "uid": "62bea4f673afed0761e4422fe2ca3d1469aa2a203e2a086ad82753258753d2dc",
                "title": "A/HRC/39/14",
                "date": "2017-07-11",
                "source_url": "https://uhri.ohchr.org/en/our-data-api",
                "file": "data/prepared/country-extension-20260914/uhri-records.jsonl",
                "line": 12023,
                "task": "upr_recommendation",
                "fields": [
                  "affected_persons",
                  "annotation_type",
                  "available_date",
                  "context",
                  "country_iso3",
                  "country_name",
                  "date_precision",
                  "derivation",
                  "document_symbols",
                  "event_date",
                  "existing_event_splits",
                  "fresh_evaluation_eligible",
                  "fresh_evaluation_note",
                  "group_id",
                  "history",
                  "id",
                  "institution",
                  "language",
                  "mechanism",
                  "proposed_split",
                  "quality_flags",
                  "quality_status",
                  "question",
                  "raw_file",
                  "raw_sha256",
                  "recommending_states",
                  "represented_entity",
                  "response_labels",
                  "review_status",
                  "reviewed_states",
                  "rights_status",
                  "schema_version",
                  "sdgs",
                  "source_id",
                  "source_record_id",
                  "source_url",
                  "speaking_capacity",
                  "split",
                  "split_group",
                  "task",
                  "text",
                  "title",
                  "topic_method",
                  "topics",
                  "training_admitted",
                  "upr_cycle",
                  "upr_session"
                ],
                "quality_flags": [
                  "document_date_not_review_date",
                  "recommendation_context_missing"
                ],
                "rights_status": "unresolved",
                "review_status": "pending",
                "split": "quarantine"
              },
              "missing_input_fields": 0,
              "recorded_group_count": 375
            },
            {
              "id": "upr_response",
              "count": 755,
              "lengths": {
                "input": {
                  "n": 755,
                  "min": 78,
                  "median": 183,
                  "p95": 330,
                  "max": 682,
                  "unit": "Unicode characters"
                },
                "target": {
                  "n": 755,
                  "min": 5,
                  "median": 9,
                  "p95": 9,
                  "max": 15,
                  "unit": "Unicode characters"
                },
                "body": null
              },
              "sample": {
                "id": "uhri:0115fa20-7881-444e-81f0-13dcbfb4c3cb:response",
                "uid": "beec4368daf700495c21991b49061535358dc507edd38224ad92c1a376fade5d",
                "title": "A/HRC/52/11",
                "date": "2022-12-06",
                "source_url": "https://uhri.ohchr.org/en/our-data-api",
                "file": "data/prepared/country-extension-20260914/uhri-records.jsonl",
                "line": 7474,
                "task": "upr_response",
                "fields": [
                  "available_date",
                  "context",
                  "country_iso3",
                  "country_name",
                  "date_precision",
                  "derivation",
                  "document_symbols",
                  "event_date",
                  "existing_event_splits",
                  "fresh_evaluation_eligible",
                  "fresh_evaluation_note",
                  "group_id",
                  "history",
                  "id",
                  "institution",
                  "language",
                  "parent_id",
                  "proposed_split",
                  "quality_flags",
                  "quality_status",
                  "question",
                  "raw_file",
                  "raw_sha256",
                  "recommending_states",
                  "represented_entity",
                  "review_status",
                  "reviewed_states",
                  "rights_status",
                  "schema_version",
                  "source_id",
                  "source_record_id",
                  "source_url",
                  "speaking_capacity",
                  "split",
                  "split_group",
                  "task",
                  "text",
                  "title",
                  "topic_method",
                  "topics",
                  "training_admitted",
                  "upr_cycle",
                  "upr_session"
                ],
                "quality_flags": [
                  "recommendation_context_missing",
                  "response_date_unverified"
                ],
                "rights_status": "unresolved",
                "review_status": "pending",
                "split": "quarantine"
              },
              "missing_input_fields": 0,
              "recorded_group_count": 4
            }
          ],
          "missing_values": 0,
          "date_range": [
            "2008-05-23",
            "2026-01-08"
          ]
        },
        {
          "id": "curated",
          "count": 12,
          "source_ids": [
            "unspecified"
          ],
          "languages": [
            "en"
          ],
          "kinds": {
            "policy_positions": 5,
            "observed_actions": 1,
            "policy_applications": 3,
            "source_records": 3
          },
          "tasks": [
            {
              "id": "policy_positions",
              "count": 5,
              "lengths": {
                "input": null,
                "target": null,
                "body": null
              },
              "sample": {
                "id": "IND-BRA-agricultural-trade-2025",
                "uid": "6dc24d4c3e26e872f18f45120f538f1441a54f47c113c2168ac198bcebc15313",
                "title": "agricultural_trade",
                "date": "2025-07-08",
                "source_url": "https://www.eoibrasilia.gov.in/pr-10-07-25.php",
                "file": "data/prepared/country-knowledge-20260914/policies.jsonl",
                "line": 8,
                "task": "policy_positions",
                "fields": [
                  "available_date",
                  "capacity",
                  "claim",
                  "country_iso3",
                  "date",
                  "evidence",
                  "fresh_evaluation_eligible",
                  "group_id",
                  "id",
                  "issue",
                  "opposes",
                  "record_type",
                  "retrieved_at",
                  "review_status",
                  "source_url",
                  "split",
                  "supports",
                  "training_admitted",
                  "truth_scope",
                  "unknown"
                ],
                "quality_flags": [],
                "rights_status": "not_recorded",
                "review_status": "author_checked_independent_review_pending",
                "split": "quarantine"
              },
              "missing_input_fields": 5,
              "recorded_group_count": 3
            },
            {
              "id": "policy_evidence",
              "count": 4,
              "lengths": {
                "input": null,
                "target": null,
                "body": null
              },
              "sample": {
                "id": "IND-ES-11-1-20220302",
                "uid": "697154df8efd5697b37821b33453fed89f632eda37f244acd2ffd137d2c68182",
                "title": "observed_vote",
                "date": "2022-03-02",
                "source_url": "",
                "file": "data/prepared/country-knowledge-20260914/actions.jsonl",
                "line": 6,
                "task": "policy_evidence",
                "fields": [
                  "amended_vote",
                  "bulk_source_id",
                  "country_iso3",
                  "csv_line",
                  "date",
                  "decision_id",
                  "document_symbols",
                  "evaluation_use",
                  "explanation_evidence",
                  "explanation_status",
                  "explanation_text_language",
                  "fresh_evaluation_eligible",
                  "group_id",
                  "id",
                  "language_of_delivery",
                  "original_vote",
                  "primary_roll_call_verified",
                  "primary_vote_pdf_pages",
                  "primary_vote_source_id",
                  "private_motive",
                  "proposal_source_id",
                  "public_explanation_summary",
                  "record_type",
                  "review_status",
                  "split",
                  "training_admitted"
                ],
                "quality_flags": [],
                "rights_status": "not_recorded",
                "review_status": "author_checked_independent_review_pending",
                "split": "quarantine"
              },
              "missing_input_fields": 4,
              "recorded_group_count": 1
            },
            {
              "id": "policy_applications",
              "count": 3,
              "lengths": {
                "input": {
                  "n": 3,
                  "min": 763,
                  "median": 1448,
                  "p95": 1834,
                  "max": 1834,
                  "unit": "Unicode characters"
                },
                "target": {
                  "n": 3,
                  "min": 280,
                  "median": 287,
                  "p95": 298,
                  "max": 298,
                  "unit": "Unicode characters"
                },
                "body": null
              },
              "sample": {
                "id": "IND-climate-2030-2022:application",
                "uid": "ffb2d2c26a216b450ac8b7a00d4b38dda55a36c11b14f1aaf6f06841b44c9a1b",
                "title": "climate_commitments",
                "date": "2022-08-03",
                "source_url": "https://www.pib.gov.in/Pressreleaseshare.aspx?PRID=1847813&lang=2&reg=48",
                "file": "data/prepared/country-extension-20260914/policy-applications.candidates.jsonl",
                "line": 7,
                "task": "policy_applications",
                "fields": [
                  "answer_language",
                  "available_date",
                  "countries",
                  "date",
                  "derivation",
                  "enable_thinking",
                  "evidence",
                  "fresh_evaluation_eligible",
                  "group_id",
                  "id",
                  "issue",
                  "messages",
