m3taversal
97607d7b88
Two-layer ontology: contributor-facing (3 concepts: claims, challenges, connections) vs agent-internal (11 concepts). This is the architectural change from the 2026-03-26 ontology audit. New files: - schemas/challenge.md — first-class challenge type with attribution, evidence chains, and resolution tracking - core/contributor-guide.md — 3-concept contributor view that hides agent infrastructure Modified files: - schemas/claim.md — challenged_by field now references challenge files, added structural importance scoring section - ops/schema-change-protocol.md — challenge added to producer/consumer map Schema Change: Format affected: claim (modified), challenge (new) Change: new challenge type; claim.challenged_by now accepts filenames Backward compatible: yes — existing claims unchanged, inline challenges still valid Migration: none needed — challenge files are additive Consumers to notify: Leo, Rio, Clay, Theseus, Vida, Astra, extract-graph-data.py Pentagon-Agent: Clay <3D549D4C-0129-4008-BF4F-FDD367C1D184>
3.4 KiB
Contributor Guide
Three concepts. That's it.
Claims
A claim is a statement about how the world works, backed by evidence.
"Legacy media is consolidating into three dominant entities because debt-loaded incumbents cannot compete with cash-rich tech companies for content rights"
Claims have confidence levels: proven, likely, experimental, speculative. Every claim cites its evidence. Every claim can be wrong.
Browse claims: Look in domains/{domain}/ — each domain has dozens of claims organized by topic. Start with whichever domain matches your expertise.
Challenges
A challenge is a counter-argument against a specific claim.
"The AI content acceptance decline may be scope-bounded to entertainment — reference and analytical AI content shows no acceptance penalty"
Challenges are the highest-value contribution. If you think a claim is wrong, too broad, or missing evidence, file a challenge. The claim author must respond — they can't ignore it.
Three types:
- Full challenge — the claim is wrong, here's why
- Scope challenge — the claim is true in context X but not Y
- Evidence challenge — the evidence doesn't support the confidence level
File a challenge: Create a file in domains/{domain}/challenge-{slug}.md following the challenge schema, or tell an agent your counter-argument and they'll draft it for you.
Connections
Connections are the links between claims. When claim A depends on claim B, or challenges claim C, those relationships form a knowledge graph.
You don't create connections as standalone files — they emerge from wiki links ([[claim-name]]) in claim and challenge bodies. But spotting a connection no one else has seen is a genuine contribution. Cross-domain connections (a pattern in entertainment that also appears in finance) are the most valuable.
Spot a connection: Tell an agent. They'll draft the cross-reference and attribute you.
What You Don't Need to Know
The system has 11 internal concept types (beliefs, positions, convictions, entities, sectors, sources, divergences, musings, attribution, contributors). Agents use these to organize their reasoning, track companies, and manage their workflow.
You don't need to learn any of them. Claims, challenges, and connections are the complete interface for contributors. Everything else is infrastructure.
How Credit Works
Every contribution is attributed. Your name stays on everything you produce or improve. The system tracks five roles:
| Role | What you did |
|---|---|
| Sourcer | Pointed to material worth analyzing |
| Extractor | Turned source material into a claim |
| Challenger | Filed counter-evidence against a claim |
| Synthesizer | Connected claims across domains |
| Reviewer | Evaluated claim quality |
You can hold multiple roles on the same claim. Credit is proportional to impact — a challenge that changes a high-importance claim earns more than a new speculative claim in an empty domain.
Getting Started
- Browse: Pick a domain. Read 5-10 claims. Find one you disagree with or know something about.
- React: Tell an agent your reaction. They'll help you figure out if it's a challenge, a new claim, or a connection.
- Approve: The agent drafts; you review and approve before anything gets published.
Nothing enters the knowledge base without your explicit approval. The conversation itself is valuable even if you never file anything.