{
    "schema": "lxkeys.world.entry@2.2.1",
    "language": "fr",
    "entry": {
        "id": "ENT-00002047",
        "status": "published",
        "name": "Penn Treebank",
        "aliases": [],
        "entity_type": "Dataset",
        "classification": "AI Dataset",
        "creator": "Linguistic Data Consortium",
        "organization": "LDC",
        "origin_context": "AI evaluation and data infrastructure",
        "first_public_appearance": "1993",
        "current_status": "Active",
        "official_website": "https://catalog.ldc.upenn.edu/LDC99T42",
        "image": "",
        "short_description": "Penn Treebank is a dataset associated with LDC, classified in LXKeys.world as AI Dataset.",
        "public_description": "Penn Treebank is a data or evaluation resource used in artificial intelligence research. It is associated with LDC and is documented as syntactically annotated corpus.",
        "technical_description": "Structured LXKeys.world registry record for Penn Treebank. Entity type: Dataset; classification: AI Dataset; creator/organization context: Linguistic Data Consortium. Canonical source anchor: https://catalog.ldc.upenn.edu/LDC99T42. 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": [
            "Evaluation resource for AI systems",
            "Dataset or benchmark documentation",
            "Machine-learning task reference",
            "Source-linked registry metadata",
            "Relationship graph compatibility"
        ],
        "limitations": [
            "Coverage and licensing should be interpreted through the linked source record.",
            "Benchmark scores or dataset contents can evolve over time through external updates."
        ],
        "timeline": [
            {
                "date": "1993",
                "title": "Initial dataset release",
                "description": "Penn Treebank entered the documented public record in 1993. This event is retained at the precision supported by the Entry’s reviewed source history.",
                "source_url": "https://catalog.ldc.upenn.edu/LDC99T42",
                "verification_status": "source_backed_official"
            }
        ],
        "sources": [
            {
                "label": "Official documentation",
                "url": "https://catalog.ldc.upenn.edu/LDC99T42",
                "source_type": "Reference Source",
                "verification_status": "verified",
                "authority": "OFFICIAL",
                "role": "primary",
                "update_enabled": true,
                "authority_basis": "curated-corpus-refresh-2026-09-08"
            }
        ],
        "relationships": [
            {
                "target": "Linguistic Data Consortium",
                "type": "Creator",
                "description": "Linguistic Data Consortium is documented as creator, contributor or originating team for Penn Treebank.",
                "evidence_level": "documentary"
            },
            {
                "target": "LDC",
                "type": "Associated organization",
                "description": "LDC is the organization or institutional context associated with Penn Treebank.",
                "evidence_level": "documentary"
            },
            {
                "target": "Evaluation / Data Resource",
                "type": "Classification",
                "description": "Penn Treebank is classified as Evaluation / Data Resource.",
                "evidence_level": "documentary"
            }
        ],
        "tags": [
            "Dataset",
            "Benchmark",
            "Evaluation",
            "Data Resource"
        ],
        "registry_status": "Documented",
        "created_at": "2026-06-17T01:33:48+00:00",
        "updated_at": "2026-09-08T04:55:00+00:00",
        "dypclt_created": "D-0 Y-2 P-3 C-3 L-22 T-4",
        "dypclt_updated": "D-0 Y-2 P-3 C-3 L-22 T-4",
        "temporal_index": {
            "start_date_utc": "2023-04-01",
            "created_utc": "2026-06-17T01:33:48+00:00",
            "created_dypclt": "D-0 Y-2 P-3 C-3 L-22 T-4",
            "updated_utc": "2026-06-17T01:33:48+00:00",
            "updated_dypclt": "D-0 Y-2 P-3 C-3 L-22 T-4"
        },
        "machine_readable_purpose": "Machine-readable registry record for Penn Treebank: entity type, classification, source, timeline, capabilities, limitations and graph relationships.",
        "schema_ready": true,
        "first_public_appearance_precision": "year",
        "first_public_appearance_verification": "preserved_from_source_record",
        "image_status": "missing_official_image_candidate",
        "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": "missing",
            "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-00002047",
        "kind": "Data and Evaluation",
        "type": "Dataset",
        "subtype": "",
        "documentation_status": "Documented",
        "facts": [],
        "canonical": [],
        "image_meta": [],
        "source_state": [],
        "i18n": {
            "en": [],
            "fr": []
        }
    },
    "computed": {
        "category": "Data and Evaluation",
        "type": "Dataset",
        "subtype": "",
        "documentation_index": {
            "total": 88,
            "documentation": 25,
            "evidence": 13,
            "structure": 25,
            "relationships": 25,
            "level": "Level V Persistent"
        },
        "is_lxkeys_entity": false,
        "graph_endpoint": "graph.php?center=ENT-00002047&depth=1"
    }
}