                  "proposed_split",
                  "record_type",
                  "represented_entity",
                  "review_status",
                  "rubric",
                  "scope",
                  "split",
                  "split_group",
                  "training_admitted"
                ],
                "quality_flags": [],
                "rights_status": "not_recorded",
                "review_status": "assistant_curated_independent_review_pending",
                "split": "quarantine"
              },
              "missing_input_fields": 0,
              "recorded_group_count": 2
            }
          ],
          "missing_values": 0,
          "date_range": [
            "2020-11-25",
            "2025-07-08"
          ]
        },
        {
          "id": "unga_speech_corpus",
          "count": 1047,
          "source_ids": [
            "unga_speech_corpus"
          ],
          "languages": [
            "en"
          ],
          "kinds": {
            "source_records": 1047
          },
          "tasks": [
            {
              "id": "unverified_speech_segment",
              "count": 536,
              "lengths": {
                "input": null,
                "target": null,
                "body": {
                  "n": 536,
                  "min": 30,
                  "median": 6411.5,
                  "p95": 16933,
                  "max": 31375,
                  "unit": "Unicode characters"
                }
              },
              "sample": {
                "id": "unga_speech_corpus:India_100_48_19940101.txt",
                "uid": "343a15ed3642963c63266c15d5ffbd9ed97d87338c2566ed77cfe38ff3534225",
                "title": "UNGA A/48/PV.100",
                "date": "1994",
                "source_url": "https://www.linneaturco.com/research",
                "file": "data/prepared/country-extension-20260914/unga-speech-segments.jsonl",
                "line": 1347,
                "task": "unverified_speech_segment",
                "fields": [
                  "available_date",
                  "context",
                  "country_iso3",
                  "country_name",
                  "date_precision",
                  "derivation",
                  "document_symbols",
                  "event_date",
                  "existing_event_splits",
                  "fresh_evaluation_eligible",
                  "fresh_evaluation_note",
                  "group_id",
                  "history",
                  "id",
                  "institution",
                  "language",
                  "meeting",
                  "proposed_split",
                  "quality_flags",
                  "quality_status",
                  "question",
                  "raw_file",
                  "raw_sha256",
                  "represented_entity",
                  "review_status",
                  "rights_status",
                  "schema_version",
                  "session",
                  "source_id",
                  "source_record_id",
                  "source_url",
                  "speaking_capacity",
                  "split",
                  "split_group",
                  "task",
                  "text",
                  "title",
                  "topic_method",
                  "topics",
                  "training_admitted",
                  "upstream_country_code",
                  "upstream_words_spoken"
                ],
                "quality_flags": [
                  "upstream_speaker_segmentation_unverified",
                  "year_precision_only"
                ],
                "rights_status": "unresolved",
                "review_status": "pending",
                "split": "quarantine"
              },
              "missing_input_fields": 536,
              "recorded_group_count": 535
            },
            {
              "id": "statement_reconstruction",
              "count": 511,
              "lengths": {
                "input": null,
                "target": {
                  "n": 511,
                  "min": 214,
                  "median": 6173,
                  "p95": 16006,
                  "max": 26220,
                  "unit": "Unicode characters"
                },
                "body": null
              },
              "sample": {
                "id": "unga_speech_corpus:India_100_48_19940101.txt:speaker",
                "uid": "700746b73881f52fa5c47978ed364f8ef659526772b298a668bd8494dbc3b0ba",
                "title": "UNGA A/48/PV.100",
                "date": "1994",
                "source_url": "https://www.linneaturco.com/research",
                "file": "data/prepared/country-extension-20260914/unga-speech-segments.jsonl",
                "line": 1348,
                "task": "statement_reconstruction",
                "fields": [
                  "available_date",
                  "context",
                  "country_iso3",
                  "country_name",
                  "date_precision",
                  "derivation",
                  "document_symbols",
                  "event_date",
                  "existing_event_splits",
                  "fresh_evaluation_eligible",
                  "fresh_evaluation_note",
                  "group_id",
                  "history",
                  "id",
                  "institution",
                  "language",
                  "meeting",
                  "parent_id",
                  "proposed_split",
                  "quality_flags",
                  "quality_status",
                  "question",
                  "raw_file",
                  "raw_sha256",
                  "represented_entity",
                  "review_status",
                  "rights_status",
                  "schema_version",
                  "session",
                  "source_char_span",
                  "source_id",
                  "source_record_id",
                  "source_url",
                  "speaking_capacity",
                  "split",
                  "split_group",
                  "task",
                  "text",
                  "title",
                  "topic_method",
                  "topics",
                  "training_admitted"
                ],
                "quality_flags": [
                  "meeting_agenda_missing",
                  "speaker_boundary_rule_requires_review",
                  "year_precision_only"
                ],
                "rights_status": "unresolved",
                "review_status": "pending",
                "split": "quarantine"
              },
              "missing_input_fields": 511,
              "recorded_group_count": 510
            }
          ],
          "missing_values": 0,
          "date_range": [
            "1993",
            "2017-12-05"
          ]
        },
        {
          "id": "unga_dm",
          "count": 7509,
          "source_ids": [
            "unga_dm"
          ],
          "languages": [
            "en"
          ],
          "kinds": {
            "observed_actions": 7509
          },
          "tasks": [
            {
              "id": "vote_label_only",
              "count": 7509,
              "lengths": {
                "input": null,
                "target": null,
                "body": {
                  "n": 7509,
                  "min": 7,
                  "median": 8,
                  "p95": 10,
                  "max": 10,
                  "unit": "Unicode characters"
                }
              },
              "sample": {
                "id": "unga_dm:A/1081-S0100:750",
                "uid": "1993b029b61002136e3d74135ee14aa90c7f1ee6f573969b4608e19dd995d5d1",
                "title": "A/1081-S0100",
                "date": "1949-11-25",
                "source_url": "https://unvotes.unige.ch/",
                "file": "data/prepared/country-extension-20260914/unga-votes.jsonl",
                "line": 27836,
                "task": "vote_label_only",
                "fields": [
                  "amended_vote",
                  "available_date",
                  "context",
                  "country_iso3",
                  "country_name",
                  "current_seat_name",
                  "date_precision",
                  "decision_mode",
                  "decision_topic",
                  "derivation",
                  "document_symbols",
                  "draft_resolution_id",
                  "event_date",
                  "existing_event_splits",
                  "fresh_evaluation_eligible",
                  "fresh_evaluation_note",
                  "group_id",
                  "history",
                  "id",
                  "institution",
                  "language",
                  "meeting_record_id",
                  "member_state_id",
                  "original_seat_name",
                  "original_vote",
                  "proposed_split",
                  "quality_flags",
                  "quality_status",
                  "question",
                  "raw_file",
                  "raw_sha256",
                  "represented_entity",
                  "resolution_id",
                  "review_status",
                  "rights_status",
                  "schema_version",
                  "session_id",
                  "source_id",
                  "source_record_id",
                  "source_url",
                  "speaking_capacity",
                  "split",
                  "split_group",
                  "task",
                  "text",
                  "title",
                  "topic_method",
                  "topics",
                  "training_admitted",
                  "vote_was_amended"
                ],
                "quality_flags": [
                  "proposal_text_missing"
                ],
                "rights_status": "unresolved",
                "review_status": "pending",
                "split": "quarantine"
              },
              "missing_input_fields": 7509,
              "recorded_group_count": 7509
            }
          ],
          "missing_values": 0,
          "date_range": [
            "1946-01-26",
            "2023-09-01"
          ]
        },
        {
          "id": "upr_reports",
          "count": 231,
          "source_ids": [
            "un_upr_national_report"
          ],
          "languages": [
            "ar",
            "en",
            "es",
            "fr",
            "ru",
            "zh"
          ],
          "kinds": {
            "source_records": 6,
            "evidence_passages": 225
          },
          "tasks": [
            {
              "id": "policy_evidence",
              "count": 225,
              "lengths": {
                "input": null,
                "target": null,
                "body": {
                  "n": 225,
                  "min": 226,
                  "median": 1762,
                  "p95": 2800,
                  "max": 2800,
                  "unit": "Unicode characters"
                }
              },
              "sample": {
                "id": "un_upr_national_report:upr4-IND-ar:span:0:417",
