Properties
| Name | Type | Description |
|---|---|---|
| schemaVersion | object | |
| artifactId | string | |
| state | object | |
| source | object | |
| license | object | |
| structure | object | |
| files | array | |
| claims | object | |
| hosting | object | |
| evidence | object | |
| crossSourceEquality | object | |
| blockers | array | |
| uncertainties | array | |
| inspectionCommand | object | |
| action | object | |
| safety | object | |
| note | object | |
| noteMessage | string | Original route note, when a public qualification occupies note. |
JSON Schema
{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"$id": "https://artifacts.apis.io/huggingbay-xyz/json-schema/huggingbay-xyz-public-dataset-inspection-schema.json",
"title": "PublicDatasetInspection",
"x-generated": "2026-10-30",
"x-method": "derived",
"x-generator": "derive-json-schema.py",
"x-source": "openapi/huggingbay-xyz-openapi.json#/components/schemas/PublicDatasetInspection",
"type": "object",
"required": [
"schemaVersion",
"artifactId",
"state",
"source",
"license",
"structure",
"files",
"claims",
"hosting",
"evidence",
"crossSourceEquality",
"blockers",
"uncertainties",
"inspectionCommand",
"action",
"safety"
],
"properties": {
"schemaVersion": {
"const": "hugging-bay.public-dataset-inspection.v1"
},
"artifactId": {
"type": "string",
"minLength": 1,
"maxLength": 300,
"pattern": "^[^/\\\\\\u0000-\\u001f\\u007f]+$"
},
"state": {
"enum": [
"ready",
"degraded",
"blocked"
]
},
"source": {
"anyOf": [
{
"type": "null"
},
{
"type": "object",
"required": [
"provider",
"identity",
"revision",
"immutable",
"treeDigest",
"url"
],
"properties": {
"provider": {
"const": "huggingface"
},
"identity": {
"type": "string",
"pattern": "^[A-Za-z0-9][A-Za-z0-9._-]{0,99}/[A-Za-z0-9][A-Za-z0-9._-]{0,199}$"
},
"revision": {
"type": "string",
"pattern": "^[a-f0-9]{40}(?:[a-f0-9]{24})?$"
},
"immutable": {
"const": true
},
"treeDigest": {
"type": "string",
"pattern": "^sha256:[a-f0-9]{64}$"
},
"url": {
"type": "string",
"maxLength": 1024,
"pattern": "^https://huggingface\\.co/datasets/[A-Za-z0-9._%~-]+/[A-Za-z0-9._%~-]+/tree/[a-f0-9]{40}(?:[a-f0-9]{24})?$"
},
"note": {
"anyOf": [
{
"type": "string"
},
{
"type": "object",
"required": [
"summary"
],
"properties": {
"summary": {
"type": "string"
},
"downloadable": {
"type": "boolean"
}
},
"additionalProperties": false
}
]
},
"noteMessage": {
"type": "string",
"description": "Original route note, when a public qualification occupies note."
}
},
"additionalProperties": false
}
]
},
"license": {
"type": "object",
"required": [
"expression",
"gating",
"redistribution"
],
"properties": {
"expression": {
"anyOf": [
{
"type": "string",
"minLength": 1,
"maxLength": 240
},
{
"type": "null"
}
]
},
"gating": {
"enum": [
"public-ungated",
"gated",
"unknown"
]
},
"redistribution": {
"enum": [
"approved",
"unknown"
]
},
"policy": {
"const": "mirror"
},
"evidenceDigest": {
"type": "string",
"pattern": "^sha256:[a-f0-9]{64}$"
},
"reviewedAt": {
"type": "string",
"pattern": "^\\d{4}-\\d{2}-\\d{2}T\\d{2}:\\d{2}:\\d{2}(?:\\.\\d{1,3})?Z$"
},
"note": {
"anyOf": [
{
"type": "string"
},
{
"type": "object",
"required": [
"summary"
],
"properties": {
"summary": {
"type": "string"
},
"downloadable": {
"type": "boolean"
}
},
"additionalProperties": false
}
]
},
"noteMessage": {
"type": "string",
"description": "Original route note, when a public qualification occupies note."
