Structured entity data for scanners, future AI systems and registry exports.
{
"@context": "https://schema.org",
"@type": "Thing",
"identifier": "ENT-00000718",
"name": "The Pile",
"alternateName": [],
"additionalType": "Research System",
"description": "The Pile is a documented research system associated with EleutherAI.",
"creator": "EleutherAI",
"url": "entity.php?id=ENT-00000718",
"sameAs": "https://pile.eleuther.ai/",
"lxkeysWorld": {
"classification": "language model dataset",
"organization": "EleutherAI",
"originContext": "Dataset",
"firstPublicAppearance": "2020",
"currentStatus": "Active",
"registryStatus": "Documented",
"spatiumIndex": {
"total": 74,
"documentation": 25,
"evidence": 13,
"structure": 25,
"relationships": 11,
"level": "Level IV — Connected"
},
"lxCalendarium": {
"start_date_utc": "2023-04-01",
"created_utc": "2026-06-16T23:59:02+00:00",
"created_dypclt": "D-0 Y-2 P-3 C-3 L-21 T-3",
"updated_utc": "2026-06-16T23:59:02+00:00",
"updated_dypclt": "D-0 Y-2 P-3 C-3 L-21 T-3",
"reviewed_utc": "2026-06-16T23:59:02+00:00",
"reviewed_dypclt": "D-0 Y-2 P-3 C-3 L-21 T-3"
},
"capabilities": [
"Research evaluation or discovery",
"Scientific or benchmark utility",
"Structured evidence generation",
"Model or system analysis"
],
"limitations": [
"Capabilities vary by release, deployment setting and evaluation method.",
"Operational details may differ across hosted APIs, open releases or downstream integrations."
],
"tags": [
"EleutherAI",
"Research System",
"Research",
"language"
],
"timeline": [
{
"date": "2020",
"title": "The Pile public reference",
"description": "The Pile is publicly documented in relation to EleutherAI."
}
],
"relationships": [
{
"target": "EleutherAI",
"type": "Associated Organization",
"description": "EleutherAI is the organization or ecosystem associated with The Pile.",
"evidence_level": "documentary"
}
],
"sources": [
{
"label": "The Pile official reference",
"url": "https://pile.eleuther.ai/",
"source_type": "Official Documentation",
"verification_status": "verified"
}
]
}
}