                "uid": "6188b6ee7c1f3cc758274d26db45ce646b7eaa71b50587980bee8c0b68330e2e",
                "title": "un_upr_national_report:upr4-IND-ar:span:0:417",
                "date": "2022-08-17",
                "source_url": "https://documents.un.org/api/symbol/access?l=ar&s=A%2FHRC%2FWG.6%2F41%2FIND%2F1&t=pdf",
                "file": "data/prepared/country-extension-20260914/evidence-passages.jsonl",
                "line": 1985,
                "task": "policy_evidence",
                "fields": [
                  "available_date",
                  "country_iso3",
                  "document_type",
                  "end_char",
                  "event_date",
                  "group_id",
                  "id",
                  "language",
                  "parent_id",
                  "pdf_page",
                  "proposed_split",
                  "raw_sha256",
                  "related_countries",
                  "represented_entity",
                  "review_status",
                  "source_id",
                  "source_url",
                  "split",
                  "split_group",
                  "start_char",
                  "text",
                  "training_admitted",
                  "use"
                ],
                "quality_flags": [],
                "rights_status": "not_recorded",
                "review_status": "pending",
                "split": "quarantine"
              },
              "missing_input_fields": 225,
              "recorded_group_count": 1
            },
            {
              "id": "policy_evidence_document",
              "count": 6,
              "lengths": {
                "input": null,
                "target": null,
                "body": {
                  "n": 6,
                  "min": 24002,
                  "median": 84142.0,
                  "p95": 87690,
                  "max": 87690,
                  "unit": "Unicode characters"
                }
              },
              "sample": {
                "id": "un_upr_national_report:upr4-IND-ar",
                "uid": "22b59ab5777f7f905ddea46cf1030735f3fb9706fcb05b5f8f3268d7facd8de3",
                "title": "IND fourth-cycle UPR national report",
                "date": "2022-08-17",
                "source_url": "https://documents.un.org/api/symbol/access?l=ar&s=A%2FHRC%2FWG.6%2F41%2FIND%2F1&t=pdf",
                "file": "data/prepared/country-extension-20260914/documents.jsonl",
                "line": 34,
                "task": "policy_evidence_document",
                "fields": [
                  "available_date",
                  "context",
                  "country_iso3",
                  "country_name",
                  "date_basis",
                  "date_precision",
                  "derivation",
                  "document_symbols",
                  "document_type",
                  "event_date",
                  "existing_event_splits",
                  "extracted_text_file",
                  "extracted_text_sha256",
                  "fresh_evaluation_eligible",
                  "fresh_evaluation_note",
                  "group_id",
                  "history",
                  "id",
                  "institution",
                  "language",
                  "original_language",
                  "pdf_pages",
                  "proposed_split",
                  "publisher_date_label",
                  "quality_flags",
                  "quality_status",
                  "question",
                  "raw_file",
                  "raw_sha256",
                  "related_countries",
                  "represented_entity",
                  "retrieved_at",
                  "review_status",
                  "rights_status",
                  "schema_version",
                  "source_id",
                  "source_record_id",
                  "source_url",
                  "speaking_capacity",
                  "split",
                  "split_group",
                  "task",
                  "text",
                  "title",
                  "topic_method",
                  "topics",
                  "training_admitted",
                  "translation_family",
                  "translation_status",
                  "upr_cycle"
                ],
                "quality_flags": [
                  "evidence_document_not_response_target",
                  "historical_version_availability_unverified",
                  "individual_claims_require_review"
                ],
                "rights_status": "unresolved",
                "review_status": "pending",
                "split": "quarantine"
              },
              "missing_input_fields": 6,
              "recorded_group_count": 1
            }
          ],
          "missing_values": 0,
          "date_range": [
            "2022-08-17",
            "2022-08-17"
          ]
        },
        {
          "id": "decision_cases",
          "count": 2,
          "source_ids": [
            "unspecified"
          ],
          "languages": [
            "en"
          ],
          "kinds": {
            "decision_cases": 2
          },
          "tasks": [
            {
              "id": "decision_cases",
              "count": 2,
              "lengths": {
                "input": null,
                "target": null,
                "body": null
              },
              "sample": {
                "id": "decision:IND-ES-11-1-20220302",
                "uid": "d4620affd5968667b19e0638743e30aa82451bc18dafda89fd3b337cd3fdf15b",
                "title": "Aggression against Ukraine — March 2022",
                "date": "2022-03-02",
                "source_url": "https://docs.un.org/A/ES-11/PV.5",
                "file": "data/prepared/decision-cases-20260914/cases.jsonl",
                "line": 6,
                "task": "decision_cases",
                "fields": [
                  "amended_action",
                  "author",
                  "conditions_for_agreement",
                  "conditions_status",
                  "country_iso3",
                  "country_name",
                  "derivation",
                  "event_date",
                  "explanation_evidence",
                  "explanation_kind",
                  "fresh_evaluation_eligible",
                  "group_id",
                  "id",
                  "issue",
                  "language",
                  "material_context",
                  "missing_context",
                  "observed_action",
                  "private_motive",
                  "proposal_evidence",
                  "proposal_summary",
                  "proposal_symbol",
                  "public_explanation",
                  "record_type",
                  "related_group_ids",
                  "represented_entity",
                  "requested_changes",
                  "resolution_symbol",
                  "review_status",
                  "schema_version",
                  "source_coverage",
                  "source_url",
                  "split",
                  "stated_considerations",
                  "title",
                  "training_admitted",
                  "use",
                  "vote_evidence"
                ],
                "quality_flags": [],
                "rights_status": "not_recorded",
                "review_status": "source_checked_independent_review_pending",
                "split": "quarantine"
              },
              "missing_input_fields": 2,
              "recorded_group_count": 2
            }
          ],
          "missing_values": 0,
          "date_range": [
            "2022-03-02",
            "2022-10-12"
          ]
        },
        {
          "id": "world_bank",
          "count": 43,
          "source_ids": [
            "unspecified",
            "world_bank_2024"
          ],
          "languages": [],
          "kinds": {
            "country_statistics": 43
          },
          "tasks": [
            {
              "id": "country_statistics",
              "count": 43,
              "lengths": {
                "input": null,
                "target": null,
                "body": null
              },
              "sample": {
                "id": "WDI-IND-NE.TRD.GNFS.ZS-2024",
                "uid": "9990e00566a2c6e90366458d1b73489dcd5b9bd8d0ebf4c2a25e4d98363ea907",
                "title": "Trade (% of GDP)",
                "date": "2024",
                "source_url": "https://api.worldbank.org/v2/country/bra;chn;deu;fra;gbr;ind/indicator/SP.POP.TOTL;NY.GDP.MKTP.CD;NE.TRD.GNFS.ZS?source=2&date=2024&format=json&per_page=1000",
                "file": "data/prepared/country-knowledge-20260914/facts.jsonl",
                "line": 18,
                "task": "country_statistics",
                "fields": [
                  "available_at_reference_year",
                  "country_iso3",
                  "database_last_updated",
                  "definition",
                  "fresh_evaluation_eligible",
                  "id",
                  "indicator",
                  "label",
                  "missing",
                  "record_type",
                  "reference_year",
                  "retrieved_at",
                  "review_status",
                  "source_id",
                  "source_pointer",
                  "source_url",
                  "split",
                  "training_admitted",
                  "unit",
                  "upstream_organization",
                  "use",
                  "value"
                ],
                "quality_flags": [],
                "rights_status": "not_recorded",
                "review_status": "author_checked_independent_review_pending",
                "split": "quarantine"
              },
              "missing_input_fields": 43,
              "recorded_group_count": 0
            }
          ],
          "missing_values": 4,
          "date_range": [
            "2020",
            "2024"
          ]
        },
        {
          "id": "wto",
          "count": 41,
          "source_ids": [
            "wto_government_reports"
          ],
          "languages": [
            "en"
          ],
          "kinds": {
            "source_records": 1,
            "evidence_passages": 40
          },
          "tasks": [
            {
              "id": "policy_evidence",
              "count": 40,
              "lengths": {
                "input": null,
                "target": null,
                "body": {
                  "n": 40,
                  "min": 400,
                  "median": 2018.0,
                  "p95": 2800,
                  "max": 2800,
                  "unit": "Unicode characters"
                }
              },
              "sample": {
                "id": "wto_government_reports:IND-wto-2021-en:span:0:507",
                "uid": "4f8ca90e1b5c1ead0745e47d22296d5c2cd7c57e9233fa60d1dcde6ea0504a3a",
                "title": "wto_government_reports:IND-wto-2021-en:span:0:507",
                "date": "2021",
                "source_url": "https://www.wto.org/english/tratop_e/tpr_e/g403_e.pdf",
                "file": "data/prepared/country-extension-20260914/evidence-passages.jsonl",
