# OAIS Archival Information Package (AIP) Schema # Based on REF-061 OAIS Reference Model # Issue: #133 $schema: "https://json-schema.org/draft/2020-12/schema" $id: "https://aiwg.io/schemas/oais-aip/v1" title: "OAIS Archival Information Package Schema" description: | Schema for OAIS-compliant Archival Information Packages. Provides complete preservation metadata and chain-of-custody for research sources and generated artifacts. type: object required: - aip_id - content_information - preservation_description_information properties: aip_id: type: string format: uuid description: "Unique AIP identifier" created_at: type: string format: date-time updated_at: type: string format: date-time status: type: string enum: - draft - submitted - archived - deprecated default: draft content_information: $ref: "#/$defs/ContentInformation" description: "The actual content being preserved" preservation_description_information: $ref: "#/$defs/PDI" description: "Information needed to preserve content" packaging_information: $ref: "#/$defs/PackagingInformation" description: "How AIP is packaged" descriptive_information: $ref: "#/$defs/DescriptiveInformation" description: "Discovery and access metadata" $defs: ContentInformation: type: object required: - content_object - representation_information properties: content_object: type: object properties: type: type: string enum: - research_paper - generated_artifact - source_code - documentation path: type: string format: type: string examples: ["application/pdf", "text/markdown", "text/typescript"] size_bytes: type: integer checksum: type: object properties: algorithm: type: string enum: [sha256, sha512, md5] value: type: string representation_information: type: object properties: structure: type: object description: "How bits map to content" semantics: type: object description: "What content means" other: type: object description: "Additional interpretation info" PDI: type: object description: "Preservation Description Information" properties: reference_information: type: object description: "Identifiers for content" properties: identifiers: type: array items: type: object properties: type: type: string enum: [doi, arxiv, isbn, issn, ref_id, uuid] value: type: string provenance_information: type: object description: "History and chain-of-custody" properties: origin: type: object properties: source: type: string acquisition_date: type: string format: date-time acquisition_method: type: string enum: [download, upload, generation, derivation] custody_history: type: array items: type: object properties: timestamp: type: string format: date-time event: type: string agent: type: string details: type: string context_information: type: object description: "Why content is being preserved" properties: purpose: type: string relationships: type: array items: type: object properties: type: type: string enum: [cites, cited_by, derives_from, source_of, implements, documents] target: type: string collection: type: string description: "Collection this belongs to" fixity_information: type: object description: "Data integrity verification" properties: checksums: type: array items: type: object properties: algorithm: type: string value: type: string computed_at: type: string format: date-time last_verified: type: string format: date-time verification_history: type: array items: type: object properties: timestamp: type: string format: date-time result: type: string enum: [pass, fail] details: type: string access_rights_information: type: object description: "Who can access and how" properties: license: type: object properties: type: type: string url: type: string access_level: type: string enum: [public, internal, restricted, confidential] restrictions: type: array items: type: string PackagingInformation: type: object properties: format: type: string enum: [directory, tar, zip, bagit] default: directory structure: type: object properties: manifest_path: type: string default: "manifest.json" content_path: type: string default: "content/" metadata_path: type: string default: "metadata/" DescriptiveInformation: type: object description: "Discovery metadata" properties: title: type: string description: type: string creators: type: array items: type: string subjects: type: array items: type: string dates: type: object properties: created: type: string format: date-time modified: type: string format: date-time published: type: string format: date coverage: type: object properties: temporal: type: string spatial: type: string # Package structure package_structure: description: "Standard AIP directory structure" layout: | AIP-{id}/ ├── manifest.json # This AIP schema instance ├── content/ │ ├── original/ # Original files │ │ └── paper.pdf │ └── derived/ # Derived representations │ └── paper.md ├── metadata/ │ ├── pdi.json # Preservation Description Information │ ├── provenance.json # Full provenance chain │ └── dc.xml # Dublin Core metadata └── logs/ └── fixity.log # Verification history # Agent protocol agent_protocol: create_aip: description: "Create new AIP for content" steps: - validate_content - compute_checksums - extract_metadata - build_pdi - create_package - validate_package ingest_aip: description: "Ingest new content as AIP" steps: - receive_sip (Submission Information Package) - validate_sip - transform_to_aip - store_aip - index_for_discovery access_aip: description: "Generate DIP from AIP" steps: - verify_access_rights - verify_fixity - create_dip (Dissemination Information Package) - deliver_to_user verify_aip: description: "Verify AIP integrity" schedule: weekly steps: - load_manifest - verify_all_checksums - report_results - update_verification_history # Storage locations storage: research_aips: ".aiwg/research/aips/" artifact_aips: ".aiwg/artifacts/aips/" index: ".aiwg/research/aips/index.json" # Examples examples: research_paper_aip: aip_id: "aip-ref-056-001" content_information: content_object: type: research_paper path: "content/original/fair-principles.pdf" format: "application/pdf" size_bytes: 1250000 checksum: algorithm: sha256 value: "abc123..." representation_information: structure: format: "PDF 1.7" semantics: domain: "data management" language: "en" preservation_description_information: reference_information: identifiers: - type: doi value: "10.1038/sdata.2016.18" - type: ref_id value: "REF-056" provenance_information: origin: source: "https://doi.org/10.1038/sdata.2016.18" acquisition_date: "2026-01-15T10:00:00Z" acquisition_method: download fixity_information: checksums: - algorithm: sha256 value: "abc123..." computed_at: "2026-01-15T10:00:00Z" last_verified: "2026-01-25T00:00:00Z" access_rights_information: license: type: CC-BY-4.0 url: "https://creativecommons.org/licenses/by/4.0/" access_level: public # References references: research: - "@.aiwg/research/findings/REF-061-oais.md" implementation: - "#133" related: - "@agentic/code/frameworks/sdlc-complete/schemas/research/fixity-manifest.yaml" - "@agentic/code/frameworks/sdlc-complete/schemas/research/bibtex-export.yaml"