Files
thinkloom-openai-hackathon/schemas/provenance/v1/expression-segment.schema.json
T

257 lines
6.6 KiB
JSON

{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"$id": "https://thinkloom.app/schemas/provenance/1.0/expression-segment.schema.json",
"title": "Surviving expression segment",
"description": "Stable surviving deposit expression with revision-bound range, digest, recorded origin, lineage, transformations, and separate selection/arrangement assertions.",
"type": "object",
"properties": {
"schema_version": {
"const": "1.0"
},
"segment_id": {
"type": "string",
"pattern": "^segment_[0-9A-HJKMNP-TV-Z]{26}$"
},
"project_id": {
"type": "string",
"pattern": "^project_[0-9A-HJKMNP-TV-Z]{26}$"
},
"revision_id": {
"type": "string",
"pattern": "^revision_[0-9A-HJKMNP-TV-Z]{26}$"
},
"segment_sequence": {
"type": "integer",
"minimum": 1
},
"range": {
"$ref": "https://thinkloom.app/schemas/provenance/1.0/text-fragment-reference.schema.json"
},
"content_sha256": {
"type": "string",
"pattern": "^sha256:[a-f0-9]{64}$"
},
"normalized_unicode_scalar_length": {
"type": "integer",
"minimum": 1
},
"recorded_origin_kind": {
"enum": [
"recorded_direct_human_input",
"human_expressive_input_via_transcription",
"accepted_ai_output",
"imported_or_pasted",
"system_restoration",
"unattested"
]
},
"actor_identity_status": {
"enum": [
"verified",
"self_declared",
"unknown",
"not_applicable"
]
},
"generation_status": {
"enum": [
"recorded",
"unknown"
]
},
"lineage_status": {
"enum": [
"recorded",
"unattested",
"unknown"
]
},
"lineage_reference_ids": {
"type": "array",
"items": {
"type": "string",
"pattern": "^[a-z][a-z0-9_]*_[0-9A-HJKMNP-TV-Z]{26}$"
},
"uniqueItems": true
},
"operation_ids": {
"type": "array",
"items": {
"type": "string",
"pattern": "^operation_[0-9A-HJKMNP-TV-Z]{26}$"
},
"uniqueItems": true
},
"transformation_relationships": {
"type": "array",
"items": {
"enum": [
"inserted",
"deleted",
"replaced",
"moved",
"pasted_from_external",
"transcribed_from_human_speech",
"generated_by_ai",
"modified_by_human",
"restored_from_revision",
"derived_from"
]
},
"uniqueItems": true
},
"assertion_ids": {
"type": "array",
"items": {
"type": "string",
"pattern": "^assertion_[0-9A-HJKMNP-TV-Z]{26}$"
},
"uniqueItems": true
},
"selection_arrangement_assertion_ids": {
"type": "array",
"items": {
"type": "string",
"pattern": "^assertion_[0-9A-HJKMNP-TV-Z]{26}$"
},
"uniqueItems": true
},
"included_in_deposit_assertion_id": {
"anyOf": [
{
"type": "string",
"pattern": "^assertion_[0-9A-HJKMNP-TV-Z]{26}$"
},
{
"type": "null"
}
]
},
"classification_status": {
"enum": [
"exact",
"degraded",
"stale",
"unverified"
]
}
},
"required": [
"schema_version",
"segment_id",
"project_id",
"revision_id",
"segment_sequence",
"range",
"content_sha256",
"normalized_unicode_scalar_length",
"recorded_origin_kind",
"actor_identity_status",
"generation_status",
"lineage_status",
"lineage_reference_ids",
"operation_ids",
"transformation_relationships",
"assertion_ids",
"selection_arrangement_assertion_ids",
"included_in_deposit_assertion_id",
"classification_status"
],
"additionalProperties": false,
"allOf": [
{
"if": {
"properties": {
"classification_status": {
"const": "exact"
}
},
"required": [
"classification_status"
]
},
"then": {
"properties": {
"recorded_origin_kind": {
"enum": [
"recorded_direct_human_input",
"human_expressive_input_via_transcription",
"accepted_ai_output",
"imported_or_pasted",
"system_restoration"
]
},
"actor_identity_status": {
"enum": [
"verified",
"self_declared",
"not_applicable"
]
},
"generation_status": {
"const": "recorded"
},
"lineage_status": {
"const": "recorded"
},
"lineage_reference_ids": {
"type": "array",
"minItems": 1
},
"operation_ids": {
"type": "array",
"minItems": 1
},
"assertion_ids": {
"type": "array",
"minItems": 1
},
"included_in_deposit_assertion_id": {
"type": "string",
"pattern": "^assertion_[0-9A-HJKMNP-TV-Z]{26}$"
}
}
}
}
],
"examples": [
{
"schema_version": "1.0",
"segment_id": "segment_01J0000000000000000000000Y",
"project_id": "project_01J00000000000000000000001",
"revision_id": "revision_01J0000000000000000000000B",
"segment_sequence": 1,
"range": {
"schema_version": "1.0",
"document_revision_id": "revision_01J0000000000000000000000B",
"coordinate_system": "unicode_scalar",
"start": 0,
"end": 12,
"preimage_sha256": "sha256:2222222222222222222222222222222222222222222222222222222222222222",
"text_fragment_id": "fragment_01J0000000000000000000000C"
},
"content_sha256": "sha256:2222222222222222222222222222222222222222222222222222222222222222",
"normalized_unicode_scalar_length": 12,
"recorded_origin_kind": "recorded_direct_human_input",
"actor_identity_status": "self_declared",
"generation_status": "recorded",
"lineage_status": "recorded",
"lineage_reference_ids": [
"operation_01J0000000000000000000000X"
],
"operation_ids": [
"operation_01J0000000000000000000000X"
],
"transformation_relationships": [
"inserted"
],
"assertion_ids": [
"assertion_01J0000000000000000000000V"
],
"selection_arrangement_assertion_ids": [],
"included_in_deposit_assertion_id": "assertion_01J0000000000000000000000V",
"classification_status": "exact"
}
]
}