                "line": 634,
                "task": "policy_evidence",
                "fields": [
                  "available_date",
                  "country_iso3",
                  "document_type",
                  "end_char",
                  "event_date",
                  "group_id",
                  "id",
                  "language",
                  "parent_id",
                  "pdf_page",
                  "proposed_split",
                  "raw_sha256",
                  "related_countries",
                  "represented_entity",
                  "review_status",
                  "source_id",
                  "source_url",
                  "split",
                  "split_group",
                  "start_char",
                  "text",
                  "training_admitted",
                  "use"
                ],
                "quality_flags": [],
                "rights_status": "not_recorded",
                "review_status": "pending",
                "split": "quarantine"
              },
              "missing_input_fields": 40,
              "recorded_group_count": 1
            },
            {
              "id": "policy_evidence_document",
              "count": 1,
              "lengths": {
                "input": null,
                "target": null,
                "body": {
                  "n": 1,
                  "min": 78991,
                  "median": 78991,
                  "p95": 78991,
                  "max": 78991,
                  "unit": "Unicode characters"
                }
              },
              "sample": {
                "id": "wto_government_reports:IND-wto-2021-en",
                "uid": "3b55d5176453a6df61dfb9443cc602cbb7ef4a086a6f7803823ee5be3ad86584",
                "title": "WTO Trade Policy Review: report by India",
                "date": "2021",
                "source_url": "https://www.wto.org/english/tratop_e/tpr_e/g403_e.pdf",
                "file": "data/prepared/country-extension-20260914/documents.jsonl",
                "line": 7,
                "task": "policy_evidence_document",
                "fields": [
                  "available_date",
                  "context",
                  "country_iso3",
                  "country_name",
                  "date_basis",
                  "date_precision",
                  "derivation",
                  "document_symbols",
                  "document_type",
                  "event_date",
                  "existing_event_splits",
                  "extracted_text_file",
                  "extracted_text_sha256",
                  "fresh_evaluation_eligible",
                  "fresh_evaluation_note",
                  "group_id",
                  "history",
                  "id",
                  "institution",
                  "language",
                  "original_language",
                  "pdf_issue_date_label",
                  "pdf_pages",
                  "proposed_split",
                  "publisher_date_label",
                  "quality_flags",
                  "quality_status",
                  "question",
                  "raw_file",
                  "raw_sha256",
                  "related_countries",
                  "represented_entity",
                  "retrieved_at",
                  "review_status",
                  "rights_status",
                  "schema_version",
                  "source_id",
                  "source_record_id",
                  "source_url",
                  "speaking_capacity",
                  "split",
                  "split_group",
                  "task",
                  "text",
                  "title",
                  "topic_method",
                  "topics",
                  "training_admitted",
                  "translation_family",
                  "translation_status",
                  "upr_cycle"
                ],
                "quality_flags": [
                  "evidence_document_not_response_target",
                  "historical_version_availability_unverified",
                  "individual_claims_require_review",
                  "government_submission_not_independent_WTO_assessment"
                ],
                "rights_status": "unresolved",
                "review_status": "pending",
                "split": "quarantine"
              },
              "missing_input_fields": 1,
              "recorded_group_count": 1
            }
          ],
          "missing_values": 0,
          "date_range": [
            "2021",
            "2021"
          ]
        }
      ]
    },
    "BRA": {
      "count": 11234,
      "sources": [
        {
          "id": "brazil_funag",
          "count": 261,
          "source_ids": [
            "brazil_funag"
          ],
          "languages": [
            "pt"
          ],
          "kinds": {
            "source_records": 1,
            "evidence_passages": 260
          },
          "tasks": [
            {
              "id": "policy_evidence",
              "count": 260,
              "lengths": {
                "input": null,
                "target": null,
                "body": {
                  "n": 260,
                  "min": 333,
                  "median": 1837.0,
                  "p95": 2260,
                  "max": 2656,
                  "unit": "Unicode characters"
                }
              },
              "sample": {
                "id": "brazil_funag:BRA-foreign-policy-2023-2024-pt:span:100444:102386",
                "uid": "4efd7540ac8506b6b60d3c77abc46cda0b59e2dbd68a6df9b055db10ed345f4a",
                "title": "brazil_funag:BRA-foreign-policy-2023-2024-pt:span:100444:102386",
                "date": "",
                "source_url": "https://funag.gov.br/biblioteca-nova/produto/loc_pdf/1299/1/repertorio_de_politica_externa%3A_posicoes_do_brasil_2023-2024",
                "file": "data/prepared/country-extension-20260914/evidence-passages.jsonl",
                "line": 1062,
                "task": "policy_evidence",
                "fields": [
                  "available_date",
                  "country_iso3",
                  "document_type",
                  "end_char",
                  "event_date",
                  "group_id",
                  "id",
                  "language",
                  "parent_id",
                  "pdf_page",
                  "proposed_split",
                  "raw_sha256",
                  "related_countries",
                  "represented_entity",
                  "review_status",
                  "source_id",
                  "source_url",
                  "split",
                  "split_group",
                  "start_char",
                  "text",
                  "training_admitted",
                  "use"
                ],
                "quality_flags": [],
                "rights_status": "not_recorded",
                "review_status": "pending",
                "split": "quarantine"
              },
              "missing_input_fields": 260,
              "recorded_group_count": 1
            },
            {
              "id": "policy_evidence_document",
              "count": 1,
              "lengths": {
                "input": null,
                "target": null,
                "body": {
                  "n": 1,
                  "min": 461473,
                  "median": 461473,
                  "p95": 461473,
                  "max": 461473,
                  "unit": "Unicode characters"
                }
              },
              "sample": {
                "id": "brazil_funag:BRA-foreign-policy-2023-2024-pt",
                "uid": "5e2bd260bbe63d2eddaa92027e718ea2c15dd77d48204d02b1320fadd0732536",
                "title": "Repertório de política externa: posições do Brasil 2023–2024",
                "date": "",
                "source_url": "https://funag.gov.br/biblioteca-nova/produto/loc_pdf/1299/1/repertorio_de_politica_externa%3A_posicoes_do_brasil_2023-2024",
                "file": "data/prepared/country-extension-20260914/documents.jsonl",
                "line": 11,
                "task": "policy_evidence_document",
                "fields": [
                  "available_date",
                  "context",
                  "country_iso3",
                  "country_name",
                  "date_basis",
                  "date_precision",
                  "derivation",
                  "document_symbols",
                  "document_type",
                  "event_date",
                  "existing_event_splits",
                  "extracted_text_file",
                  "extracted_text_sha256",
                  "fresh_evaluation_eligible",
                  "fresh_evaluation_note",
                  "group_id",
                  "history",
                  "id",
                  "institution",
                  "language",
                  "original_language",
                  "pdf_pages",
                  "proposed_split",
                  "publisher_date_label",
                  "quality_flags",
                  "quality_status",
                  "question",
                  "raw_file",
                  "raw_sha256",
                  "related_countries",
                  "represented_entity",
                  "retrieved_at",
                  "review_status",
                  "rights_status",
                  "schema_version",
                  "source_id",
                  "source_record_id",
                  "source_url",
                  "speaking_capacity",
                  "split",
                  "split_group",
                  "task",
                  "text",
                  "title",
                  "topic_method",
                  "topics",
                  "training_admitted",
                  "translation_family",
                  "translation_status",
                  "upr_cycle"
                ],
                "quality_flags": [
                  "compendium_extract_each_speaker_and_date_before_supervision",
                  "evidence_document_not_response_target",
                  "historical_version_availability_unverified",
                  "individual_claims_require_review",
                  "reporting_period_not_event_date"
                ],
                "rights_status": "unresolved",
                "review_status": "pending",
                "split": "quarantine"
              },
              "missing_input_fields": 1,
              "recorded_group_count": 1
            }
          ],
          "missing_values": 0,
          "date_range": []
        },
        {
          "id": "brazil_mma",
          "count": 65,
          "source_ids": [
            "brazil_mma"
          ],
          "languages": [
            "pt"
          ],
          "kinds": {
            "source_records": 1,
            "evidence_passages": 64
          },
          "tasks": [
            {
              "id": "policy_evidence",
              "count": 64,
              "lengths": {
                "input": null,
                "target": null,
                "body": {
                  "n": 64,
                  "min": 1998,
