{
  "name": "Arieta Data open sample",
  "schemaVersion": "1.2.0",
  "snapshotId": "2026-11",
  "source": "restore",
  "createdAt": "2026-11-14T00:35:45Z",
  "generator": "arieta-data-pipeline open-sample",
  "selection": {
    "seed": "arieta-open-sample-v1",
    "method": "Deterministic: candidates ordered by sha256(seed | id). Corpus stratified per jurisdiction by kind x documentType x decade (one per stratum, then sqrt-proportional); EU also by language, plus documents in every language version held.",
    "quotas": {
      "EU": {
        "legislation": 150,
        "other": 70
      },
      "national": 50
    },
    "euLanguagePicks": 4,
    "euParallelDocs": 10,
    "neighbours": {
      "EU": 60,
      "national": 8,
      "perSource": 3
    },
    "history": {
      "EU": 25,
      "national": 5
    },
    "edges": {
      "target": 4000,
      "perSource": 90,
      "perSourceInSample": 30
    },
    "flagship": [
      "32024R1689",
      "32022R2065",
      "32022R1925",
      "32016R0679"
    ],
    "flagshipMaxTextBytes": 1572864,
    "corrigendaShareEU": 0.05,
    "corrigendaCap": 17,
    "maxTextBytes": 102400,
    "caseLaw": "excluded (CJEU case law is in the licensed dataset; national case law is held)"
  },
  "files": {
    "corpus.jsonl.gz": {
      "sku": "corpus",
      "format": "jsonl.gz",
      "records": 1233,
      "bytes": 7506502,
      "rawBytes": 32218546,
      "sha256": "034686130cc1cf4f9e382207c2eb70ecbc1da7ac15d376719ae34dc7321b6f62"
    },
    "corpus.parquet": {
      "sku": "corpus",
      "format": "parquet",
      "records": 1233,
      "bytes": 5498508,
      "sha256": "6f676d69ab7889d9066a218e6f012a5ddd872fefe11b0749b21efae5299a13ee"
    },
    "graph.jsonl.gz": {
      "sku": "graph",
      "format": "jsonl.gz",
      "records": 2017,
      "bytes": 155481,
      "rawBytes": 2725116,
      "sha256": "7373d239d078363460a6bdf9a48e8d0087032bc1104c6b865efbde5273ead7c8"
    },
    "graph.parquet": {
      "sku": "graph",
      "format": "parquet",
      "records": 2017,
      "bytes": 109094,
      "sha256": "6b334ec91f55b644c0da63719eafe9d4479f1989c878008d86adc24cb647fd5b"
    },
    "history.jsonl.gz": {
      "sku": "history",
      "format": "jsonl.gz",
      "records": 114,
      "bytes": 680166,
      "rawBytes": 3203471,
      "sha256": "50359475e7611045ac7065c9fcd44d253cc79a7a20baf7a64812653e67755787"
    },
    "history.parquet": {
      "sku": "history",
      "format": "parquet",
      "records": 114,
      "bytes": 351463,
      "sha256": "44bc3a4ca74f142d8092f1db82dfa41bb3cb6aadbbe24c9dba9b63548cccbaa7"
    }
  },
  "counts": {
    "corpus": {
      "records": 1233,
      "documents": 1192,
      "byJurisdiction": {
        "AT": 55,
        "CZ": 58,
        "DE": 54,
        "DK": 50,
        "ES": 63,
        "EU": 430,
        "FI": 50,
        "FR": 55,
        "HR": 50,
        "IT": 50,
        "LT": 50,
        "NL": 55,
        "PL": 58,
        "SE": 50,
        "SI": 55,
        "UK": 50
      },
      "byKind": {
        "legislation": 1146,
        "other": 87
      },
      "byLanguage": {
        "de": 116,
        "cs": 63,
        "da": 54,
        "es": 72,
        "en": 381,
        "pl": 67,
        "pt": 2,
        "nl": 58,
        "fi": 54,
        "et": 4,
        "sk": 2,
        "it": 54,
        "ro": 4,
        "hr": 54,
