81 lines
2.0 KiB
JSON
81 lines
2.0 KiB
JSON
{
|
|
"$schema": "https://json-schema.org/draft/2020-12/schema",
|
|
"$id": "https://thinkloom.app/schemas/provenance/1.0/transcript-normalization.schema.json",
|
|
"title": "Transcript normalization",
|
|
"description": "Immutable normalized representation derived from a transcript revision.",
|
|
"type": "object",
|
|
"properties": {
|
|
"schema_version": {
|
|
"const": "1.0"
|
|
},
|
|
"normalization_id": {
|
|
"type": "string",
|
|
"pattern": "^normalization_[0-9A-HJKMNP-TV-Z]{26}$"
|
|
},
|
|
"turn_id": {
|
|
"type": "string",
|
|
"pattern": "^turn_[0-9A-HJKMNP-TV-Z]{26}$"
|
|
},
|
|
"revision_number": {
|
|
"type": "integer",
|
|
"minimum": 1
|
|
},
|
|
"normalized_text": {
|
|
"type": "string",
|
|
"minLength": 1
|
|
},
|
|
"method": {
|
|
"enum": [
|
|
"application",
|
|
"user_approved",
|
|
"provider"
|
|
]
|
|
},
|
|
"source_correction_id": {
|
|
"anyOf": [
|
|
{
|
|
"type": "string",
|
|
"pattern": "^correction_[0-9A-HJKMNP-TV-Z]{26}$"
|
|
},
|
|
{
|
|
"type": "null"
|
|
}
|
|
]
|
|
},
|
|
"created_at": {
|
|
"type": "string",
|
|
"format": "date-time",
|
|
"pattern": "^\\d{4}-\\d{2}-\\d{2}T\\d{2}:\\d{2}:\\d{2}\\.\\d{3}Z$"
|
|
},
|
|
"event_id": {
|
|
"type": "string",
|
|
"pattern": "^event_[0-9A-HJKMNP-TV-Z]{26}$"
|
|
}
|
|
},
|
|
"required": [
|
|
"schema_version",
|
|
"normalization_id",
|
|
"turn_id",
|
|
"revision_number",
|
|
"normalized_text",
|
|
"method",
|
|
"source_correction_id",
|
|
"created_at",
|
|
"event_id"
|
|
],
|
|
"additionalProperties": false,
|
|
"examples": [
|
|
{
|
|
"schema_version": "1.0",
|
|
"normalization_id": "normalization_01J0000000000000000000000K",
|
|
"turn_id": "turn_01J00000000000000000000007",
|
|
"revision_number": 1,
|
|
"normalized_text": "Attention shapes public life.",
|
|
"method": "application",
|
|
"source_correction_id": "correction_01J0000000000000000000000J",
|
|
"created_at": "2026-07-17T18:43:11.456Z",
|
|
"event_id": "event_01J00000000000000000000004"
|
|
}
|
|
]
|
|
}
|