ENT-00001513 · Language Model

mBART

mBART is a multilingual denoising sequence-to-sequence model associated with Meta AI.

Level IV — ConnectedActiveConnected

Human readable record

Overview

mBART is a documented AI model or assistant-related entity associated with Meta AI. The record focuses on its public identity, release context, capability class, source lineage and relationship to adjacent model or product families.

Timeline

2020mBART public documentation anchor
mBART appears in public documentation or stable reference sources as a multilingual denoising sequence-to-sequence model associated with Meta AI.

Capabilities

Model capabilityBenchmarkable systemPublic technical record

Known limitations

The record describes the public identity and documented role of the entity, not private implementation details.Capabilities depend on version, deployment context, access conditions and the available public documentation.

Technical and registry detail

Technical description

Structured record for mBART. The technical layer identifies entity type, classification, creator or organization, public source anchors, timeline entry, capabilities, limitations, registry status and graph relationships. Source anchor: https://arxiv.org/abs/2001.08210.

Controlled tags

Foundation ModelAI ModelResearch System

Relationship graph

mBART

Created byMeta AI

mBART is associated with Meta AI through its documented source context.

Machine readable layer

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

{
    "@context": "https://schema.org",
    "@type": "Thing",
    "identifier": "ENT-00001513",
    "name": "mBART",
    "alternateName": [],
    "additionalType": "Language Model",
    "description": "mBART is a multilingual denoising sequence-to-sequence model associated with Meta AI.",
    "creator": "Meta AI",
    "url": "entity.php?id=ENT-00001513",
    "sameAs": "https://github.com/facebookresearch/fairseq/tree/main/examples/mbart",
    "lxkeysWorld": {
        "classification": "multilingual denoising sequence-to-sequence model",
        "organization": "Meta AI",
        "originContext": "Public AI and technical record",
        "firstPublicAppearance": "2020",
        "currentStatus": "Active",
        "registryStatus": "Connected",
        "spatiumIndex": {
            "total": 74,
            "documentation": 25,
            "evidence": 13,
            "structure": 25,
            "relationships": 11,
            "level": "Level IV — Connected"
        },
        "lxCalendarium": {
            "start_date_utc": "2023-04-01",
            "created_utc": "2026-06-16T23:59:28+00:00",
            "created_dypclt": "D-0 Y-2 P-3 C-3 L-21 T-3",
            "updated_utc": "2026-06-16T23:59:28+00:00",
            "updated_dypclt": "D-0 Y-2 P-3 C-3 L-21 T-3",
            "reviewed_utc": "2026-06-16T23:59:28+00:00",
            "reviewed_dypclt": "D-0 Y-2 P-3 C-3 L-21 T-3"
        },
        "capabilities": [
            "Model capability",
            "Benchmarkable system",
            "Public technical record"
        ],
        "limitations": [
            "The record describes the public identity and documented role of the entity, not private implementation details.",
            "Capabilities depend on version, deployment context, access conditions and the available public documentation."
        ],
        "tags": [
            "Foundation Model",
            "AI Model",
            "Research System"
        ],
        "timeline": [
            {
                "date": "2020",
                "title": "mBART public documentation anchor",
                "description": "mBART appears in public documentation or stable reference sources as a multilingual denoising sequence-to-sequence model associated with Meta AI."
            }
        ],
        "relationships": [
            {
                "target": "Meta AI",
                "type": "Created by",
                "description": "mBART is associated with Meta AI through its documented source context.",
                "evidence_level": "documentary"
            }
        ],
        "sources": [
            {
                "label": "mBART paper reference",
                "url": "https://arxiv.org/abs/2001.08210",
                "source_type": "Research Paper",
                "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.