}
},
"additionalProperties": false
},
"structure": {
"type": "object",
"required": [
"configs",
"selectedCoverage"
],
"properties": {
"selectedCoverage": {
"enum": [
"complete-selected-subset",
"unknown"
]
},
"configs": {
"type": "array",
"maxItems": 1,
"items": {
"type": "object",
"required": [
"name",
"splits"
],
"properties": {
"name": {
"type": "string",
"minLength": 1,
"maxLength": 1024
},
"splits": {
"type": "array",
"minItems": 1,
"maxItems": 1,
"items": {
"type": "object",
"required": [
"name",
"subsets"
],
"properties": {
"name": {
"type": "string",
"minLength": 1,
"maxLength": 1024
},
"subsets": {
"type": "array",
"minItems": 1,
"maxItems": 1,
"items": {
"type": "object",
"required": [
"name",
"partitions"
],
"properties": {
"name": {
"type": "string",
"minLength": 1,
"maxLength": 1024
},
"partitions": {
"type": "array",
"minItems": 1,
"maxItems": 256,
"items": {
"type": "object",
"required": [
"key",
"files",
"rowCount"
],
"properties": {
"key": {
"type": "string",
"minLength": 1,
"maxLength": 1024
},
"files": {
"type": "array",
"minItems": 1,
"maxItems": 256,
"uniqueItems": true,
"items": {
"type": "string",
"minLength": 1,
"maxLength": 1024,
"pattern": "^(?!/)(?!.*(?:^|/)\\.{1,2}(?:/|$))(?!.*\\\\)[^\\u0000-\\u001f\\u007f]+$"
}
},
"rowCount": {
"type": "object",
"required": [
"value",
"attestation",
"evidenceDigest"
],
"properties": {
"value": {
"type": "integer",
"minimum": 0,
"maximum": 9007199254740991
},
"attestation": {
"const": "authoritative"
},
"evidenceDigest": {
"type": "string",
"pattern": "^sha256:[a-f0-9]{64}$"
},
"note": {
"anyOf": [
{
"type": "string"
},
{
"type": "object",
"required": [
"summary"
],
"properties": {
"summary": {
"type": "string"
},
"downloadable": {
"type": "boolean"
}
},
"additionalProperties": false
}
]
},
"noteMessage": {
"type": "string",
"description": "Original route note, when a public qualification occupies note."
}
},
"additionalProperties": false
},
"note": {
"anyOf": [
{
"type": "string"
},
{
"type": "object",
"required": [
"summary"
],
"properties": {
"summary": {
"type": "string"
},
"downloadable": {
"type": "boolean"
}
},
"additionalProperties": false
}
]
},
"noteMessage": {
"type": "string",
"description": "Original route note, when a public qualification occupies note."
}
},
"additionalProperties": false
}
},
"note": {
"anyOf": [
{
"type": "string"
},
{
"type": "object",
"required": [
"summary"
],
"properties": {
"summary": {
"type": "string"
},
"downloadable": {
"type": "boolean"
}
},
"additionalProperties": false
}
]
},
"noteMessage": {
"type": "string",
"description": "Original route note, when a public qualification occupies note."
}
},
"additionalProperties": false
}
},
"note": {
"anyOf": [
{
"type": "string"
},
{
"type": "object",
"required": [
"summary"
],
"properties": {
"summary": {
"type": "string"
},
"downloadable": {
"type": "boolean"
}
},
"additionalProperties": false
}
]
},
"noteMessage": {
"type": "string",
"description": "Original route note, when a public qualification occupies note."
}
},
"additionalProperties": false
}
},
"note": {
"anyOf": [
{
"type": "string"
},
{
"type": "object",
"required": [
"summary"
],
"properties": {
"summary": {
"type": "string"
},
"downloadable": {
"type": "boolean"
}
},
"additionalProperties": false
}
]
},
"noteMessage": {
"type": "string",
"description": "Original route note, when a public qualification occupies note."
}
},
"additionalProperties": false
}
},
"note": {
"anyOf": [
{
"type": "string"
},
{
"type": "object",
"required": [
"summary"
],
"properties": {
"summary": {
"type": "string"
},
"downloadable": {
"type": "boolean"
}
},
"additionalProperties": false
}
]
},
"noteMessage": {
"type": "string",
"description": "Original route note, when a public qualification occupies note."
}
},
"additionalProperties": false
},
"files": {
"type": "array",
"maxItems": 256,
"items": {
"type": "object",
"required": [
"path",
"partition",
"format",
"sizeBytes",
"sha256",
"hosted"
],
"properties": {
"path": {
"type": "string",
"minLength": 1,
"maxLength": 1024,
"pattern": "^(?!/)(?!.*(?:^|/)\\.{1,2}(?:/|$))(?!.*\\\\)[^\\u0000-\\u001f\\u007f]+$"
},
"partition": {
"type": "string",
"minLength": 1,
"maxLength": 1024
},
"format": {
"const": "parquet"
},
"sizeBytes": {
"type": "integer",
"minimum": 0,
"maximum": 9007199254740991
},
"sha256": {
"type": "string",
"pattern": "^sha256:[a-f0-9]{64}$"
},
"hosted": {
"type": "boolean"
},
"note": {
"anyOf": [
{
"type": "string"
},
{
"type": "object",
"required": [
"summary"
],
"properties": {
"summary": {
"type": "string"
},
"downloadable": {
"type": "boolean"
}
},
"additionalProperties": false
}
]
},
"noteMessage": {
"type": "string",
"description": "Original route note, when a public qualification occupies note."