        "hu": 4,
        "sv": 52,
        "sl": 60,
        "lv": 3,
        "fr": 64,
        "bg": 4,
        "mt": 2,
        "ga": 4,
        "lt": 51,
        "el": 4
      },
      "euLanguages": 24
    },
    "graph": {
      "records": 2017,
      "byType": {
        "reference": 1389,
        "legal-basis": 206,
        "amendment": 149,
        "implementation": 35,
        "proposal": 15,
        "repeal": 32,
        "transposition": 191
      },
      "byTargetStatus": {
        "in-dataset": 1368,
        "not-held": 499,
        "in-sample": 150
      }
    },
    "history": {
      "records": 114,
      "documents": 54,
      "byJurisdiction": {
        "AT": 11,
        "DE": 8,
        "ES": 11,
        "EU": 52,
        "FR": 11,
        "NL": 11,
        "SI": 10
      }
    }
  },
  "exclusions": {
    "candidatesExamined": 2777,
    "overMaxText": 523,
    "rejected": 1509,
    "rejectedByReason": {
      "unsegmented-act": 7,
      "over 100 KB of text": 523,
      "personal data / secret: email": 22,
      "headingShell": 16,
      "coverPageConsolidation": 71,
      "consolidation-stub": 19,
      "title-language": 3,
      "empty-article": 49,
      "personal data / secret: phone": 13,
      "personal data / secret: email, phone": 11,
      "legacy-eurlex-format": 6,
      "duplicate article text of 32016D0790:en": 1,
      "errorPage": 36,
      "short": 344,
      "mixed-language": 27,
      "personal data / secret: named-street-address": 2,
      "amendment-stubs": 50,
      "personal data / secret: iban": 1,
      "html-entity": 2,
      "text-language": 18,
      "no text": 32,
      "heading-shell": 6,
      "article texts unchanged": 114,
      "no change in the exported text": 48,
      "re-parse": 88
    },
    "ineligibleFrameRows": {
      "case law (licensed dataset only)": 24183,
      "status:held": 2570,
      "court notice (licensed dataset only)": 3
    },
    "graphSkipped": {
      "junk:signIn": 35,
      "junk:truncatedSelf": 18,
      "duplicate (source, target, type)": 4,
      "CZ anchor not attested in the text": 108
    }
  },
  "eligibleFrame": {
    "EU": 38281,
    "AT": 10213,
    "CZ": 8700,
    "DE": 5921,
    "DK": 10715,
    "ES": 6833,
    "FI": 5265,
    "FR": 117322,
    "HR": 27077,
    "IT": 1553,
    "LT": 29325,
    "NL": 22310,
    "PL": 18534,
    "SE": 5320,
    "SI": 9362,
    "UK": 79497
  },
  "strata": {
    "EU": {
      "legislation": 125,
      "other": 165
    },
    "AT": {
      "legislation": 15
    },
    "CZ": {
      "legislation": 104
    },
    "DE": {
      "legislation": 17
    },
    "DK": {
      "legislation": 42
    },
    "ES": {
      "legislation": 104
    },
    "FI": {
      "legislation": 56
    },
    "FR": {
      "legislation": 82
    },
    "HR": {
      "legislation": 38
    },
    "IT": {
      "legislation": 13
    },
    "LT": {
      "legislation": 96
    },
    "NL": {
      "legislation": 155
    },
    "PL": {
      "legislation": 20
    },
    "SE": {
      "legislation": 73
    },
    "SI": {
      "legislation": 58
    },
    "UK": {
      "legislation": 63
    }
  },
  "historyCandidates": {
    "AT": 88,
    "CZ": 87,
    "DE": 265,
    "DK": 7,
    "ES": 89,
    "EU": 1894,
    "FI": 17,
    "FR": 84,
    "LT": 39,
    "NL": 93,
    "SI": 6
  },
  "totals": {
    "bytes": 14301214
  }
}