science.alt.dataset.entry

{
  "id": "science.alt.dataset.entry",
  "defs": {
    "main": {
      "key": "tid",
      "type": "record",
      "record": {
        "type": "object",
        "required": [
          "name",
          "schemaRef",
          "storage",
          "createdAt"
        ],
        "properties": {
          "name": {
            "type": "string",
            "maxLength": 200,
            "description": "Human-readable dataset name"
          },
          "size": {
            "ref": "#datasetSize",
            "type": "ref",
            "description": "Dataset size information (optional)"
          },
          "tags": {
            "type": "array",
            "items": {
              "type": "string",
              "maxLength": 150
            },
            "maxLength": 30,
            "description": "Searchable tags for dataset 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."
          },
          "storage": {
            "refs": [
              "science.alt.dataset.storageHttp",
              "science.alt.dataset.storageS3",
              "science.alt.dataset.storageBlobs"
            ],
            "type": "union",
            "description": "Storage location for dataset files (WebDataset tar archives)"
          },
          "metadata": {
            "type": "bytes",
            "maxLength": 100000,
            "description": "Msgpack-encoded metadata dict for arbitrary extended key-value pairs. Use this for additional metadata beyond the core top-level fields (license, tags, size). Top-level fields are preferred for discoverable/searchable metadata."
          },
          "createdAt": {
            "type": "string",
            "format": "datetime",
            "description": "Timestamp when this dataset entry was created"
          },
          "schemaRef": {
            "type": "string",
            "format": "at-uri",
            "maxLength": 500,
            "description": "AT-URI reference to the schema record for this dataset's samples"
          },
          "description": {
            "type": "string",
            "maxLength": 5000,
            "description": "Human-readable description of the dataset"
          },
          "contentMetadata": {
            "type": "unknown",
            "description": "Dataset-level content metadata (e.g., instrument settings, acquisition parameters). Structure is validated against the schema referenced by metadataSchemaRef when present. Stored as an open JSON object."
          },
          "metadataSchemaRef": {
            "type": "string",
            "format": "at-uri",
            "maxLength": 500,
            "description": "Optional AT-URI reference to a schema record defining the structure of this dataset's content metadata. When present, contentMetadata is validated against this schema at write time."
          }
        }
      },
      "description": "Index entry for a WebDataset-backed dataset with references to storage location and sample schema"
    },
    "datasetSize": {
      "type": "object",
      "properties": {
        "bytes": {
          "type": "integer",
          "minimum": 0,
          "description": "Total size in bytes"
        },
        "shards": {
          "type": "integer",
          "minimum": 1,
          "description": "Number of WebDataset shards"
        },
        "samples": {
          "type": "integer",
          "minimum": 0,
          "description": "Total number of samples in the dataset"
        }
      },
      "description": "Information about dataset size"
    },
    "shardChecksum": {
      "type": "object",
      "required": [
        "algorithm",
        "digest"
      ],
      "properties": {
        "digest": {
          "type": "string",
          "maxLength": 128,
          "description": "Hex-encoded hash digest"
        },
        "algorithm": {
          "type": "string",
          "maxLength": 20,
          "description": "Hash algorithm identifier (e.g., 'sha256', 'blake3')"
        }
      },
      "description": "Content hash for shard integrity verification. Algorithm is flexible to allow SHA-256, BLAKE3, or other hash functions."
    }
  },
  "$type": "com.atproto.lexicon.schema",
  "lexicon": 1
}