Semantic Scholar Open Research Corpus

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

{
    "@context": "https://schema.org",
    "@type": "Thing",
    "identifier": "ENT-00002055",
    "name": "Semantic Scholar Open Research Corpus",
    "alternateName": [],
    "additionalType": "Dataset / Benchmark",
    "description": "Semantic Scholar Open Research Corpus is a evaluation / data resource associated with AI2.",
    "creator": "Allen Institute for AI",
    "url": "entity.php?id=ENT-00002055",
    "sameAs": "https://allenai.org/data/s2orc",
    "lxkeysWorld": {
        "classification": "Evaluation / Data Resource",
        "organization": "AI2",
        "originContext": "AI evaluation and data infrastructure",
        "firstPublicAppearance": "2015",
        "currentStatus": "Active",
        "registryStatus": "Documented",
        "spatiumIndex": {
            "total": 88,
            "documentation": 25,
            "evidence": 13,
            "structure": 25,
            "relationships": 25,
            "level": "Level V — Persistent"
        },
        "lxCalendarium": {
            "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",
            "reviewed_utc": "2026-06-17T01:33:48+00:00",
            "reviewed_dypclt": "D-0 Y-2 P-3 C-3 L-22 T-4"
        },
        "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."
        ],
        "tags": [
            "Dataset",
            "Benchmark",
            "Evaluation",
            "Data Resource"
        ],
        "timeline": [
            {
                "date": "2015",
                "title": "Public release or publication",
                "description": "Semantic Scholar Open Research Corpus appears in public documentation or research records associated with AI2."
            }
        ],
        "relationships": [
            {
                "target": "Allen Institute for AI",
                "type": "Creator",
                "description": "Allen Institute for AI is documented as creator, contributor or originating team for Semantic Scholar Open Research Corpus.",
                "evidence_level": "documentary"
            },
            {
                "target": "AI2",
                "type": "Associated organization",
                "description": "AI2 is the organization or institutional context associated with Semantic Scholar Open Research Corpus.",
                "evidence_level": "documentary"
            },
            {
                "target": "Evaluation / Data Resource",
                "type": "Classification",
                "description": "Semantic Scholar Open Research Corpus is classified as Evaluation / Data Resource.",
                "evidence_level": "documentary"
            }
        ],
        "sources": [
            {
                "label": "Official documentation",
                "url": "https://allenai.org/data/s2orc",
                "source_type": "Reference Source",
                "verification_status": "verified"
            }
        ]
    }
}