                  "median": 2368.5,
                  "p95": 2520,
                  "max": 2572,
                  "unit": "Unicode characters"
                }
              },
              "sample": {
                "id": "brazil_mma:BRA-ndc-2024-government-pt:span:0:2152",
                "uid": "e68e82addb81a8a7dfe31fe8118b468c8ed46abbb69e0021660486b6abc97163",
                "title": "brazil_mma:BRA-ndc-2024-government-pt:span:0:2152",
                "date": "2024-11-13",
                "source_url": "https://www.gov.br/mma/pt-br/assuntos/noticias/brasil-entrega-a-onu-nova-ndc-alinhada-ao-acordo-de-paris/ndc-versao-em-portugues.pdf",
                "file": "data/prepared/country-extension-20260914/evidence-passages.jsonl",
                "line": 1263,
                "task": "policy_evidence",
                "fields": [
                  "available_date",
                  "country_iso3",
                  "document_type",
                  "end_char",
                  "event_date",
                  "group_id",
                  "id",
                  "language",
                  "parent_id",
                  "pdf_page",
                  "proposed_split",
                  "raw_sha256",
                  "related_countries",
                  "represented_entity",
                  "review_status",
                  "source_id",
                  "source_url",
                  "split",
                  "split_group",
                  "start_char",
                  "text",
                  "training_admitted",
                  "use"
                ],
                "quality_flags": [],
                "rights_status": "not_recorded",
                "review_status": "pending",
                "split": "quarantine"
              },
              "missing_input_fields": 64,
              "recorded_group_count": 1
            },
            {
              "id": "policy_evidence_document",
              "count": 1,
              "lengths": {
                "input": null,
                "target": null,
                "body": {
                  "n": 1,
                  "min": 150781,
                  "median": 150781,
                  "p95": 150781,
                  "max": 150781,
                  "unit": "Unicode characters"
                }
              },
              "sample": {
                "id": "brazil_mma:BRA-ndc-2024-government-pt",
                "uid": "83f3346e7807fc38917ec00680f994b5507f966b58361fde8590a62d5905738d",
                "title": "NDC do Brasil — versão em português",
                "date": "2024-11-13",
                "source_url": "https://www.gov.br/mma/pt-br/assuntos/noticias/brasil-entrega-a-onu-nova-ndc-alinhada-ao-acordo-de-paris/ndc-versao-em-portugues.pdf",
                "file": "data/prepared/country-extension-20260914/documents.jsonl",
                "line": 12,
                "task": "policy_evidence_document",
                "fields": [
                  "available_date",
                  "context",
                  "country_iso3",
                  "country_name",
                  "date_basis",
                  "date_precision",
                  "derivation",
                  "document_symbols",
                  "document_type",
                  "event_date",
                  "existing_event_splits",
                  "extracted_text_file",
                  "extracted_text_sha256",
                  "fresh_evaluation_eligible",
                  "fresh_evaluation_note",
                  "group_id",
                  "history",
                  "id",
                  "institution",
                  "language",
                  "original_language",
                  "pdf_pages",
                  "proposed_split",
                  "publisher_date_label",
                  "quality_flags",
                  "quality_status",
                  "question",
                  "raw_file",
                  "raw_sha256",
                  "related_countries",
                  "represented_entity",
                  "retrieved_at",
                  "review_status",
                  "rights_status",
                  "schema_version",
                  "source_id",
                  "source_record_id",
                  "source_url",
                  "speaking_capacity",
                  "split",
                  "split_group",
                  "task",
                  "text",
                  "title",
                  "topic_method",
                  "topics",
                  "training_admitted",
                  "translation_family",
                  "translation_status",
                  "upr_cycle"
                ],
                "quality_flags": [
                  "evidence_document_not_response_target",
                  "historical_version_availability_unverified",
                  "individual_claims_require_review"
                ],
                "rights_status": "unresolved",
                "review_status": "pending",
                "split": "quarantine"
              },
              "missing_input_fields": 1,
              "recorded_group_count": 1
            }
          ],
          "missing_values": 0,
          "date_range": [
            "2024-11-13",
            "2024-11-13"
          ]
        },
        {
          "id": "uhri",
          "count": 2198,
          "source_ids": [
            "uhri"
          ],
          "languages": [
            "en"
          ],
          "kinds": {
            "source_records": 1474,
            "observed_actions": 724
          },
          "tasks": [
            {
              "id": "upr_recommendation",
              "count": 1474,
              "lengths": {
                "input": {
                  "n": 1474,
                  "min": 42,
                  "median": 45.0,
                  "p95": 65,
                  "max": 90,
                  "unit": "Unicode characters"
                },
                "target": {
                  "n": 1474,
                  "min": 36,
                  "median": 166.0,
                  "p95": 301,
                  "max": 829,
                  "unit": "Unicode characters"
                },
                "body": null
              },
              "sample": {
                "id": "uhri:0000512f-2460-466d-b3f9-30ccaa4342d6",
                "uid": "816834b88bd0ab99d9551f9a48ba8fe789dcd57f0bac92a911d30f6492e92eb3",
                "title": "A/HRC/61/17",
                "date": "2026-01-02",
                "source_url": "https://uhri.ohchr.org/en/our-data-api",
                "file": "data/prepared/country-extension-20260914/uhri-records.jsonl",
                "line": 3586,
                "task": "upr_recommendation",
                "fields": [
                  "affected_persons",
                  "annotation_type",
                  "available_date",
                  "context",
                  "country_iso3",
                  "country_name",
                  "date_precision",
                  "derivation",
                  "document_symbols",
                  "event_date",
                  "existing_event_splits",
                  "fresh_evaluation_eligible",
                  "fresh_evaluation_note",
                  "group_id",
                  "history",
                  "id",
                  "institution",
                  "language",
                  "mechanism",
                  "proposed_split",
                  "quality_flags",
                  "quality_status",
                  "question",
                  "raw_file",
                  "raw_sha256",
                  "recommending_states",
                  "represented_entity",
                  "response_labels",
                  "review_status",
                  "reviewed_states",
                  "rights_status",
                  "schema_version",
                  "sdgs",
                  "source_id",
                  "source_record_id",
                  "source_url",
                  "speaking_capacity",
                  "split",
                  "split_group",
                  "task",
                  "text",
                  "title",
                  "topic_method",
                  "topics",
                  "training_admitted",
                  "upr_cycle",
                  "upr_session"
                ],
                "quality_flags": [
                  "document_date_not_review_date",
                  "recommendation_context_missing"
                ],
                "rights_status": "unresolved",
                "review_status": "pending",
                "split": "quarantine"
              },
              "missing_input_fields": 0,
              "recorded_group_count": 648
            },
            {
              "id": "upr_response",
              "count": 724,
              "lengths": {
                "input": {
                  "n": 724,
                  "min": 76,
                  "median": 183.0,
                  "p95": 320,
                  "max": 604,
                  "unit": "Unicode characters"
                },
                "target": {
                  "n": 724,
                  "min": 5,
                  "median": 9.0,
                  "p95": 9,
                  "max": 15,
                  "unit": "Unicode characters"
                },
                "body": null
              },
              "sample": {
                "id": "uhri:00710954-ab1d-4190-a356-fd6cfab69178:response",
                "uid": "dc7a6fd1a19afbc895884dfae5753ca9ac2b84341e0eebc6217c7a43b6073927",
                "title": "A/HRC/52/14",
                "date": "2022-12-13",
                "source_url": "https://uhri.ohchr.org/en/our-data-api",
                "file": "data/prepared/country-extension-20260914/uhri-records.jsonl",
                "line": 6340,
                "task": "upr_response",
                "fields": [
                  "available_date",
                  "context",
                  "country_iso3",
                  "country_name",
                  "date_precision",
                  "derivation",
                  "document_symbols",
                  "event_date",
                  "existing_event_splits",
                  "fresh_evaluation_eligible",
                  "fresh_evaluation_note",
                  "group_id",
                  "history",
                  "id",
                  "institution",
                  "language",
                  "parent_id",
                  "proposed_split",
                  "quality_flags",
                  "quality_status",
                  "question",
                  "raw_file",
                  "raw_sha256",
                  "recommending_states",
                  "represented_entity",
                  "review_status",
                  "reviewed_states",
                  "rights_status",
                  "schema_version",
                  "source_id",
                  "source_record_id",
                  "source_url",
                  "speaking_capacity",
                  "split",
                  "split_group",
                  "task",
                  "text",
                  "title",
