{
 "name": "china-entry-rules",
 "title": "China and Hong Kong Entry Rules for International Bachelor Applicants (2026)",
 "version": "2026.11",
 "description": "China and Hong Kong Entry Rules for International Bachelor Applicants (2026): Which school certificates are accepted, admission calendars, language and preparatory routes, the HSK 3.0 transition, apostille, study visas by passport and work rules for students. Scope: 16 mainland universities in the ARWU 2026 top 100 plus 3 in Hong Kong. The Long Bet, original research by M. Atamanova. Version 2026.11, data checked up to 2026-11-08.",
 "homepage": "https://mariascales.com/research/long-bet/data/china-entry-rules/",
 "licenses": [
  {
   "name": "CC-BY-4.0",
   "path": "https://creativecommons.org/licenses/by/4.0/",
   "title": "Creative Commons Attribution 4.0 International"
  }
 ],
 "sources": [
  {
   "title": "Original research: The Long Bet (mariascales.com)",
   "path": "https://mariascales.com/research/long-bet/"
  },
  {
   "title": "132 pages listed in sources.csv",
   "path": "sources.csv"
  }
 ],
 "resources": [
  {
   "name": "data",
   "path": "data.csv",
   "format": "csv",
   "mediatype": "text/csv",
   "encoding": "utf-8",
   "schema": {
    "fields": [
     {
      "name": "university_id",
      "type": "string",
      "description": "Stable slug of the university, the same id as in the other Long Bet datasets (e.g. `tsinghua-university`).",
      "constraints": {
       "required": true
      }
     },
     {
      "name": "certificate",
      "type": "string",
      "description": "School-leaving certificate: `ru_attestat_ege` (Russian attestat with EGE), `tr_lise_diplomasi` (Turkish lise diploma), `rs_matura` (Serbian matura), `eu_school_leaving` (EU school-leaving certificates such as Abitur, baccalaureat, maturita), `uk_a_level`.",
      "constraints": {
       "required": true,
       "enum": [
        "eu_school_leaving",
        "rs_matura",
        "ru_attestat_ege",
        "tr_lise_diplomasi",
        "uk_a_level"
       ]
      }
     },
     {
      "name": "accepted",
      "type": "string",
      "description": "`yes` = the certificate is named as accepted; `yes_generic_hs_diploma` = any high school diploma accepted, certificate not named; `conditional` = accepted with an extra step; `not_stated`.",
      "constraints": {
       "enum": [
        "conditional",
        "not_stated",
        "yes",
        "yes_generic_hs_diploma"
       ]
      }
     },
     {
      "name": "certificate_named",
      "type": "string",
      "description": "Name of the certificate as written on the page, when named."
     },
     {
      "name": "extra_requirements",
      "type": "string",
      "description": "Tests, language and other requirements on top of the certificate."
     },
     {
      "name": "document_rules",
      "type": "string",
      "description": "Rules on transcripts, translations, notarisation and apostille."
     },
     {
      "name": "min_grades",
      "type": "string",
      "description": "Minimum grades for this certificate, when published."
     },
     {
      "name": "intake",
      "type": "string",
      "description": "Intake the page refers to."
     },
     {
      "name": "status",
      "type": "string",
      "description": "`found` = the fact was read on the source page; `not_found` = the page was checked and the fact is not there: the row records what was looked for, `source_url` gives the URL tried and `note` says what was missing.",
      "constraints": {
       "required": true,
       "enum": [
        "found"
       ]
      }
     },
     {
      "name": "source_url",
      "type": "string",
      "description": "Page(s) where the fact is stated, \"; \"-separated, primary pages first. For `not_found` rows: the page(s) tried."
     },
     {
      "name": "source_type",
      "type": "string",
      "description": "`official` = university, government, embassy, airport or ranking publisher page; `law` = legal act; `secondary` = media, Wikipedia, agencies, aggregators.",
      "constraints": {
       "enum": [
        "official"
       ]
      }
     },
     {
      "name": "checked_at",
      "type": "string",
      "description": "Date the row was last read on the source, ISO 8601."
