science.alt.dataset.schema

{
  "id": "science.alt.dataset.schema",
  "defs": {
    "main": {
      "key": "any",
      "type": "record",
      "record": {
        "type": "object",
        "required": [
          "name",
          "version",
          "schemaType",
          "schema",
          "createdAt"
        ],
        "properties": {
          "name": {
            "type": "string",
            "maxLength": 100,
            "description": "Human-readable display name for this sample type. Used for documentation and UI. The NSID in the record URI provides unique identification; name collisions across NSIDs are acceptable."
          },
          "schema": {
            "refs": [
              "science.alt.dataset.schema#jsonSchemaFormat"
            ],
            "type": "union",
            "closed": false,
            "description": "Schema definition for this sample type. Currently supports JSON Schema Draft 7. Union allows for future schema formats (Avro, Protobuf, etc.) without breaking changes."
          },
          "version": {
            "type": "string",
            "pattern": "^(0|[1-9]\\d*)\\.(0|[1-9]\\d*)\\.(0|[1-9]\\d*)(?:-((?:0|[1-9]\\d*|\\d*[a-zA-Z-][0-9a-zA-Z-]*)(?:\\.(?:0|[1-9]\\d*|\\d*[a-zA-Z-][0-9a-zA-Z-]*))*))?(?:\\+([0-9a-zA-Z-]+(?:\\.[0-9a-zA-Z-]+)*))?$",
            "maxLength": 100,
            "description": "Semantic version (e.g., '1.0.0')"
          },
          "metadata": {
            "ref": "#schemaMetadata",
            "type": "ref",
            "description": "Optional metadata about this schema. Common fields include license and tags, but any additional fields are permitted."
          },
          "createdAt": {
            "type": "string",
            "format": "datetime",
            "description": "Timestamp when this schema version was created. Immutable once set (ATProto records are permanent)."
          },
          "schemaType": {
            "ref": "science.alt.dataset.schemaType",
            "type": "ref",
            "description": "Type of schema definition. This field indicates which union member is present in the schema field."
          },
          "description": {
            "type": "string",
            "maxLength": 5000,
            "description": "Human-readable description of what this sample type represents"
          },
          "$atdataSchemaVersion": {
            "type": "integer",
            "minimum": 1,
            "description": "Format version discriminator for the schema record itself. Used to detect breaking changes in the record structure. When absent, treated as version 1 for backward compatibility."
          }
        }
      },
      "description": "Definition of a PackableSample-compatible sample type. Supports versioning via rkey format: {NSID}@{semver}. Schema format is extensible via union type."
    },
    "schemaMetadata": {
      "type": "object",
      "properties": {
        "tags": {
          "type": "array",
          "items": {
            "type": "string",
            "maxLength": 150
          },
          "maxLength": 30,
          "description": "Categorization keywords for discovery. Aligns with Schema.org keywords property."
        },
        "license": {
          "type": "string",
          "maxLength": 200,
          "description": "License identifier or URL. SPDX identifiers recommended (e.g., MIT, Apache-2.0, CC-BY-4.0) or full SPDX URLs (e.g., http://spdx.org/licenses/MIT). Aligns with Schema.org license property."
        }
      },
      "description": "Open metadata object for schema records. Common fields include license and tags. Applications may extend with additional fields."
    },
    "jsonSchemaFormat": {
      "type": "object",
      "required": [
        "draft",
        "content"
      ],
      "properties": {
        "draft": {
          "type": "string",
          "const": "draft-07",
          "description": "JSON Schema draft version identifier"
        },
        "content": {
          "type": "unknown",
          "description": "JSON Schema object (e.g., Draft 7). Contains the full schema including $schema, type, properties, etc. Stored as opaque data to avoid $-prefix collisions with ATProto reserved fields."
        },
        "arrayFormatVersions": {
          "type": "unknown",
          "description": "Mapping from array format identifiers to semantic versions. Keys are science.alt.dataset.arrayFormat values (e.g., 'ndarrayBytes'), values are semver strings (e.g., '1.0.0'). Canonical shim schemas are maintained at https://json-schema.alt.science/atdata-{format}/{version}/."
        }
      },
      "description": "JSON Schema format for sample type definitions. The content field holds the actual JSON Schema document (Draft 7+). This envelope separates ATProto protocol fields from JSON Schema's $-prefixed fields."
    }
  },
  "$type": "com.atproto.lexicon.schema",
  "lexicon": 1
}