{
    "schema": "lxkeys.world.entry@2.2.1",
    "language": "fr",
    "entry": {
        "id": "ENT-00002671",
        "status": "published",
        "name": "AdvBench",
        "aliases": [],
        "entity_type": "Benchmark",
        "classification": "AI Benchmark / Evaluation",
        "creator": "LLM safety research community",
        "organization": "LLM safety research community",
        "origin_context": "AI evaluation",
        "first_public_appearance": "2023",
        "current_status": "Active",
        "official_website": "https://github.com/llm-attacks/llm-attacks",
        "image": "",
        "short_description": "AdvBench is a AI benchmark associated with LLM safety research community, classified in LXKeys.world as AI Benchmark / Evaluation.",
        "public_description": "AdvBench is an AI evaluation entity associated with LLM safety research community. It is documented as adversarial behavior benchmark and helps evaluate model behavior, safety, reasoning, agents, tools, code, reinforcement learning or embodied interaction.",
        "technical_description": "Structured LXKeys.world registry record for AdvBench. Entity type: Benchmark; classification: AI Benchmark / Evaluation; creator/organization context: LLM safety research community. Canonical source anchor: https://github.com/llm-attacks/llm-attacks. 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 protocol documentation",
            "Model comparison support",
            "Task taxonomy mapping",
            "Reproducible benchmark anchoring",
            "Relationship graph compatibility"
        ],
        "limitations": [
            "Benchmark results can become stale as models improve and evaluation protocols evolve.",
            "A benchmark measures a defined task scope rather than complete intelligence."
        ],
        "timeline": [
            {
                "date": "2023",
                "title": "Initial benchmark release",
                "description": "AdvBench entered the documented public record in 2023. This event is retained at the precision supported by the Entry’s reviewed source history.",
                "source_url": "https://github.com/llm-attacks/llm-attacks",
                "verification_status": "source_backed_curated_baseline"
            }
        ],
        "sources": [
            {
                "label": "Official documentation",
                "url": "https://github.com/llm-attacks/llm-attacks",
                "source_type": "Official / Research Source",
                "verification_status": "verified",
                "authority": "TRUSTED_PRIMARY",
                "role": "code_repository",
                "update_enabled": false,
                "authority_basis": "curated-corpus-refresh-2026-09-08"
            }
        ],
        "relationships": [
            {
                "target": "LLM safety research community",
                "type": "Associated organization",
                "description": "LLM safety research community is the organization, project community or institutional context associated with AdvBench.",
                "evidence_level": "documentary"
            },
            {
                "target": "AI evaluation",
                "type": "Domain context",
                "description": "AdvBench belongs to the AI evaluation layer of the intelligent-entity registry.",
                "evidence_level": "documentary"
            }
        ],
        "tags": [
            "Benchmark",
            "Evaluation",
            "AI Safety",
            "Agent Evaluation"
        ],
        "registry_status": "Documented",
        "created_at": "2026-06-17T01:48:33+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": "2026-06-17T01:48:33+00:00",
            "created_dypclt": "D-0 Y-2 P-3 C-3 L-22 T-4",
            "updated_utc": "2026-06-17T01:48:33+00:00",
            "updated_dypclt": "D-0 Y-2 P-3 C-3 L-22 T-4"
        },
        "machine_readable_purpose": "Machine-readable record for AdvBench: classification, source anchor, timeline, limitations, tags and relationship mapping for intelligent-entity discovery.",
        "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": 0,
            "trusted_primary_sources": 1,
            "secondary_sources": 0,
            "date_status": "preserved_from_source_record",
            "image_status": "missing",
            "manual_followup_required": true,
            "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-00002671",
        "kind": "Data and Evaluation",
        "type": "Benchmark",
        "subtype": "",
        "documentation_status": "Documented",
        "facts": [],
        "canonical": [],
        "image_meta": [],
        "source_state": [],
        "i18n": {
            "en": [],
            "fr": []
        }
    },
    "computed": {
        "category": "Data and Evaluation",
        "type": "Benchmark",
        "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-00002671&depth=1"
    }
}