     },
     {
      "name": "confidence",
      "type": "string",
      "description": "`verified` = read on an official or legal page for the current cycle; `partial` = official but older cycle or incomplete, or a reputable secondary source; `estimate` = derived or calculated, method in `note`. Empty for `not_found` rows.",
      "constraints": {
       "enum": [
        "partial",
        "verified"
       ]
      }
     },
     {
      "name": "note",
      "type": "string",
      "description": "Caveats in English. \"Updated 2026-10-23:\" marks text added by the second verification pass of 23 October 2026."
     }
    ],
    "primaryKey": [
     "university_id",
     "certificate"
    ]
   }
  },
  {
   "name": "admission_cycle",
   "path": "admission_cycle.csv",
   "format": "csv",
   "mediatype": "text/csv",
   "encoding": "utf-8",
   "schema": {
    "fields": [
     {
      "name": "university_id",
      "type": "string",
      "description": "Stable slug of the university, the same id as in the other Long Bet datasets (e.g. `tsinghua-university`).",
      "constraints": {
       "required": true
      }
     },
     {
      "name": "intake",
      "type": "string",
      "description": "Intake the page refers to."
     },
     {
      "name": "application_open",
      "type": "string",
      "description": "Application opening date (ISO 8601 where the page gives one date; text where routes or rounds differ)."
     },
     {
      "name": "application_deadline",
      "type": "string",
      "description": "Application deadline (ISO date where the page gives one date; text where there are several rounds)."
     },
     {
      "name": "results_date",
      "type": "string",
      "description": "When decisions are published."
     },
     {
      "name": "study_start",
      "type": "string",
      "description": "Start of study."
     },
     {
      "name": "csca_required",
      "type": "string",
      "description": "China Scholastic Competency Assessment (CSCA): `true` required, `false` not required, `optional` accepted as evidence.",
      "constraints": {
       "enum": [
        "false",
        "optional",
        "true"
       ]
      }
     },
     {
      "name": "own_exam",
      "type": "string",
      "description": "University entrance exam or interview."
     },
     {
      "name": "intl_quota_or_competition",
      "type": "string",
      "description": "Published quota or competition figures for international applicants."
     },
     {
      "name": "status",
      "type": "string",
      "description": "`found` = the fact was read on the source page; `not_found` = the page was checked and the fact is not there: the row records what was looked for, `source_url` gives the URL tried and `note` says what was missing.",
      "constraints": {
       "required": true,
       "enum": [
        "found"
       ]
      }
     },
     {
      "name": "source_url",
      "type": "string",
      "description": "Page(s) where the fact is stated, \"; \"-separated, primary pages first. For `not_found` rows: the page(s) tried."
     },
     {
      "name": "source_type",
      "type": "string",
      "description": "`official` = university, government, embassy, airport or ranking publisher page; `law` = legal act; `secondary` = media, Wikipedia, agencies, aggregators.",
      "constraints": {
       "enum": [
        "official",
        "secondary"
       ]
      }
     },
     {
      "name": "checked_at",
      "type": "string",
      "description": "Date the row was last read on the source, ISO 8601."
     },
     {
      "name": "confidence",
      "type": "string",
      "description": "`verified` = read on an official or legal page for the current cycle; `partial` = official but older cycle or incomplete, or a reputable secondary source; `estimate` = derived or calculated, method in `note`. Empty for `not_found` rows.",
      "constraints": {
       "enum": [
        "partial",
        "verified"
       ]
      }
     },
     {
      "name": "note",
      "type": "string",
      "description": "Caveats in English. \"Updated 2026-10-23:\" marks text added by the second verification pass of 23 October 2026."
     }
    ],
    "primaryKey": [
     "university_id"
    ]
   }
  },
  {
   "name": "apostille",
   "path": "apostille.csv",
   "format": "csv",
   "mediatype": "text/csv",
   "encoding": "utf-8",
   "schema": {
    "fields": [
     {
      "name": "record_id",
      "type": "string",
      "description": "Row id: `<party_a slug>__<topic>__<n>`.",
      "constraints": {
       "required": true
      }
     },
     {
      "name": "topic",
      "type": "string",
      "description": "Topic: `bilateral_in_force`, `mainland_hong_kong`, `hong_kong_status`, `objection` and others.",
      "constraints": {
       "enum": [
        "bilateral_in_force",
        "china_mainland_accession",
        "hong_kong_status",
        "mainland_hong_kong",
        "objection"
       ]
      }
     },
     {
      "name": "party_a",
      "type": "string",
      "description": "Jurisdiction on one side (China mainland or Hong Kong SAR)."