                  "topic_method",
                  "topics",
                  "training_admitted",
                  "upr_cycle",
                  "upr_session"
                ],
                "quality_flags": [
                  "recommendation_context_missing",
                  "response_date_unverified"
                ],
                "rights_status": "unresolved",
                "review_status": "pending",
                "split": "quarantine"
              },
              "missing_input_fields": 0,
              "recorded_group_count": 4
            }
          ],
          "missing_values": 0,
          "date_range": [
            "2008-05-22",
            "2026-01-08"
          ]
        },
        {
          "id": "curated",
          "count": 13,
          "source_ids": [
            "unspecified"
          ],
          "languages": [
            "en",
            "pt"
          ],
          "kinds": {
            "observed_actions": 1,
            "policy_positions": 5,
            "policy_applications": 4,
            "source_records": 3
          },
          "tasks": [
            {
              "id": "policy_positions",
              "count": 5,
              "lengths": {
                "input": null,
                "target": null,
                "body": null
              },
              "sample": {
                "id": "BRA-climate-2035-2024",
                "uid": "b51987f18afb02860fecaa4f5f39f0949ec9b13b01de7102cf3d6c42252eb41a",
                "title": "climate_commitments",
                "date": "2024-11-13",
                "source_url": "https://www.gov.br/mma/pt-br/assuntos/noticias/brasil-entrega-a-onu-nova-ndc-alinhada-ao-acordo-de-paris/ndc-versao-em-portugues.pdf",
                "file": "data/prepared/country-extension-20260914/policy-positions.candidates.jsonl",
                "line": 10,
                "task": "policy_positions",
                "fields": [
                  "available_date",
                  "claim",
                  "claim_language",
                  "countries",
                  "date",
                  "date_note",
                  "evidence",
                  "fresh_evaluation_eligible",
                  "group_id",
                  "id",
                  "issue",
                  "proposed_split",
                  "record_type",
                  "represented_entity",
                  "review_status",
                  "scope",
                  "split",
                  "split_group",
                  "training_admitted",
                  "translation_status"
                ],
                "quality_flags": [],
                "rights_status": "not_recorded",
                "review_status": "assistant_curated_independent_review_pending",
                "split": "quarantine"
              },
              "missing_input_fields": 5,
              "recorded_group_count": 4
            },
            {
              "id": "policy_applications",
              "count": 4,
              "lengths": {
                "input": {
                  "n": 4,
                  "min": 837,
                  "median": 1153.0,
                  "p95": 3580,
                  "max": 3580,
                  "unit": "Unicode characters"
                },
                "target": {
                  "n": 4,
                  "min": 209,
                  "median": 284.5,
                  "p95": 339,
                  "max": 339,
                  "unit": "Unicode characters"
                },
                "body": null
              },
              "sample": {
                "id": "BRA-climate-2035-2024:application",
                "uid": "5763eb0252ee7eec58cb0cb20cef6f8915124074fdfc4beda49a389f484793b8",
                "title": "climate_commitments",
                "date": "2024-11-13",
                "source_url": "https://www.gov.br/mma/pt-br/assuntos/noticias/brasil-entrega-a-onu-nova-ndc-alinhada-ao-acordo-de-paris/ndc-versao-em-portugues.pdf",
                "file": "data/prepared/country-extension-20260914/policy-applications.candidates.jsonl",
                "line": 10,
                "task": "policy_applications",
                "fields": [
                  "answer_language",
                  "available_date",
                  "countries",
                  "date",
                  "derivation",
                  "enable_thinking",
                  "evidence",
                  "fresh_evaluation_eligible",
                  "group_id",
                  "id",
                  "issue",
                  "messages",
                  "proposed_split",
                  "record_type",
                  "represented_entity",
                  "review_status",
                  "rubric",
                  "scope",
                  "split",
                  "split_group",
                  "training_admitted"
                ],
                "quality_flags": [],
                "rights_status": "not_recorded",
                "review_status": "assistant_curated_independent_review_pending",
                "split": "quarantine"
              },
              "missing_input_fields": 0,
              "recorded_group_count": 3
            },
            {
              "id": "policy_evidence",
              "count": 4,
              "lengths": {
                "input": null,
                "target": null,
                "body": null
              },
              "sample": {
                "id": "BRA-ES-11-1-20220302",
                "uid": "15543bb9f15537d131f985ed85db0a151126085d84f26ae2920584d6834e5f64",
                "title": "observed_vote",
                "date": "2022-03-02",
                "source_url": "",
                "file": "data/prepared/country-knowledge-20260914/actions.jsonl",
                "line": 1,
                "task": "policy_evidence",
                "fields": [
                  "amended_vote",
                  "bulk_source_id",
                  "country_iso3",
                  "csv_line",
                  "date",
                  "decision_id",
                  "document_symbols",
                  "evaluation_use",
                  "explanation_evidence",
                  "explanation_status",
                  "explanation_text_language",
                  "fresh_evaluation_eligible",
                  "group_id",
                  "id",
                  "language_of_delivery",
                  "original_vote",
                  "primary_roll_call_verified",
                  "primary_vote_pdf_pages",
                  "primary_vote_source_id",
                  "private_motive",
                  "proposal_source_id",
                  "public_explanation_summary",
                  "record_type",
                  "review_status",
                  "split",
                  "training_admitted"
                ],
                "quality_flags": [],
                "rights_status": "not_recorded",
                "review_status": "author_checked_independent_review_pending",
                "split": "quarantine"
              },
              "missing_input_fields": 4,
              "recorded_group_count": 1
            }
          ],
          "missing_values": 0,
          "date_range": [
            "2022-03-02",
            "2025-07-08"
          ]
        },
        {
          "id": "unga_speech_corpus",
          "count": 849,
          "source_ids": [
            "unga_speech_corpus"
          ],
          "languages": [
            "en"
          ],
          "kinds": {
            "source_records": 849
          },
          "tasks": [
            {
              "id": "unverified_speech_segment",
              "count": 435,
              "lengths": {
                "input": null,
                "target": null,
                "body": {
                  "n": 435,
                  "min": 36,
                  "median": 4976,
                  "p95": 14150,
                  "max": 66082,
                  "unit": "Unicode characters"
                }
              },
              "sample": {
                "id": "unga_speech_corpus:Brazil_100_48_19940101.txt",
                "uid": "5385dbf801212046f08b27d80759455e7ebd73286139e9e223796d6d7e04810a",
                "title": "UNGA A/48/PV.100",
                "date": "1994",
                "source_url": "https://www.linneaturco.com/research",
                "file": "data/prepared/country-extension-20260914/unga-speech-segments.jsonl",
                "line": 4,
                "task": "unverified_speech_segment",
                "fields": [
                  "available_date",
                  "context",
                  "country_iso3",
                  "country_name",
                  "date_precision",
                  "derivation",
                  "document_symbols",
                  "event_date",
                  "existing_event_splits",
                  "fresh_evaluation_eligible",
                  "fresh_evaluation_note",
                  "group_id",
                  "history",
                  "id",
                  "institution",
                  "language",
                  "meeting",
                  "proposed_split",
                  "quality_flags",
                  "quality_status",
                  "question",
                  "raw_file",
                  "raw_sha256",
                  "represented_entity",
                  "review_status",
                  "rights_status",
                  "schema_version",
                  "session",
                  "source_id",
                  "source_record_id",
                  "source_url",
                  "speaking_capacity",
                  "split",
                  "split_group",
                  "task",
                  "text",
                  "title",
                  "topic_method",
                  "topics",
                  "training_admitted",
                  "upstream_country_code",
                  "upstream_words_spoken"
                ],
                "quality_flags": [
                  "upstream_speaker_segmentation_unverified",
                  "year_precision_only"
                ],
                "rights_status": "unresolved",
                "review_status": "pending",
                "split": "quarantine"
              },
              "missing_input_fields": 435,
              "recorded_group_count": 435
            },
            {
              "id": "statement_reconstruction",
              "count": 414,
              "lengths": {
                "input": null,
                "target": {
                  "n": 414,
                  "min": 191,
                  "median": 4877.0,
                  "p95": 12609,
                  "max": 64635,
                  "unit": "Unicode characters"
                },
                "body": null
              },
              "sample": {
                "id": "unga_speech_corpus:Brazil_100_48_19940101.txt:speaker",
                "uid": "5424dc135c77400485fc5be23d7936b797427702e3ebbfef88cfdfcf1a94029c",
                "title": "UNGA A/48/PV.100",
                "date": "1994",
                "source_url": "https://www.linneaturco.com/research",
