teleo-codex/schemas/source.md

Source Schema

Sources are the raw material that feeds claim extraction. Every piece of external content that enters the knowledge base gets archived in inbox/archive/ with standardized frontmatter so agents can track what's been processed, what's pending, and what yielded claims.

Source Intake Tiers

Every source is classified by how it enters the system. The tier determines extraction priority and process.

Tier	Label	Description	Extraction approach
1	Directed	Contributor provides a rationale — WHY this source matters, what question it answers, which claim it challenges	Agent extracts with the contributor's rationale as the directive. Highest priority.
2	Undirected	Source submitted without rationale. Agent decides the lens.	Agent extracts open-ended. Lower priority than directed.
3	Research task	Proactive — agents or team identify a gap and seek sources to fill it	The gap identification IS the rationale. Agent extracts against the research question.

The rationale IS the contribution. A contributor who says "this contradicts Rio's claim about launch pricing because the data shows Dutch auctions don't solve cold-start" has done the hardest intellectual work — identifying what's relevant and why. The agent's job is extraction and integration, not relevance judgment.

X intake flow: Someone replies to a claim tweet with a source link and says why it matters. The reply IS the extraction directive.

YAML Frontmatter

---
type: source
title: "Article or thread title"
author: "Name (@handle if applicable)"
url: https://example.com/article
date: YYYY-MM-DD
domain: internet-finance | entertainment | ai-alignment | health | grand-strategy
intake_tier: directed | undirected | research-task
rationale: "Why this source matters — what question it answers, which claim it challenges"
proposed_by: "contributor name or handle"
format: essay | newsletter | tweet | thread | whitepaper | paper | report | news
status: unprocessed | processing | processed | null-result
processed_by: agent-name
processed_date: YYYY-MM-DD
claims_extracted:
  - "claim title 1"
  - "claim title 2"
enrichments:
  - "existing claim title that was enriched"
tags: [topic1, topic2]
linked_set: set-name-if-part-of-a-group
---

Required Fields

Field	Type	Description
type	enum	Always source
title	string	Human-readable title of the source material
author	string	Who wrote it — name and handle
url	string	Original URL (even if content was provided manually)
date	date	Publication date
domain	enum	Primary domain for routing
intake_tier	enum	directed, undirected, or research-task (see intake tiers above)
status	enum	Processing state (see lifecycle below)

Optional Fields

Field	Type	Description
rationale	string	WHY this source matters — what question it answers, which claim it challenges. Required for directed tier, serves as extraction directive.
proposed_by	string	Who submitted this source (contributor name/handle). For attribution tracking.
format	enum	paper, essay, newsletter, tweet, thread, whitepaper, report, news — source format affects evidence weight assessment (a peer-reviewed paper carries different weight than a tweet)
processed_by	string	Which agent extracted claims from this source
processed_date	date	When extraction happened
claims_extracted	list	Titles of standalone claims created from this source
enrichments	list	Titles of existing claims enriched with evidence from this source
tags	list	Topic tags for discovery
linked_set	string	Group identifier when sources form a debate or series (e.g., ai-intelligence-crisis-divergence-feb2026)
cross_domain_flags	list	Flags for other agents/domains surfaced during extraction
flagged_for_{agent}	list	Items flagged for a specific agent's domain (e.g., flagged_for_theseus, flagged_for_vida)
notes	string	Extraction notes — why null result, what was paywalled, etc.

Status Lifecycle

unprocessed → processing → processed | null-result

Status	Meaning
unprocessed	Content archived, no agent has extracted from it yet
processing	An agent is actively working on extraction
processed	Extraction complete — claims_extracted and/or enrichments populated
null-result	Agent reviewed and determined no extractable claims (must include notes explaining why)

Note: Legacy files may use partial for paywalled content. Treat as equivalent to processing with a notes field explaining the limitation.

Filing Convention

Filename: YYYY-MM-DD-{author-handle}-{brief-slug}.md

Examples:

• 2026-02-22-citriniresearch-2028-global-intelligence-crisis.md
• 2026-03-06-time-anthropic-drops-rsp.md
• 2024-01-doppler-whitepaper-liquidity-bootstrapping.md

Body: After the frontmatter, include a summary of the source content. This serves two purposes:

1. Agents can extract claims without re-fetching the URL
2. Content persists even if the original URL goes down

The body is NOT a claim — it's a reference document. Use descriptive sections, not argumentative ones.

Governance

• Who archives: Any agent can archive sources. The processed_by field tracks who extracted, not who archived.
• When to archive: Archive at ingestion time, before extraction begins. Set status: unprocessed.
• After extraction: Update frontmatter with status: processed, processed_by, processed_date, claims_extracted, and enrichments.
• Null results: Set status: null-result and explain in notes why no claims were extracted. Null results are valuable — they prevent duplicate work.
• No deletion: Sources are never deleted from the archive, even if they yield no claims.

Legacy Fields

Older archive files (pre-migration) may use different field names:

• type: evidence or type: archive instead of type: source
• source: instead of url:
• date_published: or date_archived: instead of date:
• source_type: instead of format:
• archived_by: (still valid, just not required)
• status: partial instead of processing with notes

These are accepted for backward compatibility. New files should use the canonical field names above.