     },
     {
      "name": "party_b",
      "type": "string",
      "description": "Other party (country or group of countries)."
     },
     {
      "name": "since",
      "type": "string",
      "description": "Date the Apostille Convention applies between the parties, ISO 8601."
     },
     {
      "name": "detail",
      "type": "string",
      "description": "What applies."
     },
     {
      "name": "status",
      "type": "string",
      "description": "`found` = the fact was read on the source page; `not_found` = the page was checked and the fact is not there: the row records what was looked for, `source_url` gives the URL tried and `note` says what was missing.",
      "constraints": {
       "required": true,
       "enum": [
        "found"
       ]
      }
     },
     {
      "name": "source_url",
      "type": "string",
      "description": "Page(s) where the fact is stated, \"; \"-separated, primary pages first. For `not_found` rows: the page(s) tried."
     },
     {
      "name": "source_type",
      "type": "string",
      "description": "`official` = university, government, embassy, airport or ranking publisher page; `law` = legal act; `secondary` = media, Wikipedia, agencies, aggregators.",
      "constraints": {
       "enum": [
        "official",
        "secondary"
       ]
      }
     },
     {
      "name": "checked_at",
      "type": "string",
      "description": "Date the row was last read on the source, ISO 8601."
     },
     {
      "name": "confidence",
      "type": "string",
      "description": "`verified` = read on an official or legal page for the current cycle; `partial` = official but older cycle or incomplete, or a reputable secondary source; `estimate` = derived or calculated, method in `note`. Empty for `not_found` rows.",
      "constraints": {
       "enum": [
        "partial",
        "verified"
       ]
      }
     },
     {
      "name": "note",
      "type": "string",
      "description": "Caveats in English. \"Updated 2026-10-23:\" marks text added by the second verification pass of 23 October 2026."
     }
    ],
    "primaryKey": [
     "record_id"
    ]
   }
  },
  {
   "name": "visa_by_passport",
   "path": "visa_by_passport.csv",
   "format": "csv",
   "mediatype": "text/csv",
   "encoding": "utf-8",
   "schema": {
    "fields": [
     {
      "name": "passport",
      "type": "string",
      "description": "Passport, ISO 3166-1 alpha-2 (`RU`, `TR`, `RS`, `DE`, `FR`, `IT`, `PL`).",
      "constraints": {
       "required": true
      }
     },
     {
      "name": "destination",
      "type": "string",
      "description": "`mainland` or `hong_kong`.",
      "constraints": {
       "required": true,
       "enum": [
        "hong_kong",
        "mainland"
       ]
      }
     },
     {
      "name": "short_stay_visa_free_days",
      "type": "integer",
      "description": "Visa-free stay for short visits. Unit: days (0 = a visa is needed). Never covers study."
     },
     {
      "name": "short_stay_basis",
      "type": "string",
      "description": "Legal basis of the visa-free stay."
     },
     {
      "name": "study_visa_type",
      "type": "string",
      "description": "Visa or entry permit needed for a bachelor programme."
     },
     {
      "name": "where_to_apply",
      "type": "string",
      "description": "Where the study visa is applied for."
     },
     {
      "name": "visa_fee_amount_local",
      "type": "integer",
      "description": "Consular visa fee, single entry. Unit: `visa_fee_currency` (one-off)."
     },
     {
      "name": "visa_fee_currency",
      "type": "string",
      "description": "ISO 4217 currency of the visa fee; null when the source does not state it."
     },
     {
      "name": "visa_fee_period",
      "type": "string",
      "description": "Always `one_off`.",
      "constraints": {
       "enum": [
        "one_off"
       ]
      }
     },
     {
      "name": "service_fee_amount_local",
      "type": "string",
      "description": "Visa centre service fee, as text with its currency (standard, express, urgent)."
     },
     {
      "name": "processing_days",
      "type": "string",
      "description": "Processing time."
     },
     {
      "name": "passport_validity",
      "type": "string",
      "description": "Passport validity required."
     },
     {
      "name": "documents",
      "type": "string",
      "description": "Documents for the study visa."