                "file": "data/prepared/country-extension-20260914/unga-speech-segments.jsonl",
                "line": 5,
                "task": "statement_reconstruction",
                "fields": [
                  "available_date",
                  "context",
                  "country_iso3",
                  "country_name",
                  "date_precision",
                  "derivation",
                  "document_symbols",
                  "event_date",
                  "existing_event_splits",
                  "fresh_evaluation_eligible",
                  "fresh_evaluation_note",
                  "group_id",
                  "history",
                  "id",
                  "institution",
                  "language",
                  "meeting",
                  "parent_id",
                  "proposed_split",
                  "quality_flags",
                  "quality_status",
                  "question",
                  "raw_file",
                  "raw_sha256",
                  "represented_entity",
                  "review_status",
                  "rights_status",
                  "schema_version",
                  "session",
                  "source_char_span",
                  "source_id",
                  "source_record_id",
                  "source_url",
                  "speaking_capacity",
                  "split",
                  "split_group",
                  "task",
                  "text",
                  "title",
                  "topic_method",
                  "topics",
                  "training_admitted"
                ],
                "quality_flags": [
                  "meeting_agenda_missing",
                  "speaker_boundary_rule_requires_review",
                  "year_precision_only"
                ],
                "rights_status": "unresolved",
                "review_status": "pending",
                "split": "quarantine"
              },
              "missing_input_fields": 414,
              "recorded_group_count": 414
            }
          ],
          "missing_values": 0,
          "date_range": [
            "1993",
            "2018"
          ]
        },
        {
          "id": "unga_dm",
          "count": 7509,
          "source_ids": [
            "unga_dm"
          ],
          "languages": [
            "en"
          ],
          "kinds": {
            "observed_actions": 7509
          },
          "tasks": [
            {
              "id": "vote_label_only",
              "count": 7509,
              "lengths": {
                "input": null,
                "target": null,
                "body": {
                  "n": 7509,
                  "min": 7,
                  "median": 8,
                  "p95": 10,
                  "max": 10,
                  "unit": "Unicode characters"
                }
              },
              "sample": {
                "id": "unga_dm:A/1081-S0100:140",
                "uid": "492d45b4d2baf4d18c5a1fb50fc30e43b269feb09e6d027fcde11c905f0009f1",
                "title": "A/1081-S0100",
                "date": "1949-11-25",
                "source_url": "https://unvotes.unige.ch/",
                "file": "data/prepared/country-extension-20260914/unga-votes.jsonl",
                "line": 27833,
                "task": "vote_label_only",
                "fields": [
                  "amended_vote",
                  "available_date",
                  "context",
                  "country_iso3",
                  "country_name",
                  "current_seat_name",
                  "date_precision",
                  "decision_mode",
                  "decision_topic",
                  "derivation",
                  "document_symbols",
                  "draft_resolution_id",
                  "event_date",
                  "existing_event_splits",
                  "fresh_evaluation_eligible",
                  "fresh_evaluation_note",
                  "group_id",
                  "history",
                  "id",
                  "institution",
                  "language",
                  "meeting_record_id",
                  "member_state_id",
                  "original_seat_name",
                  "original_vote",
                  "proposed_split",
                  "quality_flags",
                  "quality_status",
                  "question",
                  "raw_file",
                  "raw_sha256",
                  "represented_entity",
                  "resolution_id",
                  "review_status",
                  "rights_status",
                  "schema_version",
                  "session_id",
                  "source_id",
                  "source_record_id",
                  "source_url",
                  "speaking_capacity",
                  "split",
                  "split_group",
                  "task",
                  "text",
                  "title",
                  "topic_method",
                  "topics",
                  "training_admitted",
                  "vote_was_amended"
                ],
                "quality_flags": [
                  "proposal_text_missing"
                ],
                "rights_status": "unresolved",
                "review_status": "pending",
                "split": "quarantine"
              },
              "missing_input_fields": 7509,
              "recorded_group_count": 7509
            }
          ],
          "missing_values": 0,
          "date_range": [
            "1946-01-26",
            "2023-09-01"
          ]
        },
        {
          "id": "upr_reports",
          "count": 197,
          "source_ids": [
            "un_upr_national_report"
          ],
          "languages": [
            "ar",
            "en",
            "es",
            "fr",
            "ru",
            "zh"
          ],
          "kinds": {
            "source_records": 6,
            "evidence_passages": 191
          },
          "tasks": [
            {
              "id": "policy_evidence",
              "count": 191,
              "lengths": {
                "input": null,
                "target": null,
                "body": {
                  "n": 191,
                  "min": 229,
                  "median": 1844,
                  "p95": 2800,
                  "max": 2800,
                  "unit": "Unicode characters"
                }
              },
              "sample": {
                "id": "un_upr_national_report:upr4-BRA-ar:span:0:420",
                "uid": "b83a9fc652e886c4d962a0a22eee72c18ef2a939d50a96085412615ff837f672",
                "title": "un_upr_national_report:upr4-BRA-ar:span:0:420",
                "date": "2022-09-01",
                "source_url": "https://documents.un.org/api/symbol/access?l=ar&s=A%2FHRC%2FWG.6%2F41%2FBRA%2F1&t=pdf",
                "file": "data/prepared/country-extension-20260914/evidence-passages.jsonl",
                "line": 2185,
                "task": "policy_evidence",
                "fields": [
                  "available_date",
                  "country_iso3",
                  "document_type",
                  "end_char",
                  "event_date",
                  "group_id",
                  "id",
                  "language",
                  "parent_id",
                  "pdf_page",
                  "proposed_split",
                  "raw_sha256",
                  "related_countries",
                  "represented_entity",
                  "review_status",
                  "source_id",
                  "source_url",
                  "split",
                  "split_group",
                  "start_char",
                  "text",
                  "training_admitted",
                  "use"
                ],
                "quality_flags": [],
                "rights_status": "not_recorded",
                "review_status": "pending",
                "split": "quarantine"
              },
              "missing_input_fields": 191,
              "recorded_group_count": 1
            },
            {
              "id": "policy_evidence_document",
              "count": 6,
              "lengths": {
                "input": null,
                "target": null,
                "body": {
                  "n": 6,
                  "min": 22519,
                  "median": 67556.0,
                  "p95": 73272,
                  "max": 73272,
                  "unit": "Unicode characters"
                }
              },
              "sample": {
                "id": "un_upr_national_report:upr4-BRA-ar",
                "uid": "88038b67f9431650d70460065a0f461ee489bc96c3af779308b3ad24580dfd06",
                "title": "BRA fourth-cycle UPR national report",
                "date": "2022-09-01",
                "source_url": "https://documents.un.org/api/symbol/access?l=ar&s=A%2FHRC%2FWG.6%2F41%2FBRA%2F1&t=pdf",
                "file": "data/prepared/country-extension-20260914/documents.jsonl",
                "line": 40,
                "task": "policy_evidence_document",
                "fields": [
                  "available_date",
                  "context",
                  "country_iso3",
                  "country_name",
                  "date_basis",
                  "date_precision",
                  "derivation",
                  "document_symbols",
                  "document_type",
                  "event_date",
                  "existing_event_splits",
                  "extracted_text_file",
                  "extracted_text_sha256",
                  "fresh_evaluation_eligible",
                  "fresh_evaluation_note",
                  "group_id",
                  "history",
                  "id",
                  "institution",
                  "language",
                  "original_language",
                  "pdf_pages",
                  "proposed_split",
                  "publisher_date_label",
                  "quality_flags",
                  "quality_status",
                  "question",
                  "raw_file",
                  "raw_sha256",
                  "related_countries",
                  "represented_entity",
                  "retrieved_at",
                  "review_status",
                  "rights_status",
                  "schema_version",
                  "source_id",
                  "source_record_id",
                  "source_url",
                  "speaking_capacity",
                  "split",
                  "split_group",
                  "task",
                  "text",
                  "title",
                  "topic_method",
                  "topics",
                  "training_admitted",
                  "translation_family",
                  "translation_status",
                  "upr_cycle"
                ],
                "quality_flags": [
                  "evidence_document_not_response_target",
                  "historical_version_availability_unverified",
                  "individual_claims_require_review"
                ],
                "rights_status": "unresolved",
                "review_status": "pending",
                "split": "quarantine"
              },
