Files
thinkloom-openai-hackathon/schemas/provenance/v1/contribution-map.schema.json
T

410 lines
11 KiB
JSON

{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"$id": "https://thinkloom.app/schemas/provenance/1.0/contribution-map.schema.json",
"title": "Deposit contribution map",
"description": "Deterministic non-authoritative projection providing complete ordered deposit coverage while keeping origin, transformation, selection/arrangement, evaluation, and registration treatment independent. Its digest identity excludes contribution_map_sha256.",
"type": "object",
"properties": {
"schema_version": {
"const": "1.0"
},
"contribution_map_id": {
"type": "string",
"pattern": "^map_[0-9A-HJKMNP-TV-Z]{26}$"
},
"project_id": {
"type": "string",
"pattern": "^project_[0-9A-HJKMNP-TV-Z]{26}$"
},
"deposit_id": {
"type": "string",
"pattern": "^deposit_[0-9A-HJKMNP-TV-Z]{26}$"
},
"deposit_sha256": {
"type": "string",
"pattern": "^sha256:[a-f0-9]{64}$"
},
"manuscript_revision_id": {
"type": "string",
"pattern": "^revision_[0-9A-HJKMNP-TV-Z]{26}$"
},
"manuscript_revision_sha256": {
"type": "string",
"pattern": "^sha256:[a-f0-9]{64}$"
},
"cpl_chain_head": {
"type": "string",
"pattern": "^sha256:[a-f0-9]{64}$"
},
"cpl_event_sequence": {
"type": "integer",
"minimum": 1
},
"coordinate_system": {
"const": "unicode_scalar"
},
"coverage": {
"type": "object",
"properties": {
"denominator": {
"type": "integer",
"minimum": 0
},
"recorded_positions": {
"type": "integer",
"minimum": 0
},
"coverage_status": {
"enum": [
"complete",
"partial"
]
},
"denominator_unit": {
"const": "normalized_unicode_scalar_position"
},
"denominator_definition": {
"type": "string",
"minLength": 1
}
},
"required": [
"denominator",
"recorded_positions",
"coverage_status",
"denominator_unit",
"denominator_definition"
],
"additionalProperties": false
},
"layers": {
"type": "array",
"items": {
"enum": [
"recorded_origin",
"transformation",
"selection_arrangement",
"evidentiary_evaluation",
"suggested_registration_treatment",
"structural_locator"
]
},
"minItems": 5,
"uniqueItems": true,
"allOf": [
{
"contains": {
"const": "recorded_origin"
},
"minContains": 1,
"maxContains": 1
},
{
"contains": {
"const": "transformation"
},
"minContains": 1,
"maxContains": 1
},
{
"contains": {
"const": "selection_arrangement"
},
"minContains": 1,
"maxContains": 1
},
{
"contains": {
"const": "evidentiary_evaluation"
},
"minContains": 1,
"maxContains": 1
},
{
"contains": {
"const": "suggested_registration_treatment"
},
"minContains": 1,
"maxContains": 1
}
]
},
"segments": {
"type": "array",
"items": {
"$ref": "https://thinkloom.app/schemas/provenance/1.0/expression-segment.schema.json"
},
"minItems": 1
},
"structural_locators": {
"type": "array",
"items": {
"type": "object",
"properties": {
"segment_id": {
"type": "string",
"pattern": "^segment_[0-9A-HJKMNP-TV-Z]{26}$"
},
"chapter": {
"anyOf": [
{
"type": "integer",
"minimum": 1
},
{
"type": "null"
}
]
},
"paragraph": {
"anyOf": [
{
"type": "integer",
"minimum": 1
},
{
"type": "null"
}
]
},
"page": {
"anyOf": [
{
"type": "integer",
"minimum": 1
},
{
"type": "null"
}
]
}
},
"required": [
"segment_id",
"chapter",
"paragraph",
"page"
],
"additionalProperties": false
}
},
"layout_profile": {
"anyOf": [
{
"type": "object",
"properties": {
"layout_profile_id": {
"type": "string",
"pattern": "^layout_[0-9A-HJKMNP-TV-Z]{26}$"
},
"layout_profile_sha256": {
"type": "string",
