OBLITERATUS/docs/checkpoints/schemas/artifact-provenance-v1.schema.json

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://obliteratus.dev/schemas/artifact-provenance-v1.schema.json",
  "title": "OBLITERATUS Artifact Provenance v1",
  "type": "object",
  "additionalProperties": false,
  "required": [
    "schema_id",
    "schema_version",
    "artifact_id",
    "record_digest",
    "sources",
    "converter",
    "obliteratus_commit",
    "configuration_digest",
    "tokenizer",
    "base_model",
    "command",
    "environment",
    "source_topology",
    "lineage",
    "input_digests",
    "output_digests",
    "transformations",
    "state",
    "adapter",
    "dataset",
    "training",
    "unknowns"
  ],
  "properties": {
    "schema_id": {"const": "obliteratus.artifact-provenance"},
    "schema_version": {"const": "1.0.0"},
    "artifact_id": {"type": "string", "pattern": "^artifact-sha256:[0-9a-f]{64}$"},
    "record_digest": {"$ref": "#/$defs/digest"},
    "sources": {"type": "array", "minItems": 1, "uniqueItems": true, "items": {"$ref": "#/$defs/artifactIdentity"}},
    "converter": {"$ref": "#/$defs/toolIdentity"},
    "obliteratus_commit": {"type": "string", "pattern": "^[0-9a-f]{40}$"},
    "configuration_digest": {"anyOf": [{"$ref": "#/$defs/digest"}, {"type": "null"}]},
    "tokenizer": {"anyOf": [{"$ref": "#/$defs/artifactIdentity"}, {"type": "null"}]},
    "base_model": {"anyOf": [{"$ref": "#/$defs/artifactIdentity"}, {"type": "null"}]},
    "command": {"type": "array", "maxItems": 256, "items": {"type": "string", "maxLength": 4096}},
    "environment": {
      "type": "object",
      "additionalProperties": false,
      "required": ["packages", "platform", "python"],
      "properties": {
        "python": {"type": ["string", "null"], "maxLength": 128},
        "platform": {"type": ["string", "null"], "maxLength": 256},
        "packages": {"type": "object", "additionalProperties": {"type": "string", "maxLength": 128}}
      }
    },
    "source_topology": {"type": "object"},
    "lineage": {"type": "array", "uniqueItems": true, "items": {"$ref": "#/$defs/lineageEvent"}},
    "input_digests": {"type": "array", "minItems": 1, "uniqueItems": true, "items": {"$ref": "#/$defs/digest"}},
    "output_digests": {"type": "array", "minItems": 1, "uniqueItems": true, "items": {"$ref": "#/$defs/digest"}},
    "transformations": {"type": "array", "uniqueItems": true, "items": {"$ref": "#/$defs/id"}},
    "state": {
      "type": "object",
      "additionalProperties": false,
      "required": ["classification", "observed_scopes", "lost_state"],
      "properties": {
        "classification": {"enum": ["weights_only", "model_and_optimizer", "exact_resume", "unknown"]},
        "observed_scopes": {"type": "array", "uniqueItems": true, "items": {"$ref": "#/$defs/id"}},
        "lost_state": {"type": "array", "uniqueItems": true, "items": {"$ref": "#/$defs/id"}}
      }
    },
    "adapter": {"anyOf": [{"$ref": "#/$defs/adapterIdentity"}, {"type": "null"}]},
    "dataset": {"anyOf": [{"$ref": "#/$defs/datasetIdentity"}, {"type": "null"}]},
    "training": {"anyOf": [{"$ref": "#/$defs/trainingIdentity"}, {"type": "null"}]},
    "unknowns": {"type": "array", "uniqueItems": true, "items": {"type": "string", "minLength": 1, "maxLength": 1024}}
  },
  "$defs": {
    "id": {"type": "string", "minLength": 1, "maxLength": 512},
    "digest": {"type": "string", "pattern": "^sha256:[0-9a-f]{64}$"},
    "artifactIdentity": {
      "type": "object",
      "additionalProperties": false,
      "required": ["kind", "identity", "revision", "digest"],
      "properties": {
        "kind": {"enum": ["local", "hub", "generated"]},
        "identity": {"$ref": "#/$defs/id"},
        "revision": {"type": ["string", "null"], "maxLength": 256},
        "digest": {"$ref": "#/$defs/digest"}
      }
    },
    "toolIdentity": {
      "type": "object",
      "additionalProperties": false,
      "required": ["name", "version", "commit"],
      "properties": {
        "name": {"$ref": "#/$defs/id"},
        "version": {"$ref": "#/$defs/id"},
        "commit": {"type": "string", "pattern": "^[0-9a-f]{40}$"}
      }
    },
    "lineageEvent": {
      "type": "object",
      "additionalProperties": false,
      "required": ["event_id", "event_type", "parent_artifact_ids", "tool", "transformations"],
      "properties": {
        "event_id": {"$ref": "#/$defs/id"},
        "event_type": {"enum": ["consolidation", "reshard", "pretrain", "full_finetune", "adapter_train", "adapter_merge", "quantization", "dequantization", "surgery"]},
        "parent_artifact_ids": {"type": "array", "uniqueItems": true, "items": {"type": "string", "pattern": "^artifact-sha256:[0-9a-f]{64}$"}},
        "tool": {"$ref": "#/$defs/id"},
        "transformations": {"type": "array", "uniqueItems": true, "items": {"$ref": "#/$defs/id"}}
      }
    },
    "adapterIdentity": {
      "type": "object",
      "additionalProperties": false,
      "required": ["adapter_type", "base_model", "config_digest", "key_map_digest"],
      "properties": {
        "adapter_type": {"$ref": "#/$defs/id"},
        "base_model": {"$ref": "#/$defs/artifactIdentity"},
        "config_digest": {"$ref": "#/$defs/digest"},
        "key_map_digest": {"$ref": "#/$defs/digest"}
      }
    },
    "datasetIdentity": {
      "type": "object",
      "additionalProperties": false,
      "required": ["identifier", "revision", "digest", "split", "subset", "record_count"],
      "properties": {
        "identifier": {"$ref": "#/$defs/id"},
        "revision": {"type": ["string", "null"], "maxLength": 256},
        "digest": {"$ref": "#/$defs/digest"},
        "split": {"type": ["string", "null"], "maxLength": 256},
        "subset": {"type": ["string", "null"], "maxLength": 256},
        "record_count": {"type": "integer", "minimum": 0, "maximum": 9223372036854775807}
      }
    },
    "trainingIdentity": {
      "type": "object",
      "additionalProperties": false,
      "required": ["method", "framework", "framework_version", "hyperparameters_digest"],
      "properties": {
        "method": {"enum": ["pretrain", "full_finetune", "adapter_train", "unknown"]},
        "framework": {"type": ["string", "null"], "maxLength": 256},
        "framework_version": {"type": ["string", "null"], "maxLength": 128},
        "hyperparameters_digest": {"anyOf": [{"$ref": "#/$defs/digest"}, {"type": "null"}]}
      }
    }
  }
}