     },
     {
      "name": "criminal_record_rule",
      "type": "string",
      "description": "Whether a criminal-record certificate is required and by whom."
     },
     {
      "name": "residence_permit",
      "type": "string",
      "description": "Residence permit after arrival: deadline, fee, validity."
     },
     {
      "name": "status",
      "type": "string",
      "description": "`found` = the fact was read on the source page; `not_found` = the page was checked and the fact is not there: the row records what was looked for, `source_url` gives the URL tried and `note` says what was missing.",
      "constraints": {
       "required": true,
       "enum": [
        "found"
       ]
      }
     },
     {
      "name": "source_url",
      "type": "string",
      "description": "Page(s) where the fact is stated, \"; \"-separated, primary pages first. For `not_found` rows: the page(s) tried."
     },
     {
      "name": "source_type",
      "type": "string",
      "description": "`official` = university, government, embassy, airport or ranking publisher page; `law` = legal act; `secondary` = media, Wikipedia, agencies, aggregators.",
      "constraints": {
       "enum": [
        "official",
        "secondary"
       ]
      }
     },
     {
      "name": "checked_at",
      "type": "string",
      "description": "Date the row was last read on the source, ISO 8601."
     },
     {
      "name": "confidence",
      "type": "string",
      "description": "`verified` = read on an official or legal page for the current cycle; `partial` = official but older cycle or incomplete, or a reputable secondary source; `estimate` = derived or calculated, method in `note`. Empty for `not_found` rows.",
      "constraints": {
       "enum": [
        "estimate",
        "partial",
        "verified"
       ]
      }
     },
     {
      "name": "note",
      "type": "string",
      "description": "Caveats in English. \"Updated 2026-10-23:\" marks text added by the second verification pass of 23 October 2026."
     }
    ],
    "primaryKey": [
     "passport",
     "destination"
    ]
   }
  },
  {
   "name": "work_rules",
   "path": "work_rules.csv",
   "format": "csv",
   "mediatype": "text/csv",
   "encoding": "utf-8",
   "schema": {
    "fields": [
     {
      "name": "region",
      "type": "string",
      "description": "`mainland` (mainland China) or `hong_kong` (Hong Kong SAR).",
      "constraints": {
       "required": true,
       "enum": [
        "hong_kong",
        "mainland"
       ]
      }
     },
     {
      "name": "topic",
      "type": "string",
      "description": "Rule topic, e.g. `part_time_work`, `internship`, `off_campus_permission`.",
      "constraints": {
       "required": true,
       "enum": [
        "general_rule",
        "illegal_employment",
        "illegal_employment_penalty",
        "internship",
        "off_campus_permission",
        "on_campus",
        "part_time_work",
        "post_graduation_work",
        "summer",
        "temporary_relaxation"
       ]
      }
     },
     {
      "name": "rule",
      "type": "string",
      "description": "The rule, in words."
     },
     {
      "name": "legal_basis",
      "type": "string",
      "description": "Law, regulation or scheme the rule is based on."
     },
     {
      "name": "status",
      "type": "string",
      "description": "`found` = the fact was read on the source page; `not_found` = the page was checked and the fact is not there: the row records what was looked for, `source_url` gives the URL tried and `note` says what was missing.",
      "constraints": {
       "required": true,
       "enum": [
        "found"
       ]
      }
     },
     {
      "name": "source_url",
      "type": "string",
      "description": "Page(s) where the fact is stated, \"; \"-separated, primary pages first. For `not_found` rows: the page(s) tried."
     },
     {
      "name": "source_type",
      "type": "string",
      "description": "`official` = university, government, embassy, airport or ranking publisher page; `law` = legal act; `secondary` = media, Wikipedia, agencies, aggregators.",
      "constraints": {
       "enum": [
        "law",
        "official"
       ]
      }
     },
     {
      "name": "checked_at",
      "type": "string",
      "description": "Date the row was last read on the source, ISO 8601."
     },
     {
      "name": "confidence",
      "type": "string",
      "description": "`verified` = read on an official or legal page for the current cycle; `partial` = official but older cycle or incomplete, or a reputable secondary source; `estimate` = derived or calculated, method in `note`. Empty for `not_found` rows.",
      "constraints": {
       "enum": [
        "partial",
        "verified"
       ]
      }
     },
     {
      "name": "note",
      "type": "string",
      "description": "Caveats in English. \"Updated 2026-10-23:\" marks text added by the second verification pass of 23 October 2026."