}
},
"additionalProperties": false
}
},
"claims": {
"type": "object",
"required": [
"rows",
"schema",
"rawRowsIncluded"
],
"properties": {
"rows": {
"anyOf": [
{
"type": "null"
},
{
"type": "object",
"required": [
"value",
"scope",
"attestation",
"method",
"observedAt",
"evidenceDigest"
],
"properties": {
"value": {
"type": "integer",
"minimum": 0,
"maximum": 9007199254740991
},
"scope": {
"const": "complete-selected-subset"
},
"attestation": {
"const": "authoritative"
},
"method": {
"type": "string",
"minLength": 1,
"maxLength": 120
},
"observedAt": {
"type": "string",
"pattern": "^\\d{4}-\\d{2}-\\d{2}T\\d{2}:\\d{2}:\\d{2}(?:\\.\\d{1,3})?Z$"
},
"evidenceDigest": {
"type": "string",
"pattern": "^sha256:[a-f0-9]{64}$"
},
"note": {
"anyOf": [
{
"type": "string"
},
{
"type": "object",
"required": [
"summary"
],
"properties": {
"summary": {
"type": "string"
},
"downloadable": {
"type": "boolean"
}
},
"additionalProperties": false
}
]
},
"noteMessage": {
"type": "string",
"description": "Original route note, when a public qualification occupies note."
}
},
"additionalProperties": false
}
]
},
"schema": {
"anyOf": [
{
"type": "null"
},
{
"type": "object",
"required": [
"format",
"fingerprint",
"physicalLeafColumnCount",
"fieldNamesIncluded",
"rowValuesIncluded",
"attestation",
"evidenceDigest"
],
"properties": {
"format": {
"const": "parquet"
},
"fingerprint": {
"type": "string",
"pattern": "^sha256:[a-f0-9]{64}$"
},
"physicalLeafColumnCount": {
"anyOf": [
{
"type": "integer",
"minimum": 1,
"maximum": 256
},
{
"type": "null"
}
]
},
"fieldNamesIncluded": {
"const": false
},
"rowValuesIncluded": {
"const": false
},
"attestation": {
"const": "authoritative"
},
"evidenceDigest": {
"type": "string",
"pattern": "^sha256:[a-f0-9]{64}$"
},
"note": {
"anyOf": [
{
"type": "string"
},
{
"type": "object",
"required": [
"summary"
],
"properties": {
"summary": {
"type": "string"
},
"downloadable": {
"type": "boolean"
}
},
"additionalProperties": false
}
]
},
"noteMessage": {
"type": "string",
"description": "Original route note, when a public qualification occupies note."
}
},
"additionalProperties": false
}
]
},
"rawRowsIncluded": {
"const": false
},
"note": {
"anyOf": [
{
"type": "string"
},
{
"type": "object",
"required": [
"summary"
],
"properties": {
"summary": {
"type": "string"
},
"downloadable": {
"type": "boolean"
}
},
"additionalProperties": false
}
]
},
"noteMessage": {
"type": "string",
"description": "Original route note, when a public qualification occupies note."
}
},
"additionalProperties": false
},
"hosting": {
"type": "object",
"required": [
"state",
"selectedFileCount",
"verifiedHostedFileCount",
"preview"
],
"properties": {
"state": {
"enum": [
"external",
"partial",
"complete",
"unknown"
]
},
"selectedFileCount": {
"type": "integer",
"minimum": 0,
"maximum": 256
},
"verifiedHostedFileCount": {
"type": "integer",
"minimum": 0,
"maximum": 256
},
"preview": {
"anyOf": [
{
"type": "object",
"required": [
"state",
"coverage",
"fullCoverage"
],
"properties": {
"state": {
"const": "unavailable"
},
"coverage": {
"const": "sample-only"
},
"fullCoverage": {
"const": false
},
"note": {
"anyOf": [
{
"type": "string"
},
{
"type": "object",
"required": [
"summary"
],
"properties": {
"summary": {
"type": "string"
},
"downloadable": {
"type": "boolean"
}
},
"additionalProperties": false
}
]
},
"noteMessage": {
"type": "string",
"description": "Original route note, when a public qualification occupies note."
