ENT-00002666 · Benchmark

Safety Gymnasium

Safety Gymnasium is a evaluation framework / benchmark associated with PKU Alignment.

Level V — PersistentActiveDocumented

Human readable record

Overview

Safety Gymnasium is an AI evaluation entity associated with PKU Alignment. It is documented as safe reinforcement learning benchmark suite and helps evaluate model behavior, safety, reasoning, agents, tools, code, reinforcement learning or embodied interaction.

Timeline

2023Public release or documentation
Safety Gymnasium appears in public documentation, project records, benchmark descriptions or research references associated with PKU Alignment.

Capabilities

Evaluation protocol documentationModel comparison supportTask taxonomy mappingReproducible benchmark anchoringRelationship graph compatibility

Known limitations

Benchmark results can become stale as models improve and evaluation protocols evolve.A benchmark measures a defined task scope rather than complete intelligence.

Technical and registry detail

Technical description

Structured record for Safety Gymnasium. The technical layer identifies the entity type, classification, creator or organization, official source anchor, capabilities, limitations, timeline entries and graph relationships without adding internal import events to the public history.

Controlled tags

BenchmarkEvaluationAI SafetyAgent Evaluation

Relationship graph

Safety Gymnasium

Associated organizationPKU Alignment

PKU Alignment is the organization, project community or institutional context associated with Safety Gymnasium.

Domain contextAI evaluation

Safety Gymnasium belongs to the AI evaluation layer of the intelligent-entity registry.

Machine readable layer

Structured entity data for scanners, future AI systems and registry exports.

{
    "@context": "https://schema.org",
    "@type": "Thing",
    "identifier": "ENT-00002666",
    "name": "Safety Gymnasium",
    "alternateName": [],
    "additionalType": "Benchmark",
    "description": "Safety Gymnasium is a evaluation framework / benchmark associated with PKU Alignment.",
    "creator": "PKU Alignment",
    "url": "entity.php?id=ENT-00002666",
    "sameAs": "https://github.com/PKU-Alignment/safety-gymnasium",
    "lxkeysWorld": {
        "classification": "Evaluation Framework / Benchmark",
        "organization": "PKU Alignment",
        "originContext": "AI evaluation",
        "firstPublicAppearance": "2023",
        "currentStatus": "Active",
        "registryStatus": "Documented",
        "spatiumIndex": {
            "total": 82,
            "documentation": 25,
            "evidence": 13,
            "structure": 25,
            "relationships": 19,
            "level": "Level V — Persistent"
        },
        "lxCalendarium": {
            "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",
            "reviewed_utc": "2026-06-17T01:48:33+00:00",
            "reviewed_dypclt": "D-0 Y-2 P-3 C-3 L-22 T-4"
        },
        "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."
        ],
        "tags": [
            "Benchmark",
            "Evaluation",
            "AI Safety",
            "Agent Evaluation"
        ],
        "timeline": [
            {
                "date": "2023",
                "title": "Public release or documentation",
                "description": "Safety Gymnasium appears in public documentation, project records, benchmark descriptions or research references associated with PKU Alignment."
            }
        ],
        "relationships": [
            {
                "target": "PKU Alignment",
                "type": "Associated organization",
                "description": "PKU Alignment is the organization, project community or institutional context associated with Safety Gymnasium.",
                "evidence_level": "documentary"
            },
            {
                "target": "AI evaluation",
                "type": "Domain context",
                "description": "Safety Gymnasium belongs to the AI evaluation layer of the intelligent-entity registry.",
                "evidence_level": "documentary"
            }
        ],
        "sources": [
            {
                "label": "Official documentation",
                "url": "https://github.com/PKU-Alignment/safety-gymnasium",
                "source_type": "Official / Research Source",
                "verification_status": "verified"
            }
        ]
    }
}

Proof and discussion layer

Contribute to this record

Submit a proof, correction or comment. Public display is moderated. Every submission remains preserved in the export archive.

Submit proof or comment

Approved comments

No approved public comment yet.