     }
    ],
    "primaryKey": [
     "region",
     "topic"
    ]
   }
  },
  {
   "name": "language_requirements",
   "path": "language_requirements.csv",
   "format": "csv",
   "mediatype": "text/csv",
   "encoding": "utf-8",
   "schema": {
    "fields": [
     {
      "name": "university_id",
      "type": "string",
      "description": "Stable slug of the university, the same id as in the other Long Bet datasets (e.g. `tsinghua-university`).",
      "constraints": {
       "required": true
      }
     },
     {
      "name": "track",
      "type": "string",
      "description": "Programme track: `zh_taught`, `en_taught` (run by the university), `en_taught_joint_institute`, `en_taught_international_college`.",
      "constraints": {
       "required": true,
       "enum": [
        "en_taught",
        "zh_taught"
       ]
      }
     },
     {
      "name": "track_offered",
      "type": "string",
      "description": "`yes` if the university offers this track to international bachelor applicants, `no` if not.",
      "constraints": {
       "enum": [
        "no",
        "yes"
       ]
      }
     },
     {
      "name": "intake_cycle",
      "type": "string",
      "description": "Intake or cycle the requirement was published for."
     },
     {
      "name": "hsk_level_required",
      "type": "string",
      "description": "HSK level required at application or enrolment; `none` = not required."
     },
     {
      "name": "hsk_min_score",
      "type": "string",
      "description": "Minimum HSK score as published (text: some pages give alternatives)."
     },
     {
      "name": "hsk_section_min",
      "type": "string",
      "description": "Minimum score per HSK section, when published."
     },
     {
      "name": "hsk_scale",
      "type": "string",
      "description": "Which HSK version the threshold refers to (2.0 or 3.0), as far as the page says."
     },
     {
      "name": "english_test_required",
      "type": "string",
      "description": "English test and minimum score required."
     },
     {
      "name": "hsk_required_to_graduate",
      "type": "string",
      "description": "Chinese-language requirement to graduate."
     },
     {
      "name": "status",
      "type": "string",
      "description": "`found` = the fact was read on the source page; `not_found` = the page was checked and the fact is not there: the row records what was looked for, `source_url` gives the URL tried and `note` says what was missing.",
      "constraints": {
       "required": true,
       "enum": [
        "found",
        "not_found"
       ]
      }
     },
     {
      "name": "source_url",
      "type": "string",
      "description": "Page(s) where the fact is stated, \"; \"-separated, primary pages first. For `not_found` rows: the page(s) tried."
     },
     {
      "name": "source_type",
      "type": "string",
      "description": "`official` = university, government, embassy, airport or ranking publisher page; `law` = legal act; `secondary` = media, Wikipedia, agencies, aggregators.",
      "constraints": {
       "enum": [
        "official"
       ]
      }
     },
     {
      "name": "checked_at",
      "type": "string",
      "description": "Date the row was last read on the source, ISO 8601."
     },
     {
      "name": "confidence",
      "type": "string",
      "description": "`verified` = read on an official or legal page for the current cycle; `partial` = official but older cycle or incomplete, or a reputable secondary source; `estimate` = derived or calculated, method in `note`. Empty for `not_found` rows.",
      "constraints": {
       "enum": [
        "partial",
        "verified"
       ]
      }
     },
     {
      "name": "note",
      "type": "string",
      "description": "Caveats in English. \"Updated 2026-10-23:\" marks text added by the second verification pass of 23 October 2026."
     }
    ],
    "primaryKey": [
     "university_id",
     "track"
    ]
   }
  },
  {
   "name": "prep_programmes",
   "path": "prep_programmes.csv",
   "format": "csv",
   "mediatype": "text/csv",
   "encoding": "utf-8",
   "schema": {
    "fields": [
     {
      "name": "university_id",
      "type": "string",
      "description": "Stable slug of the university, the same id as in the other Long Bet datasets (e.g. `tsinghua-university`).",
      "constraints": {
       "required": true
      }
     },
     {
      "name": "prep_programme_name",
      "type": "string",
      "description": "Name of the preparatory (pre-university, foundation) programme; text starting with `none` = no such programme found.",
      "constraints": {
       "required": true
      }
     },
     {
      "name": "provider",
      "type": "string",
      "description": "Who runs it."