}
},
"additionalProperties": false
},
{
"type": "object",
"required": [
"state",
"coverage",
"fullCoverage",
"rowCount",
"truncated",
"evidenceDigest"
],
"properties": {
"state": {
"enum": [
"attested-not-published",
"publication-authority-missing"
]
},
"coverage": {
"const": "sample-only"
},
"fullCoverage": {
"const": false
},
"rowCount": {
"type": "integer",
"minimum": 0,
"maximum": 5
},
"truncated": {
"type": "boolean"
},
"evidenceDigest": {
"type": "string",
"pattern": "^sha256:[a-f0-9]{64}$"
},
"note": {
"anyOf": [
{
"type": "string"
},
{
"type": "object",
"required": [
"summary"
],
"properties": {
"summary": {
"type": "string"
},
"downloadable": {
"type": "boolean"
}
},
"additionalProperties": false
}
]
},
"noteMessage": {
"type": "string",
"description": "Original route note, when a public qualification occupies note."
}
},
"additionalProperties": false
}
]
},
"note": {
"anyOf": [
{
"type": "string"
},
{
"type": "object",
"required": [
"summary"
],
"properties": {
"summary": {
"type": "string"
},
"downloadable": {
"type": "boolean"
}
},
"additionalProperties": false
}
]
},
"noteMessage": {
"type": "string",
"description": "Original route note, when a public qualification occupies note."
}
},
"additionalProperties": false
},
"evidence": {
"type": "object",
"required": [
"representationState",
"freshness",
"digests"
],
"properties": {
"representationState": {
"enum": [
"unknown",
"missing",
"ambiguous-parquet-inspection",
"invalid",
"metadata-only",
"support-only",
"partial-selected-data",
"evidence-incomplete",
"review-blocked",
"load-unverified",
"complete-selected-data"
]
},
"freshness": {
"type": "object",
"required": [
"status",
"evaluatedAt",
"maxAgeMs",
"items",
"stale"
],
"properties": {
"status": {
"enum": [
"current",
"stale",
"unknown"
]
},
"evaluatedAt": {
"type": "string",
"pattern": "^\\d{4}-\\d{2}-\\d{2}T\\d{2}:\\d{2}:\\d{2}(?:\\.\\d{1,3})?Z$"
},
"maxAgeMs": {
"anyOf": [
{
"type": "integer",
"minimum": 1,
"maximum": 31536000000
},
{
"type": "null"
}
]
},
"items": {
"type": "array",
"maxItems": 5,
"items": {
"type": "object",
"required": [
"kind",
"observedAt"
],
"properties": {
"kind": {
"enum": [
"inventory",
"rights-review",
"pii-review",
"row-count",
"clean-load"
]
},
"observedAt": {
"type": "string",
"pattern": "^\\d{4}-\\d{2}-\\d{2}T\\d{2}:\\d{2}:\\d{2}(?:\\.\\d{1,3})?Z$"
},
"note": {
"anyOf": [
{
"type": "string"
},
{
"type": "object",
"required": [
"summary"
],
"properties": {
"summary": {
"type": "string"
},
"downloadable": {
"type": "boolean"
}
},
"additionalProperties": false
}
]
},
"noteMessage": {
"type": "string",
"description": "Original route note, when a public qualification occupies note."
}
},
"additionalProperties": false
}
},
"stale": {
"type": "array",
"maxItems": 5,
"uniqueItems": true,
"items": {
"enum": [
"inventory",
"rights-review",
"pii-review",
"row-count",
"clean-load"
]
}
},
"note": {
"anyOf": [
{
"type": "string"
},
{
"type": "object",
"required": [
"summary"
],
"properties": {
"summary": {
"type": "string"
},
"downloadable": {
"type": "boolean"
}
},
"additionalProperties": false
}
]
},
"noteMessage": {
"type": "string",
"description": "Original route note, when a public qualification occupies note."
}
},
"additionalProperties": false
},
"digests": {
"anyOf": [
{
"type": "null"
},
{
"type": "object",
"required": [
"representation",
"inventory",
"selectedFiles",
"schema",
"rows",
# --- truncated at 32 KB (51 KB total) ---
# Full source: https://artifacts.apis.io/huggingbay-xyz/json-schema/huggingbay-xyz-public-dataset-inspection-schema.json
Work with this as data
Every JSON Schema here is available over the APIs.io API and to AI agents over MCP.
MCP server
One button, every client — Claude, Cursor, VS Code and the rest.
https://apis.io/mcp
Tools for schemas
4 MCP tools reach this
find_json_schemasBrowse and filter every JSON Schema in the catalog.apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.resolveTurn a domain, URL or GitHub org into the provider it belongs to.find_cohortsEvery scored population of providers in the catalog.
Call it yourself
curl for this page
This JSON Schema
curl "https://apis.io/api/v1/json-schemas/huggingbay-xyz-public-dataset-inspection"
All schemas
curl "https://apis.io/api/v1/json-schemas?limit=25"Discovery needs no key. Ratings and market analysis are Pro.
Get an API key
Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.
A second provider on the same verified email joins the account you already have.