FID-060 · Open question
Cross-Faith Sacred Text and Source Schema
What metadata schema is needed for faith-facing AI systems to represent sacred texts, commentaries, institutional documents, oral traditions, translations, editions, and authority levels across faith traditions?
Why the question remains open
Formal verification and reliable retrieval both depend on knowing what a source is. A passage may be scripture, commentary, denominational policy, devotional writing, historical scholarship, minority interpretation, or pastoral guidance. Without source metadata, AI systems can cite religious material while hiding important differences in authority, scope, translation, and context.
Working hypothesis
A proposition to test, not a finding.
A cross-faith source schema can capture enough metadata to support verification without forcing every tradition into the same authority model. Required fields should describe source type, tradition scope, authority status, version, translation, licensing, provenance, context-window rules, and claim types.
Proposed method
How the question could be tested
- 01Review existing metadata practices from libraries, religious publishers, digital scripture projects, academic databases, and RAG corpus cards.
- 02Draft a minimal source-card schema for faith-facing AI corpora.
- 03Test the schema on Christian, Jewish, Muslim, Buddhist, Hindu, and other faith-facing source examples where appropriate reviewers are available.
- 04Evaluate whether the schema improves retrieval, citation, and verification tasks compared with unstructured source metadata.
Needed controls
What must constrain the study
- 01Do not impose a single hierarchy of authority across traditions.
- 02Separate source metadata from claims about truth, orthodoxy, or institutional approval.
- 03Track licensing, redistribution rights, source provenance, and edition drift.
- 04Include fields for contested status, minority use, or tradition-specific authority where relevant.
Expected outputs
Artifacts the work should produce
- 01Cross-faith source-card schema.
- 02Example metadata records for sacred texts, commentaries, policies, and educational resources.
- 03Corpus-readiness checklist for faith-facing RAG and verification systems.
- 04Schema validation tool for missing or ambiguous source metadata.
- 05Guidance for public benchmarks that rely on copyrighted or restricted sources.
Open questions
Uncertainties the protocol must resolve
- 01Which metadata fields are essential versus useful but too burdensome?
- 02How should oral, embodied, or community-governed sources be represented?
- 03How can the schema respect traditions that reject external classification of authority?
- 04What metadata is required before a source can support formal verification?
Related calls
Continue through this research area
FID-077
Independent Agent Incident Investigation and Evidence Sufficiency
What operational evidence lets independent investigators reconstruct an agent incident, distinguish competing explanations, and identify which interventions could have changed the outcome?
FID-005
Scripture, Tradition, and Moral-Framing Interventions
Do Scripture, sacred tradition, religious identity, familial embeddedness, or other morally thick framings measurably change model behavior in faith-facing tasks, and can those effects be separated from style, length, familiarity, and response-bias artifacts?
FID-006
Faith-Facing Retrieval Grounding and Citation Reliability
How reliably do faith-facing AI systems retrieve, cite, and represent religious sources when users ask theological, historical, pastoral, or institution-specific questions?
Open question
Open work
Primary need: source metadata, corpus design, theological librarianship
- Contribute source-card examples from different faith traditions.
- Review metadata fields as a librarian, publisher, scholar, clergy member, or corpus builder.
- Build schema validators and corpus-quality checks.
- Identify licensing and provenance constraints for public benchmark sources.