     },
     {
      "name": "language_of_prep",
      "type": "string",
      "description": "Language of instruction of the preparatory programme."
     },
     {
      "name": "duration_months",
      "type": "string",
      "description": "Duration. Unit: months (range as text)."
     },
     {
      "name": "cost_amount_local",
      "type": "integer",
      "description": "Tuition of the preparatory programme. Unit: `currency` per `period`."
     },
     {
      "name": "currency",
      "type": "string",
      "description": "ISO 4217 currency of `cost_amount_local`."
     },
     {
      "name": "period",
      "type": "string",
      "description": "Period the amount refers to, e.g. `per_year`, `per_month`, `one_off`.",
      "constraints": {
       "enum": [
        "one_off",
        "per_semester",
        "per_year"
       ]
      }
     },
     {
      "name": "intake_cycle",
      "type": "string",
      "description": "Intake or cycle the requirement was published for."
     },
     {
      "name": "entry_level",
      "type": "string",
      "description": "Language or academic level needed to start."
     },
     {
      "name": "target_level",
      "type": "string",
      "description": "Level the programme leads to, or the condition to enter the bachelor."
     },
     {
      "name": "progression_guaranteed",
      "type": "string",
      "description": "Whether finishing the programme guarantees a bachelor place, as stated."
     },
     {
      "name": "status",
      "type": "string",
      "description": "`found` = the fact was read on the source page; `not_found` = the page was checked and the fact is not there: the row records what was looked for, `source_url` gives the URL tried and `note` says what was missing.",
      "constraints": {
       "required": true,
       "enum": [
        "found",
        "not_found"
       ]
      }
     },
     {
      "name": "source_url",
      "type": "string",
      "description": "Page(s) where the fact is stated, \"; \"-separated, primary pages first. For `not_found` rows: the page(s) tried."
     },
     {
      "name": "source_type",
      "type": "string",
      "description": "`official` = university, government, embassy, airport or ranking publisher page; `law` = legal act; `secondary` = media, Wikipedia, agencies, aggregators.",
      "constraints": {
       "enum": [
        "official",
        "secondary"
       ]
      }
     },
     {
      "name": "checked_at",
      "type": "string",
      "description": "Date the row was last read on the source, ISO 8601."
     },
     {
      "name": "confidence",
      "type": "string",
      "description": "`verified` = read on an official or legal page for the current cycle; `partial` = official but older cycle or incomplete, or a reputable secondary source; `estimate` = derived or calculated, method in `note`. Empty for `not_found` rows.",
      "constraints": {
       "enum": [
        "partial",
        "verified"
       ]
      }
     },
     {
      "name": "note",
      "type": "string",
      "description": "Caveats in English. \"Updated 2026-10-23:\" marks text added by the second verification pass of 23 October 2026."
     }
    ],
    "primaryKey": [
     "university_id",
     "prep_programme_name"
    ]
   }
  },
  {
   "name": "hsk_status",
   "path": "hsk_status.csv",
   "format": "csv",
   "mediatype": "text/csv",
   "encoding": "utf-8",
   "schema": {
    "fields": [
     {
      "name": "topic",
      "type": "string",
      "description": "Topic of the HSK 2.0 to HSK 3.0 transition, e.g. `hsk3_released`, `last_hsk2_sitting`.",
      "constraints": {
       "required": true
      }
     },
     {
      "name": "value",
      "type": "string",
      "description": "The fact, in words."
     },
     {
      "name": "status",
      "type": "string",
      "description": "`found` = the fact was read on the source page; `not_found` = the page was checked and the fact is not there: the row records what was looked for, `source_url` gives the URL tried and `note` says what was missing.",
      "constraints": {
       "required": true,
       "enum": [
        "found"
       ]
      }
     },
     {
      "name": "source_url",
      "type": "string",
      "description": "Page(s) where the fact is stated, \"; \"-separated, primary pages first. For `not_found` rows: the page(s) tried."
