epistemic-arbitrage
Propagator-based parallel structure for exploiting knowledge differentials across domains using local scoped propagators and SplitMixTernary RNG.
npx skills add majiayu000/claude-skill-registry --skill epistemic-arbitrage --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Epistemic Arbitrage: Propagator-Based Knowledge Synthesis Epistemic arbitrage exploits **knowledge differentials** between domains. When concept A in domain X is well-understood, but its isomorphic counterpart A' in domain Y is mysterious, we can **arbitrage** by transferring understanding. ## Core Architecture ### Propagator Networks (Radul/Sussman) A propagator network consists of: ``` ┌─────────┐ ┌─────────────┐ ┌─────────┐ │ Cell A │────▶│ Propagator │────▶│ Cell B │ │ (known) │ │ (transfer) │ │(derived)│ └─────────┘ └─────────────┘ └─────────┘ ``` - **Cells**: Containers for partial information - **Propagators**: Functions that combine/transform information - **Merging**: Monotonic accumulation (information only increases) ### SplitMixTernary RNG For parallel propagation with determinism: ```ruby class SplitMixTernary GOLDEN = 0x9e3779b97f4a7c15 # Golden ratio constant def initialize(seed) @state = seed end def next_ternary # Advance state (SplitMix64) @state = (@state + GOLDEN) & 0xFFFFFFFFFFFFFFFF z = @state z = ((z ^ (z >> 30)) * 0xbf58476d1ce4e5b9) & 0xFFFFFFFFFFFFFFFF z = ((z ^ (z >> 27)) * 0x94d049bb133111eb) & 0xFFFFFFFFFFFFFFFF z = z ^ (z >> 31) # Map to ternary: -1,
- Core Architecture
- Propagator Networks (Radul/Sussman)
- SplitMixTernary RNG
- Arbitrage Patterns
- Pattern 1: Domain Transfer
- Pattern 2: Dual Discovery
- Pattern 3: Triangle Arbitrage
- Local Scoped Propagators
- Scoping for Parallelism
- Parallel Arbitrage Network
- Integration with Music Topos
- With World Broadcast
- With Synadia
- With Glass Bead Game
just arbitrage # Run arbitrage network just arbitrage-domains a b # Arbitrage between specific domains just propagator-network # Visualize propagator network just knowledge-flow # Show knowledge flow diagram
What does the epistemic-arbitrage skill do?
Propagator-based parallel structure for exploiting knowledge differentials across domains using local scoped propagators and SplitMixTernary RNG.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill epistemic-arbitrage --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.