{
    "schema": "lxkeys.world.entry@2.2.1",
    "language": "fr",
    "entry": {
        "id": "ENT-00000719",
        "status": "published",
        "name": "C4 Dataset",
        "aliases": [],
        "entity_type": "Research System",
        "classification": "AI Research / Specialized System",
        "creator": "Google Research",
        "organization": "Google",
        "origin_context": "Dataset",
        "first_public_appearance": "2020",
        "current_status": "Active",
        "official_website": "https://www.tensorflow.org/datasets/catalog/c4",
        "image": "uploads/entity-images/ENT-00000719.png",
        "short_description": "C4 Dataset is a research system associated with Google, classified in LXKeys.world as AI Research / Specialized System.",
        "public_description": "C4 Dataset is documented as a research system, benchmark, dataset or scientific AI record associated with Google. It is relevant for cleaned Common Crawl corpus used in text-to-text model training. The record helps situate evaluation, discovery, training evidence or scientific capability in the registry graph.",
        "technical_description": "Structured LXKeys.world registry record for C4 Dataset. Entity type: Research System; classification: AI Research / Specialized System; creator/organization context: Google Research. Canonical source anchor: https://www.tensorflow.org/datasets/catalog/c4. The record tracks source authority, first public appearance, timeline, capabilities, limitations, registry status and graph relationships. Automatic refresh is limited to sources explicitly classified as OFFICIAL and enabled for updates; documentary and research references remain non-authoritative unless reviewed.",
        "capabilities": [
            "Research evaluation or discovery",
            "Scientific or benchmark utility",
            "Structured evidence generation",
            "Model or system analysis"
        ],
        "limitations": [
            "Capabilities vary by release, deployment setting and evaluation method.",
            "Operational details may differ across hosted APIs, open releases or downstream integrations."
        ],
        "timeline": [
            {
                "date": "2020",
                "title": "Initial research publication or demonstration",
                "description": "C4 Dataset entered the documented public record in 2020. This event is retained at the precision supported by the Entry’s reviewed source history.",
                "source_url": "https://www.tensorflow.org/datasets/catalog/c4",
                "verification_status": "source_backed_official"
            }
        ],
        "sources": [
            {
                "label": "C4 Dataset official reference",
                "url": "https://www.tensorflow.org/datasets/catalog/c4",
                "source_type": "Official Documentation",
                "verification_status": "verified",
                "authority": "OFFICIAL",
                "role": "primary",
                "update_enabled": true,
                "authority_basis": "curated-corpus-refresh-2026-09-08"
            }
        ],
        "relationships": [
            {
                "target": "Google",
                "type": "Associated Organization",
                "description": "Google is the organization or ecosystem associated with C4 Dataset.",
                "evidence_level": "documentary"
            },
            {
                "target": "Google Research",
                "type": "Creator or Developer",
                "description": "Google Research is identified as a creator, developer or originating actor for C4 Dataset.",
                "evidence_level": "documentary"
            }
        ],
        "tags": [
            "Google",
            "Research System",
            "Research",
            "language"
        ],
        "registry_status": "Documented",
        "created_at": "2026-06-16T23:59:02+00:00",
        "updated_at": "2026-09-08T04:55:00+00:00",
        "dypclt_created": "D-0 Y-2 P-3 C-3 L-21 T-3",
        "dypclt_updated": "D-0 Y-2 P-3 C-3 L-21 T-3",
        "temporal_index": {
            "start_date_utc": "2023-04-01",
            "created_utc": "2026-06-16T23:59:02+00:00",
            "created_dypclt": "D-0 Y-2 P-3 C-3 L-21 T-3",
            "updated_utc": "2026-06-16T23:59:02+00:00",
            "updated_dypclt": "D-0 Y-2 P-3 C-3 L-21 T-3"
        },
        "machine_readable_purpose": "Machine-readable registry record for C4 Dataset: entity type, classification, sources, timeline, capabilities, limitations and graph relationships.",
        "schema_ready": true,
        "first_public_appearance_precision": "year",
        "first_public_appearance_verification": "preserved_from_source_record",
        "image_meta": {
            "path": "uploads/entity-images/ENT-00000719.png",
            "sha256": "106b8ebbcf0de0074f212da5a1a397a2d18427c854b5d543acc94e5f534da264",
            "width": 512,
            "height": 512,
            "mime": "image/png",
            "provenance_status": "PROVENANCE_UNCONFIRMED",
            "review_status": "preserved_pending_official_verification",
            "legacy_provenance_status": "legacy_unverified",
            "source_type": "historical",
            "source_label": "LXKeys.world historical media corpus",
            "metadata_namespace": "urn:lxkeys:xmp:1.0",
            "metadata_embedded": true,
            "metadata_verified": true,
            "asset_id": "LXW-IMG-ENT-00000719-106B8EBBCF0D",
            "processing_id": "LXP-20260908-00AB56EADF65",
            "processed_at_utc": "2026-09-08T18:00:00Z",
            "dypclt": "D-0 Y-2 P-4 C-4 L-33 T-6",
            "rights_holder": "",
            "rights_policy": "PROVENANCE_REVIEW_REQUIRED",
            "original_sha256": "106b8ebbcf0de0074f212da5a1a397a2d18427c854b5d543acc94e5f534da264",
            "processed_sha256": "658d258789d5110fef5137085c85612dc8e46c11400fccd055ec7458ce759531"
        },
        "reviewed_at": "2026-09-08T04:55:00+00:00",
        "quality_status": "curated_official_first_baseline",
        "source_policy": "official_first_secondary_context_only",
        "quality_review": {
            "reviewed_at": "2026-09-08T04:55:00+00:00",
            "official_sources": 1,
            "trusted_primary_sources": 0,
            "secondary_sources": 0,
            "date_status": "preserved_from_source_record",
            "image_status": "legacy_unverified",
            "manual_followup_required": false,
            "review_scope": "official-first structural curation; records flagged for follow-up are not claimed as individually exhaustive fact-checks"
        },
        "dypclt_reviewed": "D-0 Y-2 P-4 C-4 L-33 T-6",
        "world_id": "ENT-00000719",
        "kind": "Methods and Research",
        "type": "Research System",
        "subtype": "",
        "documentation_status": "Documented",
        "facts": [],
        "canonical": [],
        "source_state": [],
        "i18n": {
            "en": [],
            "fr": []
        }
    },
    "computed": {
        "category": "Methods and Research",
        "type": "Research System",
        "subtype": "",
        "documentation_index": {
            "total": 82,
            "documentation": 25,
            "evidence": 13,
            "structure": 25,
            "relationships": 19,
            "level": "Level V Persistent"
        },
        "is_lxkeys_entity": false,
        "graph_endpoint": "graph.php?center=ENT-00000719&depth=1"
    }
}