"pattern": "^sha256:[a-f0-9]{64}$"
}
},
"required": [
"layout_profile_id",
"layout_profile_sha256"
],
"additionalProperties": false
},
{
"type": "null"
}
]
},
"generator": {
"type": "object",
"properties": {
"name": {
"type": "string",
"minLength": 1
},
"version": {
"type": "string",
"pattern": "^\\d+\\.\\d+\\.\\d+$"
},
"configuration_sha256": {
"type": "string",
"pattern": "^sha256:[a-f0-9]{64}$"
}
},
"required": [
"name",
"version",
"configuration_sha256"
],
"additionalProperties": false
},
"classification_status": {
"enum": [
"exact",
"degraded",
"stale",
"unverified"
]
},
"contribution_map_sha256": {
"type": "string",
"pattern": "^sha256:[a-f0-9]{64}$"
}
},
"required": [
"schema_version",
"contribution_map_id",
"project_id",
"deposit_id",
"deposit_sha256",
"manuscript_revision_id",
"manuscript_revision_sha256",
"cpl_chain_head",
"cpl_event_sequence",
"coordinate_system",
"coverage",
"layers",
"segments",
"structural_locators",
"layout_profile",
"generator",
"classification_status",
"contribution_map_sha256"
],
"additionalProperties": false,
"allOf": [
{
"if": {
"properties": {
"classification_status": {
"const": "exact"
}
},
"required": [
"classification_status"
]
},
"then": {
"properties": {
"coverage": {
"type": "object",
"properties": {
"coverage_status": {
"const": "complete"
}
},
"required": [
"coverage_status"
]
},
"segments": {
"type": "array",
"items": {
"allOf": [
{
"$ref": "https://thinkloom.app/schemas/provenance/1.0/expression-segment.schema.json"
},
{
"type": "object",
"properties": {
"classification_status": {
"const": "exact"
}
},
"required": [
"classification_status"
]
}
]
}
}
}
}
}
],
"examples": [
{
"schema_version": "1.0",
"contribution_map_id": "map_01J0000000000000000000000Z",
"project_id": "project_01J00000000000000000000001",
"deposit_id": "deposit_01J00000000000000000000000",
"deposit_sha256": "sha256:3333333333333333333333333333333333333333333333333333333333333333",
"manuscript_revision_id": "revision_01J0000000000000000000000B",
"manuscript_revision_sha256": "sha256:2222222222222222222222222222222222222222222222222222222222222222",
"cpl_chain_head": "sha256:4444444444444444444444444444444444444444444444444444444444444444",
"cpl_event_sequence": 42,
"coordinate_system": "unicode_scalar",
"coverage": {
"denominator": 12,
"recorded_positions": 12,
"coverage_status": "complete",
"denominator_unit": "normalized_unicode_scalar_position",
"denominator_definition": "All normalized Unicode scalar positions in the exact frozen deposit manuscript; this is provenance coverage, not a human-authorship percentage."
},
"layers": [
"recorded_origin",
"transformation",
"selection_arrangement",
"evidentiary_evaluation",
"suggested_registration_treatment"
],
"segments": [
{
"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"
}
],
"structural_locators": [
{
"segment_id": "segment_01J0000000000000000000000Y",
"chapter": 1,
"paragraph": 1,
"page": 1
}
],
"layout_profile": {
"layout_profile_id": "layout_01J00000000000000000000005",
"layout_profile_sha256": "sha256:5555555555555555555555555555555555555555555555555555555555555555"
},
"generator": {
"name": "thinkloom-contribution-map",
"version": "1.0.0",
"configuration_sha256": "sha256:6666666666666666666666666666666666666666666666666666666666666666"
},
"classification_status": "exact",
"contribution_map_sha256": "sha256:28562ec310a4eda35436bf01ec534d0639939365af453e3c922c492ee0ebff00"
}
]
}