     },
     {
      "name": "source_type",
      "type": "string",
      "description": "`official` = university, government, embassy, airport or ranking publisher page; `law` = legal act; `secondary` = media, Wikipedia, agencies, aggregators.",
      "constraints": {
       "enum": [
        "official",
        "secondary"
       ]
      }
     },
     {
      "name": "checked_at",
      "type": "string",
      "description": "Date the row was last read on the source, ISO 8601."
     },
     {
      "name": "confidence",
      "type": "string",
      "description": "`verified` = read on an official or legal page for the current cycle; `partial` = official but older cycle or incomplete, or a reputable secondary source; `estimate` = derived or calculated, method in `note`. Empty for `not_found` rows.",
      "constraints": {
       "enum": [
        "partial",
        "verified"
       ]
      }
     },
     {
      "name": "note",
      "type": "string",
      "description": "Caveats in English. \"Updated 2026-10-23:\" marks text added by the second verification pass of 23 October 2026."
     }
    ],
    "primaryKey": [
     "topic"
    ]
   }
  },
  {
   "name": "language_realism_evidence",
   "path": "language_realism_evidence.csv",
   "format": "csv",
   "mediatype": "text/csv",
   "encoding": "utf-8",
   "schema": {
    "fields": [
     {
      "name": "claim",
      "type": "string",
      "description": "Statement about how realistic the language route is.",
      "constraints": {
       "required": true
      }
     },
     {
      "name": "figure",
      "type": "string",
      "description": "The number behind the statement, as published."
     },
     {
      "name": "population",
      "type": "string",
      "description": "Whom the figure refers to."
     },
     {
      "name": "evidence_type",
      "type": "string",
      "description": "`official_statistic` or `university_statement`.",
      "constraints": {
       "enum": [
        "official_statistic",
        "university_statement"
       ]
      }
     },
     {
      "name": "status",
      "type": "string",
      "description": "`found` = the fact was read on the source page; `not_found` = the page was checked and the fact is not there: the row records what was looked for, `source_url` gives the URL tried and `note` says what was missing.",
      "constraints": {
       "required": true,
       "enum": [
        "found"
       ]
      }
     },
     {
      "name": "source_url",
      "type": "string",
      "description": "Page(s) where the fact is stated, \"; \"-separated, primary pages first. For `not_found` rows: the page(s) tried."
     },
     {
      "name": "source_type",
      "type": "string",
      "description": "`official` = university, government, embassy, airport or ranking publisher page; `law` = legal act; `secondary` = media, Wikipedia, agencies, aggregators.",
      "constraints": {
       "enum": [
        "official",
        "secondary"
       ]
      }
     },
     {
      "name": "checked_at",
      "type": "string",
      "description": "Date the row was last read on the source, ISO 8601."
     },
     {
      "name": "confidence",
      "type": "string",
      "description": "`verified` = read on an official or legal page for the current cycle; `partial` = official but older cycle or incomplete, or a reputable secondary source; `estimate` = derived or calculated, method in `note`. Empty for `not_found` rows.",
      "constraints": {
       "enum": [
        "estimate",
        "partial",
        "verified"
       ]
      }
     },
     {
      "name": "note",
      "type": "string",
      "description": "Caveats in English. \"Updated 2026-10-23:\" marks text added by the second verification pass of 23 October 2026."
     }
    ],
    "primaryKey": [
     "claim"
    ]
   }
  },
  {
   "name": "sources",
   "path": "sources.csv",
   "format": "csv",
   "mediatype": "text/csv",
   "encoding": "utf-8",
   "schema": {
    "fields": [
     {
      "name": "source_id",
      "type": "string",
      "description": "Source id, S001 upwards."
     },
     {
      "name": "url",
      "type": "string",
      "description": "URL as cited in the data (spaces encoded as %20)."
     },
     {
      "name": "title",
      "type": "string",
      "description": "Publisher and host of the page."
     },
     {
      "name": "source_type",
      "type": "string",
      "description": "`official`, `law` or `secondary` (most frequent type of the rows citing it)."
     },
     {
      "name": "accessed_at",
      "type": "string",
      "description": "Latest date a row citing the URL was checked, ISO 8601."
     },
     {
      "name": "used_for",
      "type": "string",
      "description": "File, column and number of rows that cite the URL."
     }
    ],
    "primaryKey": [
     "source_id"
    ]
   }
  }
 ]
}