              "missing_input_fields": 6,
              "recorded_group_count": 1
            }
          ],
          "missing_values": 0,
          "date_range": [
            "2022-09-01",
            "2022-09-01"
          ]
        },
        {
          "id": "decision_cases",
          "count": 2,
          "source_ids": [
            "unspecified"
          ],
          "languages": [
            "en"
          ],
          "kinds": {
            "decision_cases": 2
          },
          "tasks": [
            {
              "id": "decision_cases",
              "count": 2,
              "lengths": {
                "input": null,
                "target": null,
                "body": null
              },
              "sample": {
                "id": "decision:BRA-ES-11-1-20220302",
                "uid": "3ede541b9a969e8011bbc82548efba11442dfe96b9403d210fe14cd2abd2e840",
                "title": "Aggression against Ukraine — March 2022",
                "date": "2022-03-02",
                "source_url": "https://docs.un.org/A/ES-11/PV.5",
                "file": "data/prepared/decision-cases-20260914/cases.jsonl",
                "line": 1,
                "task": "decision_cases",
                "fields": [
                  "amended_action",
                  "author",
                  "conditions_for_agreement",
                  "conditions_status",
                  "country_iso3",
                  "country_name",
                  "derivation",
                  "event_date",
                  "explanation_evidence",
                  "explanation_kind",
                  "fresh_evaluation_eligible",
                  "group_id",
                  "id",
                  "issue",
                  "language",
                  "material_context",
                  "missing_context",
                  "observed_action",
                  "private_motive",
                  "proposal_evidence",
                  "proposal_summary",
                  "proposal_symbol",
                  "public_explanation",
                  "record_type",
                  "related_group_ids",
                  "represented_entity",
                  "requested_changes",
                  "resolution_symbol",
                  "review_status",
                  "schema_version",
                  "source_coverage",
                  "source_url",
                  "split",
                  "stated_considerations",
                  "title",
                  "training_admitted",
                  "use",
                  "vote_evidence"
                ],
                "quality_flags": [],
                "rights_status": "not_recorded",
                "review_status": "source_checked_independent_review_pending",
                "split": "quarantine"
              },
              "missing_input_fields": 2,
              "recorded_group_count": 2
            }
          ],
          "missing_values": 0,
          "date_range": [
            "2022-03-02",
            "2022-10-12"
          ]
        },
        {
          "id": "world_bank",
          "count": 43,
          "source_ids": [
            "unspecified",
            "world_bank_2024"
          ],
          "languages": [],
          "kinds": {
            "country_statistics": 43
          },
          "tasks": [
            {
              "id": "country_statistics",
              "count": 43,
              "lengths": {
                "input": null,
                "target": null,
                "body": null
              },
              "sample": {
                "id": "WDI-BRA-NE.TRD.GNFS.ZS-2024",
                "uid": "af49ed81ceb309f26efd22fb5a8e38537cbd84388862b7c6f01e3858afc7d566",
                "title": "Trade (% of GDP)",
                "date": "2024",
                "source_url": "https://api.worldbank.org/v2/country/bra;chn;deu;fra;gbr;ind/indicator/SP.POP.TOTL;NY.GDP.MKTP.CD;NE.TRD.GNFS.ZS?source=2&date=2024&format=json&per_page=1000",
                "file": "data/prepared/country-knowledge-20260914/facts.jsonl",
                "line": 13,
                "task": "country_statistics",
                "fields": [
                  "available_at_reference_year",
                  "country_iso3",
                  "database_last_updated",
                  "definition",
                  "fresh_evaluation_eligible",
                  "id",
                  "indicator",
                  "label",
                  "missing",
                  "record_type",
                  "reference_year",
                  "retrieved_at",
                  "review_status",
                  "source_id",
                  "source_pointer",
                  "source_url",
                  "split",
                  "training_admitted",
                  "unit",
                  "upstream_organization",
                  "use",
                  "value"
                ],
                "quality_flags": [],
                "rights_status": "not_recorded",
                "review_status": "author_checked_independent_review_pending",
                "split": "quarantine"
              },
              "missing_input_fields": 43,
              "recorded_group_count": 0
            }
          ],
          "missing_values": 4,
          "date_range": [
            "2020",
            "2024"
          ]
        },
        {
          "id": "wto",
          "count": 97,
          "source_ids": [
            "wto_government_reports"
          ],
          "languages": [
            "en"
          ],
          "kinds": {
            "source_records": 1,
            "evidence_passages": 96
          },
          "tasks": [
            {
              "id": "policy_evidence",
              "count": 96,
              "lengths": {
                "input": null,
                "target": null,
                "body": {
                  "n": 96,
                  "min": 382,
                  "median": 2319.0,
                  "p95": 2800,
                  "max": 2800,
                  "unit": "Unicode characters"
                }
              },
              "sample": {
                "id": "wto_government_reports:BRA-wto-2022-en:span:0:509",
                "uid": "db2a9ec27ecf1d6f9d66d2250bf4152723ddcf646195adeb681e11b214a504df",
                "title": "wto_government_reports:BRA-wto-2022-en:span:0:509",
                "date": "2022-10-19",
                "source_url": "https://www.wto.org/english/tratop_e/tpr_e/g432_e.pdf",
                "file": "data/prepared/country-extension-20260914/evidence-passages.jsonl",
                "line": 674,
                "task": "policy_evidence",
                "fields": [
                  "available_date",
                  "country_iso3",
                  "document_type",
                  "end_char",
                  "event_date",
                  "group_id",
                  "id",
                  "language",
                  "parent_id",
                  "pdf_page",
                  "proposed_split",
                  "raw_sha256",
                  "related_countries",
                  "represented_entity",
                  "review_status",
                  "source_id",
                  "source_url",
                  "split",
                  "split_group",
                  "start_char",
                  "text",
                  "training_admitted",
                  "use"
                ],
                "quality_flags": [],
                "rights_status": "not_recorded",
                "review_status": "pending",
                "split": "quarantine"
              },
              "missing_input_fields": 96,
              "recorded_group_count": 1
            },
            {
              "id": "policy_evidence_document",
              "count": 1,
              "lengths": {
                "input": null,
                "target": null,
                "body": {
                  "n": 1,
                  "min": 209685,
                  "median": 209685,
                  "p95": 209685,
                  "max": 209685,
                  "unit": "Unicode characters"
                }
              },
              "sample": {
                "id": "wto_government_reports:BRA-wto-2022-en",
                "uid": "68eb1bd1d45cd8bccd3f20adb6e52e86a6f69b6b37b9ffe0bba0654d94a3d819",
                "title": "WTO Trade Policy Review: report by Brazil",
                "date": "2022-10-19",
                "source_url": "https://www.wto.org/english/tratop_e/tpr_e/g432_e.pdf",
                "file": "data/prepared/country-extension-20260914/documents.jsonl",
                "line": 8,
                "task": "policy_evidence_document",
                "fields": [
                  "available_date",
                  "context",
                  "country_iso3",
                  "country_name",
                  "date_basis",
                  "date_precision",
                  "derivation",
                  "document_symbols",
                  "document_type",
                  "event_date",
                  "existing_event_splits",
                  "extracted_text_file",
                  "extracted_text_sha256",
                  "fresh_evaluation_eligible",
                  "fresh_evaluation_note",
                  "group_id",
                  "history",
                  "id",
                  "institution",
                  "language",
                  "original_language",
                  "pdf_issue_date_label",
                  "pdf_pages",
                  "proposed_split",
                  "publisher_date_label",
                  "quality_flags",
                  "quality_status",
                  "question",
                  "raw_file",
                  "raw_sha256",
                  "related_countries",
                  "represented_entity",
                  "retrieved_at",
                  "review_status",
                  "rights_status",
                  "schema_version",
                  "source_id",
                  "source_record_id",
                  "source_url",
                  "speaking_capacity",
                  "split",
                  "split_group",
                  "task",
                  "text",
                  "title",
                  "topic_method",
                  "topics",
                  "training_admitted",
                  "translation_family",
                  "translation_status",
                  "upr_cycle"
                ],
                "quality_flags": [
                  "evidence_document_not_response_target",
                  "historical_version_availability_unverified",
                  "individual_claims_require_review",
                  "government_submission_not_independent_WTO_assessment"
                ],
                "rights_status": "unresolved",
                "review_status": "pending",
                "split": "quarantine"
              },
              "missing_input_fields": 1,
              "recorded_group_count": 1
            }
          ],
          "missing_values": 0,
          "date_range": [
            "2022-10-19",
            "2022-10-19"
          ]
        }
      ]
    }
  }
}
